add up to bowtie

torres-alexis · torres-alexis · commit 45409274c171 · 2025-01-28T13:00:37.000-08:00
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/bin/gtf_to_bed.py b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/bin/gtf_to_bed.py
@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+
+import sys
+import re
+
+def gtf_to_bed(input_file, output_file):
+    """
+    Convert GTF file to BED format
+    Parameters:
+        input_file (str): Path to input GTF file
+        output_file (str): Path to output BED file
+    """
+    with open(input_file, 'r') as f_in, open(output_file, 'w') as f_out:
+        for line in f_in:
+            # Skip comment lines
+            if line.startswith('#'):
+                continue
+            
+            try:
+                # Parse GTF line
+                fields = line.strip().split('\t')
+                if len(fields) < 9:  # GTF must have 9 fields
+                    continue
+                
+                chrom = fields[0]
+                start = int(fields[3]) - 1  # Convert to 0-based
+                end = int(fields[4])
+                strand = fields[6]
+                
+                # Extract gene_id from attributes
+                attributes = fields[8]
+                gene_id_match = re.search(r'gene_id "([^"]+)"', attributes)
+                gene_id = gene_id_match.group(1) if gene_id_match else "unknown"
+                
+                # Write BED line
+                bed_line = f"{chrom}\t{start}\t{end}\t{gene_id}\t0\t{strand}\n"
+                f_out.write(bed_line)
+                
+            except (IndexError, ValueError) as e:
+                # Skip malformed lines
+                continue
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print("Usage: python gtf_to_bed.py input.gtf output.bed")
+        sys.exit(1)
+    
+    input_file = sys.argv[1]
+    output_file = sys.argv[2]
+    gtf_to_bed(input_file, output_file) 
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/conf/by_docker_image.config b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/conf/by_docker_image.config
@@ -19,7 +19,7 @@ process {
          container = "quay.io/biocontainers/samtools:1.21--h50ea8bc_0"
      }
 
-    withName: 'QUANTIFY_STAR_GENES|QUANTIFY_RSEM_GENES|DESEQ2_DGE|ADD_GENE_ANNOTATIONS|EXTEND_DGE_TABLE' {
+    withName: 'QUANTIFY_STAR_GENES|QUANTIFY_RSEM_GENES|DGE_DESEQ2|ADD_GENE_ANNOTATIONS|EXTEND_DGE_TABLE' {
         // This image includes a collection of R libraries that support all R scripts in the workflow
         container = "quay.io/torres-alexis/gl_images:DESeq2_1.0.9" 
     }
@@ -31,7 +31,7 @@ process {
 
      withName: 'MULTIQC' {
          // MultiQC 1.26 (12/21/2024)
-         container = "quay.io/biocontainers/multiqc:1.26--pyhdfd78af_0"
+         container = "quay.io/nasa_genelab/dp_tools:1.3.5"
      }
 
      withName: 'TRIMGALORE' {
@@ -60,12 +60,12 @@ 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' {
+   withName: 'GET_ACCESSIONS|FETCH_ISA|ISA_TO_RUNSHEET|RUNSHEET_FROM_ISA|GENERATE_MD5SUMS|SOFTWARE_VERSIONS|UPDATE_ISA_TABLES|PARSE_QC_METRICS|GTF_TO_BED' {
         container = "quay.io/nasa_genelab/dp_tools:1.3.5"
     }
 
     withLabel: 'VV' {
-        // container = "quay.io/nasa_genelab/dp_tools:1.3.5"
+         container = "quay.io/nasa_genelab/dp_tools:1.3.5"
     }
     // withName: 'QUALIMAP_BAM_QC|QUALIMAP_RNASEQ_QC' {
          container = "quay.io/biocontainers/qualimap:2.3--hdfd78af_0"
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/conf/slurm.config b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/conf/slurm.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' {
+    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|GTF_TO_BED' {
         cpus   = { 1                    }
         memory = { 2.GB                 }
     }
@@ -46,6 +46,14 @@ process {
         cpus   = { 8     * task.attempt }
         memory = { 32.GB * task.attempt }
     }
+    withName:BUILD_BOWTIE2_INDEX {
+        cpus   = { 8     * task.attempt }
+        memory = { 32.GB * task.attempt }
+    }
+    withName:ALIGN_BOWTIE2 {
+        cpus   = { 4     * task.attempt }
+        memory = { 16.GB * task.attempt }
+    }
     withName:INFER_EXPERIMENT {
         // To do: test 2, 1-2gb, consider qualimap alternatives for rseqc processes
         cpus   = { 2    * task.attempt }
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/align_bowtie2.nf b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/align_bowtie2.nf
@@ -21,7 +21,7 @@ process ALIGN_BOWTIE2 {
 
