Merge pull request #962 from drpatelh/fixes

Fix #878 #931 #960
nf-core · Mar 16, 2023 · 9851365 · 9851365
2 parents 4656b56 + 192dcb9
commit 9851365
Show file tree

Hide file tree

Showing 7 changed files with 116 additions and 115 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,10 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Enhancements & fixes
 
+- [[#878](https://github.com/nf-core/rnaseq/pull/878)] - Allow tabs in fasta header when creating decoys for salmon index
+- [[#931](https://github.com/nf-core/rnaseq/pull/931)] - Save transcriptome BAM files when using `--save_umi_intermeds` / `--save_align_intermeds`
 - [[#934](https://github.com/nf-core/rnaseq/pull/934)] - Union of `ext.args` and `params.extra_star_align_args` prevents parameter clashes in the STAR module
 - [[#940](https://github.com/nf-core/rnaseq/issues/940)] - Bugfix in `salmon_summarizedexperiment.r` to ensure `rbind` doesn't fail when `rowdata` has no `tx` column. See ([[#941](https://github.com/nf-core/rnaseq/pull/941)]) for details.
 - [[#944](https://github.com/nf-core/rnaseq/issues/944)] - Read clipping using clip_r1, clip_r2, three_prime_clip_r1, three_prime_clip_r2 disabled in 3.10
 - [[#956](https://github.com/nf-core/rnaseq/pull/956)] - Implement 'auto' as default strandedness argument in `fastq_dir_to_samplesheet.py` script
+- [[#960](https://github.com/nf-core/rnaseq/pull/960)] - Failure with awsbatch when running processes that are using `executor: local`
 - Remove HISAT2 from automated AWS full-sized tests
 
 ### Software dependencies

diff --git a/conf/modules.config b/conf/modules.config
@@ -237,13 +237,6 @@ if (!params.skip_trimming) {
                 ]
             ]
         }
-
-        withName: 'MULTIQC_TSV_FAIL_TRIMMED' {
-            publishDir = [
-                path: { "${params.outdir}/multiqc" },
-                enabled: false
-            ]
-        }
     }
 }
 
@@ -517,17 +510,6 @@ if (!params.skip_alignment) {
             }
         }
     }
-
-    if (params.aligner.contains('star')) {
-        process {
-            withName: 'MULTIQC_TSV_FAIL_MAPPED' {
-                publishDir = [
-                    path: { "${params.outdir}/multiqc" },
-                    enabled: false
-                ]
-            }
-        }
-    }
 }
 
 //
@@ -613,39 +595,70 @@ if (!params.skip_alignment && params.aligner == 'star_salmon') {
                 ext.prefix = { "${meta.id}.umi_dedup.transcriptome" }
                 publishDir = [
                     path: { "${params.outdir}/${params.aligner}" },
-                    enabled: false
+                    mode: params.publish_dir_mode,
+                    pattern: '*.bam',
+                    enabled: (
+                        params.save_align_intermeds ||
+                        params.save_umi_intermeds
+                    )
                 ]
             }
 
             withName: 'NFCORE_RNASEQ:RNASEQ:UMITOOLS_PREPAREFORSALMON' {
                 ext.prefix = { "${meta.id}.umi_dedup.transcriptome.filtered" }
                 publishDir = [
-                    path: { "${params.outdir}/${params.aligner}/umitools/log" },
-                    mode: params.publish_dir_mode,
-                    pattern: '*.log'
+                    [
+                        path: { "${params.outdir}/${params.aligner}/umitools/log" },
+                        mode: params.publish_dir_mode,
+                        pattern: '*.log'
+                    ],
+                    [
+                        path: { "${params.outdir}/${params.aligner}" },
+                        mode: params.publish_dir_mode,
+                        pattern: '*.bam',
+                        enabled: (
+                            params.save_align_intermeds ||
+                            params.save_umi_intermeds
+                        )
+                    ]
                 ]
             }
 
             withName: 'NFCORE_RNASEQ:RNASEQ:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_SORT' {
                 ext.prefix = { "${meta.id}.transcriptome.sorted" }
                 publishDir = [
                     path: { "${params.outdir}/${params.aligner}" },
-                    enabled: false
+                    mode: params.publish_dir_mode,
+                    pattern: '*.bam',
+                    enabled: (
+                        params.save_align_intermeds ||
+                        params.save_umi_intermeds
+                    )
                 ]
             }
 
             withName: 'NFCORE_RNASEQ:RNASEQ:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_INDEX' {
                 publishDir = [
                     path: { "${params.outdir}/${params.aligner}" },
-                    enabled: false
+                    mode: params.publish_dir_mode,
+                    pattern: '*.bai',
+                    enabled: (
+                        params.save_align_intermeds ||
+                        params.save_umi_intermeds
+                    )
                 ]
             }
 
