Merge pull request #12 from nf-core/alignment_phase

Add alignment via STAR + postprocessing
nf-core · Feb 19, 2024 · d14a8d9 · d14a8d9
2 parents ca556ad + 74fc9f3
commit d14a8d9
Show file tree

Hide file tree

Showing 79 changed files with 5,431 additions and 31 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#8](https://github.com/nf-core/riboseq/pull/8) - Preprocessing from rnaseq ([@pinin4fjords](https://github.com/pinin4fjords), review by [@maxulysse](https://github.com/maxulysse) review by [@adamrtalbot](https://github.com/adamrtalbot))
 - [[#10](https://github.com/nf-core/riboseq/pull/10)] - Take preprocessing from nf-core ([@pinin4fjords](https://github.com/pinin4fjords), review by [@adamrtalbot](https://github.com/adamrtalbot))
 - [[#9](https://github.com/nf-core/riboseq/pull/9)] - Important! Template update for nf-core/tools v2.12 ([nf-core-bot](https://github.com/nf-core-bot), review by [@pinin4fjords](https://github.com/pinin4fjords))
+- [[#12](https://github.com/nf-core/riboseq/pull/12) - Add alignment via STAR + postprocessing (([@pinin4fjords](https://github.com/pinin4fjords), review by )
 
 Initial release of nf-core/riboseq, created with the [nf-core](https://nf-co.re/) template.
 

diff --git a/conf/modules.config b/conf/modules.config
@@ -348,7 +348,7 @@ if (params.remove_ribo_rna) {
 
 if (!params.skip_alignment) {
     process {
-        withName: 'NFCORE_RNASEQ:RNASEQ:.*:BAM_SORT_STATS_SAMTOOLS:BAM_STATS_SAMTOOLS:.*' {
+        withName: 'NFCORE_RIBOSEQ:RIBOSEQ:.*:BAM_SORT_STATS_SAMTOOLS:BAM_STATS_SAMTOOLS:.*' {
             ext.prefix = { "${meta.id}.sorted.bam" }
             publishDir = [
                 path: { "${params.outdir}/${params.aligner}/samtools_stats" },
@@ -357,7 +357,7 @@ if (!params.skip_alignment) {
             ]
         }
 
-        withName: 'NFCORE_RNASEQ:RNASEQ:.*:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_SORT' {
+        withName: 'NFCORE_RIBOSEQ:RIBOSEQ:.*:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_SORT' {
             ext.prefix = { "${meta.id}.sorted" }
             publishDir = [
                 path: { "${params.outdir}/${params.aligner}" },
@@ -369,7 +369,7 @@ if (!params.skip_alignment) {
             ]
         }
 
-        withName: 'NFCORE_RNASEQ:RNASEQ:.*:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_INDEX' {
+        withName: 'NFCORE_RIBOSEQ:RIBOSEQ:.*:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_INDEX' {
             ext.args   = { params.bam_csi_index ? '-c' : '' }
             publishDir = [
                 path: { "${params.outdir}/${params.aligner}" },
@@ -534,19 +534,20 @@ if (!params.skip_alignment) {
 
 if (!params.skip_alignment && params.aligner == 'star_salmon') {
     process {
-        withName: '.*:ALIGN_STAR:STAR_ALIGN|.*:ALIGN_STAR:STAR_ALIGN_IGENOMES' {
+        withName: 'STAR_ALIGN' {
             ext.args   = { [
-                '--quantMode TranscriptomeSAM',
-                '--twopassMode Basic',
+                '--alignSJDBoverhangMin 1',
+                '--alignEndsType EndToEnd',
+                '--outFilterMultimapNmax 20',
+                params.save_unaligned ? '--outReadsUnmapped Fastx' : '',
+                '--outSAMattributes All',
+                '--outSAMstrandField intronMotif',
                 '--outSAMtype BAM Unsorted',
+                '--quantMode TranscriptomeSAM',
+                '--quantTranscriptomeBan Singleend',
                 '--readFilesCommand zcat',
                 '--runRNGseed 0',
-                '--outFilterMultimapNmax 20',
-                '--alignSJDBoverhangMin 1',
-                '--outSAMattributes NH HI AS NM MD',
-                '--quantTranscriptomeBan Singleend',
-                '--outSAMstrandField intronMotif',
-                params.save_unaligned ? '--outReadsUnmapped Fastx' : '',
+                '--twopassMode Basic',
                 params.extra_star_align_args ? params.extra_star_align_args.split("\\s(?=--)") : ''
             ].flatten().unique(false).join(' ').trim() }
             publishDir = [
@@ -607,7 +608,7 @@ if (!params.skip_alignment && params.aligner == 'star_salmon') {
 
