Zotero.bib

@article{jung_impact_2014,
	title = {Impact of sequencing depth in {ChIP}-seq experiments},
	volume = {42},
	issn = {1362-4962},
	doi = {10.1093/nar/gku178},
	abstract = {In a chromatin immunoprecipitation followed by high-throughput sequencing (ChIP-seq) experiment, an important consideration in experimental design is the minimum number of sequenced reads required to obtain statistically significant results. We present an extensive evaluation of the impact of sequencing depth on identification of enriched regions for key histone modifications (H3K4me3, H3K36me3, H3K27me3 and H3K9me2/me3) using deep-sequenced datasets in human and fly. We propose to define sufficient sequencing depth as the number of reads at which detected enrichment regions increase {\textless}1\% for an additional million reads. Although the required depth depends on the nature of the mark and the state of the cell in each experiment, we observe that sufficient depth is often reached at {\textless}20 million reads for fly. For human, there are no clear saturation points for the examined datasets, but our analysis suggests 40-50 million reads as a practical minimum for most marks. We also devise a mathematical model to estimate the sufficient depth and total genomic coverage of a mark. Lastly, we find that the five algorithms tested do not agree well for broad enrichment profiles, especially at lower depths. Our findings suggest that sufficient sequencing depth and an appropriate peak-calling algorithm are essential for ensuring robustness of conclusions derived from ChIP-seq data.},
	language = {eng},
	number = {9},
	journal = {Nucleic Acids Research},
	author = {Jung, Youngsook L. and Luquette, Lovelace J. and Ho, Joshua W. K. and Ferrari, Francesco and Tolstorukov, Michael and Minoda, Aki and Issner, Robbyn and Epstein, Charles B. and Karpen, Gary H. and Kuroda, Mitzi I. and Park, Peter J.},
	month = may,
	year = {2014},
	pmid = {24598259},
	pmcid = {PMC4027199},
	keywords = {Algorithms, Animals, Chromatin Immunoprecipitation, Drosophila melanogaster, Genome, Human, Genome, Insect, Genomic Library, High-Throughput Nucleotide Sequencing, Histones, Humans, Models, Genetic, Protein Processing, Post-Translational, Sequence Analysis, DNA},
	pages = {e74}
}

@article{khan_heterogeneous_2017,
	title = {Heterogeneous {Cell} {Types} in {Single}-cell-derived {Clones} of {MCF}7 and {MDA}-{MB}-231 {Cells}},
	volume = {37},
	issn = {1791-7530},
	doi = {10.21873/anticanres.11572},
	abstract = {BACKGROUND/AIM: Variations in cell phenotype in a single-cell-derived clone may result from asymmetric cell divisions that lead to different cell fate in a homogenous microenvironment. The aim of this study was to demonstrate the extent of cell variety in single-cell-derived clones and propose a different strategy in treating cancer by observed phenotypic heterogeneity in cellular types. Additionally, the role of metabolic enzyme and housekeeping gene, glyceraldehyde-3-phosphate dehydrogenase (GAPDH), in cellular phenotype was evaluated in two breast cancer cell lines.
MATERIALS AND METHODS: Two GAPDH-overexpressing breast cancer cell lines, MCF7-GAPDH-RFP (MCF7-RFP) and MDA-MB-231-GAPDH-RFP (MDA-RFP), were established. Microscopic recordings were made at 12-h intervals in single-cell-derived clones of both cell lines up to 8-10 days. Crystal violet and Hoechst 33342 (Hoechst), as well as specific cell-type (epithelial and mesenchymal) antibodies, were used for cytochemical and immunohistochemical staining analyses, respectively, at 3, 6 and 9 days during cell growth.
RESULTS: Three types of clones with distinct morphologies were identified as holo-, mero- and paraclones. The rates of colony survival during cell growth were 8.3 and 41.7\% in MCF7-RFP and MDA-RFP, respectively. Although no significant difference was found in the colony forming efficiency (CFE) of both MCF7 and MDA-MD-231 wild-type cells, a markedly significant difference was seen in the CFE of MCF7-RFP and MDA-RFP cells (p=0.001). Wild-type cell-derived holoclones of both cell lines showed drug resistance to doxorubicin (Dox). However, levels of proliferating cell nuclear antigen (PCNA) and vimentin (VIM) marginally decreased in Dox-treated clones. Furthermore, high level of intraclonal heterogeneity was found for CD44, CD140a, VIM, fibronectin (FN), focal adhesion kinase (FAK), paxillin (PXN) and vinculin (VCL) in MCF7 and MDA clones during different stages of clonal development. Expressions of CD140a, FN, VIM and FAK were induced in GAPDH-red fluorescent protein (RFP)-tagged clones of both cell lines.
CONCLUSION: The GAPDH-RFP recombinant protein played an important role in morphological heterogeneity detection in early stages of clonal development. Moreover, phenotypic heterogeneity in clones, caused by the cells expressing specific antigens, such as CD44, CD140a, FN, VIM, FAK and VCL, can be the right target for therapeutic drugs.},
	language = {eng},
	number = {5},
	journal = {Anticancer Research},
	author = {Khan, Gul Nabi and Kim, Eun Jin and Shin, Tae Seop and Lee, Sang Ho},
	year = {2017},
	pmid = {28476800},
	keywords = {Antibiotics, Antineoplastic, Breast Neoplasms, Cell Line, Tumor, Doxorubicin, Drug Resistance, Neoplasm, GAPDH, Glyceraldehyde 3-Phosphate Dehydrogenase (NADP+), Heterogeneity, Humans, Luminescent Proteins, MCF7, MDA-MB-231, Phenotype, Recombinant Proteins, clonal analysis, surface markers},
	pages = {2343--2354}
}

@article{jemaa_heterogeneity_2017,
	title = {Heterogeneity in sarcoma cell lines reveals enhanced motility of tetraploid versus diploid cells},
	volume = {8},
	issn = {1949-2553},
	doi = {10.18632/oncotarget.14291},
	abstract = {Soft tissue sarcomas with complex genomics are very heterogeneous tumors lacking simple prognosis markers or targeted therapies. Overexpression of a subset of mitotic genes from a signature called CINSARC is of bad prognosis, but the significance of this signature remains elusive. Here we precisely measure the cell cycle and mitosis duration of sarcoma cell lines and we found that the mitotic gene products overexpression does not reflect variation in the time spent during mitosis or G2/M. We also found that the CINSARC cell lines, we studied, are composed of a mixture of aneuploid, diploid, and tetraploid cells that are highly motile in vitro. After sorting diploid and tetraploid cells, we showed that the tetraploid cell clones do not possess a proliferative advantage, but are strikingly more motile and invasive than their diploid counterparts. This is correlated with higher levels of mitotic proteins overexpression. Owing that mitotic proteins are almost systematically degraded at the end of mitosis, we propose that it is the abnormal activity of the mitotic proteins during interphase that boosts the sarcoma cells migratory properties by affecting their cytoskeleton. To test this hypothesis, we designed a screen for mitotic or cytoskeleton protein inhibitors affecting the sarcoma cell migration potential independently of cytotoxic activities. We found that inhibition of several mitotic kinases drastically impairs the CINSARC cell invasive and migratory properties. This finding could provide a handle by which to selectively inhibit the most invasive cells.},
	language = {eng},
	number = {10},
	journal = {Oncotarget},
	author = {Jemaà, Mohamed and Abdallah, Samer and Lledo, Gwendaline and Perrot, Gaelle and Lesluyes, Tom and Teyssier, Catherine and Roux, Pierre and van Dijk, Juliette and Chibon, Frederic and Abrieu, Ariane and Morin, Nathalie},
	month = mar,
	year = {2017},
	pmid = {28035071},
	pmcid = {PMC5369993},
	keywords = {CINSARC, Cell Line, Cell Movement, DNA, Neoplasm, Diploidy, Genetic Heterogeneity, Humans, Sarcoma, Tetraploidy, diploid/tetraploid, mitosis, motility},
	pages = {16669--16689}
}

@article{nagano_comparison_2015,
	title = {Comparison of {Hi}-{C} results using in-solution versus in-nucleus ligation},
	volume = {16},
	issn = {1474-7596},
	url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4580221/},
	doi = {10.1186/s13059-015-0753-7},
	abstract = {BACKGROUND: Chromosome conformation capture and various derivative methods such as 4C, 5C and Hi-C have emerged as standard tools to analyze the three-dimensional organization of the genome in the nucleus. These methods employ ligation of diluted cross-linked chromatin complexes, intended to favor proximity-dependent, intra-complex ligation. During development of single-cell Hi-C, we devised an alternative Hi-C protocol with ligation in preserved nuclei rather than in solution. Here we directly compare Hi-C methods employing in-nucleus ligation with the standard in-solution ligation. RESULTS: We show in-nucleus ligation results in consistently lower levels of inter-chromosomal contacts. Through chromatin mixing experiments we show that a significantly large fraction of inter-chromosomal contacts are the result of spurious ligation events formed during in-solution ligation. In-nucleus ligation significantly reduces this source of experimental noise, and results in improved reproducibility between replicates. We also find that in-nucleus ligation eliminates restriction fragment length bias found with in-solution ligation. These improvements result in greater reproducibility of long-range intra-chromosomal and inter-chromosomal contacts, as well as enhanced detection of structural features such as topologically associated domain boundaries. CONCLUSIONS: We conclude that in-nucleus ligation captures chromatin interactions more consistently over a wider range of distances, and significantly reduces both experimental noise and bias. In-nucleus ligation creates higher quality Hi-C libraries while simplifying the experimental procedure. We suggest that the entire range of 3C applications are likely to show similar benefits from in-nucleus ligation. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (doi:10.1186/s13059-015-0753-7) contains supplementary material, which is available to authorized users.},
	number = {1},
	journal = {Genome Biology},
	author = {Nagano, Takashi and Várnai, Csilla and Schoenfelder, Stefan and Javierre, Biola-Maria and Wingett, Steven W and Fraser, Peter},
	year = {2015},
	pages = {175}
}

@article{landt_chip-seq_2012,
	title = {{ChIP}-seq guidelines and practices of the {ENCODE} and {modENCODE} consortia},
	volume = {22},
	issn = {1549-5469 (Electronic) 1088-9051 (Linking)},
	shorttitle = {{ChIP}-seq guidelines and practices of the {ENCODE} and {modENCODE} consortia},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/22955991},
	doi = {10.1101/gr.136184.111},
	abstract = {Chromatin immunoprecipitation (ChIP) followed by high-throughput DNA sequencing (ChIP-seq) has become a valuable and widely used approach for mapping the genomic location of transcription-factor binding and histone modifications in living cells. Despite its widespread use, there are considerable differences in how these experiments are conducted, how the results are scored and evaluated for quality, and how the data and metadata are archived for public use. These practices affect the quality and utility of any global ChIP experiment. Through our experience in performing ChIP-seq experiments, the ENCODE and modENCODE consortia have developed a set of working standards and guidelines for ChIP experiments that are updated routinely. The current guidelines address antibody validation, experimental replication, sequencing depth, data and metadata reporting, and data quality assessment. We discuss how ChIP quality, assessed in these ways, affects different uses of ChIP-seq data. All data sets used in the analysis have been deposited for public viewing and downloading at the ENCODE (http://encodeproject.org/ENCODE/) and modENCODE (http://www.modencode.org/) portals.},
	number = {9},
	journal = {Genome Res},
	author = {Landt, S. G. and Marinov, G. K. and Kundaje, A. and Kheradpour, P. and Pauli, F. and Batzoglou, S. and Bernstein, B. E. and Bickel, P. and Brown, J. B. and Cayting, P. and Chen, Y. and DeSalvo, G. and Epstein, C. and Fisher-Aylor, K. I. and Euskirchen, G. and Gerstein, M. and Gertz, J. and Hartemink, A. J. and Hoffman, M. M. and Iyer, V. R. and Jung, Y. L. and Karmakar, S. and Kellis, M. and Kharchenko, P. V. and Li, Q. and Liu, T. and Liu, X. S. and Ma, L. and Milosavljevic, A. and Myers, R. M. and Park, P. J. and Pazin, M. J. and Perry, M. D. and Raha, D. and Reddy, T. E. and Rozowsky, J. and Shoresh, N. and Sidow, A. and Slattery, M. and Stamatoyannopoulos, J. A. and Tolstorukov, M. Y. and White, K. P. and Xi, S. and Farnham, P. J. and Lieb, J. D. and Wold, B. J. and Snyder, M.},
	month = sep,
	year = {2012},
	keywords = {*Databases, Genetic, Animals, Chromatin Immunoprecipitation/*methods, Genome/genetics, Genomics/methods, Guidelines as Topic, High-Throughput Nucleotide Sequencing/*methods, Histones/metabolism, Humans, Internet, Transcription Factors/metabolism},
	pages = {1813--31}
}

@article{diaz_chance:_2012,
	title = {{CHANCE}: comprehensive software for quality control and validation of {ChIP}-seq data},
	volume = {13},
	issn = {1474-760X (Electronic) 1474-7596 (Linking)},
	shorttitle = {{CHANCE}: comprehensive software for quality control and validation of {ChIP}-seq data},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/23068444},
	doi = {10.1186/gb-2012-13-10-r98},
	abstract = {ChIP-seq is a powerful method for obtaining genome-wide maps of protein-DNA interactions and epigenetic modifications. CHANCE (CHip-seq ANalytics and Confidence Estimation) is a standalone package for ChIP-seq quality control and protocol optimization. Our user-friendly graphical software quickly estimates the strength and quality of immunoprecipitations, identifies biases, compares the user's data with ENCODE's large collection of published datasets, performs multi-sample normalization, checks against quantitative PCR-validated control regions, and produces informative graphical reports. CHANCE is available at https://github.com/songlab/chance.},
	number = {10},
	journal = {Genome Biol},
	author = {Diaz, A. and Nellore, A. and Song, J. S.},
	month = oct,
	year = {2012},
	keywords = {Animals, Chromatin Immunoprecipitation/*methods, Epigenesis, Genetic, Epigenomics/*methods, Humans, Reproducibility of Results, Sequence Analysis, DNA/*methods, Web Browser},
	pages = {R98}
}

@article{yu_chipseeker:_2015,
	title = {{ChIPseeker}: an {R}/{Bioconductor} package for {ChIP} peak annotation, comparison and visualization},
	volume = {31},
	issn = {1367-4811 (Electronic) 1367-4803 (Linking)},
	shorttitle = {{ChIPseeker}: an {R}/{Bioconductor} package for {ChIP} peak annotation, comparison and visualization},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/25765347},
	doi = {10.1093/bioinformatics/btv145},
	abstract = {UNLABELLED: ChIPseeker is an R package for annotating ChIP-seq data analysis. It supports annotating ChIP peaks and provides functions to visualize ChIP peaks coverage over chromosomes and profiles of peaks binding to TSS regions. Comparison of ChIP peak profiles and annotation are also supported. Moreover, it supports evaluating significant overlap among ChIP-seq datasets. Currently, ChIPseeker contains 15 000 bed file information from GEO database. These datasets can be downloaded and compare with user's own data to explore significant overlap datasets for inferring co-regulation or transcription factor complex for further investigation. AVAILABILITY AND IMPLEMENTATION: ChIPseeker is released under Artistic-2.0 License. The source code and documents are freely available through Bioconductor (http://www.bioconductor.org/packages/release/bioc/html/ChIPseeker.html).},
	number = {14},
	journal = {Bioinformatics},
	author = {Yu, G. and Wang, L. G. and He, Q. Y.},
	month = jul,
	year = {2015},
	keywords = {*Chromatin Immunoprecipitation, *High-Throughput Nucleotide Sequencing, *Sequence Analysis, DNA, *Software, Binding Sites, Computer Graphics, DNA/chemistry/metabolism, Molecular Sequence Annotation, Transcription Factors/*metabolism, Transcription Initiation Site},
	pages = {2382--3}
}

@article{planet_htseqtools:_2012,
	title = {{htSeqTools}: high-throughput sequencing quality control, processing and visualization in {R}},
	volume = {28},
	issn = {1367-4811 (Electronic) 1367-4803 (Linking)},
	shorttitle = {{htSeqTools}: high-throughput sequencing quality control, processing and visualization in {R}},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/22199381},
	doi = {10.1093/bioinformatics/btr700},
	abstract = {UNLABELLED: We provide a Bioconductor package with quality assessment, processing and visualization tools for high-throughput sequencing data, with emphasis in ChIP-seq and RNA-seq studies. It includes detection of outliers and biases, inefficient immuno-precipitation and overamplification artifacts, de novo identification of read-rich genomic regions and visualization of the location and coverage of genomic region lists. AVAILABILITY: www.bioconductor.org.},
	number = {4},
	journal = {Bioinformatics},
	author = {Planet, E. and Attolini, C. S. and Reina, O. and Flores, O. and Rossell, D.},
	month = feb,
	year = {2012},
	keywords = {*Software, Genomics, High-Throughput Nucleotide Sequencing/*methods, Humans, Internet, Oligonucleotide Array Sequence Analysis, Quality Control, Saccharomyces cerevisiae/genetics},
	pages = {589--90}
}

@article{carroll_impact_2014,
	title = {Impact of artifact removal on {ChIP} quality metrics in {ChIP}-seq and {ChIP}-exo data},
	volume = {5},
	issn = {1664-8021 (Print) 1664-8021 (Linking)},
	shorttitle = {Impact of artifact removal on {ChIP} quality metrics in {ChIP}-seq and {ChIP}-exo data},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/24782889},
	doi = {10.3389/fgene.2014.00075},
	abstract = {With the advent of ChIP-seq multiplexing technologies and the subsequent increase in ChIP-seq throughput, the development of working standards for the quality assessment of ChIP-seq studies has received significant attention. The ENCODE consortium's large scale analysis of transcription factor binding and epigenetic marks as well as concordant work on ChIP-seq by other laboratories has established a new generation of ChIP-seq quality control measures. The use of these metrics alongside common processing steps has however not been evaluated. In this study, we investigate the effects of blacklisting and removal of duplicated reads on established metrics of ChIP-seq quality and show that the interpretation of these metrics is highly dependent on the ChIP-seq preprocessing steps applied. Further to this we perform the first investigation of the use of these metrics for ChIP-exo data and make recommendations for the adaptation of the NSC statistic to allow for the assessment of ChIP-exo efficiency.},
	journal = {Front Genet},
	author = {Carroll, T. S. and Liang, Z. and Salama, R. and Stark, R. and de Santiago, I.},
	year = {2014},
	keywords = {ChIP-exo, ChIP-seq, Qc, blacklist, duplicates},
	pages = {75}
}

@article{marinov_large-scale_2014,
	title = {Large-scale quality analysis of published {ChIP}-seq data},
	volume = {4},
	issn = {2160-1836 (Electronic) 2160-1836 (Linking)},
	shorttitle = {Large-scale quality analysis of published {ChIP}-seq data},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/24347632},
	doi = {10.1534/g3.113.008680},
	abstract = {ChIP-seq has become the primary method for identifying in vivo protein-DNA interactions on a genome-wide scale, with nearly 800 publications involving the technique appearing in PubMed as of December 2012. Individually and in aggregate, these data are an important and information-rich resource. However, uncertainties about data quality confound their use by the wider research community. Recently, the Encyclopedia of DNA Elements (ENCODE) project developed and applied metrics to objectively measure ChIP-seq data quality. The ENCODE quality analysis was useful for flagging datasets for closer inspection, eliminating or replacing poor data, and for driving changes in experimental pipelines. There had been no similarly systematic quality analysis of the large and disparate body of published ChIP-seq profiles. Here, we report a uniform analysis of vertebrate transcription factor ChIP-seq datasets in the Gene Expression Omnibus (GEO) repository as of April 1, 2012. The majority (55\%) of datasets scored as being highly successful, but a substantial minority (20\%) were of apparently poor quality, and another approximately 25\% were of intermediate quality. We discuss how different uses of ChIP-seq data are affected by specific aspects of data quality, and we highlight exceptional instances for which the metric values should not be taken at face value. Unexpectedly, we discovered that a significant subset of control datasets (i.e., no immunoprecipitation and mock immunoprecipitation samples) display an enrichment structure similar to successful ChIP-seq data. This can, in turn, affect peak calling and data interpretation. Published datasets identified here as high-quality comprise a large group that users can draw on for large-scale integrated analysis. In the future, ChIP-seq quality assessment similar to that used here could guide experimentalists at early stages in a study, provide useful input in the publication process, and be used to stratify ChIP-seq data for different community-wide uses.},
	number = {2},
	journal = {G3 (Bethesda)},
	author = {Marinov, G. K. and Kundaje, A. and Park, P. J. and Wold, B. J.},
	month = feb,
	year = {2014},
	keywords = {Animals, ChIP-seq, Chromatin Immunoprecipitation, Chromatin Immunoprecipitation/*standards, Data Interpretation, Statistical, Databases, Genetic/*standards, High-Throughput Nucleotide Sequencing/methods/*standards, MyoD Protein/genetics, Quality Control, Sequence Analysis, DNA/methods/*standards, Transcription Factors/genetics, cross-correlation, quality assessment, transcription factor},
	pages = {209--23}
}

@article{qin_chilin:_2016,
	title = {{ChiLin}: a comprehensive {ChIP}-seq and {DNase}-seq quality control and analysis pipeline},
	volume = {17},
	issn = {1471-2105 (Electronic) 1471-2105 (Linking)},
	shorttitle = {{ChiLin}: a comprehensive {ChIP}-seq and {DNase}-seq quality control and analysis pipeline},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/27716038},
	doi = {10.1186/s12859-016-1274-4},
	abstract = {BACKGROUND: Transcription factor binding, histone modification, and chromatin accessibility studies are important approaches to understanding the biology of gene regulation. ChIP-seq and DNase-seq have become the standard techniques for studying protein-DNA interactions and chromatin accessibility respectively, and comprehensive quality control (QC) and analysis tools are critical to extracting the most value from these assay types. Although many analysis and QC tools have been reported, few combine ChIP-seq and DNase-seq data analysis and quality control in a unified framework with a comprehensive and unbiased reference of data quality metrics. RESULTS: ChiLin is a computational pipeline that automates the quality control and data analyses of ChIP-seq and DNase-seq data. It is developed using a flexible and modular software framework that can be easily extended and modified. ChiLin is ideal for batch processing of many datasets and is well suited for large collaborative projects involving ChIP-seq and DNase-seq from different designs. ChiLin generates comprehensive quality control reports that include comparisons with historical data derived from over 23,677 public ChIP-seq and DNase-seq samples (11,265 datasets) from eight literature-based classified categories. To the best of our knowledge, this atlas represents the most comprehensive ChIP-seq and DNase-seq related quality metric resource currently available. These historical metrics provide useful heuristic quality references for experiment across all commonly used assay types. Using representative datasets, we demonstrate the versatility of the pipeline by applying it to different assay types of ChIP-seq data. The pipeline software is available open source at https://github.com/cfce/chilin . CONCLUSION: ChiLin is a scalable and powerful tool to process large batches of ChIP-seq and DNase-seq datasets. The analysis output and quality metrics have been structured into user-friendly directories and reports. We have successfully compiled 23,677 profiles into a comprehensive quality atlas with fine classification for users.},
	number = {1},
	journal = {BMC Bioinformatics},
	author = {Qin, Q. and Mei, S. and Wu, Q. and Sun, H. and Li, L. and Taing, L. and Chen, S. and Li, F. and Liu, T. and Zang, C. and Xu, H. and Chen, Y. and Meyer, C. A. and Zhang, Y. and Brown, M. and Long, H. W. and Liu, X. S.},
	month = oct,
	year = {2016},
	keywords = {*Gene Expression Regulation, *Quality Control, *Software, Analysis pipeline, ChIP-seq, Chromatin Immunoprecipitation/*methods, Chromosome Mapping, DNase-seq, Data Interpretation, Statistical, Databases, Genetic, Deoxyribonucleases/*genetics/metabolism, High-Throughput Nucleotide Sequencing/*methods, Humans, Quality atlas, Sequence Analysis, DNA/*methods},
	pages = {404}
}

