Merge pull request #35 from CCBR/dev

Dev

.gitignore

@@ -10,3 +10,6 @@ site/
 *RData
 *Rhistory
 .*Rmd
+
+# ignore resources for deeptools
+resources/*gencode*

.test/README.md

@@ -0,0 +1,30 @@
+# 12/16/22
+New test data is added to pipeline
+
+# sample location
+/data/CCBR/projects/ccbr1155/CS031014/fastq
+
+# sample ids mapping; original to renamed
+VS586.R1.fastq.gz,HN6_IgG_rabbit_negative_control_1.R1.fastq.gz
+VS586.R2.fastq.gz,HN6_IgG_rabbit_negative_control_1.R2.fastq.gz
+VS588.R1.fastq.gz,HN6_H3K4me3_1.R1.fastq.gz
+VS588.R2.fastq.gz,HN6_H3K4me3_1.R2.fastq.gz
+VS589.R1.fastq.gz,HN6_H3K4me3_2.R1.fastq.gz
+VS589.R2.fastq.gz,HN6_H3K4me3_2.R2.fastq.gz
+VS591.R1.fastq.gz,53_H3K4me3_1.R1.fastq.gz
+VS591.R2.fastq.gz,53_H3K4me3_1.R2.fastq.gz
+VS592.R1.fastq.gz,53_H3K4me3_2.R1.fastq.gz
+VS592.R2.fastq.gz,53_H3K4me3_2.R2.fastq.gz
+VS594.R1.fastq.gz,HN6_H4K20me3_1.R1.fastq.gz
+VS594.R2.fastq.gz,HN6_H4K20me3_1.R2.fastq.gz
+VS595.R1.fastq.gz,HN6_H4K20me3_2.R1.fastq.gz
+VS595.R2.fastq.gz,HN6_H4K20me3_2.R2.fastq.gz
+VS597.R1.fastq.gz,53_H4K20m3_1.R1.fastq.gz
+VS597.R2.fastq.gz,53_H4K20m3_1.R2.fastq.gz
+VS598.R1.fastq.gz,53_H4K20m3_2.R1.fastq.gz
+
+# subset each of the samples 
+fq_original_loc="/data/CCBR/projects/ccbr1155/CS031014/fastq";\
+test_loc="/data/CCBR_Pipeliner/Pipelines/CARLISLE_dev/.test";\
+fq_list=("HN6_IgG_rabbit_negative_control_1.R1.fastq.gz" "HN6_IgG_rabbit_negative_control_1.R2.fastq.gz" "HN6_H3K4me3_1.R1.fastq.gz" "HN6_H3K4me3_1.R2.fastq.gz" "HN6_H3K4me3_2.R1.fastq.gz" "HN6_H3K4me3_2.R2.fastq.gz" "53_H3K4me3_1.R1.fastq.gz" "53_H3K4me3_1.R2.fastq.gz" "53_H3K4me3_2.R1.fastq.gz" "53_H3K4me3_2.R2.fastq.gz" "HN6_H4K20me3_1.R1.fastq.gz" "HN6_H4K20me3_1.R2.fastq.gz" "HN6_H4K20me3_2.R1.fastq.gz" "HN6_H4K20me3_2.R2.fastq.gz" "53_H4K20m3_1.R1.fastq.gz" "53_H4K20m3_1.R2.fastq.gz" "53_H4K20m3_2.R1.fastq.gz" "53_H4K20m3_2.R2.fastq.gz");\
+for fq in ${fq_list[@]}; do echo $fq; remove_ext=`echo $fq | sed "s/.gz//g"`; zcat $fq_original_loc/$fq | head -1000000 > $test_loc/$remove_ext; gzip $test_loc/$remove_ext; done

.test/contrasts.test.tsv

@@ -0,0 +1,3 @@
+condition1	condition2
+53_H3K4me3	HN6_H3K4me3
+53_H4K20m3	HN6_H4K20me3