     if (params.with_umi) {
         process {
-            withName: 'NFCORE_RNASEQ:RNASEQ:SAMTOOLS_SORT' {
+            withName: 'NFCORE_RIBOSEQ:RIBOSEQ:SAMTOOLS_SORT' {
                 ext.args   = '-n'
                 ext.prefix = { "${meta.id}.umi_dedup.transcriptome" }
                 publishDir = [
@@ -618,7 +619,7 @@ if (!params.skip_alignment && params.aligner == 'star_salmon') {
                 ]
             }
 
-            withName: 'NFCORE_RNASEQ:RNASEQ:UMITOOLS_PREPAREFORSALMON' {
+            withName: 'NFCORE_RIBOSEQ:RIBOSEQ:UMITOOLS_PREPAREFORSALMON' {
                 ext.prefix = { "${meta.id}.umi_dedup.transcriptome.filtered" }
                 publishDir = [
                     [
@@ -635,7 +636,7 @@ if (!params.skip_alignment && params.aligner == 'star_salmon') {
                 ]
             }
 
-            withName: 'NFCORE_RNASEQ:RNASEQ:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_SORT' {
+            withName: 'NFCORE_RIBOSEQ:RIBOSEQ:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_SORT' {
                 ext.prefix = { "${meta.id}.transcriptome.sorted" }
                 publishDir = [
                     path: { "${params.outdir}/${params.aligner}" },
@@ -645,7 +646,7 @@ if (!params.skip_alignment && params.aligner == 'star_salmon') {
                 ]
             }
 
-            withName: 'NFCORE_RNASEQ:RNASEQ:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_INDEX' {
+            withName: 'NFCORE_RIBOSEQ:RIBOSEQ:BAM_SORT_STATS_SAMTOOLS:SAMTOOLS_INDEX' {
                 publishDir = [
                     path: { "${params.outdir}/${params.aligner}" },
                     mode: params.publish_dir_mode,
@@ -654,7 +655,7 @@ if (!params.skip_alignment && params.aligner == 'star_salmon') {
                 ]
             }
 
-            withName: 'NFCORE_RNASEQ:RNASEQ:BAM_SORT_STATS_SAMTOOLS:BAM_STATS_SAMTOOLS:.*' {
+            withName: 'NFCORE_RIBOSEQ:RIBOSEQ:BAM_SORT_STATS_SAMTOOLS:BAM_STATS_SAMTOOLS:.*' {
                 ext.prefix = { "${meta.id}.transcriptome.sorted.bam" }
                 publishDir = [
                     path: { "${params.outdir}/${params.aligner}/samtools_stats" },

diff --git a/conf/test.config b/conf/test.config
@@ -16,13 +16,13 @@ params {
 
     // Limit resources so that this can run on GitHub Actions
     max_cpus   = 2
-    max_memory = '6.GB'
+    max_memory = '12.GB'
     max_time   = '6.h'
 
     // Input data
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/riboseq/testdata/samplesheet.csv'
 
-    fasta = 'http://ftp.ensembl.org/pub/release-110/fasta/mus_musculus/dna/Mus_musculus.GRCm39.dna.chromosome.1.fa.gz'
+    fasta = 'http://ftp.ensembl.org/pub/release-110/fasta/mus_musculus/dna/Mus_musculus.GRCm39.dna.chromosome.19.fa.gz'
     gtf = 'http://ftp.ensembl.org/pub/release-110/gtf/mus_musculus/Mus_musculus.GRCm39.110.gtf.gz'
     min_trimmed_reads = 1000
 }
diff --git a/conf/test_full.config b/conf/test_full.config
@@ -2,7 +2,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     Nextflow config file for running full-size tests
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    Defines input files and everything required to run a full size pipeline test.
+    Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
         nextflow run nf-core/riboseq -profile test_full,<docker/singularity> --outdir <OUTDIR>
@@ -14,11 +14,10 @@ params {
     config_profile_name        = 'Full test profile'
     config_profile_description = 'Full test dataset to check pipeline function'
 
-    // Input data for full size test
-    // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA)
-    // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv'
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/riboseq/testdata/samplesheet.csv'
 
