Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

deprecate .contrasts and update tests #239

Merged
merged 2 commits into from
Jun 26, 2022
Merged

deprecate .contrasts and update tests #239

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a284fc6
deprecate .contrasts and update tests
stemangiola Jun 25, 2022
2b729ef
Merge branch 'dev' into deprecate_dot_contrasts
stemangiola Jun 26, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
71 changes: 42 additions & 29 deletions R/methods.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2118,7 +2118,7 @@ setMethod("ensembl_to_symbol", "tidybulk", .ensembl_to_symbol)
#' @param .sample The name of the sample column
#' @param .transcript The name of the transcript/gene column
#' @param .abundance The name of the transcript/gene abundance column
#' @param .contrasts This parameter takes the format of the contrast parameter of the method of choice. For edgeR and limma-voom is a character vector. For DESeq2 is a list including a character vector of length three. The first covariate is the one the model is tested against (e.g., ~ factor_of_interest)
#' @param contrasts This parameter takes the format of the contrast parameter of the method of choice. For edgeR and limma-voom is a character vector. For DESeq2 is a list including a character vector of length three. The first covariate is the one the model is tested against (e.g., ~ factor_of_interest)
#' @param method A string character. Either "edgeR_quasi_likelihood" (i.e., QLF), "edgeR_likelihood_ratio" (i.e., LRT), "edger_robust_likelihood_ratio", "DESeq2", "limma_voom", "limma_voom_sample_weights"
#' @param test_above_log2_fold_change A positive real value. This works for edgeR and limma_voom methods. It uses the `treat` function, which tests that the difference in abundance is bigger than this threshold rather than zero \url{https://pubmed.ncbi.nlm.nih.gov/19176553}.
#' @param scaling_method A character string. The scaling method passed to the back-end functions: edgeR and limma-voom (i.e., edgeR::calcNormFactors; "TMM","TMMwsp","RLE","upperquartile"). Setting the parameter to \"none\" will skip the compensation for sequencing-depth for the method edgeR or limma-voom.
Expand All @@ -2127,6 +2127,7 @@ setMethod("ensembl_to_symbol", "tidybulk", .ensembl_to_symbol)
#' @param action A character string. Whether to join the new information to the input tbl (add), or just get the non-redundant tbl with the new information (get).
#' @param significance_threshold DEPRECATED - A real between 0 and 1 (usually 0.05).
#' @param fill_missing_values DEPRECATED - A boolean. Whether to fill missing sample/transcript values with the median of the transcript. This is rarely needed.
#' @param .contrasts DEPRECATED - This parameter takes the format of the contrast parameter of the method of choice. For edgeR and limma-voom is a character vector. For DESeq2 is a list including a character vector of length three. The first covariate is the one the model is tested against (e.g., ~ factor_of_interest)
#' @param ... Further arguments passed to some of the internal functions. Currently, it is needed just for internal debug.
#'
#'
Expand Down Expand Up @@ -2189,7 +2190,7 @@ setMethod("ensembl_to_symbol", "tidybulk", .ensembl_to_symbol)
#' identify_abundant() |>
#' test_differential_abundance(
#' ~ 0 + condition,
#' .contrasts = c( "conditionTRUE - conditionFALSE")
#' contrasts = c( "conditionTRUE - conditionFALSE")
#' )
#'
#' # DESeq2 - equivalent for limma-voom
Expand All @@ -2207,7 +2208,7 @@ setMethod("ensembl_to_symbol", "tidybulk", .ensembl_to_symbol)
#' identify_abundant() |>
#' test_differential_abundance(
#' ~ 0 + condition,
#' .contrasts = list(c("condition", "TRUE", "FALSE")),
#' contrasts = list(c("condition", "TRUE", "FALSE")),
#' method="deseq2"
#' )
#'
Expand All @@ -2220,7 +2221,7 @@ setGeneric("test_differential_abundance", function(.data,
.sample = NULL,
.transcript = NULL,
.abundance = NULL,
.contrasts = NULL,
contrasts = NULL,
method = "edgeR_quasi_likelihood",
test_above_log2_fold_change = NULL,
scaling_method = "TMM",
Expand All @@ -2231,7 +2232,8 @@ setGeneric("test_differential_abundance", function(.data,

# DEPRECATED
significance_threshold = NULL,
fill_missing_values = NULL
fill_missing_values = NULL,
.contrasts = NULL
)
standardGeneric("test_differential_abundance"))

Expand All @@ -2242,7 +2244,7 @@ setGeneric("test_differential_abundance", function(.data,
.sample = NULL,
.transcript = NULL,
.abundance = NULL,
.contrasts = NULL,
contrasts = NULL,
method = "edgeR_quasi_likelihood",
test_above_log2_fold_change = NULL,
scaling_method = "TMM",
Expand All @@ -2254,7 +2256,8 @@ setGeneric("test_differential_abundance", function(.data,

# DEPRECATED
significance_threshold = NULL,
fill_missing_values = NULL
fill_missing_values = NULL,
.contrasts = NULL
)
{
# Get column names
Expand Down Expand Up @@ -2282,6 +2285,15 @@ setGeneric("test_differential_abundance", function(.data,