@article{yang_hicrep:_2017,
	title = {{HiCRep}: assessing the reproducibility of {Hi}-{C} data using a stratum- adjusted correlation coefficient},
	issn = {1549-5469 (Electronic) 1088-9051 (Linking)},
	shorttitle = {{HiCRep}: assessing the reproducibility of {Hi}-{C} data using a stratum- adjusted correlation coefficient},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28855260},
	doi = {10.1101/gr.220640.117},
	abstract = {Hi-C is a powerful technology for studying genome-wide chromatin interactions. However, current methods for assessing Hi-C data reproducibility can produce misleading results because they ignore spatial features in Hi-C data, such as domain structure and distance dependence. We present HiCRep, a framework for assessing the reproducibility of Hi-C data that systematically accounts for these features. In particular, we introduce a novel similarity measure, the stratum adjusted correlation coefficient (SCC), for quantifying the similarity between Hi-C interaction matrices. Not only does it provide a statistically sound and reliable evaluation of reproducibility, SCC can also be used to quantify differences between Hi-C contact matrices and to determine the optimal sequencing depth for a desired resolution. The measure consistently shows higher accuracy than existing approaches in distinguishing subtle differences in reproducibility and depicting interrelationships of cell lineages. The proposed measure is straightforward to interpret and easy to compute, making it well-suited for providing standardized, interpretable, automatable, and scalable quality control. The freely available R package HiCRep implements our approach.},
	journal = {Genome Res},
	author = {Yang, T. and Zhang, F. and Yardimci, G. G. and Song, F. and Hardison, R. C. and Noble, W. S. and Yue, F. and Li, Q.},
	month = aug,
	year = {2017}
}

@article{krijger_cell--origin-specific_2016,
	title = {Cell-of-{Origin}-{Specific} 3D {Genome} {Structure} {Acquired} during {Somatic} {Cell} {Reprogramming}},
	volume = {18},
	issn = {1875-9777},
	doi = {10.1016/j.stem.2016.01.007},
	abstract = {Forced expression of reprogramming factors can convert somatic cells into induced pluripotent stem cells (iPSCs). Here we studied genome topology dynamics during reprogramming of different somatic cell types with highly distinct genome conformations. We find large-scale topologically associated domain (TAD) repositioning and alterations of tissue-restricted genomic neighborhoods and chromatin loops, effectively erasing the somatic-cell-specific genome structures while establishing an embryonic stem-cell-like 3D genome. Yet, early passage iPSCs carry topological hallmarks that enable recognition of their cell of origin. These hallmarks are not remnants of somatic chromosome topologies. Instead, the distinguishing topological features are acquired during reprogramming, as we also find for cell-of-origin-dependent gene expression patterns.},
	language = {eng},
	number = {5},
	journal = {Cell Stem Cell},
	author = {Krijger, Peter Hugo Lodewijk and Di Stefano, Bruno and de Wit, Elzo and Limone, Francesco and van Oevelen, Chris and de Laat, Wouter and Graf, Thomas},
	month = may,
	year = {2016},
	pmid = {26971819},
	pmcid = {PMC4858530},
	pages = {597--610}
}

@article{burren_chromosome_2017,
	title = {Chromosome contacts in activated {T} cells identify autoimmune disease candidate genes},
	volume = {18},
	issn = {1474-760X (Electronic) 1474-7596 (Linking)},
	shorttitle = {Chromosome contacts in activated {T} cells identify autoimmune disease candidate genes},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28870212},
	doi = {10.1186/s13059-017-1285-0},
	abstract = {BACKGROUND: Autoimmune disease-associated variants are preferentially found in regulatory regions in immune cells, particularly CD4+ T cells. Linking such regulatory regions to gene promoters in disease-relevant cell contexts facilitates identification of candidate disease genes. RESULTS: Within 4 h, activation of CD4+ T cells invokes changes in histone modifications and enhancer RNA transcription that correspond to altered expression of the interacting genes identified by promoter capture Hi-C. By integrating promoter capture Hi-C data with genetic associations for five autoimmune diseases, we prioritised 245 candidate genes with a median distance from peak signal to prioritised gene of 153 kb. Just under half (108/245) prioritised genes related to activation-sensitive interactions. This included IL2RA, where allele-specific expression analyses were consistent with its interaction-mediated regulation, illustrating the utility of the approach. CONCLUSIONS: Our systematic experimental framework offers an alternative approach to candidate causal gene identification for variants with cell state-specific functional effects, with achievable sample sizes.},
	number = {1},
	journal = {Genome Biol},
	author = {Burren, O. S. and Rubio Garcia, A. and Javierre, B. M. and Rainbow, D. B. and Cairns, J. and Cooper, N. J. and Lambourne, J. J. and Schofield, E. and Castro Dopico, X. and Ferreira, R. C. and Coulson, R. and Burden, F. and Rowlston, S. P. and Downes, K. and Wingett, S. W. and Frontini, M. and Ouwehand, W. H. and Fraser, P. and Spivakov, M. and Todd, J. A. and Wicker, L. S. and Cutler, A. J. and Wallace, C.},
	month = sep,
	year = {2017},
	keywords = {Autoimmune disease, CD4+ T cell activation, CD4+ T cells, Chromatin conformation, Genetics, Genome-wide association studies, Genomics},
	pages = {165}
}

@article{beagrie_complex_2017,
	title = {Complex multi-enhancer contacts captured by genome architecture mapping},
	volume = {543},
	issn = {1476-4687 (Electronic) 0028-0836 (Linking)},
	shorttitle = {Complex multi-enhancer contacts captured by genome architecture mapping},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28273065},
	doi = {10.1038/nature21411},
	abstract = {The organization of the genome in the nucleus and the interactions of genes with their regulatory elements are key features of transcriptional control and their disruption can cause disease. Here we report a genome-wide method, genome architecture mapping (GAM), for measuring chromatin contacts and other features of three-dimensional chromatin topology on the basis of sequencing DNA from a large collection of thin nuclear sections. We apply GAM to mouse embryonic stem cells and identify enrichment for specific interactions between active genes and enhancers across very large genomic distances using a mathematical model termed SLICE (statistical inference of co-segregation). GAM also reveals an abundance of three-way contacts across the genome, especially between regions that are highly transcribed or contain super-enhancers, providing a level of insight into genome architecture that, owing to the technical limitations of current technologies, has previously remained unattainable. Furthermore, GAM highlights a role for gene-expression-specific contacts in organizing the genome in mammalian nuclei.},
	number = {7646},
	journal = {Nature},
	author = {Beagrie, R. A. and Scialdone, A. and Schueler, M. and Kraemer, D. C. and Chotalia, M. and Xie, S. Q. and Barbieri, M. and de Santiago, I. and Lavitas, L. M. and Branco, M. R. and Fraser, J. and Dostie, J. and Game, L. and Dillon, N. and Edwards, P. A. and Nicodemi, M. and Pombo, A.},
	month = mar,
	year = {2017},
	keywords = {*Chromosome Mapping, Animals, Chromatin/chemistry/*genetics/*metabolism, Enhancer Elements, Genetic/*genetics, Epigenesis, Genetic, Genome/*genetics, Male, Mice, Models, Genetic, Mouse Embryonic Stem Cells/cytology/metabolism, Sequence Analysis, DNA, Transcription, Genetic/genetics},
	pages = {519--524}
}

@article{ma_using_2017,
	title = {Using {DNase} {Hi}-{C} techniques to map global and local three-dimensional genome architecture at high resolution},
	shorttitle = {Using {DNase} {Hi}-{C} techniques to map global and local three-dimensional genome architecture at high resolution},
	doi = {10.1101/184846},
	abstract = {The folding and three-dimensional (3D) organization of chromatin in the nucleus critically impacts genome function. The past decade has witnessed rapid advances in genomic tools for delineating 3D genome architecture. Among them, chromosome conformation capture (3C)-based methods such as Hi-C are the most widely used techniques for mapping chromatin interactions. However, traditional Hi-C protocols rely on restriction enzymes (REs) to fragment chromatin and are therefore limited in resolution. We recently developed DNase Hi-C for mapping 3D genome organization, which uses DNase I for chromatin fragmentation. DNase Hi-C overcomes RE-related limitations associated with traditional Hi-C methods, leading to improved methodological resolution. Furthermore, combining this method with DNA capture technology provides a high-throughput approach (targeted DNase Hi-C) that allows for mapping fine-scale chromatin architecture at exceptionally high resolution. Hence, targeted DNase Hi-C will be valuable for delineating the physical landscapes of cis-regulatory networks that control gene expression and for characterizing phenotype-associated chromatin 3D signatures. Here, we provide a detailed description of method design and step-by-step working protocols for these two methods.\%U http://www.biorxiv.org/content/biorxiv/early/2017/09/05/184846.full.pdf},
	journal = {bioRxiv},
	author = {Ma, Wenxiu and Ay, Ferhat and Lee, Choli and Gulsoy, Gunhan and Deng, Xinxian and Cook, Savannah and Hesson, Jennifer and Cavanaugh, Christopher and Ware, Carol B. and Krumm, Anton and Shendure, Jay and Blau, C. Anthony and Disteche, Christine M. and Noble, William S. and Duan, Zhijun},
	year = {2017}
}

@article{tran_smc_2017,
	title = {{SMC} {Progressively} {Aligns} {Chromosomal} {Arms} in {Caulobacter} crescentus but {Is} {Antagonized} by {Convergent} {Transcription}},
	volume = {20},
	issn = {2211-1247 (Electronic)},
	shorttitle = {{SMC} {Progressively} {Aligns} {Chromosomal} {Arms} in {Caulobacter} crescentus but {Is} {Antagonized} by {Convergent} {Transcription}},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28854358},
	doi = {10.1016/j.celrep.2017.08.026},
	abstract = {The structural maintenance of chromosomes (SMC) complex plays an important role in chromosome organization and segregation in most living organisms. In Caulobacter crescentus, SMC is required to align the left and the right arms of the chromosome that run in parallel down the long axis of the cell. However, the mechanism of SMC-mediated alignment of chromosomal arms remains elusive. Here, using genome-wide methods and microscopy of single cells, we show that Caulobacter SMC is recruited to the centromeric parS site and that SMC-mediated arm alignment depends on the chromosome-partitioning protein ParB. We provide evidence that SMC likely tethers the parS-proximal regions of the chromosomal arms together, promoting arm alignment. Furthermore, we show that highly transcribed genes near parS that are oriented against SMC translocation disrupt arm alignment, suggesting that head-on transcription interferes with SMC translocation. Our results demonstrate a tight interdependence of bacterial chromosome organization and global patterns of transcription.},
	number = {9},
	journal = {Cell Rep},
	author = {Tran, N. T. and Laub, M. T. and Le, T. B. K.},
	month = aug,
	year = {2017},
	keywords = {Caulobacter, ChIP-seq, Hi-C, ParB, Smc, chromosome organization, chromosome segregation, head-on transcription conflicts, parS, structural maintenance of chromosomes},
	pages = {2057--2071}
}

@article{siersbaek_dynamic_2017,
	title = {Dynamic {Rewiring} of {Promoter}-{Anchored} {Chromatin} {Loops} during {Adipocyte} {Differentiation}},
	volume = {66},
	issn = {1097-4164 (Electronic) 1097-2765 (Linking)},
	shorttitle = {Dynamic {Rewiring} of {Promoter}-{Anchored} {Chromatin} {Loops} during {Adipocyte} {Differentiation}},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28475875},
	doi = {10.1016/j.molcel.2017.04.010},
	abstract = {Interactions between transcriptional promoters and their distal regulatory elements play an important role in transcriptional regulation; however, the extent to which these interactions are subject to rapid modulations in response to signals is unknown. Here, we use promoter capture Hi-C to demonstrate a rapid reorganization of promoter-anchored chromatin loops within 4 hr after inducing differentiation of 3T3-L1 preadipocytes. The establishment of new promoter-enhancer loops is tightly coupled to activation of poised (histone H3 lysine 4 mono- and dimethylated) enhancers, as evidenced by the acquisition of histone H3 lysine 27 acetylation and the binding of MED1, SMC1, and P300 proteins to these regions, as well as to activation of target genes. Intriguingly, formation of loops connecting activated enhancers and promoters is also associated with extensive recruitment of corepressors such as NCoR and HDACs, indicating that this class of coregulators may play a previously unrecognized role during enhancer activation.},
	number = {3},
	journal = {Mol Cell},
	author = {Siersbaek, R. and Madsen, J. G. S. and Javierre, B. M. and Nielsen, R. and Bagge, E. K. and Cairns, J. and Wingett, S. W. and Traynor, S. and Spivakov, M. and Fraser, P. and Mandrup, S.},
	month = may,
	year = {2017},
	keywords = {ChIP-seq, adipocyte differentiation, chromatin looping, corepressors, poised enhancers, promoter capture Hi-C, single nucleotide variance, super-enhancers, topologically associating domains, transcriptional regulation},
	pages = {420--435 e5}
}

@article{du_three_2017,
	title = {Three distinct mechanisms of long-distance modulation of gene expression in yeast},
	volume = {13},
	issn = {1553-7404 (Electronic) 1553-7390 (Linking)},
	shorttitle = {Three distinct mechanisms of long-distance modulation of gene expression in yeast},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28426659},
	doi = {10.1371/journal.pgen.1006736},
	abstract = {Recent Hi-C measurements have revealed numerous intra- and inter-chromosomal interactions in various eukaryotic cells. To what extent these interactions regulate gene expression is not clear. This question is particularly intriguing in budding yeast because it has extensive long-distance chromosomal interactions but few cases of gene regulation over-a-distance. Here, we developed a medium-throughput assay to screen for functional long-distance interactions that affect the average expression level of a reporter gene as well as its cell-to-cell variability (noise). We ectopically inserted an insulated MET3 promoter (MET3pr) flanked by {\textasciitilde}1kb invariable sequences into thousands of genomic loci, allowing it to make contacts with different parts of the genome, and assayed the MET3pr activity in single cells. Changes of MET3pr activity in this case necessarily involve mechanisms that function over a distance. MET3pr has similar activities at most locations. However, at some locations, they deviate from the norm and exhibit three distinct patterns including low expression / high noise, low expression / low noise, and high expression / low noise. We provided evidence that these three patterns of MET3pr expression are caused by Sir2-mediated silencing, transcriptional interference, and 3D clustering. The clustering also occurs in the native genome and enhances the transcription of endogenous Met4-targeted genes. Overall, our results demonstrate that a small fraction of long-distance chromosomal interactions can affect gene expression in yeast.},
	number = {4},
	journal = {PLoS Genet},
	author = {Du, M. and Zhang, Q. and Bai, L.},
	month = apr,
	year = {2017},
	keywords = {*Transcription, Genetic, Basic-Leucine Zipper Transcription Factors/*genetics/metabolism, Chromatin/genetics, Chromosomes, Fungal/genetics, F-Box Proteins/*genetics/metabolism, Gene Expression Regulation, Fungal, Genes, Reporter, Genome, Fungal, Promoter Regions, Genetic, Saccharomyces cerevisiae Proteins/*genetics/metabolism, Saccharomyces cerevisiae/genetics, Silent Information Regulator Proteins, Saccharomyces, Sirtuin 2/*genetics/metabolism, Ubiquitin-Protein Ligase Complexes/*genetics/metabolism, cerevisiae/*genetics/metabolism},
	pages = {e1006736}
}

@article{dillinger_nucleolus_2017,
	title = {Nucleolus association of chromosomal domains is largely maintained in cellular senescence despite massive nuclear reorganisation},
	volume = {12},
	issn = {1932-6203 (Electronic) 1932-6203 (Linking)},
	shorttitle = {Nucleolus association of chromosomal domains is largely maintained in cellular senescence despite massive nuclear reorganisation},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28575119},
	doi = {10.1371/journal.pone.0178821},
	abstract = {Mammalian chromosomes are organized in structural and functional domains of 0.1-10 Mb, which are characterized by high self-association frequencies in the nuclear space and different contact probabilities with nuclear sub-compartments. They exhibit distinct chromatin modification patterns, gene expression levels and replication timing. Recently, nucleolus-associated chromosomal domains (NADs) have been discovered, yet their precise genomic organization and dynamics are still largely unknown. Here, we use nucleolus genomics and single-cell experiments to address these questions in human embryonic fibroblasts during replicative senescence. Genome-wide mapping reveals 1,646 NADs in proliferating cells, which cover about 38\% of the annotated human genome. They are mainly heterochromatic and correlate with late replicating loci. Using Hi-C data analysis, we show that interactions of NADs dominate interphase chromosome contacts in the 10-50 Mb distance range. Interestingly, only minute changes in nucleolar association are observed upon senescence. These spatial rearrangements in subdomains smaller than 100 kb are accompanied with local transcriptional changes. In contrast, large centromeric and pericentromeric satellite repeat clusters extensively dissociate from nucleoli in senescent cells. Accordingly, H3K9me3-marked heterochromatin gets remodelled at the perinucleolar space as revealed by immunofluorescence analyses. Collectively, this study identifies connections between the nucleolus, 3D genome structure, and cellular aging at the level of interphase chromosome organization.},
	number = {6},
	journal = {PLoS One},
	author = {Dillinger, S. and Straub, T. and Nemeth, A.},
	year = {2017},
	pages = {e0178821}
}

@article{diament_tracking_2017,
	title = {Tracking the evolution of 3D gene organization demonstrates its connection to phenotypic divergence},
	volume = {45},
	issn = {1362-4962 (Electronic) 0305-1048 (Linking)},
	shorttitle = {Tracking the evolution of 3D gene organization demonstrates its connection to phenotypic divergence},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28369658},
	doi = {10.1093/nar/gkx205},
	abstract = {It has recently been shown that the organization of genes in eukaryotic genomes, and specifically in 3D, is strongly related to gene expression and function and partially conserved between organisms. However, previous studies of 3D genomic organization analyzed each organism independently from others. Here, we propose an approach for unified inter-organismal analysis of gene organization based on a network representation of Hi-C data. We define and detect four classes of spatially co-evolving orthologous modules (SCOMs), i.e. gene families that co-evolve in their 3D organization, based on patterns of divergence and conservation of distances. We demonstrate our methodology on Hi-C data from Saccharomyces cerevisiae and Schizosaccharomyces pombe, and identify, among others, modules relating to RNA splicing machinery and chromatin silencing by small RNA which are central to S. pombe's lifestyle. Our results emphasize the importance of 3D genomic organization in eukaryotes and suggest that the evolutionary mechanisms that shape gene organization affect the organism fitness and phenotypes. The proposed algorithms can be utilized in future studies of genome evolution and comparative analysis of spatial genomic organization in different tissues, conditions and single cells.},
	number = {8},
	journal = {Nucleic Acids Res},
	author = {Diament, A. and Tuller, T.},
	month = may,
	year = {2017},
	pages = {4330--4343}
}

@article{smukowski_heil_identification_2017,
	title = {Identification of a novel interspecific hybrid yeast from a metagenomic spontaneously inoculated beer sample using {Hi}-{C}},
	shorttitle = {Identification of a novel interspecific hybrid yeast from a metagenomic spontaneously inoculated beer sample using {Hi}-{C}},
	doi = {10.1101/150722},
	abstract = {Interspecific hybridization is a common mechanism enabling genetic diversification and adaptation; however, the detection of hybrid species has been quite difficult. The identification of microbial hybrids is made even more complicated, as most environmental microbes are resistant to culturing and must be studied in their native mixed communities. We have previously adapted the chromosome conformation capture method Hi-C to the assembly of genomes from mixed populations. Here, we show the method's application in assembling genomes directly from an uncultured, mixed population from a spontaneously inoculated beer sample. Our assembly method has enabled us to de-convolute 4 bacterial and 4 yeast genomes from this sample, including a putative yeast hybrid. Downstream isolation and analysis of this hybrid confirmed its genome to consist of Pichia membranifaciens and that of another related, but undescribed yeast. Our work shows that Hi-C-based metagenomic methods can overcome the limitation of traditional sequencing methods in studying complex mixtures of genomes.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/31/150722.full.pdf},
	journal = {bioRxiv},
	author = {Smukowski Heil, Caiti and Burton, Joshua N. and Liachko, Ivan and Friedrich, Anne and Hanson, Noah A. and Morris, Cody L. and Schacherer, Joseph and Shendure, Jay and Thomas, James H. and Dunham, Maitreya J.},
	year = {2017}
}

@article{kustatscher_pervasive_2017,
	title = {Pervasive coexpression of spatially proximal genes is buffered at the protein level},
	volume = {13},
	shorttitle = {Pervasive coexpression of spatially proximal genes is buffered at the protein level},
	doi = {10.15252/msb.20177548},
	abstract = {Genes are not randomly distributed in the genome. In humans, 10\% of protein‐coding genes are transcribed from bidirectional promoters and many more are organised in larger clusters. Intriguingly, neighbouring genes are frequently coexpressed but rarely functionally related. Here we show that coexpression of bidirectional gene pairs, and closeby genes in general, is buffered at the protein level. Taking into account the 3D architecture of the genome, we find that co‐regulation of spatially close, functionally unrelated genes is pervasive at the transcriptome level, but does not extend to the proteome. We present evidence that non‐functional mRNA coexpression in human cells arises from stochastic chromatin fluctuations and direct regulatory interference between spatially close genes. Protein‐level buffering likely reflects a lack of coordination of post‐transcriptional regulation of functionally unrelated genes. Grouping human genes together along the genome sequence, or through long‐range chromosome folding, is associated with reduced expression noise. Our results support the hypothesis that the selection for noise reduction is a major driver of the evolution of genome organisation.Mol Syst Biol. (2017) 13: 937\%U http://msb.embopress.org/content/msb/13/8/937.full.pdf},
	number = {8},
	journal = {Molecular Systems Biology},
	author = {Kustatscher, Georg and Grabowski, Piotr and Rappsilber, Juri},
	year = {2017}
}

@article{bernardi_chromatin_2017,
	title = {Chromatin domains are encoded and molded by isochores},
	shorttitle = {Chromatin domains are encoded and molded by isochores},
	doi = {10.1101/096487},
	abstract = {The formation of mammalian chromatin domains was investigated by analyzing the domain/isochore connection. This showed that LADs correspond to GC-poor isochores and are compositionally flat, flexible chromatin structures because of the local nucleosome depletions associated with the presence of oligo-As. In contrast, TADs correspond to GC-rich isochores that consist of single or (much more frequently) multiple, GC peaks that shape the single or multiple, loops of TADs. Indeed, the increasing nucleosome depletions linked to the GC gradients of isochore peaks lead to an increasing chromatin flexibility (accompanied by an increasing accessibility and decreasing supercoiling). In conclusion, isochores not only encode but also mold chromatin architecture; while architectural proteins play a role in closing and insulating TAD loops. An extension of this model concerns the encoding of open and closed chromosome compartments by alternating GC-rich and GC-poor isochores, the interactions among compartments defining the 3-D chromosome folding.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/04/096487.full.pdf},
	journal = {bioRxiv},
	author = {Bernardi, Giorgio},
	year = {2017}
}

@article{paulsen_chrom3d:_2017,
	title = {Chrom3D: three-dimensional genome modeling from {Hi}-{C} and nuclear lamin-genome contacts},
	volume = {18},
	shorttitle = {Chrom3D: three-dimensional genome modeling from {Hi}-{C} and nuclear lamin-genome contacts},
	url = {https://doi.org/10.1186/s13059-016-1146-2},
	doi = {10.1186/s13059-016-1146-2},
	journal = {Genome Biol.},
	author = {Paulsen, J. and Sekelja, M. and Oldenburg, A. R. and Barateau, A. and Briand, N. and Delbarre, E. and Shah, A. and Sorensen, A. L. and Vigouroux, C. and Buendia, B. and Collas, P.},
	year = {2017}
}

@article{li_three-dimensional_2017,
	title = {The three-dimensional genome organization of {Drosophila} melanogaster through data integration},
	volume = {18},
	issn = {1474-760X},
	shorttitle = {The three-dimensional genome organization of {Drosophila} melanogaster through data integration},
	url = {https://doi.org/10.1186/s13059-017-1264-5},
	doi = {10.1186/s13059-017-1264-5},
	abstract = {Genome structures are dynamic and non-randomly organized in the nucleus of higher eukaryotes. To maximize the accuracy and coverage of three-dimensional genome structural models, it is important to integrate all available sources of experimental information about a genome’s organization. It remains a major challenge to integrate such data from various complementary experimental methods. Here, we present an approach for data integration to determine a population of complete three-dimensional genome structures that are statistically consistent with data from both genome-wide chromosome conformation capture (Hi-C) and lamina-DamID experiments.},
	number = {1},
	journal = {Genome Biology},
	author = {Li, Qingjiao and Tjong, Harianto and Li, Xiao and Gong, Ke and Zhou, Xianghong Jasmine and Chiolo, Irene and Alber, Frank},
	month = jul,
	year = {2017},
	pages = {145}
}