             withName: 'NFCORE_RNASEQ:RNASEQ:BAM_SORT_STATS_SAMTOOLS:BAM_STATS_SAMTOOLS:.*' {
                 ext.prefix = { "${meta.id}.transcriptome.sorted.bam" }
                 publishDir = [
-                    path: { "${params.outdir}/${params.aligner}" },
-                    enabled: false
+                    path: { "${params.outdir}/${params.aligner}/samtools_stats" },
+                    mode: params.publish_dir_mode,
+                    pattern: '*.{stats,flagstat,idxstats}',
+                    enabled: (
+                        params.save_align_intermeds ||
+                        params.save_umi_intermeds
+                    )
                 ]
             }
 
@@ -657,16 +670,32 @@ if (!params.skip_alignment && params.aligner == 'star_salmon') {
                 ].join(' ').trim() }
                 ext.prefix = { "${meta.id}.umi_dedup.transcriptome.sorted" }
                 publishDir = [
-                    path: { "${params.outdir}/${params.aligner}/umitools" },
-                    mode: params.publish_dir_mode,
-                    pattern: '*.tsv'
+                    [
+                        path: { "${params.outdir}/${params.aligner}/umitools" },
+                        mode: params.publish_dir_mode,
+                        pattern: '*.tsv'
+                    ],
+                    [
+                        path: { "${params.outdir}/${params.aligner}" },
+                        mode: params.publish_dir_mode,
+                        pattern: '*.bam',
+                        enabled: (
+                            params.save_align_intermeds ||
+                            params.save_umi_intermeds
+                        )
+                    ]
                 ]
             }
 
             withName: '.*:BAM_DEDUP_STATS_SAMTOOLS_UMITOOLS_TRANSCRIPTOME:SAMTOOLS_INDEX' {
                 publishDir = [
                     path: { "${params.outdir}/${params.aligner}" },
-                    enabled: false
+                    mode: params.publish_dir_mode,
+                    pattern: '*.bai',
+                    enabled: (
+                        params.save_align_intermeds ||
+                        params.save_umi_intermeds
+                    )
                 ]
             }
 
@@ -1042,17 +1071,6 @@ if (!params.skip_alignment && !params.skip_qc) {
             }
         }
     }
-
-    if (!params.skip_rseqc && rseqc_modules) {
-        process {
-            withName: 'MULTIQC_TSV_STRAND_CHECK' {
-                publishDir = [
-                    path: { "${params.outdir}/multiqc" },
-                    enabled: false
-                ]
-            }
-        }
-    }
 }
 
 if (!params.skip_multiqc) {

diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy
@@ -273,6 +273,18 @@ class WorkflowRnaseq {
         return yaml_file_text
     }
 
+    //
+    // Create MultiQC tsv custom content from a list of values
+    //
+    public static String multiqcTsvFromList(tsv_data, header) {
+        def tsv_string = ""
+        if (tsv_data.size() > 0) {
+            tsv_string += "${header.join('\t')}\n"
+            tsv_string += tsv_data.join('\n')
+        }
+        return tsv_string
+    }
+
     public static String methodsDescriptionText(run_workflow, mqc_methods_yaml) {
         // Convert  to a named map so can be used as with familar NXF ${workflow} variable syntax in the MultiQC YML file
         def meta = [:]
@@ -288,7 +300,9 @@ class WorkflowRnaseq {
         def description_html = engine.createTemplate(methods_text).make(meta)
 
         return description_html
-    }//
+    }
+
+    //
     // Exit pipeline if incorrect --genome key provided
     //
     private static void genomeExistsError(params, log) {

diff --git a/modules.json b/modules.json
@@ -127,7 +127,7 @@
                     },
                     "salmon/index": {
                         "branch": "master",
-                        "git_sha": "94b06f1683ddf893cf06525f6e7f0573ad8fbf83",
+                        "git_sha": "cfef21995228c66af535b14c5efae1461ffb8981",
                         "installed_by": ["fastq_subsample_fq_salmon"]
                     },
                     "salmon/quant": {

