Get raw gene count tables from either Salmon and RSEM analysis

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- [#251](https://github.com/qbic-pipelines/rnadeseq/pull/251) Get raw gene count tables from either Salmon and RSEM analysis
 - [#250](https://github.com/qbic-pipelines/rnadeseq/pull/250) Added clearer error message for incorrect contrast_pairs
 
 ### Changed
@@ -32,7 +33,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Removed
 
 - [#247](https://github.com/qbic-pipelines/rnadeseq/pull/247) Removed hard-coded comment about usage of gprofiler databases KEGG and REAC in the report
-
+  
 ## 2.3 - Flowering Orchards
 
 ### Added

assets/RNAseq_report.Rmd

@@ -592,6 +592,10 @@ if (params$input_type %in% c("featurecounts", "smrnaseq")) {
 
         #dds from SummarizedExperiment <se>, then run DESeq
         cds <- DESeqDataSet(se, design = as.formula(eval(parse(text=as.character(design[[1]])))))
+        # get raw counts
+        count_table_names <- merge(x=gene_names, y=assay(cds), by.x = "Ensembl_ID", by.y="row.names")
+        count_table_names <- count_table_names[order(count_table_names$Ensembl_ID),]
+        write.table(count_table_names, paste("differential_gene_expression/gene_counts_tables/raw_gene_counts.tsv",sep=""), append =          FALSE, quote = FALSE, sep = "\t",eol = "\n", na = "NA", dec = ".", row.names = F, qmethod = c("escape", "double"))
 
 # Load salmon count files
     } else if (params$input_type == "salmon") {
@@ -625,6 +629,10 @@ if (params$input_type %in% c("featurecounts", "smrnaseq")) {
         coldata$combfactor <- metadata$combfactor
         rownames(coldata) <- qbicCodes
         cds <- DESeqDataSetFromTximport(txi=txi.salmon, colData =coldata, design = eval(parse(text=as.character(design[[1]]))))
+        # get raw counts
+        count_table_names <- merge(x=gene_names, y=assay(cds), by.x = "Ensembl_ID", by.y="row.names")
+        count_table_names <- count_table_names[order(count_table_names$Ensembl_ID),]
+        write.table(count_table_names, paste("differential_gene_expression/gene_counts_tables/raw_gene_counts.tsv",sep=""), append =          FALSE, quote = FALSE, sep = "\t",eol = "\n", na = "NA", dec = ".", row.names = F, qmethod = c("escape", "double"))
     }
 } else {
     stop(paste0("Invalid input type: ", params$input_type, "! Input type must be one of: featurecounts, rsem, salmon, smrnaseq!"))

tests/test_star_rsem.yml

@@ -13,6 +13,8 @@
     #      md5sum: ea4b16a379f09fa44c7c541ccab64ce6
     - path: results_test/differential_gene_expression/final_gene_table/final_DE_gene_list.tsv
       md5sum: f1825ed59878115a279db7151b0ed0a1
+    - path: results_test/differential_gene_expression/gene_counts_tables/raw_gene_counts.tsv
+      md5sum: f0e6bb8eab1e6e08008a5a06934ef6f3
     - path: results_test/differential_gene_expression/plots/boxplots_requested_genes/CXCL2_ENSG00000081041.pdf
     - path: results_test/differential_gene_expression/plots/boxplots_requested_genes/CXCL2_ENSG00000081041.png
     - path: results_test/differential_gene_expression/plots/boxplots_requested_genes/CXCL2_ENSG00000081041.svg

tests/test_star_salmon.yml

@@ -16,6 +16,8 @@
     - path: results_test/differential_gene_expression/gene_counts_tables/deseq2_library_scaled_gene_counts.tsv
     - path: results_test/differential_gene_expression/gene_counts_tables/rlog_transformed_gene_counts.tsv
     - path: results_test/differential_gene_expression/gene_counts_tables/sizeFactor_libraries.tsv
+    - path: results_test/differential_gene_expression/gene_counts_tables/raw_gene_counts.tsv
+      md5sum: 8ce16900c36615ae3d3b5e0bf0c856f0
     - path: results_test/differential_gene_expression/plots/boxplots_requested_genes/IL10_ENSG00000136634.pdf
     - path: results_test/differential_gene_expression/plots/boxplots_requested_genes/IL10_ENSG00000136634.png
     - path: results_test/differential_gene_expression/plots/boxplots_requested_genes/IL10_ENSG00000136634.svg