@article{finn_heterogeneity_2017,
	title = {Heterogeneity and {Intrinsic} {Variation} in {Spatial} {Genome} {Organization}},
	shorttitle = {Heterogeneity and {Intrinsic} {Variation} in {Spatial} {Genome} {Organization}},
	doi = {10.1101/171801},
	abstract = {The genome is hierarchically organized in 3D space and its architecture is altered in differentiation, development and disease. Some of the general principles that determine global 3D genome organization have been established. However, the extent and nature of cell-to-cell and cell-intrinsic variability in genome architecture are poorly characterized. Here, we systematically probe the heterogeneity in genome organization in human fibroblasts by combining high-resolution Hi-C datasets and high-throughput genome imaging. Optical mapping of several hundred genome interaction pairs at the single cell level demonstrates low steady-state frequencies of colocalization in the population and independent behavior of individual alleles in single nuclei. Association frequencies are determined by genomic distance, higher-order chromatin architecture and chromatin environment. These observations reveal extensive variability and heterogeneity in genome organization at the level of single cells and alleles and they demonstrate the coexistence of a broad spectrum of chromatin and genome conformations in a cell population.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/02/171801.full.pdf},
	journal = {bioRxiv},
	author = {Finn, Elizabeth and Pegoraro, Gianluca and Brandao, Hugo B. and Valton, Anne-Laure and Oomen, Marlies E. and Dekker, Job and Mirny, Leonid and Misteli, Tom},
	year = {2017}
}

@article{canela_genome_2017,
	title = {Genome {Organization} {Drives} {Chromosome} {Fragility}},
	issn = {1097-4172 (Electronic) 0092-8674 (Linking)},
	shorttitle = {Genome {Organization} {Drives} {Chromosome} {Fragility}},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28735753},
	doi = {10.1016/j.cell.2017.06.034},
	abstract = {In this study, we show that evolutionarily conserved chromosome loop anchors bound by CCCTC-binding factor (CTCF) and cohesin are vulnerable to DNA double strand breaks (DSBs) mediated by topoisomerase 2B (TOP2B). Polymorphisms in the genome that redistribute CTCF/cohesin occupancy rewire DNA cleavage sites to novel loop anchors. While transcription- and replication-coupled genomic rearrangements have been well documented, we demonstrate that DSBs formed at loop anchors are largely transcription-, replication-, and cell-type-independent. DSBs are continuously formed throughout interphase, are enriched on both sides of strong topological domain borders, and frequently occur at breakpoint clusters commonly translocated in cancer. Thus, loop anchors serve as fragile sites that generate DSBs and chromosomal rearrangements.},
	journal = {Cell},
	author = {Canela, A. and Maman, Y. and Jung, S. and Wong, N. and Callen, E. and Day, A. and Kieffer-Kwon, K. R. and Pekowska, A. and Zhang, H. and Rao, S. S. P. and Huang, S. C. and McKinnon, P. J. and Aplan, P. D. and Pommier, Y. and Aiden, E. L. and Casellas, R. and Nussenzweig, A.},
	month = jul,
	year = {2017},
	keywords = {Cancer, DNA breaks, breakpoint cluster regions, fragile sites, genome instability, topoisomerase, topologically associated domains, translocations}
}

@article{cortini_principles_2017,
	title = {Principles of transcription factor traffic on folded chromatin},
	shorttitle = {Principles of transcription factor traffic on folded chromatin},
	doi = {10.1101/164541},
	abstract = {All organisms regulate the transcription of their genes. To understand this process, it is essential to know how transcription factors find their targets in the genome. In addition to the DNA sequence, several variables have a known influence, but overall the binding patterns of transcription factors distribution remains mostly unexplained in animal genomes. Here we investigate the role of the chromosome conformation in shaping the search path of transcription factors. Using molecular dynamics simulations, we uncover the main principles of their diffusion on folded chromatin. Chromosome contacts play a conflicting role: at low density they enhance the traffic of transcription factors, but a high density they lower the traffic by volume exclusion. Consistently, we observe that in human cells, highly occupied targets, where protein binding is promiscuous, are found at sites engaged in chromosome loops within uncompact chromatin. In summary, those results provide a theoretical framework to understand the search trajectories of transcription factors and highlight the key contribution of genome conformation.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/17/164541.full.pdf},
	journal = {bioRxiv},
	author = {Cortini, Ruggero and Filion, Guillaume},
	year = {2017}
}

@article{du_allelic_2017,
	title = {Allelic reprogramming of 3D chromatin architecture during early mammalian development},
	volume = {547},
	issn = {1476-4687 (Electronic) 0028-0836 (Linking)},
	shorttitle = {Allelic reprogramming of 3D chromatin architecture during early mammalian development},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28703188},
	doi = {10.1038/nature23263},
	abstract = {In mammals, chromatin organization undergoes drastic reprogramming after fertilization. However, the three-dimensional structure of chromatin and its reprogramming in preimplantation development remain poorly understood. Here, by developing a low-input Hi-C (genome-wide chromosome conformation capture) approach, we examined the reprogramming of chromatin organization during early development in mice. We found that oocytes in metaphase II show homogeneous chromatin folding that lacks detectable topologically associating domains (TADs) and chromatin compartments. Strikingly, chromatin shows greatly diminished higher-order structure after fertilization. Unexpectedly, the subsequent establishment of chromatin organization is a prolonged process that extends through preimplantation development, as characterized by slow consolidation of TADs and segregation of chromatin compartments. The two sets of parental chromosomes are spatially separated from each other and display distinct compartmentalization in zygotes. Such allele separation and allelic compartmentalization can be found as late as the 8-cell stage. Finally, we show that chromatin compaction in preimplantation embryos can partially proceed in the absence of zygotic transcription and is a multi-level hierarchical process. Taken together, our data suggest that chromatin may exist in a markedly relaxed state after fertilization, followed by progressive maturation of higher-order chromatin architecture during early development.},
	number = {7662},
	journal = {Nature},
	author = {Du, Z. and Zheng, H. and Huang, B. and Ma, R. and Wu, J. and Zhang, X. and He, J. and Xiang, Y. and Wang, Q. and Li, Y. and Ma, J. and Zhang, X. and Zhang, K. and Wang, Y. and Zhang, M. Q. and Gao, J. and Dixon, J. R. and Wang, X. and Zeng, J. and Xie, W.},
	month = jul,
	year = {2017},
	pages = {232--235}
}

@article{preissl_single_2017,
	title = {Single nucleus analysis of the chromatin landscape in mouse forebrain development},
	shorttitle = {Single nucleus analysis of the chromatin landscape in mouse forebrain development},
	doi = {10.1101/159137},
	abstract = {Genome-wide analysis of chromatin accessibility in primary tissues has uncovered millions of candidate regulatory sequences in the human and mouse genomes. However, the heterogeneity of biological samples used in previous studies has prevented a precise understanding of the dynamic chromatin landscape in specific cell types. Here, we show that analysis of the transposase-accessible-chromatin in single nuclei isolated from frozen tissue samples can resolve cellular heterogeneity and delineate transcriptional regulatory sequences in the constituent cell types. Our strategy is based on a combinatorial barcoding assisted single cell assay for transposase-accessible chromatin and is optimized for nuclei from flash-frozen primary tissue samples (snATAC-seq). We used this method to examine the mouse forebrain at seven development stages and in adults. From snATAC-seq profiles of more than 15,000 high quality nuclei, we identify 20 distinct cell populations corresponding to major neuronal and non-neuronal cell-types in foetal and adult forebrains. We further define cell-type specific cis regulatory sequences and infer potential master transcriptional regulators of each cell population. Our results demonstrate the feasibility of a general approach for identifying cell-type-specific cis regulatory sequences in heterogeneous tissue samples, and provide a rich resource for understanding forebrain development in mammals.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/06/159137.full.pdf},
	journal = {bioRxiv},
	author = {Preissl, Sebastian and Fang, Rongxin and Zhao, Yuan and Raviram, Ramya and Zhang, Yanxiao and Sos, Brandon C. and Huang, Hui and Gorkin, David U. and Afzal, Veena and Dickel, Diane E. and Kuan, Samantha and Visel, Axel and Pennacchio, Len A. and Zhang, Kun and Ren, Bing},
	year = {2017}
}

@article{yan_hic-spector:_2017,
	title = {{HiC}-{Spector}: {A} matrix library for spectral and reproducibility analysis of {Hi}-{C} contact maps},
	issn = {1367-4811 (Electronic) 1367-4803 (Linking)},
	shorttitle = {{HiC}-{Spector}: {A} matrix library for spectral and reproducibility analysis of {Hi}-{C} contact maps},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28369339},
	doi = {10.1093/bioinformatics/btx152},
	abstract = {Summary: Genome-wide proximity ligation based assays like Hi-C have opened a window to the 3D organization of the genome. In so doing, they present data structures that are different from conventional 1D signal tracks. To exploit the 2D nature of Hi-C contact maps, matrix techniques like spectral analysis are particularly useful. Here, we present HiC-spector, a collection of matrix-related functions for analyzing Hi-C contact maps. In particular, we introduce a novel reproducibility metric for quantifying the similarity between contact maps based on spectral decomposition. The metric successfully separates contact maps mapped from Hi-C data coming from biological replicates, pseudo-replicates and different cell types. Availability: Source code in Julia and Python, and detailed documentation is available at https://github.com/gersteinlab/HiC-spector. Contact: mark@gersteinlab.org.},
	journal = {Bioinformatics},
	author = {Yan, K. K. and Gurkan Yardimci, G. and Yan, C. and Noble, W. S. and Gerstein, M.},
	month = mar,
	year = {2017}
}

@article{ghurye_scaffolding_2017,
	title = {Scaffolding of long read assemblies using long range contact information},
	volume = {18},
	issn = {1471-2164},
	shorttitle = {Scaffolding of long read assemblies using long range contact information},
	url = {http://dx.doi.org/10.1186/s12864-017-3879-z},
	doi = {10.1186/s12864-017-3879-z},
	abstract = {Long read technologies have revolutionized de novo genome assembly by generating contigs orders of magnitude longer than that of short read assemblies. Although assembly contiguity has increased, it usually does not reconstruct a full chromosome or an arm of the chromosome, resulting in an unfinished chromosome level assembly. To increase the contiguity of the assembly to the chromosome level, different strategies are used which exploit long range contact information between chromosomes in the genome.},
	number = {1},
	journal = {BMC Genomics},
	author = {Ghurye, Jay and Pop, Mihai and Koren, Sergey and Bickhart, Derek and Chin, Chen-Shan},
	month = jul,
	year = {2017},
	pages = {527}
}

@article{wang_sub-kb_2017,
	title = {Sub-kb resolution {Hi}-{C} in {D}. melanogaster reveals conserved characteristics of {TADs} between insect and mammalian cells},
	shorttitle = {Sub-kb resolution {Hi}-{C} in {D}. melanogaster reveals conserved characteristics of {TADs} between insect and mammalian cells},
	doi = {10.1101/164467},
	abstract = {Topologically associating domains (TADs) are fundamental elements of the 3D structure of the eukaryotic genome. However, while the structural importance of the insulator protein CTCF together with cohesin at TAD borders in mammalian cells is well established, the absence of such co-localization at most TAD borders in recent Hi-C studies of D. melanogaster is enigmatic, raising the possibility that these TAD border elements are not generally conserved among metazoans. Using in situ Hi-C with sub-kb resolution, we show that the genome of D. melanogaster is almost completely partitioned into more than 4,000 TADs (median size, 13 kb), nearly 7-fold more than previously identified. The overwhelming majority of these TADs are demarcated by pairs of Drosophila specific insulator proteins, BEAF-32/CP190 or BEAF-32/Chromator, indicating that these proteins may play an analogous role in Drosophila as that of the CTCF/cohesin pair in mammals. Moreover, we find that previously identified TADs enriched for inactive chromatin are predominantly assembled from the higher-level interactions between smaller TADs. In contrast, the contiguous small TADs in regions previously thought to be unstructured "inter-TADs" are organized in an open configuration with far fewer TAD-TAD interactions. Such structures can also be identified in some "inter-TAD" regions of the mammalian genome, suggesting that larger assemblages of small self-associating TADs separated by a "burst" of contiguous small, weakly associating TADs may be a conserved, basic characteristic of the higher order folding of the metazoan genome.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/17/164467.full.pdf},
	journal = {bioRxiv},
	author = {Wang, Qi and Sun, Qiu and Czajkowsky, Daniel M. and Shao, Zhifeng},
	year = {2017}
}

@article{harewood_hi-c_2017,
	title = {Hi-{C} as a tool for precise detection and characterisation of chromosomal rearrangements and copy number variation in human tumours},
	volume = {18},
	issn = {1474-760X (Electronic) 1474-7596 (Linking)},
	shorttitle = {Hi-{C} as a tool for precise detection and characterisation of chromosomal rearrangements and copy number variation in human tumours},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28655341},
	doi = {10.1186/s13059-017-1253-8},
	abstract = {Chromosomal rearrangements occur constitutionally in the general population and somatically in the majority of cancers. Detection of balanced rearrangements, such as reciprocal translocations and inversions, is troublesome, which is particularly detrimental in oncology where rearrangements play diagnostic and prognostic roles. Here we describe the use of Hi-C as a tool for detection of both balanced and unbalanced chromosomal rearrangements in primary human tumour samples, with the potential to define chromosome breakpoints to bp resolution. In addition, we show copy number profiles can also be obtained from the same data, all at a significantly lower cost than standard sequencing approaches.},
	number = {1},
	journal = {Genome Biol},
	author = {Harewood, L. and Kishore, K. and Eldridge, M. D. and Wingett, S. and Pearson, D. and Schoenfelder, S. and Collins, V. P. and Fraser, P.},
	month = jun,
	year = {2017},
	keywords = {Anaplastic astrocytoma, Cancer, Chromosome conformation capture, Chromosome rearrangement, Copy number variation, Glioblastoma, Hi-C, Tumour},
	pages = {125}
}

@article{gong_robust_2017,
	title = {Robust estimation of {Hi}-{C} contact matrices by fused lasso reveals preferential insulation of super-enhancers by strong {TAD} boundaries and a synergistic role in cancer},
	shorttitle = {Robust estimation of {Hi}-{C} contact matrices by fused lasso reveals preferential insulation of super-enhancers by strong {TAD} boundaries and a synergistic role in cancer},
	doi = {10.1101/141481},
	abstract = {The metazoan genome is compartmentalized in megabase-scale areas of highly interacting chromatin known as topologically associating domains (TADs), typically identified by computational analyses of Hi-C sequencing data. TADs are demarcated by boundaries that are largely conserved across cell types and even across species, although, increasing evidence suggests that the seemingly invariant TAD boundaries may exhibit plasticity and their insulating strength can vary. However, a genome-wide characterization of TAD boundary strength in mammals is still lacking. A systematic classification and characterization of TAD boundaries may generate new insights into their function. In this study, we use fused two-dimensional lasso as a machine-learning method to first improve Hi-C contact matrix reproducibility, and, subsequently, categorize TAD boundaries based on their strength. We demonstrate that increased boundary strength is associated with elevated CTCF levels and that TAD boundary insulation scores may differ across cell types. Intriguingly, we observed that super-enhancer elements are preferentially insulated by strong boundaries. Furthermore, a pan-cancer analysis revealed that strong TAD boundaries and super-enhancer elements are frequently co-duplicated. Taken together, our findings suggest that super-enhancers insulated by strong TAD boundaries may be exploited, as a functional unit, by cancer cells to promote oncogenesis.\%U http://www.biorxiv.org/content/biorxiv/early/2017/06/30/141481.full.pdf},
	journal = {bioRxiv},
	author = {Gong, Yixiao and Lazaris, Charalampos and Lozano, Aurelie and Kambadur, Prabhanjan and Ntziachristos, Panagiotis and Aifantis, Iannis and Tsirigos, Aristotelis},
	year = {2017}
}

@article{forcato_comparison_2017,
	title = {Comparison of computational methods for {Hi}-{C} data analysis},
	volume = {14},
	issn = {1548-7105 (Electronic) 1548-7091 (Linking)},
	shorttitle = {Comparison of computational methods for {Hi}-{C} data analysis},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28604721},
	doi = {10.1038/nmeth.4325},
	abstract = {Hi-C is a genome-wide sequencing technique used to investigate 3D chromatin conformation inside the nucleus. Computational methods are required to analyze Hi-C data and identify chromatin interactions and topologically associating domains (TADs) from genome-wide contact probability maps. We quantitatively compared the performance of 13 algorithms in their analyses of Hi-C data from six landmark studies and simulations. This comparison revealed differences in the performance of methods for chromatin interaction identification, but more comparable results for TAD detection between algorithms.},
	number = {7},
	journal = {Nat Methods},
	author = {Forcato, M. and Nicoletti, C. and Pal, K. and Livi, C. M. and Ferrari, F. and Bicciato, S.},
	month = jul,
	year = {2017},
	pages = {679--685}
}

@article{fudenberg_fish-ing_2017,
	title = {{FISH}-ing for captured contacts: towards reconciling {FISH} and 3C},
	volume = {14},
	issn = {1548-7105 (Electronic) 1548-7091 (Linking)},
	shorttitle = {{FISH}-ing for captured contacts: towards reconciling {FISH} and 3C},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28604723},
	doi = {10.1038/nmeth.4329},
	abstract = {Chromosome conformation capture (3C) and fluorescence in situ hybridization (FISH) are two widely used technologies that provide distinct readouts of 3D chromosome organization. While both technologies can assay locus-specific organization, how to integrate views from 3C, or genome-wide Hi-C, and FISH is far from solved. Contact frequency, measured by Hi-C, and spatial distance, measured by FISH, are often assumed to quantify the same phenomena and used interchangeably. Here, however, we demonstrate that contact frequency is distinct from average spatial distance, both in polymer simulations and in experimental data. Performing a systematic analysis of the technologies, we show that this distinction can create a seemingly paradoxical relationship between 3C and FISH, both in minimal polymer models with dynamic looping interactions and in loop-extrusion simulations. Together, our results indicate that cross-validation of Hi-C and FISH should be carefully designed, and that jointly considering contact frequency and spatial distance is crucial for fully understanding chromosome organization.},
	number = {7},
	journal = {Nat Methods},
	author = {Fudenberg, G. and Imakaev, M.},
	month = jul,
	year = {2017},
	pages = {673--678}
}

@article{pliner_chromatin_2017,
	title = {Chromatin accessibility dynamics of myogenesis at single cell resolution},
	shorttitle = {Chromatin accessibility dynamics of myogenesis at single cell resolution},
	doi = {10.1101/155473},
	abstract = {Over a million DNA regulatory elements have been cataloged in the human genome, but linking these elements to the genes that they regulate remains challenging. We introduce Cicero, a statistical method that connects regulatory elements to target genes using single cell chromatin accessibility data. We apply Cicero to investigate how thousands of dynamically accessible elements orchestrate gene regulation in differentiating myoblasts. Groups of co-accessible regulatory elements linked by Cicero meet criteria of “chromatin hubs”, in that they are physically proximal, interact with a common set of transcription factors, and undergo coordinated changes in histone marks that are predictive of gene expression. Pseudotemporal analysis revealed a subset of elements bound by MYOD in myoblasts that exhibit early opening, potentially serving as the initial sites of recruitment of chromatin remodeling and histone-modifying enzymes. The methodological framework described here constitutes a powerful new approach for elucidating the architecture, grammar and mechanisms of cis-regulation on a genome-wide basis.\%U http://www.biorxiv.org/content/biorxiv/early/2017/06/26/155473.full.pdf},
	journal = {bioRxiv},
	author = {Pliner, Hannah and Packer, Jonathan and McFaline-Figueroa, Jose and Cusanovich, Darren and Daza, Riza and Srivatsan, Sanjay and Qiu, Xiaojie and Jackson, Dana and Minkina, Anna and Adey, Andrew and Steemers, Frank and Shendure, Jay and Trapnell, Cole},
	year = {2017}
}

@article{liu_genome_2017,
	title = {Genome {Architecture} {Leads} a {Bifurcation} in {Cell} {Identity}},
	shorttitle = {Genome {Architecture} {Leads} a {Bifurcation} in {Cell} {Identity}},
	doi = {10.1101/151555},
	abstract = {Genome architecture is important in transcriptional regulation, but its dynamics and role during reprogramming are not well understood. Over a time course, we captured genome-wide architecture and transcription during MYOD1-mediated reprogramming of human fibroblasts into the myogenic lineage. We found that chromatin reorganization occurred prior to significant transcriptional changes marking activation of the myogenic program. A global bifurcation event delineated the transition into a myogenic cell identity 32 hours after exogenous MYOD1 activation, an event also reflected in the local dynamics of endogenous MYOD1 and MYOG. These data support a model in which master regulators induce lineage-specific nuclear architecture prior to fulfilling a transcriptional role. Interestingly, early in reprogramming, circadian genes that are MYOD1 targets synchronized their expression patterns. After the bifurcation, myogenic transcription factors that are MYOG targets synchronized their expression, suggesting a cell-type specific rhythm. These data support roles for MYOD1 and MYOG in entraining biological rhythms.\%U http://www.biorxiv.org/content/biorxiv/early/2017/06/18/151555.full.pdf},
	journal = {bioRxiv},
	author = {Liu, Sijia and Chen, Haiming and Ronquist, Scott and Seaman, Laura and Ceglia, Nicholas and Meixner, Walter and Muir, Lindsey A. and Chen, Pin-Yu and Higgins, Gerald and Baldi, Pierre and Smale, Steve and Hero, Alfred and Rajapakse, Indika},
	year = {2017}
}

@article{huang_dissecting_2017,
	title = {Dissecting super-enhancer hierarchy based on chromatin interactions},
	shorttitle = {Dissecting super-enhancer hierarchy based on chromatin interactions},
	url = {http://biorxiv.org/content/biorxiv/early/2017/06/13/149583.full.pdf},
	doi = {10.1101/149583},
	abstract = {Recent studies have highlighted super-enhancers (SEs) as important regulatory elements for gene expression, but their intrinsic properties remain incompletely characterized. Through an integrative analysis of Hi-C and ChIP-seq data, we find that a significant fraction of SEs are hierarchically organized, containing both hub and non-hub enhancers. Hub enhancers share similar histone marks with non-hub enhancers, but are distinctly associated with cohesin and CTCF binding sites and disease-associated genetic variants. Genetic ablation of hub enhancers results in profound defects in gene activation and local chromatin landscape. As such, hub enhancers are the major constituents responsible for SE functional and structural organization.\%U http://www.biorxiv.org/content/biorxiv/early/2017/06/13/149583.full.pdf},
	journal = {bioRxiv},
	author = {Huang, Jialiang and Li, Kailong and Cai, Wenqing and Liu, Xin and Zhang, Yuannyu and Orkin, Stuart H. and Xu, Jian and Yuan, Guo-Cheng},
	year = {2017}
}

@article{rao_cohesin_2017,
	title = {Cohesin {Loss} {Eliminates} {All} {Loop} {Domains}, {Leading} {To} {Links} {Among} {Superenhancers} {And} {Downregulation} {Of} {Nearby} {Genes}},
	shorttitle = {Cohesin {Loss} {Eliminates} {All} {Loop} {Domains}, {Leading} {To} {Links} {Among} {Superenhancers} {And} {Downregulation} {Of} {Nearby} {Genes}},
	doi = {10.1101/139782},
	abstract = {The human genome folds to create thousands of intervals, called “contact domains,” that exhibit enhanced contact frequency within themselves. “Loop domains” form because of tethering between two loci - almost always bound by CTCF and cohesin - lying on the same chromosome. “Compartment domains” form when genomic intervals with similar histone marks co-segregate. Here, we explore the effects of degrading cohesin. All loop domains are eliminated, but neither compartment domains nor histone marks are affected. Loci in different compartments that had been in the same loop domain become more segregated. Loss of loop domains does not lead to widespread ectopic gene activation, but does affect a significant minority of active genes. In particular, cohesin loss causes superenhancers to co-localize, forming hundreds of links within and across chromosomes, and affecting the regulation of nearby genes. Cohesin restoration quickly reverses these effects, consistent with a model where loop extrusion is rapid.\%U http://www.biorxiv.org/content/biorxiv/early/2017/05/18/139782.full.pdf},
	journal = {bioRxiv},
	author = {Rao, Suhas and Huang, Su-Chen and Glenn St. Hilaire, Brian and Engreitz, Jesse M. and Perez, Elizabeth M. and Kieffer-Kwon, Kyong-Rim and Sanborn, Adrian L. and Johnstone, Sarah E. and Bochkov, Ivan D. and Huang, Xingfan and Shamim, Muhammad S. and Omer, Arina D. and Bernstein, Bradley E. and Casellas, Rafael and Lander, Eric S. and Lieberman Aiden, Erez},
	year = {2017}
}