     
     mkdir -p ${ meta.id }
-    bowtie2 -x ${ BOWTIE2_INDEX_DIR } \
+    bowtie2 -x ${ BOWTIE2_INDEXES } \
     ${readArgs} \
     --threads ${ task.cpus } \
     --minins 0 \
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/build_bowtie2_index.nf b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/build_bowtie2_index.nf
@@ -1,6 +1,6 @@
 process BUILD_BOWTIE2_INDEX {
   // Builds Bowtie 2 index, this is ercc-spike-in and organism specific
-  tag "Refs: ${ genome_fasta }, ${ genome_gtf }, Source: ${reference_source}${reference_source.toLowerCase().contains('ensembl') ? ', Version: ' + reference_version : ''}, GenomeSubsample: ' + params.genome_subsample : ''}"
+  tag "Refs: ${ genome_fasta.baseName }, ${ genome_gtf.baseName }, Source: ${reference_source}${reference_source.toLowerCase().contains('ensembl') ? ', Version: ' + reference_version : ''}${params.genome_subsample ? ', GenomeSubsample: ' + params.genome_subsample : ''}"
   storeDir "${ derived_store_path }/Bowtie2_Indices/${ reference_source }/${reference_source.toLowerCase().contains('ensembl') ? reference_version + '/' : ''}${ meta.organism_sci }"
 
   input:
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/gtf_to_bed.nf b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/gtf_to_bed.nf
@@ -14,6 +14,6 @@ process GTF_TO_BED {
 
     script:
     """
-    gtf_to_bed.py ${ genome_gtf } ${ genome_gtf.baseName }.bed
+    python gtf_to_bed.py ${ genome_gtf } ${ genome_gtf.baseName }.bed
     """
 }
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/nextflow.config b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/nextflow.config
@@ -141,6 +141,6 @@ manifest {
     homePage        = 'https://github.com/nasa/GeneLab_Data_Processing/tree/master/RNAseq'
     description     = 'RNA-Seq Pipeline for Document GL-DPPD-7101-G.'
     mainScript      = 'main.nf'
-    nextflowVersion = '!>=24.10.3'
+    nextflowVersion = '!>=24.04.4'
     version         = '2.0.0'
 }
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/workflows/rnaseq.nf b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/workflows/rnaseq.nf
@@ -167,7 +167,7 @@ workflow RNASEQ {
         // Metadata and reference files are ready. Stage the raw reads, find the max read length, and build the STAR index.
 
         // Stage the raw or truncated reads.
-        STAGE_RAW_READS( publishdir, samples )
+        STAGE_RAW_READS( samples )
         raw_reads = STAGE_RAW_READS.out.raw_reads
         samples_txt = STAGE_RAW_READS.out.samples_txt
         //samples_txt | view
diff --git a/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/workflows/rnaseq_microbes.nf b/RNAseq/Workflow_Documentation/NF_RCP/workflow_code/workflows/rnaseq_microbes.nf
@@ -150,7 +150,7 @@ workflow RNASEQ_MICROBES {
         // Metadata and reference files are ready. Stage the raw reads, find the max read length, and build the Bowtie 2 index.
 
         // Stage the raw or truncated reads.
-        STAGE_RAW_READS( publishdir, samples )
+        STAGE_RAW_READS( samples )
         raw_reads = STAGE_RAW_READS.out.raw_reads
         samples_txt = STAGE_RAW_READS.out.samples_txt
         //samples_txt | view
@@ -182,7 +182,7 @@ workflow RNASEQ_MICROBES {
                               | set { trimmed_fastqc_zip }
 
 
-        // Build Bowtie 2 genome index
+        // // Build Bowtie 2 genome index
         BUILD_BOWTIE2_INDEX(derived_store_path, organism_sci, reference_source, reference_version, genome_references, ch_meta)
         bowtie2_index_dir = BUILD_BOWTIE2_INDEX.out.index_dir
 