}

# DEPRECATION OF .constrasts
if (is_present(.contrasts) & !is.null(.contrasts)) {

# Signal the deprecation to the user
deprecate_warn("1.7.4", "tidybulk::test_differential_abundance(.contrasts = )", details = "The argument .contrasts is now deprecated please use contrasts (without the dot).")

contrasts = .contrasts
}

# Clearly state what counts are used
rlang::inform("=====================================
tidybulk says: All testing methods use raw counts, irrespective of if scale_abundance
Expand Down Expand Up @@ -2322,7 +2334,7 @@ such as batch effects (if applicable) in the formula.
.sample = !!.sample,
.transcript = !!.transcript,
.abundance = !!.abundance,
.contrasts = .contrasts,
.contrasts = contrasts,
method = method,
test_above_log2_fold_change = test_above_log2_fold_change,
scaling_method = scaling_method,
Expand All @@ -2338,7 +2350,7 @@ such as batch effects (if applicable) in the formula.
.sample = !!.sample,
.transcript = !!.transcript,
.abundance = !!.abundance,
.contrasts = .contrasts,
.contrasts = contrasts,
method = method,
test_above_log2_fold_change = test_above_log2_fold_change,
scaling_method = scaling_method,
Expand All @@ -2354,7 +2366,7 @@ such as batch effects (if applicable) in the formula.
.sample = !!.sample,
.transcript = !!.transcript,
.abundance = !!.abundance,
.contrasts = .contrasts,
.contrasts = contrasts,
method = method,
scaling_method = scaling_method,
omit_contrast_in_colnames = omit_contrast_in_colnames,
Expand All @@ -2372,10 +2384,6 @@ such as batch effects (if applicable) in the formula.
.data %>%
dplyr::left_join(.data_processed, by = quo_name(.transcript)) %>%

# # Arrange
# ifelse_pipe(.contrasts %>% is.null,
# ~ .x %>% arrange(FDR)) %>%

# Attach attributes
reattach_internals(.data_processed)

Expand All @@ -2386,18 +2394,9 @@ such as batch effects (if applicable) in the formula.

# Selecting the right columns
pivot_transcript(!!.transcript) %>%
# select(
# !!.transcript,
# get_x_y_annotation_columns(.data, !!.sample,!!.transcript, !!.abundance, NULL)$vertical_cols
# ) %>%
# distinct() %>%

dplyr::left_join(.data_processed, by = quo_name(.transcript)) %>%

# # Arrange
# ifelse_pipe(.contrasts %>% is.null,
# ~ .x %>% arrange(FDR)) %>%

# Attach attributes
reattach_internals(.data_processed)

Expand Down Expand Up @@ -2837,13 +2836,14 @@ setMethod("keep_abundant", "tidybulk", .keep_abundant)
#' @param .sample The name of the sample column
#' @param .entrez The ENTREZ ID of the transcripts/genes
#' @param .abundance The name of the transcript/gene abundance column
#' @param .contrasts = NULL,
#' @param contrasts This parameter takes the format of the contrast parameter of the method of choice. For edgeR and limma-voom is a character vector. For DESeq2 is a list including a character vector of length three. The first covariate is the one the model is tested against (e.g., ~ factor_of_interest)
#' @param methods A character vector. One or 3 or more methods to use in the testing (currently EGSEA errors if 2 are used). Type EGSEA::egsea.base() to see the supported GSE methods.
#' @param gene_sets A character vector or a list. It can take one or more of the following built-in collections as a character vector: c("h", "c1", "c2", "c3", "c4", "c5", "c6", "c7", "kegg_disease", "kegg_metabolism", "kegg_signaling"), to be used with EGSEA buildIdx. c1 is human specific. Alternatively, a list of user-supplied gene sets can be provided, to be used with EGSEA buildCustomIdx. In that case, each gene set is a character vector of Entrez IDs and the names of the list are the gene set names.
#' @param species A character. It can be human, mouse or rat.
#' @param cores An integer. The number of cores available
#'
#' @param method DEPRECATED. Please use methods.
#' @param .contrasts DEPRECATED - This parameter takes the format of the contrast parameter of the method of choice. For edgeR and limma-voom is a character vector. For DESeq2 is a list including a character vector of length three. The first covariate is the one the model is tested against (e.g., ~ factor_of_interest)
#'
#' @details This wrapper executes ensemble gene enrichment analyses of the dataset using EGSEA (DOI:0.12688/f1000research.12544.1)
#'
Expand Down Expand Up @@ -2917,13 +2917,15 @@ setGeneric("test_gene_enrichment", function(.data,
.sample = NULL,
.entrez,
.abundance = NULL,
.contrasts = NULL,
contrasts = NULL,
methods = c("camera" , "roast" , "safe", "gage" , "padog" , "globaltest", "ora" ),
gene_sets = c("h", "c1", "c2", "c3", "c4", "c5", "c6", "c7", "kegg_disease", "kegg_metabolism", "kegg_signaling"),
species,
cores = 10,

method = NULL # DEPRECATED
# DEPRECATED
method = NULL,
.contrasts = NULL
)
standardGeneric("test_gene_enrichment"))