@article{fudenberg_formation_2016,
	title = {Formation of {Chromosomal} {Domains} by {Loop} {Extrusion}},
	volume = {15},
	issn = {2211-1247 (Electronic)},
	shorttitle = {Formation of {Chromosomal} {Domains} by {Loop} {Extrusion}},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/27210764},
	doi = {10.1016/j.celrep.2016.04.085},
	abstract = {Topologically associating domains (TADs) are fundamental structural and functional building blocks of human interphase chromosomes, yet the mechanisms of TAD formation remain unclear. Here, we propose that loop extrusion underlies TAD formation. In this process, cis-acting loop-extruding factors, likely cohesins, form progressively larger loops but stall at TAD boundaries due to interactions with boundary proteins, including CTCF. Using polymer simulations, we show that this model produces TADs and finer-scale features of Hi-C data. Each TAD emerges from multiple loops dynamically formed through extrusion, contrary to typical illustrations of single static loops. Loop extrusion both explains diverse experimental observations-including the preferential orientation of CTCF motifs, enrichments of architectural proteins at TAD boundaries, and boundary deletion experiments-and makes specific predictions for the depletion of CTCF versus cohesin. Finally, loop extrusion has potentially far-ranging consequences for processes such as enhancer-promoter interactions, orientation-specific chromosomal looping, and compaction of mitotic chromosomes.},
	number = {9},
	journal = {Cell Rep},
	author = {Fudenberg, G. and Imakaev, M. and Lu, C. and Goloborodko, A. and Abdennur, N. and Mirny, L. A.},
	month = may,
	year = {2016},
	pages = {2038--49}
}

@article{stansfield_hiccompare:_2017,
	title = {{HiCcompare}: a method for joint normalization of {Hi}-{C} datasets and differential chromatin interaction detection},
	shorttitle = {{HiCcompare}: a method for joint normalization of {Hi}-{C} datasets and differential chromatin interaction detection},
	doi = {10.1101/147850},
	abstract = {Changes in spatial chromatin interactions are now emerging as a unifying mechanism orchestrating regulation of gene expression. Evolution of chromatin conformation capture methods into Hi-C sequencing technology now allows an insight into chromatin interactions on a genome-wide scale. However, Hi-C data contains many DNA sequence- and technology-driven biases. These biases prevent effective comparison of chromatin interactions aimed at identifying genomic regions differentially interacting between, disease-normal states or different cell types. Several methods have been developed for normalizing individual Hi-C datasets. However, they fail to account for biases between two or more Hi-C datasets, hindering comparative analysis of chromatin interactions. We developed a simple and effective method HiCcompare for the joint normalization and differential analysis of multiple Hi-C datasets. The method avoids constraining Hi-C data within a rigid statistical model, allowing a data-driven normalization of biases using locally weighted linear regression (loess). The method identifies region-specific chromatin interaction changes complementary to changes due to large-scale genomic rearrangements, such as copy number variants (CNVs). HiCcompare outperforms methods for normalizing individual Hi-C datasets in detecting a priori known chromatin interaction differences in simulated and real-life settings while detecting biologically relevant changes. HiCcompare is freely available as a Bioconductor R package https://bioconductor.org/packages/HiCcompare.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/28/147850.full.pdf},
	journal = {bioRxiv},
	author = {Stansfield, John and Dozmorov, Mikhail G.},
	year = {2017}
}

@article{rowley_evolutionarily_2017,
	title = {Evolutionarily {Conserved} {Principles} {Predict} 3D {Chromatin} {Organization}},
	issn = {1097-4164 (Electronic) 1097-2765 (Linking)},
	shorttitle = {Evolutionarily {Conserved} {Principles} {Predict} 3D {Chromatin} {Organization}},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28826674},
	doi = {10.1016/j.molcel.2017.07.022},
	abstract = {Topologically associating domains (TADs), CTCF loop domains, and A/B compartments have been identified as important structural and functional components of 3D chromatin organization, yet the relationship between these features is not well understood. Using high-resolution Hi-C and HiChIP, we show that Drosophila chromatin is organized into domains we term compartmental domains that correspond precisely with A/B compartments at high resolution. We find that transcriptional state is a major predictor of Hi-C contact maps in several eukaryotes tested, including C. elegans and A. thaliana. Architectural proteins insulate compartmental domains by reducing interaction frequencies between neighboring regions in Drosophila, but CTCF loops do not play a distinct role in this organism. In mammals, compartmental domains exist alongside CTCF loop domains to form topological domains. The results suggest that compartmental domains are responsible for domain structure in all eukaryotes, with CTCF playing an important role in domain formation in mammals.},
	journal = {Mol Cell},
	author = {Rowley, M. J. and Nichols, M. H. and Lyu, X. and Ando-Kuri, M. and Rivera, I. S. M. and Hermetz, K. and Wang, P. and Ruan, Y. and Corces, V. G.},
	month = aug,
	year = {2017},
	keywords = {Ctcf, Hi-C, Insulator, Tad, compartment, epigenetics, loop, transcription}
}

@article{chakraborty_identification_2017,
	title = {Identification of copy number variations and translocations in cancer cells from {Hi}-{C} data},
	shorttitle = {Identification of copy number variations and translocations in cancer cells from {Hi}-{C} data},
	doi = {10.1101/179275},
	abstract = {Motivation: Eukaryotic chromosomes adapt a complex and highly dynamic three-dimensional (3D) structure, which profoundly affects different cellular functions and outcomes including changes in epigenetic landscape and in gene expression. Making the scenario even more complex, cancer cells harbor chromosomal abnormalities (e.g., copy number variations (CNVs) and translocations) altering their genomes both at the sequence level and at the level of 3D organization. High-throughput chromosome conformation capture techniques (e.g., Hi-C), which are originally developed for decoding the 3D structure of the chromatin, provide a great opportunity to simultaneously identify the locations of genomic rearrangements and to investigate the 3D genome organization in cancer cells. Even though Hi-C data has been used for validating known rearrangements, computational methods that can distinguish rearrangement signals from the inherent biases of Hi-C data and from the actual 3D conformation of chromatin, and can precisely detect rearrangement locations de novo have been missing. Results: In this work, we characterize how intra and inter-chromosomal Hi-C contacts are distributed for normal and rearranged chromosomes to devise a new set of algorithms (i) to identify genomic segments that correspond to CNV regions such as amplifications and deletions (HiCnv), (ii) to call inter-chromosomal translocations and their boundaries (HiCtrans) from Hi-C experiments, and (iii) to simulate Hi-C data from genomes with desired rearrangements and abnormalities (AveSim) in order to select optimal parameters for and to benchmark the accuracy of our methods. Our results on 10 different cancer cell lines with Hi-C data show that we identify a total number of 105 amplifications and 45 deletions together with 90 translocations, whereas we identify virtually no such events for two karyotypically normal cell lines. Our CNV predictions correlate very well with whole genome sequencing (WGS) data among chromosomes with CNV events for a breast cancer cell line (r=0.89) and capture most of the CNVs we simulate using Avesim. For HiCtrans predictions, we report evidence from the literature for 30 out of 90 translocations for eight of our cancer cell lines. Furthermore, we show that our tools identify and correctly classify relatively understudied rearrangements such as double minutes (DMs) and homogeneously staining regions (HSRs). Conclusions: Considering the inherent limitations of existing techniques for karyotyping (i.e., missing balanced rearrangements and those near repetitive regions), the accurate identification of CNVs and translocations in a cost-effective and high-throughput setting is still a challenge. Our results show that the set of tools we develop effectively utilize moderately sequenced Hi-C libraries (100-300 million reads) to identify known and de novo chromosomal rearrangements/abnormalities in well-established cancer cell lines. With the decrease in required number of cells and the increase in attainable resolution, we believe that our framework will pave the way towards comprehensive mapping of genomic rearrangements in primary cells from cancer patients using Hi-C.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/21/179275.full.pdf},
	journal = {bioRxiv},
	author = {Chakraborty, Abhijit and Ay, Ferhat},
	year = {2017}
}

@article{akdemir_spatial_2017,
	title = {Spatial {Genome} {Organization} as a {Framework} for {Somatic} {Alterations} in {Human} {Cancer}},
	shorttitle = {Spatial {Genome} {Organization} as a {Framework} for {Somatic} {Alterations} in {Human} {Cancer}},
	doi = {10.1101/179176},
	abstract = {Genomic material within the nucleus is folded into successive layers in order to package and organize the long string of linear DNA. This hierarchical level of folding is closely associated with transcriptional regulation and DNA replication. Recent chromosome conformation studies have revealed that mammalian chromosomes are structured into tissue-invariant topologically associating domains (TADs) where the DNA within a given domain interacts more frequently together than with regions in other domains. Genes within the same TADs represent similar expression and histone-modification profiles. Therefore, regions separating different TADs (boundaries) have important roles in reinforcing the stability of these domain-wide features. Indeed, TAD boundary disruptions in human genetic disorders or human cancers lead to misregulation of certain genes, due to de novo enhancer exposure to promoters. Here, to understand effects and distributions of somatic structural variations across TADs, we utilized single nucleotide variations and genomic rearrangements from 2658 high-coverage whole genome sequencing data across various cancer types with paired normal samples. Our analysis revealed that deletions between repressed and active TADs result in up-regulation of genes on the repressed end of the deletions, whereas active domain genes remain unaffected. Interestingly, we further identified a strong correlation between the mutational distributions in human cancers and the spatial organization of the genome. Transcriptionally active TADs contain less mutation burden compared to inactive TADs, as a result regional mutation rates are drastically different around the boundaries delineating epigenetically distinct domains. However, mutation rates remain similar around the boundaries for samples with the DNA mismatch repair deficiency. Taken together, our analyses reveal new insights about genome architecture, aberrant gene expression and mutational distributions in human cancers.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/22/179176.full.pdf},
	journal = {bioRxiv},
	author = {Akdemir, Kadir C. and Li, Yilong and Verhaak, Roel G. and Beroukhim, Rameen and Cambell, Peter and Chin, Lynda and Futreal, Andrew},
	year = {2017}
}

@article{chandradoss_ctcf_2017,
	title = {{CTCF} mediated genome architecture regulates the dosage of mitotically stable mono-allelic expression of autosomal genes},
	shorttitle = {{CTCF} mediated genome architecture regulates the dosage of mitotically stable mono-allelic expression of autosomal genes},
	doi = {10.1101/178749},
	abstract = {Mammalian genomes exhibit widespread mono-allelic expression of autosomal genes. However, the mechanistic insight that allows specific expression of one allele remains enigmatic. Here, we present evidence that the linear and the three dimensional architecture of the genome ascribes the appropriate framework that guides the mono-allelic expression of genes. We show that: 1) mono-allelically expressed genes are positioned in clusters that are insulated from bi-allelically expressed genes through CTCF mediated chromatin loops; 2) evolutionary and cell-type specific gain and loss of mono-allelic expression coincide respectively with the gain and loss of chromatin insulator sites; 3) dosage of mono-allelically expressed genes is more sensitive to loss of chromatin insulation associated with CTCF depletion as compared to bi-allelically expressed genes; 4) distinct susceptibility of mono- and bi-allelically expressed genes to CTCF depletion can be attributed to distinct functional roles of CTCF around these genes. Altogether, our observations highlight a general topological framework for the mono-allelic expression of genes, wherein the alleles are insulated from the spatial interference of chromatin and transcriptional states from neighbouring bi-allelic domains via CTCF mediated chromatin loops. The study also suggests that 3D genome organization might have evolved under the constraint to mitigate the fluctuations in the dosage of mono-allelically expressed genes, which otherwise are dosage sensitive.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/21/178749.full.pdf},
	journal = {bioRxiv},
	author = {Chandradoss, Keerthivasan Raanin and Sandhu, Kuljeet Singh},
	year = {2017}
}

@article{wutz_ctcf_2017,
	title = {{CTCF}, {WAPL} and {PDS}5 proteins control the formation of {TADs} and loops by cohesin},
	shorttitle = {{CTCF}, {WAPL} and {PDS}5 proteins control the formation of {TADs} and loops by cohesin},
	doi = {10.1101/177444},
	abstract = {Mammalian genomes are organized into compartments, topologically-associating domains (TADs) and loops to facilitate gene regulation and other chromosomal functions. Compartments are formed by nucleosomal interactions, but how TADs and loops are generated is unknown. It has been proposed that cohesin forms these structures by extruding loops until it encounters CTCF, but direct evidence for this hypothesis is missing. Here we show that cohesin suppresses compartments but is essential for TADs and loops, that CTCF defines their boundaries, and that WAPL and its PDS5 binding partners control the length of chromatin loops. In the absence of WAPL and PDS5 proteins, cohesin passes CTCF sites with increased frequency, forms extended chromatin loops, accumulates in axial chromosomal positions (vermicelli) and condenses chromosomes to an extent normally only seen in mitosis. These results show that cohesin has an essential genome-wide function in mediating long-range chromatin interactions and support the hypothesis that cohesin creates these by loop extrusion, until it is delayed by CTCF in a manner dependent on PDS5 proteins, or until it is released from DNA by WAPL.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/17/177444.full.pdf},
	journal = {bioRxiv},
	author = {Wutz, Gordana and Varnai, Csilla and Nagasaka, Kota and Cisneros, David Amaras and Stocsits, Roman and Tang, Wen and Schoenfelder, Stefan and Jessberger, Gregor and Muhar, Matthias and Hossain, Julius M. and Walther, Nike and Koch, Birgit and Kueblbeck, Moritz and Ellenberg, Jan and Zuber, Johannes and Fraser, Peter and Peters, Jan-Michael},
	year = {2017}
}

@article{rennie_transcriptional_2017,
	title = {Transcriptional decomposition reveals active chromatin architectures and cell specific regulatory interactions},
	shorttitle = {Transcriptional decomposition reveals active chromatin architectures and cell specific regulatory interactions},
	doi = {10.1101/130070},
	abstract = {Transcriptional regulation is tightly coupled with chromosomal positioning and three-dimensional chromatin architecture. However, it is unclear what proportion of transcriptional activity is reflecting such organisation, how much can be informed by RNA expression alone, and how this impacts disease. Here, we develop a transcriptional decomposition approach separating the proportion of expression associated with genome organisation from independent effects not directly related to genomic positioning. We show that positionally attributable expression accounts for a considerable proportion of total levels and is highly informative of topological associating domain activities and organisation, revealing boundaries and chromatin compartments. Furthermore, expression data alone accurately predicts individual enhancer-promoter interactions, drawing features from expression strength, stabilities, insulation and distance. We further characterise commonalities and differences across predictions in 76 human cell types, observing extensive sharing of domains, yet highly cell-type specific enhancer-promoter interactions and strong enrichments in relevant trait-associated variants. Our work demonstrates a close relationship between transcription and chromatin architecture, presenting a novel strategy and an unprecedented resource for investigating regulatory organisations and interpretations of disease associated genetic variants across cell types.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/10/130070.full.pdf},
	journal = {bioRxiv},
	author = {Rennie, Sarah and Dalby, Maria and van Duin, Lucas and Andersson, Robin},
	year = {2017}
}

@article{muller_redesigning_2017,
	title = {Redesigning chromosomes to optimize conformation capture ({Hi}-{C}) assays},
	shorttitle = {Redesigning chromosomes to optimize conformation capture ({Hi}-{C}) assays},
	doi = {10.1101/169847},
	abstract = {In all chromosome conformation capture based experiments the accuracy with which contacts are detected varies considerably because of the uneven distribution of restriction sites along genomes. Here, we redesigned and reassembled in yeast a 145kb region with regularly spaced restriction sites for various enzymes. Thanks to this design, we enhanced the signal to noise ratio and improved the visibility of the entire region as well as our understanding of Hi-C data, while opening new perspectives to future studies.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/28/169847.full.pdf},
	journal = {bioRxiv},
	author = {Muller, Heloise and Scolari, Vittore and Mercy, Guillaume and Agier, Nicolas and Descorps-Declere, Stephane and Fischer, Gilles and Mozziconacci, Julien and Koszul, Romain},
	year = {2017}
}

@article{borges_euplotid:_2017,
	title = {Euplotid: {A} {Linux}-based platform to physically edit the genome},
	shorttitle = {Euplotid: {A} {Linux}-based platform to physically edit the genome},
	doi = {10.1101/170159},
	abstract = {Euplotid is composed of a set of constantly evolving bioinformatic pipelines encapsulated and running in Docker containers enabling a user to build and annotate the local regulatory structure of every gene starting from raw sequencing reads of DNA-interactions, chromatin accessibility, and RNA-sequencing. Reads are quantified using the latest computational tools and the results are normalized, quality-checked, and stored. The local regulatory neighborhood of each gene is built using a Louvain based graph partitioning algorithm parameterized by the chromatin extrusion model and CTCF-CTCF interactions. Cis-Regulatory Elements are defined using chromatin accessibility peaks which are then mapped to Transcription Start Sites based on inclusion within the same neighborhood. Convolutional Neural Networks are combined with Long-Short Term Memory in order to provide a statistical model mimicking transcription factor binding, one neural network for each protein in the genome is trained on all available Chip-Seq and SELEX data, learning what pattern of DNA oligonucleotides the factor binds. The neural networks are then merged and trained on chromatin accessibility data, building a rationally designed neural network architecture capable of predicting chromatin accessibility. Transcription factor binding and identity at each peak is annotated using this trained neural network architecture. By in-silico mutating and re-applying the neural network we are able to gauge the impact of a transition mutation on the binding of any human transcription factor. The annotated output can be visualized in a variety of 1D, 2D and 3D ways overlaid with existing bodies of knowledge, such as GWAS results. Once a particular CRE of interest has been identified by a biologist the difficulty of a Base Editor 2 (BE2) mediated transition mutation can be quantitatively assessed and induced in a model organism.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/03/170159.full.pdf},
	journal = {bioRxiv},
	author = {Borges, Diego},
	year = {2017}
}

@article{delaneau_intra-_2017,
	title = {Intra- and inter-chromosomal chromatin interactions mediate genetic effects on regulatory networks},
	shorttitle = {Intra- and inter-chromosomal chromatin interactions mediate genetic effects on regulatory networks},
	doi = {10.1101/171694},
	abstract = {Genome-wide studies on the genetic basis of gene expression and the structural properties of chromatin have considerably advanced our understanding of the function of the human genome. However, it remains unclear how structure relates to function and, in this work, we aim at bridging both by assembling a dataset that combines the activity of regulatory elements (e.g. enhancers and promoters), expression of genes and genetic variations of 317 individuals and across two cell types. We show that the regulatory activity is structured within 12,583 Cis Regulatory Domains (CRDs) that are cell type specific and highly reflective of the local (i.e. Topologically Associating Domains) and global (i.e. A/B nuclear compartments) nuclear organization of the chromatin. These CRDs essentially delimit the sets of active regulatory elements involved in the transcription of most genes, thereby capturing complex regulatory networks in which the effects of regulatory variants are propagated and combined to finally mediate expression Quantitative Trait Loci. Overall, our analysis reveals the complexity and specificity of cis and trans regulatory networks and their perturbation by genetic variation.\%U http://www.biorxiv.org/content/biorxiv/early/2017/08/03/171694.full.pdf},
	journal = {bioRxiv},
	author = {Delaneau, Olivier and Zazhytska, Marianna and Borel, Christelle and Howald, Cedric and Kumar, Sunil and Ongen, Halit and Popadin, Konstantin and Marbach, Daniel and Ambrosini, Giovanna and Bielser, Deborah and Hacker, David and Romano-Palumbo, Luciana and Ribaux, Pascal and Wiederkehr, Michael and Falconnet, Emilie and Bucher, Philipp and Bergmann, Sven and Antonarakis, Stylianos and Reymond, Alexandre and Dermitzakis, Emmanouil},
	year = {2017}
}

@article{dileep_single-cell_2017,
	title = {Single-cell replication profiling reveals stochastic regulation of the mammalian replication-timing program},
	shorttitle = {Single-cell replication profiling reveals stochastic regulation of the mammalian replication-timing program},
	doi = {10.1101/158352},
	abstract = {In mammalian cells, distinct replication domains (RDs), corresponding to structural units of chromosomes called topologically-associating domains (TADs), replicate at different times during S-phase. Further, early/late replication of RDs corresponds to active/inactive chromatin interaction compartments. Although replication origins are selected stochastically, such that each cell is using a different cohort of origins to replicate their genomes, replication-timing is regulated independently and upstream of origin selection and evidence suggests that replication timing is conserved in consecutive cell cycles. Hence, quantifying the extent of cell-to-cell variation in replication timing is central to studies of chromosome structure and function. Here we devise a strategy to measure variation in single-cell replication timing using DNA copy number. We find that borders between replicated and un-replicated DNA are highly conserved between cells, demarcating active and inactive compartments of the nucleus. Nonetheless, measurable variation was evident. Surprisingly, we detected a similar degree of variation in replication timing from cell-to-cell, between homologues within cells, and between all domains genome-wide regardless of their replication timing. These results demonstrate that stochastic variation in replication timing is independent of elements that dictate timing or extrinsic environmental variation.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/14/158352.full.pdf},
	journal = {bioRxiv},
	author = {Dileep, Vishnu and Gilbert, David M.},
	year = {2017}
}

@article{kojic_distinct_2017,
	title = {Distinct roles of cohesin-{SA}1 and cohesin-{SA}2 in 3D chromosome organization},
	shorttitle = {Distinct roles of cohesin-{SA}1 and cohesin-{SA}2 in 3D chromosome organization},
	doi = {10.1101/166264},
	abstract = {In addition to mediating sister chromatid cohesion, cohesin plays a central role in DNA looping and segmentation of the genome into contact domains (TADs). Two variant cohesin complexes that contain either STAG/SA1 or SA2 are present in all cell types. Here we addressed their specific contribution to genome architecture in non-transformed human cells. We found that cohesin-SA1 drives stacking of cohesin rings at CTCF-bound sites and thereby contributes to the stabilization and preservation of TAD boundaries. In contrast, a more dynamic cohesin-SA2 promotes cell type-specific contacts between enhancers and promoters within TADs independently of CTCF. SA2 loss, a condition frequently observed in cancer cells, results in increased intra-TAD interactions, likely altering the expression of key cell identity genes.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/20/166264.full.pdf},
	journal = {bioRxiv},
	author = {Kojic, Aleksandar and Ana, Cuadrado and De Koninck, Magali and Gomez-Lopez, Gonzalo and Rodriguez-Corsino, Miriam and Le Dily, Francois and Marti-Renom, Marc and Losada, Ana},
	year = {2017}
}

@article{comoglio_thrombopoietin_2017,
	title = {Thrombopoietin signaling to chromatin elicits rapid and pervasive epigenome remodeling within poised chromatin architectures},
	shorttitle = {Thrombopoietin signaling to chromatin elicits rapid and pervasive epigenome remodeling within poised chromatin architectures},
	doi = {10.1101/163113},
	abstract = {Thrombopoietin (TPO) is a critical cytokine regulating hematopoietic stem cell maintenance and differentiation into the megakaryocytic lineage. However, the transcriptional and chromatin dynamics elicited by TPO signaling are poorly understood. Here, we study the immediate early transcriptional and cis-regulatory responses to TPO in hematopoietic stem/progenitor cells (HSPCs) and use this paradigm of cytokine signaling to chromatin to dissect the relation between cis- regulatory activity and chromatin architecture. We show that TPO profoundly alters the transcriptome of HSPCs, with key hematopoietic regulators being transcriptionally repressed within 30 minutes of TPO. By examining cis-regulatory dynamics and chromatin architectures, we demonstrate that these changes are accompanied by rapid and extensive epigenome remodeling of cis-regulatory landscapes that is spatially coordinated within topologically associating domains (TADs). Moreover, TPO-responsive enhancers are spatially clustered and engage in preferential homotypic intra- and inter-TAD interactions that are largely refractory to TPO signaling. By further examining the link between cis-regulatory dynamics and chromatin looping, we show that rapid modulation of cis-regulatory activity is largely independent of chromatin looping dynamics. Finally, we show that, although activated and repressed cis-regulatory elements share remarkably similar DNA sequence compositions, transcription factor binding patterns accurately predict rapid cis-regulatory responses to TPO.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/13/163113.full.pdf},
	journal = {bioRxiv},
	author = {Comoglio, Federico and Park, Hyun Jung and Schoenfelder, Stefan and Barozzi, Iros and Bode, Daniel and Fraser, Peter and Green, Anthony R},
	year = {2017}
}

