diff --git a/.nf-test.log b/.nf-test.log new file mode 100644 index 0000000..78d9dc4 --- /dev/null +++ b/.nf-test.log @@ -0,0 +1,72 @@ +Oct-10 10:26:30.050 [main] INFO com.askimed.nf.test.App - nf-test 0.9.0 +Oct-10 10:26:30.116 [main] INFO com.askimed.nf.test.App - Arguments: [test, /nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/subworkflows/local/prep_whole_read/main.nf.test, --profile, singularity] +Oct-10 10:26:31.962 [main] INFO com.askimed.nf.test.App - Nextflow Version: 24.04.4 +Oct-10 10:26:31.965 [main] INFO com.askimed.nf.test.commands.RunTestsCommand - Load config from file /nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/nf-test.config... +Oct-10 10:26:37.832 [main] INFO com.askimed.nf.test.lang.dependencies.DependencyResolver - Loaded 81 files from directory /nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq in 5.544 sec +Oct-10 10:26:37.836 [main] INFO com.askimed.nf.test.lang.dependencies.DependencyResolver - Found 1 tests. +Oct-10 10:26:37.837 [main] DEBUG com.askimed.nf.test.lang.dependencies.DependencyResolver - Found tests: [/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/subworkflows/local/prep_whole_read/main.nf.test] +Oct-10 10:26:37.837 [main] INFO com.askimed.nf.test.commands.RunTestsCommand - Detected 1 test files. +Oct-10 10:26:37.977 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Started test plan +Oct-10 10:26:37.977 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Running testsuite 'Test Workflow PREP_WHOLE_READ' from file '/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/subworkflows/local/prep_whole_read/main.nf.test'. +Oct-10 10:26:37.978 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Run test '9de90743: genome whole read analysis'. type: com.askimed.nf.test.lang.workflow.WorkflowTest +Oct-10 11:12:39.741 [main] DEBUG com.askimed.nf.test.lang.extensions.SnapshotFile - Load snapshots from file '/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/subworkflows/local/prep_whole_read/main.nf.test.snap' +Oct-10 11:12:40.908 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Test '9de90743: genome whole read analysis' finished. status: FAILED +java.lang.OutOfMemoryError: Required array size too large + at java.base/java.nio.file.Files.readAllBytes(Files.java:3294) + at com.askimed.nf.test.util.FileUtil.getMd5(FileUtil.java:114) + at com.askimed.nf.test.lang.extensions.PathExtension.getMd5(PathExtension.java:21) + at com.askimed.nf.test.lang.extensions.util.PathConverter.serializeFile(PathConverter.java:57) + at com.askimed.nf.test.lang.extensions.util.PathConverter.convert(PathConverter.java:42) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:185) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:164) + at groovy.json.DefaultJsonGenerator.writeIterator(DefaultJsonGenerator.java:396) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:202) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:164) + at groovy.json.DefaultJsonGenerator.writeIterator(DefaultJsonGenerator.java:396) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:202) + at groovy.json.DefaultJsonGenerator.writeMapEntry(DefaultJsonGenerator.java:381) + at groovy.json.DefaultJsonGenerator.writeMap(DefaultJsonGenerator.java:369) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:200) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:164) + at groovy.json.DefaultJsonGenerator.writeIterator(DefaultJsonGenerator.java:396) + at groovy.json.DefaultJsonGenerator.writeArray(DefaultJsonGenerator.java:279) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:221) + at groovy.json.DefaultJsonGenerator.writeObject(DefaultJsonGenerator.java:164) + at groovy.json.DefaultJsonGenerator.toJson(DefaultJsonGenerator.java:98) + at com.askimed.nf.test.lang.extensions.SnapshotFileItem.toString(SnapshotFileItem.java:80) + at