@@ -195,10 +195,10 @@ workflow RNASEQ_MICROBES {
         // MultiQC
         ch_multiqc_config = params.multiqc_config ? Channel.fromPath( params.multiqc_config ) : Channel.fromPath("NO_FILE")
         RAW_READS_MULTIQC( samples_txt, raw_fastqc_zip, ch_multiqc_config )
-        TRIMMING_MULTIQC( samples_txt, trimgalore_reports, ch_multiqc_config )
-        TRIMMED_READS_MULTIQC( samples_txt, trimmed_fastqc_zip, ch_multiqc_config )
-        ALIGN_MULTIQC( samples_txt, bowtie2_alignment_logs, ch_multiqc_config )
+        // TRIMMING_MULTIQC( samples_txt, trimgalore_reports, ch_multiqc_config )
+        // TRIMMED_READS_MULTIQC( samples_txt, trimmed_fastqc_zip, ch_multiqc_config )
+        // ALIGN_MULTIQC( samples_txt, bowtie2_alignment_logs, ch_multiqc_config )
 
     emit:
-        PARSE_QC_METRICS.out.file
+        RAW_FASTQC.out.fastqc
 }

Original file line number	Diff line number	Diff line change
`@@ -19,7 +19,7 @@ process {`
`19`	`19`	`container = "quay.io/biocontainers/samtools:1.21--h50ea8bc_0"`
`20`	`20`	`}`
`21`	`21`
`22`		`- withName: 'QUANTIFY_STAR_GENES\|QUANTIFY_RSEM_GENES\|DESEQ2_DGE\|ADD_GENE_ANNOTATIONS\|EXTEND_DGE_TABLE' {`
	`22`	`+ withName: 'QUANTIFY_STAR_GENES\|QUANTIFY_RSEM_GENES\|DGE_DESEQ2\|ADD_GENE_ANNOTATIONS\|EXTEND_DGE_TABLE' {`
`23`	`23`	`// This image includes a collection of R libraries that support all R scripts in the workflow`
`24`	`24`	`container = "quay.io/torres-alexis/gl_images:DESeq2_1.0.9"`
`25`	`25`	`}`
`@@ -31,7 +31,7 @@ process {`
`31`	`31`
`32`	`32`	`withName: 'MULTIQC' {`
`33`	`33`	`// MultiQC 1.26 (12/21/2024)`
`34`		`- container = "quay.io/biocontainers/multiqc:1.26--pyhdfd78af_0"`
	`34`	`+ container = "quay.io/nasa_genelab/dp_tools:1.3.5"`
`35`	`35`	`}`
`36`	`36`
`37`	`37`	`withName: 'TRIMGALORE' {`
`@@ -60,12 +60,12 @@ process {`
`60`	`60`	`container = "quay.io/biocontainers/rsem:1.3.3--pl526ha52163a_0"`
`61`	`61`	`}`
`62`	`62`
`63`		`- withName: 'GET_ACCESSIONS\|FETCH_ISA\|ISA_TO_RUNSHEET\|RUNSHEET_FROM_ISA\|GENERATE_MD5SUMS\|SOFTWARE_VERSIONS\|UPDATE_ISA_TABLES\|PARSE_QC_METRICS' {`
	`63`	`+ withName: 'GET_ACCESSIONS\|FETCH_ISA\|ISA_TO_RUNSHEET\|RUNSHEET_FROM_ISA\|GENERATE_MD5SUMS\|SOFTWARE_VERSIONS\|UPDATE_ISA_TABLES\|PARSE_QC_METRICS\|GTF_TO_BED' {`
`64`	`64`	`container = "quay.io/nasa_genelab/dp_tools:1.3.5"`
`65`	`65`	`}`
`66`	`66`
`67`	`67`	`withLabel: 'VV' {`
`68`		`- // container = "quay.io/nasa_genelab/dp_tools:1.3.5"`
	`68`	`+ container = "quay.io/nasa_genelab/dp_tools:1.3.5"`
`69`	`69`	`}`
`70`	`70`	`// withName: 'QUALIMAP_BAM_QC\|QUALIMAP_RNASEQ_QC' {`
`71`	`71`	`container = "quay.io/biocontainers/qualimap:2.3--hdfd78af_0"`
Original file line number	Diff line number	Diff line change
`@@ -14,6 +14,6 @@ process GTF_TO_BED {`
`14`	`14`
`15`	`15`	`script:`
`16`	`16`	`"""`
`17`		`- gtf_to_bed.py ${ genome_gtf } ${ genome_gtf.baseName }.bed`
	`17`	`+ python gtf_to_bed.py ${ genome_gtf } ${ genome_gtf.baseName }.bed`
`18`	`18`	`"""`
`19`	`19`	`}`
Original file line number	Diff line number	Diff line change
`@@ -141,6 +141,6 @@ manifest {`
`141`	`141`	`homePage = 'https://github.com/nasa/GeneLab_Data_Processing/tree/master/RNAseq'`
`142`	`142`	`description = 'RNA-Seq Pipeline for Document GL-DPPD-7101-G.'`
`143`	`143`	`mainScript = 'main.nf'`
`144`		`- nextflowVersion = '!>=24.10.3'`
	`144`	`+ nextflowVersion = '!>=24.04.4'`
`145`	`145`	`version = '2.0.0'`
`146`	`146`	`}`