@article{servant_effective_2017,
	title = {Effective normalization for copy number variation in {Hi}-{C} data},
	shorttitle = {Effective normalization for copy number variation in {Hi}-{C} data},
	doi = {10.1101/167031},
	abstract = {Normalization is essential to ensure accurate analysis and proper interpretation of sequencing data. Chromosome conformation data, such as Hi-C, is not different. The most widely used type of normalization of Hi-C data casts estimations of unwanted effects as a matrix balancing problem, relying on the assumption that all genomic regions interact as much as any other. Here, we show that these approaches, while very effective on fully haploid or diploid genome, fail to correct for unwanted effects in the presence of copy number variations. We propose a simple extension to matrix balancing methods that properly models the copy-number variation effects. Our approach can either retain the copy-number variation effects or remove it. We show that this leads to better downstream analysis of the three-dimensional organization of rearranged genome.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/21/167031.full.pdf},
	journal = {bioRxiv},
	author = {Servant, Nicolas and Varoqaux, Nelle and Heard, Edith and Vert, Jean-Philippe and Emmanuel, Barillot},
	year = {2017}
}

@article{bonora_orientation-dependent_2017,
	title = {Orientation-dependent {Dxz}4 contacts shape the 3D structure of the inactive {X} chromosome},
	shorttitle = {Orientation-dependent {Dxz}4 contacts shape the 3D structure of the inactive {X} chromosome},
	doi = {10.1101/165340},
	abstract = {The mammalian inactive X chromosome (Xi) condenses into a bipartite structure with two superdomains of frequent long-range contacts separated by a boundary or hinge region. Using in situ DNase Hi-C in mouse cells with deletions or inversions within the hinge we show that the conserved repeat locus Dxz4 alone is sufficient to maintain the bipartite structure and that Dxz4 orientation controls the distribution of long-range contacts on the Xi. Frequent long-range contacts between Dxz4 and the telomeric superdomain are either lost after its deletion or shifted to the centromeric superdomain after its inversion. This massive reversal in contact distribution is consistent with the reversal of CTCF motif orientation at Dxz4. De-condensation of the Xi after Dxz4 deletion is associated with partial restoration of TADs normally attenuated on the Xi, and with an increase in chromatin accessibility and CTCF binding, but few changes in gene expression, in accordance with multiple epigenetic mechanisms ensuring X silencing. We propose that Dxz4 represents a structural platform for frequent long-range contacts with multiple loci in a direction dictated by the orientation of a bank of CTCF motifs at Dxz4, which may work as a ratchet to form the distinctive bipartite structure of the condensed Xi.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/19/165340.full.pdf},
	journal = {bioRxiv},
	author = {Bonora, Giancarlo and Deng, Xinxian and Fang, He and Ramani, Vijay and Qui, Ruolan and Berletch, Joel and Filippova, Gala N and Duan, Zhijun and Schendure, Jay and Noble, William S and Disteche, Christine M},
	year = {2017}
}

@article{zhu_gem:_2017,
	title = {{GEM}: {A} manifold learning based framework for reconstructing spatial organizations of chromosomes},
	shorttitle = {{GEM}: {A} manifold learning based framework for reconstructing spatial organizations of chromosomes},
	doi = {10.1101/161208},
	abstract = {Decoding the spatial organizations of chromosomes has crucial implications for studying eukaryotic gene regulation. Recently, Chromosomal conformation capture based technologies, such as Hi-C, have been widely used to uncover the interaction frequencies of genomic loci in high-throughput and genome-wide manner and provide new insights into the folding of three-dimensional (3D) genome structure. In this paper, we develop a novel manifold learning framework, called GEM (Genomic organization reconstructor based on conformational Energy and Manifold learning), to elucidate the underlying 3D spatial organizations of chromosomes from Hi-C data. Unlike previous chromatin structure reconstruction methods, which explicitly assume specific relationships between Hi-C interaction frequencies and spatial distances between distal genomic loci, GEM is able to reconstruct an ensemble of chromatin conformations by directly embedding the neighboring affinities from Hi-C space into 3D Euclidean space based on a manifold learning strategy that considers both the fitness of Hi-C data and the biophysical feasibility of the modeled structures, which are measured by the conformational energy derived from our current biophysical knowledge about the 3D polymer model. Extensive validation tests on both simulated interaction frequency data and experimental Hi-C data of yeast and human demonstrated that GEM not only greatly outperformed other state-of-art modeling methods but also reconstructed accurate chromatin structures that agreed well with the hold-out or independent Hi-C data and sparse geometric restraints derived from the previous fluorescence in situ hybridization (FISH) studies. In addition, as GEM can generate accurate spatial organizations of chromosomes by integrating both experimentally-derived spatial contacts and conformational energy, we for the first time extended our modeling method to recover long-range genomic interactions that are missing from the original Hi-C data. All these results indicated that GEM can provide a physically and physiologically valid 3D representations of the organizations of chromosomes and thus serve as an effective and useful genome structure reconstructor.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/09/161208.full.pdf},
	journal = {bioRxiv},
	author = {Zhu, Guangxiang and Deng, Wenxuan and Hu, Hailin and Ma, Rui and Zhang, Sai and Yang, Jinglin and Peng, Jian and Kaplan, Tommy and Zeng, Jianyang},
	year = {2017}
}

@article{lekschas_hipiler:_2017,
	title = {{HiPiler}: {Visual} {Exploration} {Of} {Large} {Genome} {Interaction} {Matrices} {With} {Interactive} {Small} {Multiples}},
	shorttitle = {{HiPiler}: {Visual} {Exploration} {Of} {Large} {Genome} {Interaction} {Matrices} {With} {Interactive} {Small} {Multiples}},
	doi = {10.1101/123588},
	abstract = {This paper presents an interactive visualization interface - HiPiler - for the exploration and visualization of regions-of-interest in large genome interaction matrices. Genome interaction matrices approximate the physical distance of pairs of genomic regions to each other and can contain up to 3 million rows and columns with many sparse regions. Traditional matrix aggregation or pan-and-zoom interfaces largely fail in supporting search, inspection, and comparison of local regions-of-interest (ROIs). ROIs can be defined, e.g., by sets of adjacent rows and columns, or by specific visual patterns in the matrix. ROIs are first-class objects in HiPiler, which represents them as thumbnail-like “snippets”. Snippets can be laid out automatically based on their data and meta attributes. They are linked back to the matrix and can be explored interactively. The design of HiPiler is based on a series of semi-structured interviews with 10 domain experts involved in the analysis and interpretation of genome interaction matrices. We describe six exploration tasks that are crucial for analysis of interaction matrices and demonstrate how HiPiler supports these tasks. We report on a user study with a series of data exploration sessions with domain experts to assess the usability of HiPiler as well as to demonstrate respective findings in the data.\%U http://www.biorxiv.org/content/biorxiv/early/2017/07/09/123588.full.pdf},
	journal = {bioRxiv},
	author = {Lekschas, Fritz and Bach, Benjamin and Kerpedjiev, Peter and Gehlenborg, Nils and Pfister, Hanspeter},
	year = {2017}
}

@article{ke_3d_2017,
	title = {3D {Chromatin} {Structures} of {Mature} {Gametes} and {Structural} {Reprogramming} during {Mammalian} {Embryogenesis}},
	volume = {170},
	issn = {1097-4172 (Electronic) 0092-8674 (Linking)},
	shorttitle = {3D {Chromatin} {Structures} of {Mature} {Gametes} and {Structural} {Reprogramming} during {Mammalian} {Embryogenesis}},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28709003},
	doi = {10.1016/j.cell.2017.06.029},
	abstract = {High-order chromatin structure plays important roles in gene expression regulation. Knowledge of the dynamics of 3D chromatin structures during mammalian embryo development remains limited. We report the 3D chromatin architecture of mouse gametes and early embryos using an optimized Hi-C method with low-cell samples. We find that mature oocytes at the metaphase II stage do not have topologically associated domains (TADs). In sperm, extra-long-range interactions ({\textgreater}4 Mb) and interchromosomal interactions occur frequently. The high-order structures of both the paternal and maternal genomes in zygotes and two-cell embryos are obscure but are gradually re-established through development. The establishment of the TAD structure requires DNA replication but not zygotic genome activation. Furthermore, unmethylated CpGs are enriched in A compartment, and methylation levels are decreased to a greater extent in A compartment than in B compartment in embryos. In summary, the global reprogramming of chromatin architecture occurs during early mammalian development.},
	number = {2},
	journal = {Cell},
	author = {Ke, Y. and Xu, Y. and Chen, X. and Feng, S. and Liu, Z. and Sun, Y. and Yao, X. and Li, F. and Zhu, W. and Gao, L. and Chen, H. and Du, Z. and Xie, W. and Xu, X. and Huang, X. and Liu, J.},
	month = jul,
	year = {2017},
	keywords = {Hi-C, Tad, chromatin structure, compartment, embryo development, epigenetic, gamete, zygotic genome activation},
	pages = {367--381 e20}
}

@article{mackay_graphi-c:_2017,
	title = {{GrapHi}-{C}: {Graph}-based visualization of {Hi}-{C} {Datasets}},
	shorttitle = {{GrapHi}-{C}: {Graph}-based visualization of {Hi}-{C} {Datasets}},
	doi = {10.1101/156679},
	abstract = {Background: Hi-C is a proximity-based ligation reaction used to detect regions of the genome that are close in 3D space (or “interacting”). Typically, results from Hi-C experiments (whole-genome contact maps) are visualized as heatmaps or Circos plots. While informative, these visualizations do not intuitively represent the complex organization and folding of the genome in 3D space, making the interpretation of the underlying 3D genomic organization difficult. Our objective was to utilize existing tools to generate a graph-based representation of a whole-genome contact map that leads to a more intuitive visualization. Methodology: Whole-genome contact maps were converted into graphs where each vertex represented a genomic region and each edge represented a detected or known interaction between two vertices. Three types of interactions were represented in the graph: linear, intra-chromosomal (cis-), and inter-chromosomal (trans-) interactions. Each edge had an associated weight related to the linear distance (Hi-C experimental resolution) or the associated interaction frequency from the contact map. Graphs were generated based on this representation scheme for whole-genome contact maps from a fission yeast dataset where yeast mutants were used to identify specific principles influencing genome organization (GEO accession: GSE56849). Graphs were visualized in Cytoscape with an edge-weighted spring embedded layout where vertices and linear interaction edges were coloured according to their corresponding chromosome. Results: The graph-based visualizations (compared to the equivalent heatmaps) more intuitively represented the effects of the rad21 mutant on genome organization. Specifically, the graph based visualizations clearly highlighted the loss of structural globules and a greater intermingling of chromosomes in the mutant strain when compared to the wild-type. The graph-based representation and visualization protocol developed here will aid in understanding the complex organization and folding of the genome.\%U http://www.biorxiv.org/content/biorxiv/early/2017/06/27/156679.full.pdf},
	journal = {bioRxiv},
	author = {MacKay, Kimberly and Kusalik, Anthony and Eskiw, Christopher H.},
	year = {2017}
}

@article{stadler_convergence_2017,
	title = {Convergence of topological domain boundaries, insulators, and polytene interbands revealed by high-resolution mapping of chromatin contacts in the early {Drosophila} melanogaster embryo},
	shorttitle = {Convergence of topological domain boundaries, insulators, and polytene interbands revealed by high-resolution mapping of chromatin contacts in the early {Drosophila} melanogaster embryo},
	doi = {10.1101/149344},
	abstract = {Evidence has emerged in recent years linking insulators and the proteins that bind them to the higher order structure of animal chromatin, but the precise nature of this relationship and the manner by which insulators influence chromatin structure have remained elusive. Here we present high-resolution genome-wide chromatin conformation capture (Hi-C) data from early Drosophila melanogaster embryos that allow us to map three-dimensional interactions to 500 base pairs. We observe a complex, nested pattern of regions of chromatin self-association, and use a combination of computational and manual annotation to identify boundaries between these topological associated domains (TADs). We demonstrate that, when mapped at high resolution, boundaries resemble classical insulators: short (500-1000 bp) genomic regions that are sensitive to DNase digestion and strongly bound by known insulator proteins. Strikingly, we show that for regions where the banding pattern of polytene chromosomes has been mapped to genomic position at comparably high resolution, there is a perfect correspondence between polytene banding and our chromatin conformation maps, with boundary insulators forming the interband regions that separate compacted bands that correspond to TADs. We propose that this precise, high-resolution relationship between insulators and TADs on the one hand and polytene bands and interbands on the other extends across the genome, and suggest a model in which the decompaction of insulator regions drives the organization of interphase chromosomes by creating stable physical separation between adjacent domains.\%U http://biorxiv.org/content/biorxiv/early/2017/06/13/149344.full.pdf},
	journal = {bioRxiv},
	author = {Stadler, Michael R. and Haines, Jenna E. and Eisen, Michael B.},
	year = {2017}
}

@article{nora_targeted_2017,
	title = {Targeted {Degradation} of {CTCF} {Decouples} {Local} {Insulation} of {Chromosome} {Domains} from {Genomic} {Compartmentalization}},
	volume = {169},
	issn = {1097-4172 (Electronic) 0092-8674 (Linking)},
	shorttitle = {Targeted {Degradation} of {CTCF} {Decouples} {Local} {Insulation} of {Chromosome} {Domains} from {Genomic} {Compartmentalization}},
	url = {https://www.ncbi.nlm.nih.gov/pubmed/28525758},
	doi = {10.1016/j.cell.2017.05.004},
	abstract = {The molecular mechanisms underlying folding of mammalian chromosomes remain poorly understood. The transcription factor CTCF is a candidate regulator of chromosomal structure. Using the auxin-inducible degron system in mouse embryonic stem cells, we show that CTCF is absolutely and dose-dependently required for looping between CTCF target sites and insulation of topologically associating domains (TADs). Restoring CTCF reinstates proper architecture on altered chromosomes, indicating a powerful instructive function for CTCF in chromatin folding. CTCF remains essential for TAD organization in non-dividing cells. Surprisingly, active and inactive genome compartments remain properly segregated upon CTCF depletion, revealing that compartmentalization of mammalian chromosomes emerges independently of proper insulation of TADs. Furthermore, our data support that CTCF mediates transcriptional insulator function through enhancer blocking but not as a direct barrier to heterochromatin spreading. Beyond defining the functions of CTCF in chromosome folding, these results provide new fundamental insights into the rules governing mammalian genome organization.},
	number = {5},
	journal = {Cell},
	author = {Nora, E. P. and Goloborodko, A. and Valton, A. L. and Gibcus, J. H. and Uebersohn, A. and Abdennur, N. and Dekker, J. and Mirny, L. A. and Bruneau, B. G.},
	month = may,
	year = {2017},
	pages = {930--944 e22}
}

@article{zhang_hicplus:_2017,
	title = {{HiCPlus}: {Resolution} {Enhancement} of {Hi}-{C} interaction heatmap},
	shorttitle = {{HiCPlus}: {Resolution} {Enhancement} of {Hi}-{C} interaction heatmap},
	doi = {10.1101/112631},
	abstract = {Motivation: The Hi-C technology has become an efficient tool to measure the spatial organization of the genome. With the recent advance of 1Kb resolution Hi-C experiment, some of the essential regulatory features have been uncovered. However, most available Hi-C datasets are in coarse-resolution due to the extremely high cost for generating high-resolution data. Therefore, a computational method to maximum the usage of the current available Hi-C data is urgently desired. Results: Inspired by the super-resolution image technique, we develop a computational approach to impute the high-resolution Hi-C data from low-resolution Hi-C data using the deep convolutional neural network. We hypothesize that the Hi-C interaction heatmap contains the repeating features, and develop an end-to-end framework to map these features from low-resolution Hi-C heatmap to high-resolution Hi-C heatmap at the feature level. Our approach successfully reconstructs the high-resolution Hi-C interaction map from the low-resolution counterpart, which also proves that the Hi-C interaction matrix is a combination of the regional features. Besides, our approach is highly expandable, and we can also increase prediction accuracy by incorporating ChIA-PET data. Availability: Source code is publicly available at https://github.com/zhangyan32/HiCPlus\%U http://biorxiv.org/content/biorxiv/early/2017/03/01/112631.full.pdf},
	journal = {bioRxiv},
	author = {Zhang, Yan and An, Lin and Hu, Ming and Tang, Jijun and Yue, Feng},
	year = {2017}
}

@article{phanstiel_static_2017,
	title = {Static {And} {Dynamic} {DNA} {Loops} {Form} {AP}-1 {Bound} {Activation} {Hubs} {During} {Macrophage} {Development}},
	shorttitle = {Static {And} {Dynamic} {DNA} {Loops} {Form} {AP}-1 {Bound} {Activation} {Hubs} {During} {Macrophage} {Development}},
	doi = {10.1101/142026},
	abstract = {The three-dimensional arrangement of the human genome comprises a complex network of structural and regulatory chromatin loops important for coordinating changes in transcription during human development. To better understand the mechanisms underlying context-specific 3D chromatin structure and transcription during cellular differentiation, we generated comprehensive in situ Hi-C maps of DNA loops during human monocyte-to-macrophage differentiation. We demonstrate that dynamic looping events are regulatory rather than structural in nature and uncover widespread coordination of dynamic enhancer activity at preformed and acquired DNA loops. Enhancer-bound loop formation and enhancer-activation of preformed loops represent two distinct modes of regulation that together form multi-loop activation hubs at key macrophage genes. Activation hubs connect 3.4 enhancers per promoter and exhibit a strong enrichment for Activator Protein 1 (AP-1) binding events, suggesting multi-loop activation hubs driven by cell-type specific transcription factors may represent an important class of regulatory chromatin structures for the spatiotemporal control of transcription.\%U http://www.biorxiv.org/content/biorxiv/early/2017/05/25/142026.full.pdf},
	journal = {bioRxiv},
	author = {Phanstiel, Douglas H. and Van Bortle, Kevin and Spacek, Damek V. and Hess, Gaelen T. and Saad Shamim, Muhammad and Machol, Ido and Love, Michael I. and Lieberman Aiden, Erez and Bassik, Michael C. and Snyder, Michael P.},
	year = {2017}
}

@article{stevens_3d_2017,
	title = {3D structures of individual mammalian genomes studied by single-cell {Hi}-{C}},
	volume = {advance online publication},
	issn = {1476-4687},
	shorttitle = {3D structures of individual mammalian genomes studied by single-cell {Hi}-{C}},
	url = {http://dx.doi.org/10.1038/nature21429},
	doi = {10.1038/nature21429},
	abstract = {The folding of genomic DNA from the beads-on-a-string-like structure of nucleosomes into higher-order assemblies is crucially linked to nuclear processes. Here we calculate 3D structures of entire mammalian genomes using data from a new chromosome conformation capture procedure that allows us to first image and then process single cells. The technique enables genome folding to be examined at a scale of less than 100 kb, and chromosome structures to be validated. The structures of individual topological-associated domains and loops vary substantially from cell to cell. By contrast, A and B compartments, lamina-associated domains and active enhancers and promoters are organized in a consistent way on a genome-wide basis in every cell, suggesting that they could drive chromosome and genome folding. By studying genes regulated by pluripotency factor and nucleosome remodelling deacetylase (NuRD), we illustrate how the determination of single-cell genome structure provides a new approach for investigating biological processes.},
	journal = {Nature},
	author = {Stevens, Tim J. and Lando, David and Basu, Srinjan and Atkinson, Liam P. and Cao, Yang and Lee, Steven F. and Leeb, Martin and Wohlfahrt, Kai J. and Boucher, Wayne and O’Shaughnessy-Kirwan, Aoife and Cramard, Julie and Faure, Andre J. and Ralser, Meryem and Blanco, Enrique and Morey, Lluis and Sansó, Miriam and Palayret, Matthieu G. S. and Lehner, Ben and Di Croce, Luciano and Wutz, Anton and Hendrich, Brian and Klenerman, Dave and Laue, Ernest D.},
	year = {2017}
}

@article{eagen_stable_2015,
	title = {Stable {Chromosome} {Condensation} {Revealed} by {Chromosome} {Conformation} {Capture}},
	volume = {163},
	issn = {1097-4172 (Electronic) 0092-8674 (Linking)},
	shorttitle = {Stable {Chromosome} {Condensation} {Revealed} by {Chromosome} {Conformation} {Capture}},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/26544940},
	doi = {10.1016/j.cell.2015.10.026},
	abstract = {Chemical cross-linking and DNA sequencing have revealed regions of intra-chromosomal interaction, referred to as topologically associating domains (TADs), interspersed with regions of little or no interaction, in interphase nuclei. We find that TADs and the regions between them correspond with the bands and interbands of polytene chromosomes of Drosophila. We further establish the conservation of TADs between polytene and diploid cells of Drosophila. From direct measurements on light micrographs of polytene chromosomes, we then deduce the states of chromatin folding in the diploid cell nucleus. Two states of folding, fully extended fibers containing regulatory regions and promoters, and fibers condensed up to 10-fold containing coding regions of active genes, constitute the euchromatin of the nuclear interior. Chromatin fibers condensed up to 30-fold, containing coding regions of inactive genes, represent the heterochromatin of the nuclear periphery. A convergence of molecular analysis with direct observation thus reveals the architecture of interphase chromosomes.},
	number = {4},
	journal = {Cell},
	author = {Eagen, K. P. and Hartl, T. A. and Kornberg, R. D.},
	month = nov,
	year = {2015},
	keywords = {Animals, Cell Nucleus/chemistry/genetics, Chromosomal Puffs, Diploidy, Drosophila melanogaster/chemistry/cytology/*genetics/growth \& development, Genetic Techniques, Larva/chemistry, Polytene Chromosomes/*chemistry},
	pages = {934--46}
}

@article{giorgetti_predictive_2014,
	title = {Predictive polymer modeling reveals coupled fluctuations in chromosome conformation and transcription},
	volume = {157},
	issn = {1097-4172 (Electronic) 0092-8674 (Linking)},
	shorttitle = {Predictive polymer modeling reveals coupled fluctuations in chromosome conformation and transcription},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/24813616},
	doi = {10.1016/j.cell.2014.03.025},
	abstract = {A new level of chromosome organization, topologically associating domains (TADs), was recently uncovered by chromosome conformation capture (3C) techniques. To explore TAD structure and function, we developed a polymer model that can extract the full repertoire of chromatin conformations within TADs from population-based 3C data. This model predicts actual physical distances and to what extent chromosomal contacts vary between cells. It also identifies interactions within single TADs that stabilize boundaries between TADs and allows us to identify and genetically validate key structural elements within TADs. Combining the model's predictions with high-resolution DNA FISH and quantitative RNA FISH for TADs within the X-inactivation center (Xic), we dissect the relationship between transcription and spatial proximity to cis-regulatory elements. We demonstrate that contacts between potential regulatory elements occur in the context of fluctuating structures rather than stable loops and propose that such fluctuations may contribute to asymmetric expression in the Xic during X inactivation.},
	number = {4},
	journal = {Cell},
	author = {Giorgetti, L. and Galupa, R. and Nora, E. P. and Piolot, T. and Lam, F. and Dekker, J. and Tiana, G. and Heard, E.},
	month = may,
	year = {2014},
	keywords = {*Transcription, Genetic, *X Chromosome Inactivation, Animals, Chromatin/chemistry, Chromosomes/*chemistry, Female, In Situ Hybridization, Fluorescence, Male, Mice, Models, Biological, Models, Molecular, RNA, Long Noncoding/metabolism},
	pages = {950--63}
}