com.askimed.nf.test.lang.extensions.SnapshotFileItem.equals(SnapshotFileItem.java:64) + at com.askimed.nf.test.lang.extensions.Snapshot.match(Snapshot.java:57) + at com.askimed.nf.test.lang.extensions.Snapshot.match(Snapshot.java:27) + at com.askimed.nf.test.lang.extensions.Snapshot$match.call(Unknown Source) + at org.codehaus.groovy.runtime.callsite.CallSiteArray.defaultCall(CallSiteArray.java:47) + at org.codehaus.groovy.runtime.callsite.AbstractCallSite.call(AbstractCallSite.java:125) + at org.codehaus.groovy.runtime.callsite.AbstractCallSite.call(AbstractCallSite.java:130) + at main_nf$_run_closure1$_closure2$_closure4.doCall(main.nf.test:38) + at main_nf$_run_closure1$_closure2$_closure4.doCall(main.nf.test) + at java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) + at java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) + at java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) + at java.base/java.lang.reflect.Method.invoke(Method.java:568) + at org.codehaus.groovy.reflection.CachedMethod.invoke(CachedMethod.java:107) + at groovy.lang.MetaMethod.doMethodInvoke(MetaMethod.java:323) + at org.codehaus.groovy.runtime.metaclass.ClosureMetaClass.invokeMethod(ClosureMetaClass.java:274) + at groovy.lang.MetaClassImpl.invokeMethod(MetaClassImpl.java:1030) + at groovy.lang.Closure.call(Closure.java:427) + at groovy.lang.Closure.call(Closure.java:406) + at com.askimed.nf.test.lang.TestCode.execute(TestCode.java:16) + at com.askimed.nf.test.lang.workflow.WorkflowTest.execute(WorkflowTest.java:178) + at com.askimed.nf.test.core.TestExecutionEngine.execute(TestExecutionEngine.java:165) + at com.askimed.nf.test.commands.RunTestsCommand.execute(RunTestsCommand.java:299) + at com.askimed.nf.test.commands.AbstractCommand.call(AbstractCommand.java:43) + at com.askimed.nf.test.commands.AbstractCommand.call(AbstractCommand.java:18) + at picocli.CommandLine.executeUserObject(CommandLine.java:1953) + at picocli.CommandLine.access$1300(CommandLine.java:145) + at picocli.CommandLine$RunLast.executeUserObjectOfLastSubcommandWithSameParent(CommandLine.java:2352) + at picocli.CommandLine$RunLast.handle(CommandLine.java:2346) + at picocli.CommandLine$RunLast.handle(CommandLine.java:2311) + at picocli.CommandLine$AbstractParseResultHandler.execute(CommandLine.java:2179) + at picocli.CommandLine.execute(CommandLine.java:2078) + at com.askimed.nf.test.App.run(App.java:39) + at com.askimed.nf.test.App.main(App.java:46) +Oct-10 11:12:40.979 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Testsuite 'Test Workflow PREP_WHOLE_READ' finished. snapshot file: true, skipped tests: false, failed tests: true +Oct-10 11:12:40.979 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Executed 1 tests. 1 tests failed. Done! diff --git a/Documentation.md b/Documentation.md index db3ffe1..99bbe74 100644 --- a/Documentation.md +++ b/Documentation.md @@ -16,6 +16,9 @@ For a detailed review of the considerations behind each analysis step you can co This pipeline requires demultiplexed fastq sample input and an associated metadata spreadsheet. We recommend using [our demultiplex pipeline](https://github.com/goodwright/flow-nf/tree/master/subworkflows/goodwright/clip_demultiplex) to produce these individual samples fastq. +[ARTR-seq Add-On] +'pairwise_samplesheet': taking a comma-separated pairwise samplesheet for macs3 pairwise peak calling. The group and replicates must match that in the samplesheet, and duplicates of the IP sample are not allowed (however, the same control sample can be used multiple times). + ## Curated Outputs These are what we would consider to be the most commonly used outputs of the pipeline, so on the Flow platform we present these as "curated ouputs". All of the outputs are listed in the "Pipeline in Detail" section below. @@ -35,6 +38,9 @@ K-mer enrichment