Expand All @@ -2934,13 +2936,15 @@ setGeneric("test_gene_enrichment", function(.data,
.sample = NULL,
.entrez,
.abundance = NULL,
.contrasts = NULL,
contrasts = NULL,
methods = c("camera" , "roast" , "safe", "gage" , "padog" , "globaltest", "ora" ),
gene_sets = c("h", "c1", "c2", "c3", "c4", "c5", "c6", "c7", "kegg_disease", "kegg_metabolism", "kegg_signaling"),
species,
cores = 10,

method = NULL # DEPRECATED
# DEPRECATED
method = NULL,
.contrasts = NULL
) {

# DEPRECATION OF reference function
Expand All @@ -2951,6 +2955,15 @@ setGeneric("test_gene_enrichment", function(.data,
methods = method
}

# DEPRECATION OF .constrasts
if (is_present(.contrasts) & !is.null(.contrasts)) {

# Signal the deprecation to the user
deprecate_warn("1.7.4", "tidybulk::test_differential_abundance(.contrasts = )", details = "The argument .contrasts is now deprecated please use contrasts (without the dot).")

contrasts = .contrasts
}

# Make col names
.sample = enquo(.sample)
.abundance = enquo(.abundance)
Expand Down Expand Up @@ -2993,7 +3006,7 @@ setGeneric("test_gene_enrichment", function(.data,
.sample = !!.sample,
.entrez = !!.entrez,
.abundance = !!.abundance,
.contrasts = .contrasts,
.contrasts = contrasts,
methods = methods,
gene_sets = gene_sets,
species = species,
Expand Down
34 changes: 27 additions & 7 deletions R/methods_SE.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1031,7 +1031,7 @@ setMethod(
#' @importFrom rlang inform
.test_differential_abundance_se = function(.data,
.formula,
.contrasts = NULL,
contrasts = NULL,
method = "edgeR_quasi_likelihood",
test_above_log2_fold_change = NULL,
scaling_method = "TMM",
Expand All @@ -1040,6 +1040,15 @@ setMethod(
...)
{

# DEPRECATION OF .constrasts
if (is_present(.contrasts) & !is.null(.contrasts)) {

# Signal the deprecation to the user
deprecate_warn("1.7.4", "tidybulk::test_differential_abundance(.contrasts = )", details = "The argument .contrasts is now deprecated please use contrasts (without the dot).")

contrasts = .contrasts
}

# Clearly state what counts are used
# Clearly state what counts are used
rlang::inform("=====================================
Expand Down Expand Up @@ -1068,7 +1077,7 @@ such as batch effects (if applicable) in the formula.
get_differential_transcript_abundance_bulk_SE(
.,
.formula,
.contrasts = .contrasts,
.contrasts = contrasts,
colData(.data),
method = method,
test_above_log2_fold_change = test_above_log2_fold_change,
Expand All @@ -1082,7 +1091,7 @@ such as batch effects (if applicable) in the formula.
grepl("voom", method) ~ get_differential_transcript_abundance_bulk_voom_SE(
.,
.formula,
.contrasts = .contrasts,
.contrasts = contrasts,
colData(.data),
method = method,
test_above_log2_fold_change = test_above_log2_fold_change,
Expand All @@ -1095,7 +1104,7 @@ such as batch effects (if applicable) in the formula.
tolower(method)=="deseq2" ~ get_differential_transcript_abundance_deseq2_SE(
.,
.formula,
.contrasts = .contrasts,
.contrasts = contrasts,
method = method,
scaling_method = scaling_method,
omit_contrast_in_colnames = omit_contrast_in_colnames,
Expand Down Expand Up @@ -1401,13 +1410,15 @@ setMethod("keep_abundant",
.sample = NULL,
.entrez,
.abundance = NULL,
.contrasts = NULL,
contrasts = NULL,
methods = c("camera" , "roast" , "safe", "gage" , "padog" , "globaltest", "ora" ),
gene_sets = c("h", "c1", "c2", "c3", "c4", "c5", "c6", "c7", "kegg_disease", "kegg_metabolism", "kegg_signaling"),
species,
cores = 10,

method = NULL # DEPRECATED
# DEPRECATED
method = NULL,
.contrasts = NULL
) {

# DEPRECATION OF reference function
Expand All @@ -1418,6 +1429,15 @@ setMethod("keep_abundant",
methods = method
}

# DEPRECATION OF .constrasts
if (is_present(.contrasts) & !is.null(.contrasts)) {

# Signal the deprecation to the user
deprecate_warn("1.7.4", "tidybulk::test_differential_abundance(.contrasts = )", details = "The argument .contrasts is now deprecated please use contrasts (without the dot).")

contrasts = .contrasts
}

.entrez = enquo(.entrez)

# Check that there are no entrez missing
Expand Down Expand Up @@ -1465,7 +1485,7 @@ setMethod("keep_abundant",
)

my_contrasts =
.contrasts %>%
contrasts %>%
when(
length(.) > 0 ~ limma::makeContrasts(contrasts = ., levels = design),
~ NULL
Expand Down
Loading