@article{fullwood_chromatin_2010,
	title = {Chromatin interaction analysis using paired-end tag sequencing},
	volume = {Chapter 21},
	issn = {1934-3647 (Electronic) 1934-3647 (Linking)},
	shorttitle = {Chromatin interaction analysis using paired-end tag sequencing},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/20069536},
	doi = {10.1002/0471142727.mb2115s89},
	abstract = {Chromatin Interaction Analysis using Paired-End Tag sequencing (ChIA-PET) is a technique developed for large-scale, de novo analysis of higher-order chromatin structures. Cells are treated with formaldehyde to cross-link chromatin interactions, DNA segments bound by protein factors are enriched by chromatin immunoprecipitation, and interacting DNA fragments are then captured by proximity ligation. The Paired-End Tag (PET) strategy is applied to the construction of ChIA-PET libraries, which are sequenced by high-throughput next-generation sequencing technologies. Finally, raw PET sequences are subjected to bioinformatics analysis, resulting in a genome-wide map of binding sites and chromatin interactions mediated by the protein factor under study. This unit describes ChIA-PET for genome-wide analysis of chromatin interactions in mammalian cells, with the application of Roche/454 and Illumina sequencing technologies.},
	journal = {Curr Protoc Mol Biol},
	author = {Fullwood, M. J. and Han, Y. and Wei, C. L. and Ruan, X. and Ruan, Y.},
	month = jan,
	year = {2010},
	keywords = {*Databases, Nucleic Acid, Animals, Chromatin/*genetics, Computational Biology/*methods, Genome-Wide Association Study/*methods, Humans, Sequence Analysis, DNA/*methods},
	pages = {Unit 21 15 1--25}
}

@article{hughes_analysis_2014,
	title = {Analysis of hundreds of cis-regulatory landscapes at high resolution in a single, high-throughput experiment},
	volume = {46},
	issn = {1546-1718 (Electronic) 1061-4036 (Linking)},
	shorttitle = {Analysis of hundreds of cis-regulatory landscapes at high resolution in a single, high-throughput experiment},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/24413732},
	doi = {10.1038/ng.2871},
	abstract = {Gene expression during development and differentiation is regulated in a cell- and stage-specific manner by complex networks of intergenic and intragenic cis-regulatory elements whose numbers and representation in the genome far exceed those of structural genes. Using chromosome conformation capture, it is now possible to analyze in detail the interaction between enhancers, silencers, boundary elements and promoters at individual loci, but these techniques are not readily scalable. Here we present a high-throughput approach (Capture-C) to analyze cis interactions, interrogating hundreds of specific interactions at high resolution in a single experiment. We show how this approach will facilitate detailed, genome-wide analysis to elucidate the general principles by which cis-acting sequences control gene expression. In addition, we show how Capture-C will expedite identification of the target genes and functional effects of SNPs that are associated with complex diseases, which most frequently lie in intergenic cis-acting regulatory elements.},
	number = {2},
	journal = {Nat Genet},
	author = {Hughes, J. R. and Roberts, N. and McGowan, S. and Hay, D. and Giannoulatou, E. and Lynch, M. and De Gobbi, M. and Taylor, S. and Gibbons, R. and Higgs, D. R.},
	month = feb,
	year = {2014},
	keywords = {Animals, Base Sequence, Chromatin Immunoprecipitation, Female, Gene Expression Regulation, Developmental/*genetics, Gene Library, Genetic Diseases, Inborn/*genetics, High-Throughput Screening Assays/*methods, Humans, Mice, Molecular Sequence Data, Polymorphism, Single Nucleotide/genetics, Regulatory Elements, Transcriptional/*genetics, Sequence Analysis, DNA},
	pages = {205--12}
}

@article{sanborn_chromatin_2015,
	title = {Chromatin extrusion explains key features of loop and domain formation in wild-type and engineered genomes},
	issn = {1091-6490 (Electronic) 0027-8424 (Linking)},
	shorttitle = {Chromatin extrusion explains key features of loop and domain formation in wild-type and engineered genomes},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/26499245},
	doi = {10.1073/pnas.1518552112},
	abstract = {We recently used in situ Hi-C to create kilobase-resolution 3D maps of mammalian genomes. Here, we combine these maps with new Hi-C, microscopy, and genome-editing experiments to study the physical structure of chromatin fibers, domains, and loops. We find that the observed contact domains are inconsistent with the equilibrium state for an ordinary condensed polymer. Combining Hi-C data and novel mathematical theorems, we show that contact domains are also not consistent with a fractal globule. Instead, we use physical simulations to study two models of genome folding. In one, intermonomer attraction during polymer condensation leads to formation of an anisotropic "tension globule." In the other, CCCTC-binding factor (CTCF) and cohesin act together to extrude unknotted loops during interphase. Both models are consistent with the observed contact domains and with the observation that contact domains tend to form inside loops. However, the extrusion model explains a far wider array of observations, such as why loops tend not to overlap and why the CTCF-binding motifs at pairs of loop anchors lie in the convergent orientation. Finally, we perform 13 genome-editing experiments examining the effect of altering CTCF-binding sites on chromatin folding. The convergent rule correctly predicts the affected loops in every case. Moreover, the extrusion model accurately predicts in silico the 3D maps resulting from each experiment using only the location of CTCF-binding sites in the WT. Thus, we show that it is possible to disrupt, restore, and move loops and domains using targeted mutations as small as a single base pair.},
	journal = {Proc Natl Acad Sci U S A},
	author = {Sanborn, A. L. and Rao, S. S. and Huang, S. C. and Durand, N. C. and Huntley, M. H. and Jewett, A. I. and Bochkov, I. D. and Chinnappan, D. and Cutkosky, A. and Li, J. and Geeting, K. P. and Gnirke, A. and Melnikov, A. and McKenna, D. and Stamenova, E. K. and Lander, E. S. and Aiden, E. L.},
	month = oct,
	year = {2015}
}

@article{li_widespread_2015,
	title = {Widespread rearrangement of 3D chromatin organization underlies polycomb-mediated stress-induced silencing},
	volume = {58},
	issn = {1097-4164 (Electronic) 1097-2765 (Linking)},
	shorttitle = {Widespread rearrangement of 3D chromatin organization underlies polycomb-mediated stress-induced silencing},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25818644},
	doi = {10.1016/j.molcel.2015.02.023},
	abstract = {Chromosomes of metazoan organisms are partitioned in the interphase nucleus into discrete topologically associating domains (TADs). Borders between TADs are formed in regions containing active genes and clusters of architectural protein binding sites. The transcription of most genes is repressed after temperature stress in Drosophila. Here we show that temperature stress induces relocalization of architectural proteins from TAD borders to inside TADs, and this is accompanied by a dramatic rearrangement in the 3D organization of the nucleus. TAD border strength declines, allowing for an increase in long-distance inter-TAD interactions. Similar but quantitatively weaker effects are observed upon inhibition of transcription or depletion of individual architectural proteins. Heat shock-induced inter-TAD interactions result in increased contacts among enhancers and promoters of silenced genes, which recruit Pc and form Pc bodies in the nucleolus. These results suggest that the TAD organization of metazoan genomes is plastic and can be reconfigured quickly.},
	number = {2},
	journal = {Mol Cell},
	author = {Li, L. and Lyu, X. and Hou, C. and Takenaka, N. and Nguyen, H. Q. and Ong, C. T. and Cubenas-Potts, C. and Hu, M. and Lei, E. P. and Bosco, G. and Qin, Z. S. and Corces, V. G.},
	month = apr,
	year = {2015},
	keywords = {Animals, Cell Line, Chromatin/*genetics, Chromosomes/*genetics, Drosophila Proteins/chemistry/*genetics/metabolism, Drosophila melanogaster/*genetics/metabolism, Enhancer Elements, Genetic, Molecular Sequence Data, Polycomb-Group Proteins/chemistry/genetics/*metabolism, Promoter Regions, Genetic, Regulatory Sequences, Nucleic Acid, Stress, Physiological, Temperature},
	pages = {216--31}
}

@article{crane_condensin-driven_2015,
	title = {Condensin-driven remodelling of {X} chromosome topology during dosage compensation},
	volume = {523},
	issn = {1476-4687 (Electronic) 0028-0836 (Linking)},
	shorttitle = {Condensin-driven remodelling of {X} chromosome topology during dosage compensation},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/26030525},
	doi = {10.1038/nature14450},
	abstract = {The three-dimensional organization of a genome plays a critical role in regulating gene expression, yet little is known about the machinery and mechanisms that determine higher-order chromosome structure. Here we perform genome-wide chromosome conformation capture analysis, fluorescent in situ hybridization (FISH), and RNA-seq to obtain comprehensive three-dimensional (3D) maps of the Caenorhabditis elegans genome and to dissect X chromosome dosage compensation, which balances gene expression between XX hermaphrodites and XO males. The dosage compensation complex (DCC), a condensin complex, binds to both hermaphrodite X chromosomes via sequence-specific recruitment elements on X (rex sites) to reduce chromosome-wide gene expression by half. Most DCC condensin subunits also act in other condensin complexes to control the compaction and resolution of all mitotic and meiotic chromosomes. By comparing chromosome structure in wild-type and DCC-defective embryos, we show that the DCC remodels hermaphrodite X chromosomes into a sex-specific spatial conformation distinct from autosomes. Dosage-compensated X chromosomes consist of self-interacting domains ( approximately 1 Mb) resembling mammalian topologically associating domains (TADs). TADs on X chromosomes have stronger boundaries and more regular spacing than on autosomes. Many TAD boundaries on X chromosomes coincide with the highest-affinity rex sites and become diminished or lost in DCC-defective mutants, thereby converting the topology of X to a conformation resembling autosomes. rex sites engage in DCC-dependent long-range interactions, with the most frequent interactions occurring between rex sites at DCC-dependent TAD boundaries. These results imply that the DCC reshapes the topology of X chromosomes by forming new TAD boundaries and reinforcing weak boundaries through interactions between its highest-affinity binding sites. As this model predicts, deletion of an endogenous rex site at a DCC-dependent TAD boundary using CRISPR/Cas9 greatly diminished the boundary. Thus, the DCC imposes a distinct higher-order structure onto X chromosomes while regulating gene expression chromosome-wide.},
	number = {7559},
	journal = {Nature},
	author = {Crane, E. and Bian, Q. and McCord, R. P. and Lajoie, B. R. and Wheeler, B. S. and Ralston, E. J. and Uzawa, S. and Dekker, J. and Meyer, B. J.},
	month = jul,
	year = {2015},
	keywords = {Adenosine Triphosphatases/*metabolism, Animals, Caenorhabditis elegans Proteins/genetics/*metabolism, Caenorhabditis elegans/*genetics/*metabolism, DNA-Binding Proteins/*metabolism, Dosage Compensation, Genetic/genetics/*physiology, Female, Gene Expression Regulation, In Situ Hybridization, Fluorescence, Male, Multiprotein Complexes/*metabolism, Protein Binding, Sequence Analysis, RNA, X Chromosome/genetics/*metabolism},
	pages = {240--4}
}

@article{ay_statistical_2014,
	title = {Statistical confidence estimation for {Hi}-{C} data reveals regulatory chromatin contacts},
	volume = {24},
	issn = {1549-5469 (Electronic) 1088-9051 (Linking)},
	shorttitle = {Statistical confidence estimation for {Hi}-{C} data reveals regulatory chromatin contacts},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/24501021},
	doi = {10.1101/gr.160374.113},
	abstract = {Our current understanding of how DNA is packed in the nucleus is most accurate at the fine scale of individual nucleosomes and at the large scale of chromosome territories. However, accurate modeling of DNA architecture at the intermediate scale of approximately 50 kb-10 Mb is crucial for identifying functional interactions among regulatory elements and their target promoters. We describe a method, Fit-Hi-C, that assigns statistical confidence estimates to mid-range intra-chromosomal contacts by jointly modeling the random polymer looping effect and previously observed technical biases in Hi-C data sets. We demonstrate that our proposed approach computes accurate empirical null models of contact probability without any distribution assumption, corrects for binning artifacts, and provides improved statistical power relative to a previously described method. High-confidence contacts identified by Fit-Hi-C preferentially link expressed gene promoters to active enhancers identified by chromatin signatures in human embryonic stem cells (ESCs), capture 77\% of RNA polymerase II-mediated enhancer-promoter interactions identified using ChIA-PET in mouse ESCs, and confirm previously validated, cell line-specific interactions in mouse cortex cells. We observe that insulators and heterochromatin regions are hubs for high-confidence contacts, while promoters and strong enhancers are involved in fewer contacts. We also observe that binding peaks of master pluripotency factors such as NANOG and POU5F1 are highly enriched in high-confidence contacts for human ESCs. Furthermore, we show that pairs of loci linked by high-confidence contacts exhibit similar replication timing in human and mouse ESCs and preferentially lie within the boundaries of topological domains for human and mouse cell lines.},
	number = {6},
	journal = {Genome Res},
	author = {Ay, F. and Bailey, T. L. and Noble, W. S.},
	month = jun,
	year = {2014},
	keywords = {*Chromatin Assembly and Disassembly, *Models, Genetic, *Regulatory Sequences, Nucleic Acid, Animals, Chromatin/chemistry/*genetics, Confidence Intervals, Embryonic Stem Cells/metabolism, Histone Code, Homeodomain Proteins/genetics/metabolism, Humans, Mice, Neurons/metabolism, Octamer Transcription Factor-3/genetics/metabolism, Protein Binding, Species Specificity, Yeasts/genetics},
	pages = {999--1011}
}

@article{ay_identifying_2015,
	title = {Identifying multi-locus chromatin contacts in human cells using tethered multiple 3C},
	volume = {16},
	issn = {1471-2164 (Electronic) 1471-2164 (Linking)},
	shorttitle = {Identifying multi-locus chromatin contacts in human cells using tethered multiple 3C},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25887659},
	doi = {10.1186/s12864-015-1236-7},
	abstract = {BACKGROUND: Several recently developed experimental methods, each an extension of the chromatin conformation capture (3C) assay, have enabled the genome-wide profiling of chromatin contacts between pairs of genomic loci in 3D. Especially in complex eukaryotes, data generated by these methods, coupled with other genome-wide datasets, demonstrated that non-random chromatin folding correlates strongly with cellular processes such as gene expression and DNA replication. RESULTS: We describe a genome architecture assay, tethered multiple 3C (TM3C), that maps genome-wide chromatin contacts via a simple protocol of restriction enzyme digestion and religation of fragments upon agarose gel beads followed by paired-end sequencing. In addition to identifying contacts between pairs of loci, TM3C enables identification of contacts among more than two loci simultaneously. We use TM3C to assay the genome architectures of two human cell lines: KBM7, a near-haploid chronic leukemia cell line, and NHEK, a normal diploid human epidermal keratinocyte cell line. We confirm that the contact frequency maps produced by TM3C exhibit features characteristic of existing genome architecture datasets, including the expected scaling of contact probabilities with genomic distance, megabase scale chromosomal compartments and sub-megabase scale topological domains. We also confirm that TM3C captures several known cell type-specific contacts, ploidy shifts and translocations, such as Philadelphia chromosome formation (Ph+) in KBM7. We confirm a subset of the triple contacts involving the IGF2-H19 imprinting control region (ICR) using PCR analysis for KBM7 cells. Our genome-wide analysis of pairwise and triple contacts demonstrates their preference for linking open chromatin regions to each other and for linking regions with higher numbers of DNase hypersensitive sites (DHSs) to each other. For near-haploid KBM7 cells, we infer whole genome 3D models that exhibit clustering of small chromosomes with each other and large chromosomes with each other, consistent with previous studies of the genome architectures of other human cell lines. CONCLUSION: TM3C is a simple protocol for ascertaining genome architecture and can be used to identify simultaneous contacts among three or four loci. Application of TM3C to a near-haploid human cell line revealed large-scale features of chromosomal organization and multi-way chromatin contacts that preferentially link regions of open chromatin.},
	journal = {BMC Genomics},
	author = {Ay, F. and Vu, T. H. and Zeitz, M. J. and Varoquaux, N. and Carette, J. E. and Vert, J. P. and Hoffman, A. R. and Noble, W. S.},
	year = {2015},
	pages = {121}
}

@article{selvaraj_whole-genome_2013,
	title = {Whole-genome haplotype reconstruction using proximity-ligation and shotgun sequencing},
	volume = {31},
	issn = {1546-1696 (Electronic) 1087-0156 (Linking)},
	shorttitle = {Whole-genome haplotype reconstruction using proximity-ligation and shotgun sequencing},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/24185094},
	doi = {10.1038/nbt.2728},
	abstract = {Rapid advances in high-throughput sequencing facilitate variant discovery and genotyping, but linking variants into a single haplotype remains challenging. Here we demonstrate HaploSeq, an approach for assembling chromosome-scale haplotypes by exploiting the existence of 'chromosome territories'. We use proximity ligation and sequencing to show that alleles on homologous chromosomes occupy distinct territories, and therefore this experimental protocol preferentially recovers physically linked DNA variants on a homolog. Computational analysis of such data sets allows for accurate ( approximately 99.5\%) reconstruction of chromosome-spanning haplotypes for approximately 95\% of alleles in hybrid mouse cells with 30x sequencing coverage. To resolve haplotypes for a human genome, which has a low density of variants, we coupled HaploSeq with local conditional phasing to obtain haplotypes for approximately 81\% of alleles with approximately 98\% accuracy from just 17x sequencing. Whereas methods based on proximity ligation were originally designed to investigate spatial organization of genomes, our results lend support for their use as a general tool for haplotyping.},
	number = {12},
	journal = {Nat Biotechnol},
	author = {Selvaraj, S. and J, R. Dixon and Bansal, V. and Ren, B.},
	month = dec,
	year = {2013},
	keywords = {*Algorithms, Base Sequence, Chromosome Mapping/*methods, Genome, Human/*genetics, Haplotypes/*genetics, Humans, Molecular Sequence Data, Polymorphism, Single Nucleotide/*genetics, Sequence Analysis, DNA/*methods},
	pages = {1111--8}
}

@article{hu_hicnorm:_2012,
	title = {{HiCNorm}: removing biases in {Hi}-{C} data via {Poisson} regression},
	volume = {28},
	issn = {1367-4811 (Electronic) 1367-4803 (Linking)},
	shorttitle = {{HiCNorm}: removing biases in {Hi}-{C} data via {Poisson} regression},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/23023982},
	doi = {10.1093/bioinformatics/bts570},
	abstract = {SUMMARY: We propose a parametric model, HiCNorm, to remove systematic biases in the raw Hi-C contact maps, resulting in a simple, fast, yet accurate normalization procedure. Compared with the existing Hi-C normalization method developed by Yaffe and Tanay, HiCNorm has fewer parameters, runs {\textgreater}1000 times faster and achieves higher reproducibility. AVAILABILITY: Freely available on the web at: http://www.people.fas.harvard.edu/ approximately junliu/HiCNorm/. CONTACT: jliu@stat.harvard.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
	number = {23},
	journal = {Bioinformatics},
	author = {Hu, M. and Deng, K. and Selvaraj, S. and Qin, Z. and Ren, B. and Liu, J. S.},
	month = dec,
	year = {2012},
	keywords = {*Linear Models, *Software, Base Composition, Chromatin/genetics, Chromosome Mapping/*methods, Genomic Library, Internet, Reproducibility of Results, Statistics, Nonparametric},
	pages = {3131--3}
}

@article{servant_hitc:_2012,
	title = {{HiTC}: exploration of high-throughput '{C}' experiments},
	volume = {28},
	issn = {1367-4811 (Electronic) 1367-4803 (Linking)},
	shorttitle = {{HiTC}: exploration of high-throughput '{C}' experiments},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/22923296},
	doi = {10.1093/bioinformatics/bts521},
	abstract = {SUMMARY: The R/Bioconductor package HiTC facilitates the exploration of high-throughput 3C-based data. It allows users to import and export 'C' data, to transform, normalize, annotate and visualize interaction maps. The package operates within the Bioconductor framework and thus offers new opportunities for future development in this field. AVAILABILITY AND IMPLEMENTATION: The R package HiTC is available from the Bioconductor website. A detailed vignette provides additional documentation and help for using the package.},
	number = {21},
	journal = {Bioinformatics},
	author = {Servant, N. and Lajoie, B. R. and Nora, E. P. and Giorgetti, L. and Chen, C. J. and Heard, E. and Dekker, J. and Barillot, E.},
	month = nov,
	year = {2012},
	keywords = {*Software, Animals, Chromosome Mapping/instrumentation/*methods, Chromosomes, Human, Pair 14/chemistry/genetics, Data Display, Humans, Mice, Molecular Conformation, Restriction Mapping/instrumentation/*methods},
	pages = {2843--4}
}

@article{rao_3d_2014,
	title = {A 3D {Map} of the {Human} {Genome} at {Kilobase} {Resolution} {Reveals} {Principles} of {Chromatin} {Looping}},
	volume = {159},
	issn = {1097-4172 (Electronic) 0092-8674 (Linking)},
	shorttitle = {A 3D {Map} of the {Human} {Genome} at {Kilobase} {Resolution} {Reveals} {Principles} of {Chromatin} {Looping}},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25497547},
	doi = {10.1016/j.cell.2014.11.021},
	abstract = {We use in situ Hi-C to probe the 3D architecture of genomes, constructing haploid and diploid maps of nine cell types. The densest, in human lymphoblastoid cells, contains 4.9 billion contacts, achieving 1 kb resolution. We find that genomes are partitioned into contact domains (median length, 185 kb), which are associated with distinct patterns of histone marks and segregate into six subcompartments. We identify approximately 10,000 loops. These loops frequently link promoters and enhancers, correlate with gene activation, and show conservation across cell types and species. Loop anchors typically occur at domain boundaries and bind CTCF. CTCF sites at loop anchors occur predominantly ({\textgreater}90\%) in a convergent orientation, with the asymmetric motifs "facing" one another. The inactive X chromosome splits into two massive domains and contains large loops anchored at CTCF-binding repeats. PAPERFLICK:},
	number = {7},
	journal = {Cell},
	author = {Rao, S. S. and Huntley, M. H. and Durand, N. C. and Stamenova, E. K. and Bochkov, I. D. and Robinson, J. T. and Sanborn, A. L. and Machol, I. and Omer, A. D. and Lander, E. S. and Aiden, E. L.},
	month = dec,
	year = {2014},
	pages = {1665--80}
}

@article{dryden_unbiased_2014,
	title = {Unbiased analysis of potential targets of breast cancer susceptibility loci by {Capture} {Hi}-{C}},
	volume = {24},
	issn = {1549-5469 (Electronic) 1088-9051 (Linking)},
	shorttitle = {Unbiased analysis of potential targets of breast cancer susceptibility loci by {Capture} {Hi}-{C}},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25122612},
	doi = {10.1101/gr.175034.114},
	abstract = {Genome-wide association studies have identified more than 70 common variants that are associated with breast cancer risk. Most of these variants map to non-protein-coding regions and several map to gene deserts, regions of several hundred kilobases lacking protein-coding genes. We hypothesized that gene deserts harbor long-range regulatory elements that can physically interact with target genes to influence their expression. To test this, we developed Capture Hi-C (CHi-C), which, by incorporating a sequence capture step into a Hi-C protocol, allows high-resolution analysis of targeted regions of the genome. We used CHi-C to investigate long-range interactions at three breast cancer gene deserts mapping to 2q35, 8q24.21, and 9q31.2. We identified interaction peaks between putative regulatory elements ("bait fragments") within the captured regions and "targets" that included both protein-coding genes and long noncoding (lnc) RNAs over distances of 6.6 kb to 2.6 Mb. Target protein-coding genes were IGFBP5, KLF4, NSMCE2, and MYC; and target lncRNAs included DIRC3, PVT1, and CCDC26. For one gene desert, we were able to define two SNPs (rs12613955 and rs4442975) that were highly correlated with the published risk variant and that mapped within the bait end of an interaction peak. In vivo ChIP-qPCR data show that one of these, rs4442975, affects the binding of FOXA1 and implicate this SNP as a putative functional variant.},
	number = {11},
	journal = {Genome Res},
	author = {Dryden, N. H. and Broome, L. R. and Dudbridge, F. and Johnson, N. and Orr, N. and Schoenfelder, S. and Nagano, T. and Andrews, S. and Wingett, S. and Kozarewa, I. and Assiotis, I. and Fenwick, K. and Maguire, S. L. and Campbell, J. and Natrajan, R. and Lambros, M. and Perrakis, E. and Ashworth, A. and Fraser, P. and Fletcher, O.},
	month = nov,
	year = {2014},
	pages = {1854--68}
}