motif analysis performed by PEKA. PDF file with graphs showing **Quality control report** MultiQC report of important quality control metrics. Produced by MULTIQC process. +[ARTR-seq Add-On] +**MACS3 Peak Calling** +Peaks generated by MACS3. ## Commonly used parameters **Moving UMI from fastq reads to read header** @@ -62,6 +68,13 @@ When you are working with data you're already familiar with you might have speci - Minimum length of reads kept by Trim Galore! after trimming, `trim_length`, eg. `10` - Bowtie parameters for pre-mapping, `bowtie_params`, eg. `"-v 2 -m 100 --norc --best --strata"` - Paraclu minimum cut off value, `paraclu_min_value`, eg. `30` +[ARTR-seq Add-On] +- MACS3 genome-specific size, `macs_gsize`, eg. `hs` for human +- MACS3 peak calling parameters, `macs3_params`, eg. `--keep-dup all --nomodel --extsize 30 --bdg` + +**ARTR-seq Switch** + +The boolean parameter `whole_read_analysis` controls the ARTR-seq-specific pipeline running when set to true. It disables the crosslink-site processing of clip-seq and instead switches to whole-read processing and mapping. ## Pipeline in Detail @@ -147,6 +160,7 @@ This detailed description will present each subworkflow/_module_ run in t 15. CLIPSEQ_CLIPQC 16. _MULTIQC_ + ## Common Issues **Analysis of publicly available data** diff --git a/README.md b/README.md index 0b3a425..e773a59 100644 --- a/README.md +++ b/README.md @@ -17,6 +17,14 @@ profiles `test` and the container engine you wish to use eg. `docker`. For examp nextflow run main.nf -profile test,docker ``` +[ARTR-seq Test on NEMO, run as sbatch or on interactive mode] +```bash +ml Nextflow/23.04.4 +ml Singularity/3.11.3 +export NXF_SINGULARITY_CACHEDIR=/camp/lab/ulej/home/shared/singularity +nextflow run main.nf -profile crick,test_artr_seq +``` + Full dataset testing of 9 iCLIP samples can also be run using profile `test_full`. A test can also be run that skips all preparing of annotations/indexes using profile `test_no_prep_genome`. @@ -30,6 +38,12 @@ If you require all reference files (eg. genomic indexes, filtered and segmented | ------- | --------- | ---------------------------------------------------------------------- | ------- | | TDP43_1 | 1 | s3://nf-core-awsmegatests/clipseq/input_data/fastq/ERR1530360.fastq.gz | | +- `pairwise_samplesheet` : csv file containing 4 columns: group,replicate,control_group,control_replicate. group is the sample name, replicate is currently unused by the pipeline so filling with '1' is acceptable, control_group is the control sample name, with control_replicate referring to which replicate to choose for MACS3 pairwise peak calling. + +| group | replicate | control_group | control_replicate | +| ------- | --------- | ------------- | ----------------- | +| TDP43_1 | 1 | input | 1 | + - `fasta` : genome fasta file .eg './tests/data/genome/homosapien-hg37-chr21.fa.gz' - `smrna_fasta` : fasta file to be mapped to before the genome file, typically containing rRNA and tRNA sequences .eg'./tests/data/genome/homosapiens_smallRNA.fa.gz' - `gtf` : annotation file for the genome fasta .eg'./tests/data/genome/gencode.v35.chr21.gtf.gz' diff --git a/conf/crick.config b/conf/crick.config new file mode 100755 index 0000000..5313e20 --- /dev/null +++ b/conf/crick.config @@ -0,0 +1,26 @@ +//Profile config names for nf-core/configs + +params { + config_profile_description = 'The Francis Crick Institute NEMO HPC cluster profile provided by nf-core/configs.' + config_profile_contact = 'Chris Cheshire (@chris-cheshire)' + config_profile_url = 'https://www.crick.ac.uk/research/platforms-and-facilities/scientific-computing/technologies' +} + +singularity { + enabled = true + autoMounts = true + runOptions = '--bind /nemo --bind /flask' + libraryDir = '/flask/apps/containers/all-singularity-images' +} + +process { + executor = 'slurm' +} + +params { + max_memory = 2.TB + max_cpus = 256 + max_time = '168.h' + + igenomes_base = '/flask/reference/Genomics/aws-igenomes' +} \ No newline at end of file diff --git a/conf/logic.config b/conf/logic.config index 44c0311..d9c15e8 100644 --- a/conf/logic.config +++ b/conf/logic.config @@ -17,12 +17,24 @@ params { run_calc_crosslinks = true run_peak_calling = true run_reporting = true + // Additional logic + run_pairwise_input_check = false + run_whole_read_analysis = false } // Set other logic if(params.move_umi_to_header) { params.run_move_umi_to_header = true } if(params.skip_umi_dedupe) { params.run_umi_dedup = false } +// Set whole read analysis logic +if(params.whole_read_analysis) { + params.run_calc_crosslinks = false + params.run_pairwise_input_check = true + params.run_whole_read_analysis = true + params.run_peak_calling = false + params.run_reporting = false +} + // Set only logic if(params.only_input) { params.run_genome_prep = false diff --git a/conf/modules.config b/conf/modules.config index 9301b85..95e46d2 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -39,6 +39,18 @@ if(params.run_input_check) { } } +if(params.run_pairwise_input_check) { + process { + withName: 'CLIPSEQ:PARSE_PAIRWISE_INPUT:PAIRWISE_SAMPLESHEET_CHECK' { + publishDir = [ + path: { "${params.outdir}/pipeline_info" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + } +} + /* ======================================================================================== GENOME PREPARATION @@ -714,6 +726,208 @@ if(params.run_calc_crosslinks) { } } +/* +======================================================================================== + WHOLE READ ANALYSIS +======================================================================================== +*/ + +if(params.whole_read_analysis) { + process { + // WHOLE READ PREPARATION + + withName: '.*WHOLE_READ:BEDTOOLS_BAMTOBED' { + ext.args = '-split' + publishDir = [ + enabled: false + ] + } + + // Transcriptome + withName: 'CLIPSEQ:PREP_TRANSCRIPT_WHOLE_READ:SAMTOOLS_VIEW_PLUS' { + ext.prefix = { "${meta.id}_unique_transcriptome_plus" } + ext.args = "-F 16 --output-fmt bam" + publishDir = [ + path: { "${params.outdir}/04_whole_read/transcriptome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_TRANSCRIPT_WHOLE_READ:SAMTOOLS_VIEW_MINUS' { + ext.prefix = { "${meta.id}_unique_transcriptome_neg" } + ext.args = "-f 16 --output-fmt bam" + publishDir = [ + path: { "${params.outdir}/04_whole_read/transcriptome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_TRANSCRIPT_WHOLE_READ:BEDTOOLS_GENOMECOV_POS' { + ext.args = '-bg -strand +' + ext.prefix = { "${meta.id}.transcriptome" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/transcriptome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_TRANSCRIPT_WHOLE_READ:BEDTOOLS_GENOMECOV_NEG' { + ext.args = '-bg -strand -' + ext.prefix = { "${meta.id}.transcriptome" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/transcriptome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + // Genome + withName: 'CLIPSEQ:PREP_GENOME_WHOLE_READ:SAMTOOLS_VIEW_PLUS' { + ext.prefix = { "${meta.id}_unique_genome_plus" } + ext.args = "-F 16 --output-fmt bam" + publishDir = [ + path: { "${params.outdir}/04_whole_read/genome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_GENOME_WHOLE_READ:SAMTOOLS_VIEW_MINUS' { + ext.prefix = { "${meta.id}_unique_genome_neg" } + ext.args = "-f 16 --output-fmt bam" + publishDir = [ + path: { "${params.outdir}/04_whole_read/genome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_GENOME_WHOLE_READ:BEDTOOLS_GENOMECOV_POS' { + ext.args = '-bg -strand +' + ext.prefix = { "${meta.id}.genome" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/genome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_GENOME_WHOLE_READ:BEDTOOLS_GENOMECOV_NEG' { + ext.args = '-bg -strand -' + ext.prefix = { "${meta.id}.genome" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/genome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_GENOME_WHOLE_READ:BIGWIG_POS' { + ext.prefix = { "${meta.id}.genome.pos" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/genome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_GENOME_WHOLE_READ:BIGWIG_NEG' { + ext.prefix = { "${meta.id}.genome.neg" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/genome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + // SMRNA K1 + withName: 'CLIPSEQ:PREP_SMRNA_K1_WHOLE_READ:SAMTOOLS_VIEW_PLUS' { + ext.prefix = { "${meta.id}_unique_smrna_withk1_plus" } + ext.args = "-F 16 --output-fmt bam" + publishDir = [ + path: { "${params.outdir}/04_whole_read/smrna_withk1" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_SMRNA_K1_WHOLE_READ:SAMTOOLS_VIEW_MINUS' { + ext.prefix = { "${meta.id}_unique_smrna_withk1_neg" } + ext.args = "-f 16 --output-fmt bam" + publishDir = [ + path: { "${params.outdir}/04_whole_read/smrna_withk1" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_SMRNA_K1_WHOLE_READ:BEDTOOLS_GENOMECOV_POS' { + ext.args = '-bg -strand +' + ext.prefix = { "${meta.id}.smrna_withk1" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/smrna_withk1" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:PREP_SMRNA_K1_WHOLE_READ:BEDTOOLS_GENOMECOV_NEG' { + ext.args = '-bg -strand -' + ext.prefix = { "${meta.id}.smrna_withk1" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/smrna_withk1" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + // MACS3 peak calling + withName: 'CLIPSEQ:MACS3_CALLPEAK_TRANSCRIPT_PLUS' { + ext.args = { "${params.macs3_params}" } + ext.prefix = { "${meta.id}_transcriptome_plus" } + publishDir = [ + path: { "${params.outdir}/05_peak_calling/macs3" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:MACS3_CALLPEAK_TRANSCRIPT_MINUS' { + ext.args = { "${params.macs3_params}" } + ext.prefix = { "${meta.id}_transcriptome_minus" } + publishDir = [ + path: { "${params.outdir}/05_peak_calling/macs3" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:MACS3_CALLPEAK_GENOME_PLUS' { + ext.args = { "${params.macs3_params}" } + ext.prefix = { "${meta.id}_genome_plus" } + publishDir = [ + path: { "${params.outdir}/05_peak_calling/macs3" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'CLIPSEQ:MACS3_CALLPEAK_GENOME_MINUS' { + ext.args = { "${params.macs3_params}" } + ext.prefix = { "${meta.id}_genome_minus" } + publishDir = [ + path: { "${params.outdir}/05_peak_calling/macs3" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + } +} + /* ======================================================================================== PEAKCALLING diff --git a/conf/test_artr_seq.config b/conf/test_artr_seq.config new file mode 100644 index 0000000..d43e50b --- /dev/null +++ b/conf/test_artr_seq.config @@ -0,0 +1,61 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Nextflow config file for running minimal tests +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Defines input files and everything required to run a fast and simple pipeline test. + nextflow run {{ name }} -profile test, +---------------------------------------------------------------------------------------- +*/ + +process { + errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' } +} + +params { + config_profile_name = 'ARTR-seq Test profile' + config_profile_description = 'Minimal test dataset to check pipeline function' + + // Limit resources so that this can run on GitHub Actions + max_cpus = 2 + max_memory = '6.GB' + max_time = '6.h' + + // Input data + fasta = './tests/data/genome/yeast_MitoV.fa.gz' + smrna_fasta = './tests/data/genome/homosapiens_smallRNA.fa.gz' + gtf = './tests/data/genome/yeast_MitoV.gtf.gz' + samplesheet = './tests/data/samplesheets/multi-se-with-merge.csv' + + fasta_fai = './tests/data/genome/yeast_MitoV.fa.fai' + filtered_gtf = './tests/data/genome/yeast_MitoV_filtered.gtf' + chrom_sizes = './tests/data/genome/yeast_MitoV.fa.sizes' + smrna_fasta_fai = './tests/data/genome/homosapiens_smallRNA.fa.fai' + smrna_chrom_sizes = './tests/data/genome/homosapiens_smallRNA.fa.sizes' + longest_transcript = './tests/data/genome/longest_transcript.txt' + longest_transcript_fai = './tests/data/genome/longest_transcript.fai' + longest_transcript_gtf = './tests/data/genome/longest_transcript.gtf' + seg_gtf = './tests/data/genome/yeast_MitoV_seg.gtf' + seg_filt_gtf = './tests/data/genome/yeast_MitoV_filtered_seg.gtf' + seg_resolved_gtf = './tests/data/genome/yeast_MitoV_filtered_seg_genicOtherfalse.resolved.gtf' + seg_resolved_gtf_genic = './tests/data/genome/yeast_MitoV_filtered_seg_genicOthertrue.resolved.gtf' + regions_gtf = './tests/data/genome/yeast_MitoV_regions.gtf.gz' + regions_filt_gtf = './tests/data/genome/yeast_MitoV_filtered_regions.gtf.gz' + regions_resolved_gtf = './tests/data/genome/yeast_MitoV_filtered_regions_genicOtherfalse.resolved.gtf' + regions_resolved_gtf_genic = './tests/data/genome/yeast_MitoV_filtered_regions_genicOthertrue.resolved.gtf' + target_genome_index = './tests/data/genome/star.tar.gz' + smrna_genome_index = './tests/data/genome/bowtie.tar.gz' + + save_reference = true + save_indexes = true + save_merged_fastq = true + save_trimmed = true + save_align_intermed = true + save_unaligned_res = true + + // ARTR-seq specific params + whole_read_analysis = true + pairwise_samplesheet = './tests/data/samplesheets/pairwise-multi-se-with-merge.csv' + + // Processes + peka_params = "-p 0 -sr genome -sub False" +} diff --git a/main.nf b/main.nf index b457fa4..a5a5a33 100644 --- a/main.nf +++ b/main.nf @@ -116,7 +116,14 @@ include { CLIPPY as CLIPPY_TRANSCRIPT } from './modules/goodwrigh include { PEKA } from './modules/goodwright/peka/main' include { DUMP_SOFTWARE_VERSIONS } from './modules/goodwright/dump_software_versions/main' include { CLIPSEQ_CLIPQC } from './modules/goodwright/clipseq/clipqc/main' -include { ENCODE_MOVEUMI } from './modules/goodwright/clipseq/encode_moveumi/main' + + +include { ENCODE_MOVEUMI } from './modules/local/clipseq/encode_moveumi/main' + +include { MACS3_CALLPEAK as MACS3_CALLPEAK_GENOME_PLUS } from './modules/nf-core/macs3/callpeak/main' +include { MACS3_CALLPEAK as MACS3_CALLPEAK_GENOME_MINUS } from './modules/nf-core/macs3/callpeak/main' +include { MACS3_CALLPEAK as MACS3_CALLPEAK_TRANSCRIPT_PLUS } from './modules/nf-core/macs3/callpeak/main' +include { MACS3_CALLPEAK as MACS3_CALLPEAK_TRANSCRIPT_MINUS } from './modules/nf-core/macs3/callpeak/main' // // SUBWORKFLOWS @@ -138,6 +145,12 @@ include { PARACLU_ANALYSE as PARACLU_ANALYSE_GENOME } from './subwor include { PARACLU_ANALYSE as PARACLU_ANALYSE_TRANSCRIPT } from './subworkflows/goodwright/paraclu_analyse/main' include { ICOUNT_ANALYSE } from './subworkflows/goodwright/icount_analyse/main' +include { PARSE_PAIRWISE_INPUT } from './subworkflows/local/parse_pairwise_input/main' +include { PREP_WHOLE_READ as PREP_TRANSCRIPT_WHOLE_READ } from './subworkflows/local/prep_whole_read/main' +include { PREP_WHOLE_READ as PREP_GENOME_WHOLE_READ } from './subworkflows/local/prep_whole_read/main' +include { PREP_WHOLE_READ as PREP_SMRNA_K1_WHOLE_READ } from './subworkflows/local/prep_whole_read/main' + + /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ IMPORT NF-CORE MODULES/SUBWORKFLOWS @@ -277,6 +290,19 @@ workflow CLIPSEQ { ch_fastq = PARSE_FASTQ_INPUT.out.fastq } //EXAMPLE CHANNEL STRUCT: [[id:h3k27me3_R1, group:h3k27me3, replicate:1, single_end:false], [FASTQ]] + + //Additional pairwise sample sheet parsing + if(params.run_pairwise_input_check) { + ch_pairwise_samplesheet = file(params.pairwise_samplesheet, checkIfExists: true) + + PARSE_PAIRWISE_INPUT ( + ch_pairwise_samplesheet + ) + ch_versions = ch_versions.mix(PARSE_PAIRWISE_INPUT.out.versions) + ch_pairwise = PARSE_PAIRWISE_INPUT.out.pairwise + //EXAMPLE CHANNEL STRUCT: [id:WT_BRD4_plus_R1, control_id:WT_No_Ab_R1] + } + //ch_fastq | view if(params.encode_eclip){ ENCODE_MOVEUMI ( @@ -486,6 +512,82 @@ workflow CLIPSEQ { ch_trans_crosslink_coverage_norm = CALC_TRANSCRIPT_CROSSLINKS.out.coverage_norm } + if(params.run_whole_read_analysis) { + /* + * SUBWORKFLOW: Run whole read analysis + */ + PREP_TRANSCRIPT_WHOLE_READ( + ch_transcript_bam, + ch_transcript_bai, + ch_longest_transcript_fai.collect{ it[1] }, + false + ) + ch_versions = ch_versions.mix(PREP_TRANSCRIPT_WHOLE_READ.out.versions) + ch_trans_whole_read_bam_plus = PREP_TRANSCRIPT_WHOLE_READ.out.bam_plus + ch_trans_whole_read_bam_minus = PREP_TRANSCRIPT_WHOLE_READ.out.bam_minus + + ch_trans_whole_read_bed = PREP_TRANSCRIPT_WHOLE_READ.out.bed + + PREP_GENOME_WHOLE_READ ( + ch_genome_bam, + ch_genome_bai, + ch_fasta_fai.collect{ it[1] }, + true + ) + ch_versions = ch_versions.mix(PREP_GENOME_WHOLE_READ.out.versions) + ch_genome_whole_read_bam_plus = PREP_GENOME_WHOLE_READ.out.bam_plus + ch_genome_whole_read_bam_minus = PREP_GENOME_WHOLE_READ.out.bam_minus + + ch_genome_whole_read_bed = PREP_GENOME_WHOLE_READ.out.bed + + PREP_SMRNA_K1_WHOLE_READ ( + ch_smrna_k1_bam, + ch_smrna_k1_bai, + ch_smrna_fasta_fai.collect{ it[1] }, + false + ) + ch_versions = ch_versions.mix(PREP_SMRNA_K1_WHOLE_READ.out.versions) + ch_smrna_whole_read_bam_plus = PREP_SMRNA_K1_WHOLE_READ.out.bam_plus + ch_smrna_whole_read_bam_minus = PREP_SMRNA_K1_WHOLE_READ.out.bam_minus + + ch_smrna_whole_read_bed = PREP_SMRNA_K1_WHOLE_READ.out.bed + + // Sort out split bam channels for MACS3 peak calling using rearrangeChannels(), which is defined below + ch_trans_whole_read_bam_plus_pairwise = rearrangeChannels(ch_pairwise, ch_trans_whole_read_bam_plus) + ch_trans_whole_read_bam_minus_pairwise = rearrangeChannels(ch_pairwise, ch_trans_whole_read_bam_minus) + ch_genome_whole_read_bam_plus_pairwise = rearrangeChannels(ch_pairwise, ch_genome_whole_read_bam_plus) + ch_genome_whole_read_bam_minus_pairwise = rearrangeChannels(ch_pairwise, ch_genome_whole_read_bam_minus) + + // MACS3 Peak Calling + ch_macs_gsize = params.macs_gsize + + MACS3_CALLPEAK_TRANSCRIPT_PLUS ( + ch_trans_whole_read_bam_plus_pairwise, + ch_macs_gsize + ) + ch_versions = ch_versions.mix(MACS3_CALLPEAK_TRANSCRIPT_PLUS.out.versions) + + MACS3_CALLPEAK_TRANSCRIPT_MINUS ( + ch_trans_whole_read_bam_minus_pairwise, + ch_macs_gsize + ) + + MACS3_CALLPEAK_GENOME_PLUS ( + ch_genome_whole_read_bam_plus_pairwise, + ch_macs_gsize + ) + + MACS3_CALLPEAK_GENOME_MINUS ( + ch_genome_whole_read_bam_minus_pairwise, + ch_macs_gsize + ) + + // Fork bed channels for downstream peak calling + ch_genome_crosslink_bed = ch_genome_whole_read_bed + ch_trans_crosslink_bed = ch_trans_whole_read_bed + ch_smrna_crosslink_bed = ch_smrna_whole_read_bed + } + if(params.run_peak_calling) { /* * MODULE: Run clippy on genome-level crosslinks @@ -588,6 +690,36 @@ workflow CLIPSEQ { } } +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + FUNCTIONS +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +*/ + +// Function to rearrange channels to match pairwise samples +def rearrangeChannels(ch_pairwise, ch_read_bam) { + // ch_pairwise: [val(id), val(control_id)] + // ch_read_bam: [val(meta), path(bam)] + + // rearrange ch_read_bam to get sample id for .combine() + def ch_read_bam_ext1 = ch_read_bam.map {meta, bam -> [meta.id, meta, bam]}.unique() + def ch_read_bam_ext2 = ch_read_bam.map {meta, bam -> [meta.id, meta, bam]}.unique() + + // using .combine() instead of .join() to allow for duplicates in ch_pairwise + return ch_pairwise + .combine(ch_read_bam_ext1, by: 0) + .map {id, control_id, meta, bam -> [control_id, meta, bam]} + .combine(ch_read_bam_ext2, by: 0) + .map { control_id, meta, bam, control_meta, control_bam -> + if (bam != null & control_bam != null) { + [meta, bam, control_bam] + } else { + exit 1, "BAM files do not exist!