add md5sum functionality, to do: finish implementation

Author: torres-alexis

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/conf/by_docker_image.config

@@ -60,7 +60,7 @@ process {
         container = "quay.io/biocontainers/rsem:1.3.3--pl526ha52163a_0"
     }
 
-   withName: 'GET_ACCESSIONS|FETCH_ISA|ISA_TO_RUNSHEET|RUNSHEET_FROM_ISA|GENERATE_MD5SUMS|SOFTWARE_VERSIONS|UPDATE_ISA_TABLES|PARSE_QC_METRICS|REMOVE_RRNA_FEATURECOUNTS' {
+   withName: 'GET_ACCESSIONS|FETCH_ISA|ISA_TO_RUNSHEET|RUNSHEET_FROM_ISA|GENERATE_MD5SUMS|SOFTWARE_VERSIONS|UPDATE_ISA_TABLES|PARSE_QC_METRICS|REMOVE_RRNA_FEATURECOUNTS|MD5SUM' {
         container = "quay.io/nasa_genelab/dp_tools:1.3.5"
     }
 

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/conf/local.config

@@ -17,7 +17,7 @@ process {
     maxErrors     = '-1'
 
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
-    withName:'GET_ACCESSIONS|FETCH_ISA|ISA_TO_RUNSHEET|PARSE_ANNOTATIONS_TABLE|COPY_READS|GET_MAX_READ_LENGTH|ADD_GENE_ANNOTATIONS|EXTEND_DGE_TABLE|VV_RAW_READS|GET_GTF_FEATURES|REMOVE_RRNA_FEATURECOUNTS' {
+    withName:'GET_ACCESSIONS|FETCH_ISA|ISA_TO_RUNSHEET|PARSE_ANNOTATIONS_TABLE|COPY_READS|GET_MAX_READ_LENGTH|ADD_GENE_ANNOTATIONS|EXTEND_DGE_TABLE|VV_RAW_READS|GET_GTF_FEATURES|REMOVE_RRNA_FEATURECOUNTS|MD5SUM' {
         cpus   = { 1                    }
         memory = { 2.GB                 }
     }

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/conf/slurm.config

@@ -18,7 +18,7 @@ process {
     cache = 'lenient'
 
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
-    withName:'GET_ACCESSIONS|FETCH_ISA|ISA_TO_RUNSHEET|PARSE_ANNOTATIONS_TABLE|COPY_READS|GET_MAX_READ_LENGTH|ADD_GENE_ANNOTATIONS|EXTEND_DGE_TABLE|VV_RAW_READS|GET_GTF_FEATURES|REMOVE_RRNA_FEATURECOUNTS' {
+    withName:'GET_ACCESSIONS|FETCH_ISA|ISA_TO_RUNSHEET|PARSE_ANNOTATIONS_TABLE|COPY_READS|GET_MAX_READ_LENGTH|ADD_GENE_ANNOTATIONS|EXTEND_DGE_TABLE|VV_RAW_READS|GET_GTF_FEATURES|REMOVE_RRNA_FEATURECOUNTS|MD5SUM' {
         cpus   = { 1                    }
         memory = { 2.GB                 }
     }

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/md5sum.nf

@@ -0,0 +1,29 @@
+process MD5SUM {
+    /**
+     * Run recursive md5sum on files/directories and output md5sum files
+     *
+     * Inputs:
+     *   path to file(s) or directory
+     *   label for output file name
+     *
+     * Outputs:
+     *   {MD5SumLabel}_md5sums.tsv - Raw md5sums
+     */
+
+    input:
+        path files
+
+    output:
+        path("${ params.md5sumLabel }_md5sum_GLbulkRNAseq.tsv"), emit: md5sums
+
+    script:
+        """
+        # Generate raw md5sums
+        if [ -d "${ files }" ]; then
+            find "${ files }" -type f -exec md5sum {} \\; > ${ params.md5sumLabel }_md5sum_GLbulkRNAseq.tsv
+        else
+            md5sum ${ files } > ${ params.md5sumLabel }_md5sum_GLbulkRNAseq.tsv
+        fi
+
+        """
+}

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/software_versions.nf

@@ -3,11 +3,11 @@ process SOFTWARE_VERSIONS {
         path versions_file
 
     output:
-        path "software_versions_GLbulkRNAseq.txt", emit: software_versions
+        path "software_versions_GLbulkRNAseq.md", emit: software_versions
         path "software_versions_GLbulkRNAseq.yaml", emit: software_versions_yaml
 
     script:
     """
-    software_versions.py ${versions_file} software_versions_GLbulkRNAseq.txt --assay rnaseq
+    software_versions.py ${versions_file} software_versions_GLbulkRNAseq.md --assay rnaseq
     """
 }

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/workflows/rnaseq_microbes.nf

@@ -58,6 +58,9 @@ include { ADD_GENE_ANNOTATIONS } from '../modules/add_gene_annotations.nf'
 
 include { SOFTWARE_VERSIONS } from '../modules/software_versions.nf'
 
+include { MD5SUM as RAW_MD5SUM } from '../modules/md5sum.nf' addParams(md5sumLabel:"raw")
+include { MD5SUM as PROCESSED_MD5SUM } from '../modules/md5sum.nf' addParams(md5sumLabel:"processed")
+
 
 include { VV_RAW_READS;
     VV_TRIMMED_READS;
@@ -314,10 +317,10 @@ workflow RNASEQ_MICROBES {
             | mix(FEATURECOUNTS.out.versions)
             | mix(RAW_READS_MULTIQC.out.versions)
             | mix(DGE_DESEQ2.out.versions)
+            | mix(ch_nextflow_version)
         // Process the versions:
         ch_software_versions 
             | unique                          // Remove duplicates
-            | mix(ch_nextflow_version)        // Add Nextflow version
             | collectFile(                    // Combine all into one file
                 name: "software_versions.txt", 
                 newLine: true, 
@@ -327,6 +330,17 @@ workflow RNASEQ_MICROBES {
 
         SOFTWARE_VERSIONS(ch_final_software_versions)
 
+
+        // Generate md5sums for raw and processed data
+        RAW_MD5SUM( STAGE_RAW_READS.out.ch_all_raw_reads
+        | concat (RAW_READS_MULTIQC.out.zipped_report) // to do: reimplement zip output w/ cleaned paths
+        | collect)
+
+        // PROCESSED_MD5SUM(x
+        // | concat(y)
+        // | collect 
+        // )
+
     emit:
-        EXTRACT_RRNA.out.rrna_ids
+        RAW_MD5SUM.out.md5sums
 }