@article{le_dily_distinct_2014,
	title = {Distinct structural transitions of chromatin topological domains correlate with coordinated hormone-induced gene regulation},
	volume = {28},
	issn = {1549-5477 (Electronic) 0890-9369 (Linking)},
	shorttitle = {Distinct structural transitions of chromatin topological domains correlate with coordinated hormone-induced gene regulation},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25274727},
	doi = {10.1101/gad.241422.114},
	abstract = {The human genome is segmented into topologically associating domains (TADs), but the role of this conserved organization during transient changes in gene expression is not known. Here we describe the distribution of progestin-induced chromatin modifications and changes in transcriptional activity over TADs in T47D breast cancer cells. Using ChIP-seq (chromatin immunoprecipitation combined with high-throughput sequencing), Hi-C (chromosome capture followed by high-throughput sequencing), and three-dimensional (3D) modeling techniques, we found that the borders of the approximately 2000 TADs in these cells are largely maintained after hormone treatment and that up to 20\% of the TADs could be considered as discrete regulatory units where the majority of the genes are either transcriptionally activated or repressed in a coordinated fashion. The epigenetic signatures of the TADs are homogeneously modified by hormones in correlation with the transcriptional changes. Hormone-induced changes in gene activity and chromatin remodeling are accompanied by differential structural changes for activated and repressed TADs, as reflected by specific and opposite changes in the strength of intra-TAD interactions within responsive TADs. Indeed, 3D modeling of the Hi-C data suggested that the structure of TADs was modified upon treatment. The differential responses of TADs to progestins and estrogens suggest that TADs could function as "regulons" to enable spatially proximal genes to be coordinately transcribed in response to hormones.},
	number = {19},
	journal = {Genes Dev},
	author = {Le Dily, F. and Bau, D. and Pohl, A. and Vicent, G. P. and Serra, F. and Soronellas, D. and Castellano, G. and Wright, R. H. and Ballare, C. and Filion, G. and Marti-Renom, M. A. and Beato, M.},
	month = oct,
	year = {2014},
	keywords = {Hi-C, TADs, epigenetic landscape, gene expression, progesterone receptor, three-dimensional structure of the genome, transcriptional regulation},
	pages = {2151--62}
}

@article{dixon_topological_2012,
	title = {Topological domains in mammalian genomes identified by analysis of chromatin interactions},
	volume = {485},
	issn = {1476-4687 (Electronic) 0028-0836 (Linking)},
	shorttitle = {Topological domains in mammalian genomes identified by analysis of chromatin interactions},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/22495300},
	doi = {10.1038/nature11082},
	abstract = {The spatial organization of the genome is intimately linked to its biological function, yet our understanding of higher order genomic structure is coarse, fragmented and incomplete. In the nucleus of eukaryotic cells, interphase chromosomes occupy distinct chromosome territories, and numerous models have been proposed for how chromosomes fold within chromosome territories. These models, however, provide only few mechanistic details about the relationship between higher order chromatin structure and genome function. Recent advances in genomic technologies have led to rapid advances in the study of three-dimensional genome organization. In particular, Hi-C has been introduced as a method for identifying higher order chromatin interactions genome wide. Here we investigate the three-dimensional organization of the human and mouse genomes in embryonic stem cells and terminally differentiated cell types at unprecedented resolution. We identify large, megabase-sized local chromatin interaction domains, which we term 'topological domains', as a pervasive structural feature of the genome organization. These domains correlate with regions of the genome that constrain the spread of heterochromatin. The domains are stable across different cell types and highly conserved across species, indicating that topological domains are an inherent property of mammalian genomes. Finally, we find that the boundaries of topological domains are enriched for the insulator binding protein CTCF, housekeeping genes, transfer RNAs and short interspersed element (SINE) retrotransposons, indicating that these factors may have a role in establishing the topological domain structure of the genome.},
	number = {7398},
	journal = {Nature},
	author = {Dixon, J. R. and Selvaraj, S. and Yue, F. and Kim, A. and Li, Y. and Shen, Y. and Hu, M. and Liu, J. S. and Ren, B.},
	month = may,
	year = {2012},
	keywords = {*Genome, Animals, Binding Sites, Cell Differentiation, Chromatin/chemistry/*genetics/*metabolism, Chromosomes/chemistry/genetics/metabolism, Embryonic Stem Cells/metabolism, Evolution, Molecular, Female, Genes, Essential/genetics, Heterochromatin/chemistry/genetics/metabolism, Humans, Male, Mammals/genetics, Mice, RNA, Transfer/genetics, Repressor Proteins/metabolism, Short Interspersed Nucleotide Elements/genetics},
	pages = {376--80}
}

@article{hou_gene_2012,
	title = {Gene density, transcription, and insulators contribute to the partition of the {Drosophila} genome into physical domains},
	volume = {48},
	issn = {1097-4164 (Electronic) 1097-2765 (Linking)},
	shorttitle = {Gene density, transcription, and insulators contribute to the partition of the {Drosophila} genome into physical domains},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/23041285},
	doi = {10.1016/j.molcel.2012.08.031},
	abstract = {The mechanisms responsible for the establishment of physical domains in metazoan chromosomes are poorly understood. Here we find that physical domains in Drosophila chromosomes are demarcated at regions of active transcription and high gene density that are enriched for transcription factors and specific combinations of insulator proteins. Physical domains contain different types of chromatin defined by the presence of specific proteins and epigenetic marks, with active chromatin preferentially located at the borders and silenced chromatin in the interior. Domain boundaries participate in long-range interactions that may contribute to the clustering of regions of active or silenced chromatin in the nucleus. Analysis of transgenes suggests that chromatin is more accessible and permissive to transcription at the borders than inside domains, independent of the presence of active or silencing histone modifications. These results suggest that the higher-order physical organization of chromatin may impose an additional level of regulation over classical epigenetic marks.},
	number = {3},
	journal = {Mol Cell},
	author = {Hou, C. and Li, L. and Qin, Z. S. and Corces, V. G.},
	month = nov,
	year = {2012},
	keywords = {*Transcription, Genetic, Animals, Cell Line, Chromatin/genetics, Chromosome Mapping, Chromosomes, Insect/genetics, Drosophila Proteins/genetics/metabolism, Drosophila melanogaster/cytology/*genetics, Gene Dosage, Gene Expression Regulation, Genome, Insect/*genetics, Histones/metabolism, Insulator Elements/*genetics, Transcription Initiation Site},
	pages = {471--84}
}

@article{sexton_3d_2013,
	title = {The 3D genome shapes up for pluripotency},
	volume = {13},
	issn = {1875-9777 (Electronic)},
	shorttitle = {The 3D genome shapes up for pluripotency},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/23827701},
	doi = {10.1016/j.stem.2013.06.013},
	abstract = {Chromosome folding has been long associated with gene expression. Articles in Cell Stem Cell and Cell by Apostolou et al., (2013), Phillips-Cremins et al., (2013), Wei et al., (2013), and Zhang et al., (2013) uncover chromatin interaction networks linked to the establishment or maintenance of pluripotency and identify some responsible factors.},
	number = {1},
	journal = {Cell Stem Cell},
	author = {Sexton, T. and Cavalli, G.},
	month = jul,
	year = {2013},
	keywords = {*Cell Lineage, *Epigenesis, Genetic, *Genome, Animals, Cell Cycle Proteins/*metabolism, Chromatin/*genetics/*metabolism, Chromosomal Proteins, Non-Histone/*metabolism, Chromosomes/*genetics, Embryonic Stem Cells/*cytology, Humans, Induced Pluripotent Stem Cells/*cytology, Kruppel-Like Transcription Factors/*metabolism, Nuclear Proteins/*analysis, Nuclear Reprogramming/*genetics, Octamer Transcription Factor-3/*metabolism, Pluripotent Stem Cells/*cytology},
	pages = {3--4}
}

@article{sofueva_cohesin-mediated_2013,
	title = {Cohesin-mediated interactions organize chromosomal domain architecture},
	volume = {32},
	issn = {1460-2075 (Electronic) 0261-4189 (Linking)},
	shorttitle = {Cohesin-mediated interactions organize chromosomal domain architecture},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/24185899},
	doi = {10.1038/emboj.2013.237},
	abstract = {To ensure proper gene regulation within constrained nuclear space, chromosomes facilitate access to transcribed regions, while compactly packaging all other information. Recent studies revealed that chromosomes are organized into megabase-scale domains that demarcate active and inactive genetic elements, suggesting that compartmentalization is important for genome function. Here, we show that very specific long-range interactions are anchored by cohesin/CTCF sites, but not cohesin-only or CTCF-only sites, to form a hierarchy of chromosomal loops. These loops demarcate topological domains and form intricate internal structures within them. Post-mitotic nuclei deficient for functional cohesin exhibit global architectural changes associated with loss of cohesin/CTCF contacts and relaxation of topological domains. Transcriptional analysis shows that this cohesin-dependent perturbation of domain organization leads to widespread gene deregulation of both cohesin-bound and non-bound genes. Our data thereby support a role for cohesin in the global organization of domain structure and suggest that domains function to stabilize the transcriptional programmes within them.},
	number = {24},
	journal = {EMBO J},
	author = {Sofueva, S. and Yaffe, E. and Chan, W. C. and Georgopoulou, D. and Vietri Rudan, M. and Mira-Bontenbal, H. and Pollard, S. M. and Schroth, G. P. and Tanay, A. and Hadjur, S.},
	month = dec,
	year = {2013},
	keywords = {Animals, Catalytic Domain, Cell Cycle Proteins/chemistry/genetics/*metabolism, Cell Proliferation, Cells, Cultured, Chromosomal Proteins, Non-Histone/chemistry/genetics/*metabolism, Chromosomes/*chemistry/*metabolism, Gene Expression Regulation, Mice, Mitosis, Nuclear Proteins/genetics/metabolism, Phosphoproteins/genetics/metabolism, Repressor Proteins/metabolism, Stem Cells/physiology, Transcription, Genetic},
	pages = {3119--29}
}

@article{yaffe_probabilistic_2011,
	title = {Probabilistic modeling of {Hi}-{C} contact maps eliminates systematic biases to characterize global chromosomal architecture},
	volume = {43},
	issn = {1546-1718 (Electronic) 1061-4036 (Linking)},
	shorttitle = {Probabilistic modeling of {Hi}-{C} contact maps eliminates systematic biases to characterize global chromosomal architecture},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/22001755},
	doi = {10.1038/ng.947},
	abstract = {Hi-C experiments measure the probability of physical proximity between pairs of chromosomal loci on a genomic scale. We report on several systematic biases that substantially affect the Hi-C experimental procedure, including the distance between restriction sites, the GC content of trimmed ligation junctions and sequence uniqueness. To address these biases, we introduce an integrated probabilistic background model and develop algorithms to estimate its parameters and renormalize Hi-C data. Analysis of corrected human lymphoblast contact maps provides genome-wide evidence for interchromosomal aggregation of active chromatin marks, including DNase-hypersensitive sites and transcriptionally active foci. We observe extensive long-range (up to 400 kb) cis interactions at active promoters and derive asymmetric contact profiles next to transcription start sites and CTCF binding sites. Clusters of interacting chromosomal domains suggest physical separation of centromere-proximal and centromere-distal regions. These results provide a computational basis for the inference of chromosomal architectures from Hi-C experiments.},
	number = {11},
	journal = {Nat Genet},
	author = {Yaffe, E. and Tanay, A.},
	month = nov,
	year = {2011},
	keywords = {*Chromosomes, Human, *Models, Genetic, *Probability, Binding Sites, Cluster Analysis, Epigenesis, Genetic, Humans, Lymphocytes/ultrastructure},
	pages = {1059--65}
}

@article{huang_crispr_2016,
	title = {{CRISPR} {Double} {Cutting} through the {Labyrinthine} {Architecture} of 3D {Genomes}},
	volume = {43},
	issn = {1673-8527 (Print) 1673-8527 (Linking)},
	shorttitle = {{CRISPR} {Double} {Cutting} through the {Labyrinthine} {Architecture} of 3D {Genomes}},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/27210040},
	doi = {10.1016/j.jgg.2016.03.006},
	abstract = {The genomes are organized into ordered and hierarchical topological structures in interphase nuclei. Within discrete territories of each chromosome, topologically associated domains (TADs) play important roles in various nuclear processes such as gene regulation. Inside TADs separated by relatively constitutive boundaries, distal elements regulate their gene targets through specific chromatin-looping contacts such as long-distance enhancer-promoter interactions. High-throughput sequencing studies have revealed millions of potential regulatory DNA elements, which are much more abundant than the mere approximately 20,000 genes they control. The recently emerged CRISPR-Cas9 genome editing technologies have enabled efficient and precise genetic and epigenetic manipulations of genomes. The multiplexed and high-throughput CRISPR capabilities facilitate the discovery and dissection of gene regulatory elements. Here, we describe the applications of CRISPR for genome, epigenome, and 3D genome editing, focusing on CRISPR DNA-fragment editing with Cas9 and a pair of sgRNAs to investigate topological folding of chromatin TADs and developmental gene regulation.},
	number = {5},
	journal = {J Genet Genomics},
	author = {Huang, H. and Wu, Q.},
	month = may,
	year = {2016},
	keywords = {Chromatin architecture, Ctcf, DNA-fragment editing, Enhancer, Insulator, Topological domain},
	pages = {273--88}
}

@article{tiana_structural_2016,
	title = {Structural {Fluctuations} of the {Chromatin} {Fiber} within {Topologically} {Associating} {Domains}},
	volume = {110},
	issn = {1542-0086 (Electronic) 0006-3495 (Linking)},
	shorttitle = {Structural {Fluctuations} of the {Chromatin} {Fiber} within {Topologically} {Associating} {Domains}},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/27028634},
	doi = {10.1016/j.bpj.2016.02.003},
	abstract = {Experiments based on chromosome conformation capture have shown that mammalian genomes are partitioned into topologically associating domains (TADs), within which the chromatin fiber preferentially interacts. TADs may provide three-dimensional scaffolds allowing genes to contact their appropriate distal regulatory DNA sequences (e.g., enhancers) and thus to be properly regulated. Understanding the cell-to-cell and temporal variability of the chromatin fiber within TADs, and what determines them, is thus of great importance to better understand transcriptional regulation. We recently described an equilibrium polymer model that can accurately predict cell-to-cell variation of chromosome conformation within single TADs, from chromosome conformation capture-based data. Here we further analyze the conformational and energetic properties of our model. We show that the chromatin fiber within TADs can easily fluctuate between several conformational states, which are hierarchically organized and are not separated by important free energy barriers, and that this is facilitated by the fact that the chromatin fiber within TADs is close to the onset of the coil-globule transition. We further show that in this dynamic state the properties of the chromatin fiber, and its contact probabilities in particular, are determined in a nontrivial manner not only by site-specific interactions between strongly interacting loci along the fiber, but also by nonlocal correlations between pairs of contacts. Finally, we use live-cell experiments to measure the dynamics of the chromatin fiber in mouse embryonic stem cells, in combination with dynamical simulations, and predict that conformational changes within one TAD are likely to occur on timescales that are much shorter than the duration of one cell cycle. This suggests that genes and their regulatory elements may come together and disassociate several times during a cell cycle. These results have important implications for transcriptional regulation as they support the concept of highly dynamic interactions driven by a complex interplay between site-specific interactions and the intrinsic biophysical properties of the chromatin fiber.},
	number = {6},
	journal = {Biophys J},
	author = {Tiana, G. and Amitai, A. and Pollex, T. and Piolot, T. and Holcman, D. and Heard, E. and Giorgetti, L.},
	month = mar,
	year = {2016},
	pages = {1234--45}
}

@article{levy-leduc_two-dimensional_2014,
	title = {Two-dimensional segmentation for analyzing {Hi}-{C} data},
	volume = {30},
	issn = {1367-4811 (Electronic) 1367-4803 (Linking)},
	shorttitle = {Two-dimensional segmentation for analyzing {Hi}-{C} data},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25161224},
	doi = {10.1093/bioinformatics/btu443},
	abstract = {MOTIVATION: The spatial conformation of the chromosome has a deep influence on gene regulation and expression. Hi-C technology allows the evaluation of the spatial proximity between any pair of loci along the genome. It results in a data matrix where blocks corresponding to (self-)interacting regions appear. The delimitation of such blocks is critical to better understand the spatial organization of the chromatin. From a computational point of view, it results in a 2D segmentation problem. RESULTS: We focus on the detection of cis-interacting regions, which appear to be prominent in observed data. We define a block-wise segmentation model for the detection of such regions. We prove that the maximization of the likelihood with respect to the block boundaries can be rephrased in terms of a 1D segmentation problem, for which the standard dynamic programming applies. The performance of the proposed methods is assessed by a simulation study on both synthetic and resampled data. A comparative study on public data shows good concordance with biologically confirmed regions. AVAILABILITY AND IMPLEMENTATION: The HiCseg R package is available from the Comprehensive R Archive Network and from the Web page of the corresponding author.},
	number = {17},
	journal = {Bioinformatics},
	author = {Levy-Leduc, C. and Delattre, M. and Mary-Huard, T. and Robin, S.},
	month = sep,
	year = {2014},
	keywords = {Animals, Chromatin/chemistry, Chromosomes, Human/chemistry, Chromosomes, Mammalian/*chemistry, High-Throughput Nucleotide Sequencing, Humans, Mice, Models, Statistical, Sequence Analysis, DNA},
	pages = {i386--92}
}

@article{battulin_comparison_2015,
	title = {Comparison of the three-dimensional organization of sperm and fibroblast genomes using the {Hi}-{C} approach},
	volume = {16},
	issn = {1474-760X (Electronic) 1474-7596 (Linking)},
	shorttitle = {Comparison of the three-dimensional organization of sperm and fibroblast genomes using the {Hi}-{C} approach},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25886366},
	doi = {10.1186/s13059-015-0642-0},
	abstract = {BACKGROUND: The three-dimensional organization of the genome is tightly connected to its biological function. The Hi-C approach was recently introduced as a method that can be used to identify higher-order chromatin interactions genome-wide. The aim of this study was to determine genome-wide chromatin interaction frequencies using the Hi-C approach in mouse sperm cells and embryonic fibroblasts. RESULTS: The obtained data demonstrate that the three-dimensional genome organizations of sperm and fibroblast cells show a high degree of similarity both with each other and with the previously described mouse embryonic stem cells. Both A- and B-compartments and topologically associated domains are present in spermatozoa and fibroblasts. Nevertheless, sperm cells and fibroblasts exhibit statistically significant differences between each other in the contact probabilities of defined loci. Tight packaging of the sperm genome results in an enrichment of long-range contacts compared with the fibroblasts. However, only 30\% of the differences in the number of contacts are based on differences in the densities of their genome packages; the main source of the differences is the gain or loss of contacts that are specific for defined genome regions. We find that the dependence of the contact probability on genomic distance for sperm is close to the dependence predicted for the fractal globular folding of chromatin. CONCLUSIONS: Overall, we can conclude that the three-dimensional structure of the genome is passed through generations without being dramatically changed in sperm cells.},
	journal = {Genome Biol},
	author = {Battulin, N. and Fishman, V. S. and Mazur, A. M. and Pomaznoy, M. and Khabarova, A. A. and Afonnikov, D. A. and Prokhortchouk, E. B. and Serov, O. L.},
	year = {2015},
	pages = {77}
}

@article{libbrecht_joint_2015,
	title = {Joint annotation of chromatin state and chromatin conformation reveals relationships among domain types and identifies domains of cell-type-specific expression},
	volume = {25},
	issn = {1549-5469 (Electronic) 1088-9051 (Linking)},
	shorttitle = {Joint annotation of chromatin state and chromatin conformation reveals relationships among domain types and identifies domains of cell-type-specific expression},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25677182},
	doi = {10.1101/gr.184341.114},
	abstract = {The genomic neighborhood of a gene influences its activity, a behavior that is attributable in part to domain-scale regulation. Previous genomic studies have identified many types of regulatory domains. However, due to the difficulty of integrating genomics data sets, the relationships among these domain types are poorly understood. Semi-automated genome annotation (SAGA) algorithms facilitate human interpretation of heterogeneous collections of genomics data by simultaneously partitioning the human genome and assigning labels to the resulting genomic segments. However, existing SAGA methods cannot integrate inherently pairwise chromatin conformation data. We developed a new computational method, called graph-based regularization (GBR), for expressing a pairwise prior that encourages certain pairs of genomic loci to receive the same label in a genome annotation. We used GBR to exploit chromatin conformation information during genome annotation by encouraging positions that are close in 3D to occupy the same type of domain. Using this approach, we produced a model of chromatin domains in eight human cell types, thereby revealing the relationships among known domain types. Through this model, we identified clusters of tightly regulated genes expressed in only a small number of cell types, which we term "specific expression domains." We found that domain boundaries marked by promoters and CTCF motifs are consistent between cell types even when domain activity changes. Finally, we showed that GBR can be used to transfer information from well-studied cell types to less well-characterized cell types during genome annotation, making it possible to produce high-quality annotations of the hundreds of cell types with limited available data.},
	number = {4},
	journal = {Genome Res},
	author = {Libbrecht, M. W. and Ay, F. and Hoffman, M. M. and Gilbert, D. M. and Bilmes, J. A. and Noble, W. S.},
	month = apr,
	year = {2015},
	pages = {544--57}
}

@article{cournac_normalization_2012,
	title = {Normalization of a chromosomal contact map},
	volume = {13},
	issn = {1471-2164 (Electronic) 1471-2164 (Linking)},
	shorttitle = {Normalization of a chromosomal contact map},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/22935139},
	doi = {10.1186/1471-2164-13-436},
	abstract = {BACKGROUND: Chromatin organization has been increasingly studied in relation with its important influence on DNA-related metabolic processes such as replication or regulation of gene expression. Since its original design ten years ago, capture of chromosome conformation (3C) has become an essential tool to investigate the overall conformation of chromosomes. It relies on the capture of long-range trans and cis interactions of chromosomal segments whose relative proportions in the final bank reflect their frequencies of interactions, hence their spatial proximity in a population of cells. The recent coupling of 3C with deep sequencing approaches now allows the generation of high resolution genome-wide chromosomal contact maps. Different protocols have been used to generate such maps in various organisms. This includes mammals, drosophila and yeast. The massive amount of raw data generated by the genomic 3C has to be carefully processed to alleviate the various biases and byproducts generated by the experiments. Our study aims at proposing a simple normalization procedure to minimize the influence of these unwanted but inevitable events on the final results. RESULTS: Careful analysis of the raw data generated previously for budding yeast S. cerevisiae led to the identification of three main biases affecting the final datasets, including a previously unknown bias resulting from the circularization of DNA molecules. We then developed a simple normalization procedure to process the data and allow the generation of a normalized, highly contrasted, chromosomal contact map for S. cerevisiae. The same method was then extended to the first human genome contact map. Using the normalized data, we revisited the preferential interactions originally described between subsets of discrete chromosomal features. Notably, the detection of preferential interactions between tRNA in yeast and CTCF, PolII binding sites in human can vary with the normalization procedure used. CONCLUSIONS: We quantitatively reanalyzed the genomic 3C data obtained for S. cerevisiae, identified some of the biases inherent to the technique and proposed a simple normalization procedure to analyse them. Such an approach can be easily generalized for genomic 3C experiments in other organisms. More experiments and analysis will be necessary to reach optimal resolution and accuracies of the maps generated through these approaches. Working with cell population presenting highest levels of homogeneity will prove useful in this regards.},
	journal = {BMC Genomics},
	author = {Cournac, A. and Marie-Nelly, H. and Marbouty, M. and Koszul, R. and Mozziconacci, J.},
	year = {2012},
	keywords = {*Genome, Animals, Binding Sites, Chromosome Mapping/*methods, Chromosomes, Fungal/*genetics, Chromosomes, Human/*genetics, DNA Polymerase III/genetics/metabolism, DNA, Circular, Humans, RNA, Transfer/genetics/metabolism, ROC Curve, Repressor Proteins/genetics/metabolism, Saccharomyces cerevisiae/*genetics},
	pages = {436}
}

@article{knight_fast_2012,
	title = {A fast algorithm for matrix balancing},
	issn = {0272-4979},
	shorttitle = {A fast algorithm for matrix balancing},
	journal = {IMA Journal of Numerical Analysis},
	author = {Knight, Philip A and Ruiz, Daniel},
	year = {2012},
	pages = {drs019}
}