.test/samples.test.tsv

@@ -0,0 +1,10 @@
+sampleName	replicateNumber	isControl	controlName	controlReplicateNumber	path_to_R1	path_to_R2
+53_H3K4me3	1	N	HN6_IgG_rabbit_negative_control	1	PIPELINE_HOME/.test/53_H3K4me3_1.R1.fastq.gz	PIPELINE_HOME/.test/53_H3K4me3_1.R2.fastq.gz
+53_H3K4me3	2	N	HN6_IgG_rabbit_negative_control	1	PIPELINE_HOME/.test/53_H3K4me3_2.R1.fastq.gz	PIPELINE_HOME/.test/53_H3K4me3_2.R2.fastq.gz
+HN6_H3K4me3	1	N	HN6_IgG_rabbit_negative_control	1	PIPELINE_HOME/.test/HN6_H3K4me3_1.R1.fastq.gz	PIPELINE_HOME/.test/HN6_H3K4me3_1.R2.fastq.gz
+HN6_H3K4me3	2	N	HN6_IgG_rabbit_negative_control	1	PIPELINE_HOME/.test/HN6_H3K4me3_2.R1.fastq.gz	PIPELINE_HOME/.test/HN6_H3K4me3_2.R2.fastq.gz
+53_H4K20m3	1	N	HN6_IgG_rabbit_negative_control	1	PIPELINE_HOME/.test/53_H4K20m3_1.R1.fastq.gz	PIPELINE_HOME/.test/53_H4K20m3_1.R2.fastq.gz
+53_H4K20m3	2	N	HN6_IgG_rabbit_negative_control	1	PIPELINE_HOME/.test/53_H4K20m3_2.R1.fastq.gz	PIPELINE_HOME/.test/53_H4K20m3_2.R2.fastq.gz
+HN6_H4K20me3	1	N	HN6_IgG_rabbit_negative_control	1	PIPELINE_HOME/.test/HN6_H4K20me3_1.R1.fastq.gz	PIPELINE_HOME/.test/HN6_H4K20me3_1.R2.fastq.gz
+HN6_H4K20me3	2	N	HN6_IgG_rabbit_negative_control	1	PIPELINE_HOME/.test/HN6_H4K20me3_2.R1.fastq.gz	PIPELINE_HOME/.test/HN6_H4K20me3_2.R2.fastq.gz
+HN6_IgG_rabbit_negative_control	1	Y	-	-	PIPELINE_HOME/.test/HN6_IgG_rabbit_negative_control_1.R1.fastq.gz	PIPELINE_HOME/.test/HN6_IgG_rabbit_negative_control_1.R2.fastq.gz

README.md

@@ -6,4 +6,4 @@ This snakemake pipeline is built to run on [Biowulf](https://hpc.nih.gov/).
 
 For comments/suggestions/advice please reach out to [Vishal Koparde](mailto:[email protected]).
 
-For detailed documentation on running the pipeline view the [documentation](https://CCBR.github.io/CARLISLE/) page.
+For detailed documentation on running the pipeline view the [documentation](https://CCBR.github.io/CARLISLE/) page.

annotation/README.md

@@ -0,0 +1,6 @@
+`create_hs1_ucsc.sh` script was used to create the hs1 ucsc file.
+
+#### hg19_refseq.ucsc and hg38_refseq.ucsc source
+/data/khanlab3/gb_omics/processed_DATA/YueHu/cutrun_120822# hg19_refseq.ucsc and hg38_refseq.ucsc source
+
+# info on these resources is outlined in: https://github.com/CCBR/CARLISLE/issues/27

annotation/create_hs1_uscs.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+module load ucsc
+gtfToGenePred -genePredExt -ignoreGroupsWithoutExons /data/CCBR_Pipeliner/db/PipeDB/Indices/hs1/genes.gtf hs1.genes.genePred
+head -n1 hg19_refseq.ucsc > hs1.ucsc
+awk -F"\t" -v OFS="\t" '{print $NF,$_}' hs1.genes.genePred >> hs1.ucsc