diff --git a/modules/local/multiqc_tsv_from_list.nf b/modules/local/multiqc_tsv_from_list.nf
diff --git a/modules/nf-core/salmon/index/main.nf b/modules/nf-core/salmon/index/main.nf
diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf
@@ -100,9 +100,6 @@ include { DUPRADAR                           } from '../modules/local/dupradar'
 include { MULTIQC                            } from '../modules/local/multiqc'
 include { MULTIQC_CUSTOM_BIOTYPE             } from '../modules/local/multiqc_custom_biotype'
 include { UMITOOLS_PREPAREFORRSEM as UMITOOLS_PREPAREFORSALMON } from '../modules/local/umitools_prepareforrsem.nf'
-include { MULTIQC_TSV_FROM_LIST as MULTIQC_TSV_FAIL_MAPPED  } from '../modules/local/multiqc_tsv_from_list'
-include { MULTIQC_TSV_FROM_LIST as MULTIQC_TSV_FAIL_TRIMMED } from '../modules/local/multiqc_tsv_from_list'
-include { MULTIQC_TSV_FROM_LIST as MULTIQC_TSV_STRAND_CHECK } from '../modules/local/multiqc_tsv_from_list'
 
 //
 // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
@@ -309,14 +306,13 @@ workflow RNASEQ {
                     return [ "$meta.id\t$num_reads" ]
                 }
             }
-            .set { ch_num_trimmed_reads }
-
-        MULTIQC_TSV_FAIL_TRIMMED (
-            ch_num_trimmed_reads.collect(),
-            ["Sample", "Reads after trimming"],
-            'fail_trimmed_samples'
-        )
-        .set { ch_fail_trimming_multiqc }
+            .collect()                
+            .map { 
+                tsv_data ->
+                    def header = ["Sample", "Reads after trimming"]
+                    WorkflowRnaseq.multiqcTsvFromList(tsv_data, header)
+            }
+            .set { ch_fail_trimming_multiqc }
     }
 
     //
@@ -581,16 +577,15 @@ workflow RNASEQ {
             }
             .set { ch_pass_fail_mapped }
 
-        def header = [
-            "Sample",
-            "STAR uniquely mapped reads (%)"
-        ]
-        MULTIQC_TSV_FAIL_MAPPED (
-            ch_pass_fail_mapped.fail.collect(),
-            header,
-            'fail_mapped_samples'
-        )
-        .set { ch_fail_mapping_multiqc }
+        ch_pass_fail_mapped
+            .fail
+            .collect()
+            .map { 
+                tsv_data ->
+                    def header = ["Sample", "STAR uniquely mapped reads (%)"]
+                    WorkflowRnaseq.multiqcTsvFromList(tsv_data, header)
+            }
+            .set { ch_fail_mapping_multiqc }
     }
 
     //
@@ -751,22 +746,20 @@ workflow RNASEQ {
                 .map { meta, strandedness, sense, antisense, undetermined ->
                     [ "$meta.id\t$meta.strandedness\t$strandedness\t$sense\t$antisense\t$undetermined" ]
                 }
-                .set { ch_fail_strand }
-
-            def header = [
-                "Sample",
-                "Provided strandedness",
-                "Inferred strandedness",
-                "Sense (%)",
-                "Antisense (%)",
-                "Undetermined (%)"
-            ]
-            MULTIQC_TSV_STRAND_CHECK (
-                ch_fail_strand.collect(),
-                header,
-                'fail_strand_check'
-            )
-            .set { ch_fail_strand_multiqc }
+                .collect()
+                .map { 
+                    tsv_data ->
+                        def header = [
+                            "Sample",
+                            "Provided strandedness",
+                            "Inferred strandedness",
+                            "Sense (%)",
+                            "Antisense (%)",
+                            "Undetermined (%)"
+                        ]
+                        WorkflowRnaseq.multiqcTsvFromList(tsv_data, header)
+                }
+                .set { ch_fail_strand_multiqc }
         }
     }
 
@@ -824,9 +817,9 @@ workflow RNASEQ {
             ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'),
             ch_methods_description.collectFile(name: 'methods_description_mqc.yaml'),
             ch_multiqc_logo.collect().ifEmpty([]),
-            ch_fail_trimming_multiqc.ifEmpty([]),
-            ch_fail_mapping_multiqc.ifEmpty([]),
-            ch_fail_strand_multiqc.ifEmpty([]),
+            ch_fail_trimming_multiqc.collectFile(name: 'fail_trimmed_samples_mqc.tsv').ifEmpty([]),
+            ch_fail_mapping_multiqc.collectFile(name: 'fail_mapped_samples_mqc.tsv').ifEmpty([]),
+            ch_fail_strand_multiqc.collectFile(name: 'fail_strand_check_mqc.tsv').ifEmpty([]),
             FASTQ_FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_zip.collect{it[1]}.ifEmpty([]),
             FASTQ_FASTQC_UMITOOLS_TRIMGALORE.out.trim_zip.collect{it[1]}.ifEmpty([]),
             FASTQ_FASTQC_UMITOOLS_TRIMGALORE.out.trim_log.collect{it[1]}.ifEmpty([]),