@article{jin_high-resolution_2013,
	title = {A high-resolution map of the three-dimensional chromatin interactome in human cells},
	volume = {503},
	issn = {1476-4687 (Electronic) 0028-0836 (Linking)},
	shorttitle = {A high-resolution map of the three-dimensional chromatin interactome in human cells},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/24141950},
	doi = {10.1038/nature12644},
	abstract = {A large number of cis-regulatory sequences have been annotated in the human genome, but defining their target genes remains a challenge. One strategy is to identify the long-range looping interactions at these elements with the use of chromosome conformation capture (3C)-based techniques. However, previous studies lack either the resolution or coverage to permit a whole-genome, unbiased view of chromatin interactions. Here we report a comprehensive chromatin interaction map generated in human fibroblasts using a genome-wide 3C analysis method (Hi-C). We determined over one million long-range chromatin interactions at 5-10-kb resolution, and uncovered general principles of chromatin organization at different types of genomic features. We also characterized the dynamics of promoter-enhancer contacts after TNF-alpha signalling in these cells. Unexpectedly, we found that TNF-alpha-responsive enhancers are already in contact with their target promoters before signalling. Such pre-existing chromatin looping, which also exists in other cell types with different extracellular signalling, is a strong predictor of gene induction. Our observations suggest that the three-dimensional chromatin landscape, once established in a particular cell type, is relatively stable and could influence the selection or activation of target genes by a ubiquitous transcription activator in a cell-specific manner.},
	number = {7475},
	journal = {Nature},
	author = {Jin, F. and Li, Y. and Dixon, J. R. and Selvaraj, S. and Ye, Z. and Lee, A. Y. and Yen, C. A. and Schmitt, A. D. and Espinoza, C. A. and Ren, B.},
	month = nov,
	year = {2013},
	keywords = {*Chromosome Mapping, *Genome, Human, Cell Line, Chromatin/chemistry/genetics/*metabolism, Enhancer Elements, Genetic/physiology, Gene Expression Regulation, Humans, Imaging, Three-Dimensional, Promoter Regions, Genetic/physiology, Protein Binding, Signal Transduction, Tumor Necrosis Factor-alpha/metabolism},
	pages = {290--4}
}

@article{schuettengruber_cooperativity_2014,
	title = {Cooperativity, specificity, and evolutionary stability of polycomb targeting in {Drosophila}},
	volume = {9},
	issn = {2211-1247 (Electronic)},
	shorttitle = {Cooperativity, specificity, and evolutionary stability of polycomb targeting in {Drosophila}},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/25284790},
	doi = {10.1016/j.celrep.2014.08.072},
	abstract = {Metazoan genomes are partitioned into modular chromosomal domains containing active or repressive chromatin. In flies, Polycomb group (PcG) response elements (PREs) recruit PHO and other DNA-binding factors and act as nucleation sites for the formation of Polycomb repressive domains. The sequence specificity of PREs is not well understood. Here, we use comparative epigenomics and transgenic assays to show that Drosophila domain organization and PRE specification are evolutionarily conserved despite significant cis-element divergence within Polycomb domains, whereas cis-element evolution is strongly correlated with transcription factor binding divergence outside of Polycomb domains. Cooperative interactions of PcG complexes and their recruiting factor PHO stabilize PHO recruitment to low-specificity sequences. Consistently, PHO recruitment to sites within Polycomb domains is stabilized by PRC1. These data suggest that cooperative rather than hierarchical interactions among low-affinity sequences, DNA-binding factors, and the Polycomb machinery are giving rise to specific and strongly conserved 3D structures in Drosophila.},
	number = {1},
	journal = {Cell Rep},
	author = {Schuettengruber, B. and Oded Elkayam, N. and Sexton, T. and Entrevan, M. and Stern, S. and Thomas, A. and Yaffe, E. and Parrinello, H. and Tanay, A. and Cavalli, G.},
	month = oct,
	year = {2014},
	pages = {219--33}
}

@article{sexton_three-dimensional_2012,
	title = {Three-dimensional folding and functional organization principles of the {Drosophila} genome},
	volume = {148},
	issn = {1097-4172 (Electronic) 0092-8674 (Linking)},
	shorttitle = {Three-dimensional folding and functional organization principles of the {Drosophila} genome},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/22265598},
	doi = {10.1016/j.cell.2012.01.010},
	abstract = {Chromosomes are the physical realization of genetic information and thus form the basis for its readout and propagation. Here we present a high-resolution chromosomal contact map derived from a modified genome-wide chromosome conformation capture approach applied to Drosophila embryonic nuclei. The data show that the entire genome is linearly partitioned into well-demarcated physical domains that overlap extensively with active and repressive epigenetic marks. Chromosomal contacts are hierarchically organized between domains. Global modeling of contact density and clustering of domains show that inactive domains are condensed and confined to their chromosomal territories, whereas active domains reach out of the territory to form remote intra- and interchromosomal contacts. Moreover, we systematically identify specific long-range intrachromosomal contacts between Polycomb-repressed domains. Together, these observations allow for quantitative prediction of the Drosophila chromosomal contact map, laying the foundation for detailed studies of chromosome structure and function in a genetically tractable system.},
	number = {3},
	journal = {Cell},
	author = {Sexton, T. and Yaffe, E. and Kenigsberg, E. and Bantignies, F. and Leblanc, B. and Hoichman, M. and Parrinello, H. and Tanay, A. and Cavalli, G.},
	month = feb,
	year = {2012},
	keywords = {*Genome, Insect, Animals, Cell Nucleus/genetics, Chromosomes, Insect, Drosophila Proteins/metabolism, Drosophila melanogaster/cytology/embryology/*genetics, Models, Statistical, Polycomb Repressive Complex 1},
	pages = {458--72}
}
@article{imakaev_iterative_2012,
	title = {Iterative correction of {Hi}-{C} data reveals hallmarks of chromosome organization},
	volume = {9},
	issn = {1548-7105 (Electronic) 1548-7091 (Linking)},
	shorttitle = {Iterative correction of {Hi}-{C} data reveals hallmarks of chromosome organization},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/22941365},
	doi = {10.1038/nmeth.2148},
	abstract = {Extracting biologically meaningful information from chromosomal interactions obtained with genome-wide chromosome conformation capture (3C) analyses requires the elimination of systematic biases. We present a computational pipeline that integrates a strategy to map sequencing reads with a data-driven method for iterative correction of biases, yielding genome-wide maps of relative contact probabilities. We validate this ICE (iterative correction and eigenvector decomposition) technique on published data obtained by the high-throughput 3C method Hi-C, and we demonstrate that eigenvector decomposition of the obtained maps provides insights into local chromatin states, global patterns of chromosomal interactions, and the conserved organization of human and mouse chromosomes.},
	number = {10},
	journal = {Nat Methods},
	author = {Imakaev, M. and Fudenberg, G. and McCord, R. P. and Naumova, N. and Goloborodko, A. and Lajoie, B. R. and Dekker, J. and Mirny, L. A.},
	month = oct,
	year = {2012},
	keywords = {*Nucleic Acid Conformation, Chromatin/chemistry, Chromosome Mapping/*methods, Chromosomes, Human/*chemistry, High-Throughput Screening Assays/*methods, Humans},
	pages = {999--1003}
}

@article{lieberman-aiden_comprehensive_2009,
	title = {Comprehensive mapping of long-range interactions reveals folding principles of the human genome},
	volume = {326},
	issn = {1095-9203 (Electronic) 0036-8075 (Linking)},
	shorttitle = {Comprehensive mapping of long-range interactions reveals folding principles of the human genome},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/19815776},
	doi = {10.1126/science.1181369},
	abstract = {We describe Hi-C, a method that probes the three-dimensional architecture of whole genomes by coupling proximity-based ligation with massively parallel sequencing. We constructed spatial proximity maps of the human genome with Hi-C at a resolution of 1 megabase. These maps confirm the presence of chromosome territories and the spatial proximity of small, gene-rich chromosomes. We identified an additional level of genome organization that is characterized by the spatial segregation of open and closed chromatin to form two genome-wide compartments. At the megabase scale, the chromatin conformation is consistent with a fractal globule, a knot-free, polymer conformation that enables maximally dense packing while preserving the ability to easily fold and unfold any genomic locus. The fractal globule is distinct from the more commonly used globular equilibrium model. Our results demonstrate the power of Hi-C to map the dynamic conformations of whole genomes.},
	number = {5950},
	journal = {Science},
	author = {Lieberman-Aiden, E. and van Berkum, N. L. and Williams, L. and Imakaev, M. and Ragoczy, T. and Telling, A. and Amit, I. and Lajoie, B. R. and Sabo, P. J. and Dorschner, M. O. and Sandstrom, R. and Bernstein, B. and Bender, M. A. and Groudine, M. and Gnirke, A. and Stamatoyannopoulos, J. and Mirny, L. A. and Lander, E. S. and Dekker, J.},
	month = oct,
	year = {2009},
	keywords = {*Chromosomes, Human/chemistry/ultrastructure, *Genome, Human, Biotin, Cell Line, Transformed, Cell Nucleus/*ultrastructure, Chromatin Immunoprecipitation, Chromatin/*chemistry, Computational Biology, DNA/*chemistry, Gene Library, Humans, In Situ Hybridization, Fluorescence, Models, Molecular, Monte Carlo Method, Nucleic Acid Conformation, Principal Component Analysis, Protein Conformation, Sequence Analysis, DNA},
	pages = {289--93}
}

@article{walt_numpy_2011,
	title = {The {NumPy} {Array}: {A} {Structure} for {Efficient} {Numerical} {Computation}},
	volume = {13},
	issn = {1521-9615},
	doi = {10.1109/MCSE.2011.37},
	number = {2},
	journal = {Computing in Science Engineering},
	author = {Walt, S. van der and Colbert, S. C. and Varoquaux, G.},
	month = mar,
	year = {2011},
	keywords = {Arrays, Computational efficiency, Finite element methods, NumPy, Performance evaluation, Python, Python programming language, Resource management, Vector quantization, data structures, high level language, high level languages, mathematics computing, numerical analysis, numerical computation, numerical computations, numerical data, numpy array, programming libraries, scientific programming},
	pages = {22--30}
}

@article{li_sequence_2009,
	title = {The {Sequence} {Alignment}/{Map} format and {SAMtools}},
	volume = {25},
	issn = {1367-4811},
	doi = {10.1093/bioinformatics/btp352},
	abstract = {SUMMARY: The Sequence Alignment/Map (SAM) format is a generic alignment format for storing read alignments against reference sequences, supporting short and long reads (up to 128 Mbp) produced by different sequencing platforms. It is flexible in style, compact in size, efficient in random access and is the format in which alignments from the 1000 Genomes Project are released. SAMtools implements various utilities for post-processing alignments in the SAM format, such as indexing, variant caller and alignment viewer, and thus provides universal tools for processing read alignments.
AVAILABILITY: http://samtools.sourceforge.net.},
	language = {eng},
	number = {16},
	journal = {Bioinformatics (Oxford, England)},
	author = {Li, Heng and Handsaker, Bob and Wysoker, Alec and Fennell, Tim and Ruan, Jue and Homer, Nils and Marth, Gabor and Abecasis, Goncalo and Durbin, Richard and {1000 Genome Project Data Processing Subgroup}},
	month = aug,
	year = {2009},
	pmid = {19505943},
	pmcid = {PMC2723002},
	keywords = {Algorithms, Base Sequence, Computational Biology, Genome, Genomics, Molecular Sequence Data, Sequence Alignment, Sequence Analysis, DNA, Software},
	pages = {2078--2079}
}

@article{quinlan_bedtools:_2010,
	title = {{BEDTools}: a flexible suite of utilities for comparing genomic features},
	volume = {26},
	issn = {1367-4811},
	shorttitle = {{BEDTools}},
	doi = {10.1093/bioinformatics/btq033},
	abstract = {MOTIVATION: Testing for correlations between different sets of genomic features is a fundamental task in genomics research. However, searching for overlaps between features with existing web-based methods is complicated by the massive datasets that are routinely produced with current sequencing technologies. Fast and flexible tools are therefore required to ask complex questions of these data in an efficient manner.
RESULTS: This article introduces a new software suite for the comparison, manipulation and annotation of genomic features in Browser Extensible Data (BED) and General Feature Format (GFF) format. BEDTools also supports the comparison of sequence alignments in BAM format to both BED and GFF features. The tools are extremely efficient and allow the user to compare large datasets (e.g. next-generation sequencing data) with both public and custom genome annotation tracks. BEDTools can be combined with one another as well as with standard UNIX commands, thus facilitating routine genomics tasks as well as pipelines that can quickly answer intricate questions of large genomic datasets.
AVAILABILITY AND IMPLEMENTATION: BEDTools was written in C++. Source code and a comprehensive user manual are freely available at http://code.google.com/p/bedtools
CONTACT: aaronquinlan@gmail.com; imh4y@virginia.edu
SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
	language = {eng},
	number = {6},
	journal = {Bioinformatics (Oxford, England)},
	author = {Quinlan, Aaron R. and Hall, Ira M.},
	month = mar,
	year = {2010},
	pmid = {20110278},
	pmcid = {PMC2832824},
	keywords = {Genome, Genomics, Internet, Software},
	pages = {841--842}
}

@article{langmead_fast_2012,
	title = {Fast gapped-read alignment with {Bowtie} 2},
	volume = {9},
	issn = {1548-7105},
	doi = {10.1038/nmeth.1923},
	abstract = {As the rate of sequencing increases, greater throughput is demanded from read aligners. The full-text minute index is often used to make alignment very fast and memory-efficient, but the approach is ill-suited to finding longer, gapped alignments. Bowtie 2 combines the strengths of the full-text minute index with the flexibility and speed of hardware-accelerated dynamic programming algorithms to achieve a combination of high speed, sensitivity and accuracy.},
	language = {eng},
	number = {4},
	journal = {Nature Methods},
	author = {Langmead, Ben and Salzberg, Steven L.},
	month = mar,
	year = {2012},
	pmid = {22388286},
	pmcid = {PMC3322381},
	keywords = {Algorithms, Computational Biology, Databases, Genetic, Genome, Human, Humans, Sequence Alignment, Sequence Analysis, DNA},
	pages = {357--359}
}

@book{r_core_team_r:_2015,
	address = {Vienna, Austria},
	title = {R: {A} {Language} and {Environment} for {Statistical} {Computing}},
	url = {http://www.R-project.org/},
	publisher = {R Foundation for Statistical Computing},
	author = {{R Core Team}},
	year = {2015}
}

@article{albanese_mlpy:_2012,
	title = {mlpy: {Machine} {Learning} {Python}},
	doi = {arXiv:1202.6548v2},
	author = {Albanese, Davide and Visintainer, Roberto and Merler, Stefano and Riccadonna, Samantha and Jurman, Giuseppe and Furlanello, Cesare},
	year = {2012}
}

@article{zhang_model-based_2008,
	title = {Model-based analysis of {ChIP}-{Seq} ({MACS})},
	volume = {9},
	issn = {1474-760X},
	doi = {10.1186/gb-2008-9-9-r137},
	abstract = {We present Model-based Analysis of ChIP-Seq data, MACS, which analyzes data generated by short read sequencers such as Solexa's Genome Analyzer. MACS empirically models the shift size of ChIP-Seq tags, and uses it to improve the spatial resolution of predicted binding sites. MACS also uses a dynamic Poisson distribution to effectively capture local biases in the genome, allowing for more robust predictions. MACS compares favorably to existing ChIP-Seq peak-finding algorithms, and is freely available.},
	language = {eng},
	number = {9},
	journal = {Genome Biology},
	author = {Zhang, Yong and Liu, Tao and Meyer, Clifford A. and Eeckhoute, Jérôme and Johnson, David S. and Bernstein, Bradley E. and Nusbaum, Chad and Myers, Richard M. and Brown, Myles and Li, Wei and Liu, X. Shirley},
	year = {2008},
	pmid = {18798982},
	pmcid = {PMC2592715},
	keywords = {Algorithms, Cell Line, Tumor, Chromatin Immunoprecipitation, Hepatocyte Nuclear Factor 3-alpha, Humans, Models, Genetic, Oligonucleotide Array Sequence Analysis},
	pages = {R137}
}

@article{jung_chromatin_2017,
	title = {Chromatin {States} in {Mouse} {Sperm} {Correlate} with {Embryonic} and {Adult} {Regulatory} {Landscapes}},
	volume = {18},
	issn = {2211-1247},
	doi = {10.1016/j.celrep.2017.01.034},
	abstract = {The mammalian sperm genome is thought to lack substantial information for the regulation of future expression after fertilization. Here, we show that most promoters in mouse sperm are flanked by well-positioned nucleosomes marked by active histone modifications. Analysis of these modifications suggests that many enhancers and super-enhancers functional in embryonic and adult tissues are already specified in sperm. The sperm genome is bound by CTCF and cohesin at sites that are also present in round spermatids and embryonic stem cells (ESCs). These sites mediate interactions that organize the sperm genome into domains and compartments that overlap extensively with those found in mESCs. These results suggest that sperm carry a rich source of regulatory information, encoded in part by its three-dimensional folding specified by CTCF and cohesin. This information may contribute to future expression during embryonic and adult life, suggesting mechanisms by which environmental effects on the paternal germline are transmitted transgenerationally.},
	language = {eng},
	number = {6},
	journal = {Cell Reports},
	author = {Jung, Yoon Hee and Sauria, Michael E. G. and Lyu, Xiaowen and Cheema, Manjinder S. and Ausio, Juan and Taylor, James and Corces, Victor G.},
	month = feb,
	year = {2017},
	pmid = {28178516},
	pmcid = {PMC5313040},
	keywords = {CTCF, Chromatin, TAD, pluripotency, stem cell, transcription},
	pages = {1366--1382}
}

@article{koehler_uniqueome:_2011,
	title = {The uniqueome: a mappability resource for short-tag sequencing},
	volume = {27},
	issn = {1367-4811},
	shorttitle = {The uniqueome},
	doi = {10.1093/bioinformatics/btq640},
	abstract = {SUMMARY: Quantification applications of short-tag sequencing data (such as CNVseq and RNAseq) depend on knowing the uniqueness of specific genomic regions at a given threshold of error. Here, we present the 'uniqueome', a genomic resource for understanding the uniquely mappable proportion of genomic sequences. Pre-computed data are available for human, mouse, fly and worm genomes in both color-space and nucletotide-space, and we demonstrate the utility of this resource as applied to the quantification of RNAseq data.
AVAILABILITY: Files, scripts and supplementary data are available from http://grimmond.imb.uq.edu.au/uniqueome/; the ISAS uniqueome aligner is freely available from http://www.imagenix.com/.},
	language = {eng},
	number = {2},
	journal = {Bioinformatics (Oxford, England)},
	author = {Koehler, Ryan and Issac, Hadar and Cloonan, Nicole and Grimmond, Sean M.},
	month = jan,
	year = {2011},
	pmid = {21075741},
	pmcid = {PMC3018812},
	keywords = {Animals, Chromosome Mapping, Genome, Genomics, Humans, Mice, Sequence Analysis, RNA, Sequence Tagged Sites, Software},
	pages = {272--274}
}

@article{li_fast_2009,
	title = {Fast and accurate short read alignment with {Burrows}-{Wheeler} transform},
	volume = {25},
	issn = {1367-4811},
	doi = {10.1093/bioinformatics/btp324},
	abstract = {MOTIVATION: The enormous amount of short reads generated by the new DNA sequencing technologies call for the development of fast and accurate read alignment programs. A first generation of hash table-based methods has been developed, including MAQ, which is accurate, feature rich and fast enough to align short reads from a single individual. However, MAQ does not support gapped alignment for single-end reads, which makes it unsuitable for alignment of longer reads where indels may occur frequently. The speed of MAQ is also a concern when the alignment is scaled up to the resequencing of hundreds of individuals.
RESULTS: We implemented Burrows-Wheeler Alignment tool (BWA), a new read alignment package that is based on backward search with Burrows-Wheeler Transform (BWT), to efficiently align short sequencing reads against a large reference sequence such as the human genome, allowing mismatches and gaps. BWA supports both base space reads, e.g. from Illumina sequencing machines, and color space reads from AB SOLiD machines. Evaluations on both simulated and real data suggest that BWA is approximately 10-20x faster than MAQ, while achieving similar accuracy. In addition, BWA outputs alignment in the new standard SAM (Sequence Alignment/Map) format. Variant calling and other downstream analyses after the alignment can be achieved with the open source SAMtools software package.
AVAILABILITY: http://maq.sourceforge.net.},
	language = {eng},
	number = {14},
	journal = {Bioinformatics (Oxford, England)},
	author = {Li, Heng and Durbin, Richard},
	month = jul,
	year = {2009},
	pmid = {19451168},
	pmcid = {PMC2705234},
	keywords = {Algorithms, Genomics, Sequence Alignment, Sequence Analysis, DNA, Software},
	pages = {1754--1760}
}

@article{sauria_hifive:_2015,
	title = {{HiFive}: a tool suite for easy and efficient {HiC} and 5C data analysis},
	volume = {16},
	issn = {1474-760X},
	shorttitle = {{HiFive}},
	doi = {10.1186/s13059-015-0806-y},
	abstract = {The chromatin interaction assays 5C and HiC have advanced our understanding of genomic spatial organization, but analysis approaches for these data are limited by usability and flexibility. The HiFive tool suite provides efficient data handling and a variety of normalization approaches for easy, fast analysis and method comparison. Integration of MPI-based parallelization allows scalability and rapid processing time. In addition to single-command analysis of an entire experiment from mapped reads to interaction values, HiFive has been integrated into the open-source, web-based platform Galaxy to connect users with computational resources and a graphical interface. HiFive is open-source software available from http://taylorlab.org/software/hifive/ .},
	language = {eng},
	journal = {Genome Biology},
	author = {Sauria, Michael E. G. and Phillips-Cremins, Jennifer E. and Corces, Victor G. and Taylor, James},
	month = oct,
	year = {2015},
	pmid = {26498826},
	keywords = {Algorithms, Chromatin, Genomics, Software},
	pages = {237}
}

@article{lin_global_2012,
	title = {Global changes in the nuclear positioning of genes and intra- and interdomain genomic interactions that orchestrate {B} cell fate},
	volume = {13},
	issn = {1529-2916},
	doi = {10.1038/ni.2432},
	abstract = {The genome is folded into domains located in compartments that are either transcriptionally inert or transcriptionally permissive. Here we used genome-wide strategies to characterize domains during B cell development. Structured interaction matrix analysis showed that occupancy by the architectural protein CTCF was associated mainly with intradomain interactions, whereas sites bound by the histone acetyltransferase p300 or the transcription factors E2A or PU.1 were associated with intra- and interdomain interactions that are developmentally regulated. We identified a spectrum of genes that switched nuclear location during early B cell development. In progenitor cells, the transcriptionally inactive locus encoding early B cell factor (Ebf1) was sequestered at the nuclear lamina, which thereby preserved their multipotency. After development into the pro-B cell stage, Ebf1 and other genes switched compartments to establish new intra- and interdomain interactions associated with a B lineage-specific transcription signature.},
	language = {eng},
	number = {12},
	journal = {Nature Immunology},
	author = {Lin, Yin C. and Benner, Christopher and Mansson, Robert and Heinz, Sven and Miyazaki, Kazuko and Miyazaki, Masaki and Chandra, Vivek and Bossen, Claudia and Glass, Christopher K. and Murre, Cornelis},
	month = dec,
	year = {2012},
	pmid = {23064439},
	pmcid = {PMC3501570},
	keywords = {Animals, B-Lymphocytes, Basic Helix-Loop-Helix Transcription Factors, Cell Lineage, Cell Nucleus, Cells, Cultured, DNA-Binding Proteins, Gene Expression Regulation, Developmental, Lymphopoiesis, Mice, Mice, Inbred C57BL, Nuclear Lamina, Precursor Cells, B-Lymphoid, Promoter Regions, Genetic, Proto-Oncogene Proteins, Repressor Proteins, Trans-Activators, Transcription, Genetic, p300-CBP Transcription Factors},
	pages = {1196--1204}
}

@article{langmead_ultrafast_2009,
	title = {Ultrafast and memory-efficient alignment of short {DNA} sequences to the human genome},
	volume = {10},
	issn = {1474-760X},
	doi = {10.1186/gb-2009-10-3-r25},
	abstract = {Bowtie is an ultrafast, memory-efficient alignment program for aligning short DNA sequence reads to large genomes. For the human genome, Burrows-Wheeler indexing allows Bowtie to align more than 25 million reads per CPU hour with a memory footprint of approximately 1.3 gigabytes. Bowtie extends previous Burrows-Wheeler techniques with a novel quality-aware backtracking algorithm that permits mismatches. Multiple processor cores can be used simultaneously to achieve even greater alignment speeds. Bowtie is open source (http://bowtie.cbcb.umd.edu).},
	language = {eng},
	number = {3},
	journal = {Genome Biology},
	author = {Langmead, Ben and Trapnell, Cole and Pop, Mihai and Salzberg, Steven L.},
	year = {2009},
	pmid = {19261174},
	pmcid = {PMC2690996},
	keywords = {Algorithms, Base Sequence, Genome, Human, Humans, Sequence Alignment},
	pages = {R25}
}