-    // Genome references
-    genome = 'R64-1-1'
+    fasta = 'http://ftp.ensembl.org/pub/release-110/fasta/mus_musculus/dna/Mus_musculus.GRCm39.dna.primary_assembly.fa.gz'
+    gtf = 'http://ftp.ensembl.org/pub/release-110/gtf/mus_musculus/Mus_musculus.GRCm39.110.gtf.gz'
+    min_trimmed_reads = 1000
 }
diff --git a/modules.json b/modules.json
@@ -90,11 +90,41 @@
                         "git_sha": "003920c7f9a8ae19b69a97171922880220bedf56",
                         "installed_by": ["fastq_subsample_fq_salmon"]
                     },
+                    "samtools/flagstat": {
+                        "branch": "master",
+                        "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
+                        "installed_by": ["bam_stats_samtools"]
+                    },
+                    "samtools/idxstats": {
+                        "branch": "master",
+                        "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
+                        "installed_by": ["bam_stats_samtools"]
+                    },
+                    "samtools/index": {
+                        "branch": "master",
+                        "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
+                        "installed_by": ["bam_dedup_stats_samtools_umitools", "bam_sort_stats_samtools"]
+                    },
+                    "samtools/sort": {
+                        "branch": "master",
+                        "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
+                        "installed_by": ["bam_sort_stats_samtools"]
+                    },
+                    "samtools/stats": {
+                        "branch": "master",
+                        "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
+                        "installed_by": ["bam_stats_samtools"]
+                    },
                     "sortmerna": {
                         "branch": "master",
                         "git_sha": "003920c7f9a8ae19b69a97171922880220bedf56",
                         "installed_by": ["preprocess_rnaseq"]
                     },
+                    "star/align": {
+                        "branch": "master",
+                        "git_sha": "a21faa6a3481af92a343a10926f59c189a2c16c9",
+                        "installed_by": ["fastq_align_star", "modules"]
+                    },
                     "star/genomegenerate": {
                         "branch": "master",
                         "git_sha": "003920c7f9a8ae19b69a97171922880220bedf56",
@@ -105,11 +135,21 @@
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
                         "installed_by": ["fastq_fastqc_umitools_trimgalore"]
                     },
+                    "umitools/dedup": {
+                        "branch": "master",
+                        "git_sha": "ff7e93715a2acecf3f143ec78c9858deba2984d0",
+                        "installed_by": ["bam_dedup_stats_samtools_umitools"]
+                    },
                     "umitools/extract": {
                         "branch": "master",
                         "git_sha": "65ad3e0b9a4099592e1102e92e10455dc661cf53",
                         "installed_by": ["fastq_fastqc_umitools_fastp", "fastq_fastqc_umitools_trimgalore"]
                     },
+                    "umitools/prepareforrsem": {
+                        "branch": "master",
+                        "git_sha": "ff7e93715a2acecf3f143ec78c9858deba2984d0",
+                        "installed_by": ["modules"]
+                    },
                     "untar": {
                         "branch": "master",
                         "git_sha": "e719354ba77df0a1bd310836aa2039b45c29d620",
@@ -119,6 +159,26 @@
             },
             "subworkflows": {
                 "nf-core": {
+                    "bam_dedup_stats_samtools_umitools": {
+                        "branch": "master",
+                        "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
+                        "installed_by": ["subworkflows"]
+                    },
+                    "bam_sort_stats_samtools": {
+                        "branch": "master",
+                        "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
+                        "installed_by": ["fastq_align_star", "subworkflows"]
+                    },
+                    "bam_stats_samtools": {
+                        "branch": "master",
+                        "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
+                        "installed_by": ["bam_dedup_stats_samtools_umitools", "bam_sort_stats_samtools"]
+                    },
+                    "fastq_align_star": {
+                        "branch": "master",
+                        "git_sha": "4cef5bd781be21ecb80de664d1a8c5eba980f304",
+                        "installed_by": ["subworkflows"]
+                    },
                     "fastq_fastqc_umitools_fastp": {
                         "branch": "master",
                         "git_sha": "003920c7f9a8ae19b69a97171922880220bedf56",

diff --git a/modules/nf-core/samtools/flagstat/environment.yml b/modules/nf-core/samtools/flagstat/environment.yml
diff --git a/modules/nf-core/samtools/flagstat/main.nf b/modules/nf-core/samtools/flagstat/main.nf
diff --git a/modules/nf-core/samtools/flagstat/meta.yml b/modules/nf-core/samtools/flagstat/meta.yml
diff --git a/modules/nf-core/samtools/flagstat/tests/main.nf.test b/modules/nf-core/samtools/flagstat/tests/main.nf.test