\n${bam}\n${control_bam}" + } + } + // final channel structure: [val(meta), path(bam), path(control_bam)] + } + /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ RUN MAIN WORKFLOW diff --git a/modules.json b/modules.json index 3519b29..ffe8e81 100644 --- a/modules.json +++ b/modules.json @@ -151,6 +151,11 @@ "git_sha": "e06548bfa36ee31869b81041879dd6b3a83b1d57", "installed_by": ["modules"] }, + "macs3/callpeak": { + "branch": "master", + "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", + "installed_by": ["modules"] + }, "samtools/flagstat": { "branch": "master", "git_sha": "570ec5bcfe19c49e16c9ca35a7a116563af6cc1c", @@ -196,6 +201,11 @@ "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, + "ucsc/bedgraphtobigwig": { + "branch": "master", + "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358", + "installed_by": ["modules"] + }, "umicollapse": { "branch": "master", "git_sha": "b97197968ac12dde2463fa54541f6350c46f2035", diff --git a/modules/local/clipseq/encode_moveumi/main.nf b/modules/local/clipseq/encode_moveumi/main.nf new file mode 100644 index 0000000..2e2069d --- /dev/null +++ b/modules/local/clipseq/encode_moveumi/main.nf @@ -0,0 +1,22 @@ +process ENCODE_MOVEUMI { + label "process_single" + + conda "bioconda::biopython=1.78 pigz=2.6" + container "quay.io/biocontainers/mulled-v2-877c4e5a8fad685ea5bde487e04924ac447923b9:b7daa641364165419b9a87d9988bc803f913c5b6-0" + + input: + tuple val(meta), path(reads) + + output: + tuple val(meta), path("*.fastq.gz"), emit: reads + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + shell: + def args = task.ext.args ?: '' + prefix = task.ext.prefix ?: "${meta.id}" + process_name = task.process + template 'encode_moveumi.py' +} diff --git a/modules/local/clipseq/encode_moveumi/meta.yml b/modules/local/clipseq/encode_moveumi/meta.yml new file mode 100644 index 0000000..8429c6e --- /dev/null +++ b/modules/local/clipseq/encode_moveumi/meta.yml @@ -0,0 +1,40 @@ +name: clipseq_clipqc +description: Runs python-based clip quality control and outputs to a set of tsv files +keywords: + - iCLIP + - eCLIP + - CLIP + - qc +input: + - premap: + type: file + description: Premap metrics files + - mapped: + type: file + description: Alignment metrics files + - collapse: + type: file + description: UMI collapse metrics files + - xlinks: + type: file + description: xlinks metric files + - icount: + type: file + description: iCount metrics files + - paraclu: + type: file + description: paraclu metrics files + - clippy: + type: file + description: Clippy metrics files +output: + - tsv: + type: file + description: All tsv file outputs + pattern: "*.tsv" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@chris-cheshire" diff --git a/modules/local/clipseq/encode_moveumi/templates/encode_moveumi.py b/modules/local/clipseq/encode_moveumi/templates/encode_moveumi.py new file mode 100644 index 0000000..4b4ff31 --- /dev/null +++ b/modules/local/clipseq/encode_moveumi/templates/encode_moveumi.py @@ -0,0 +1,29 @@ +#!/usr/bin/env python + +import os +import sys +import gzip +import platform +from Bio import SeqIO +import Bio + +input_fq = "!{reads}" +output_fq = "!{prefix}.umi.fastq" + +with gzip.open(input_fq, mode = 'rt') as f_in: + with open(output_fq, mode = 'w') as f_out: + for record in SeqIO.parse(f_in, 'fastq'): + header = record.id.split(":") + if '_' not in header[-1]: + rearranged = ":".join(header[1:]) + '_rbc:' + header[0] + record.id = rearranged + record.name = rearranged + record.description = rearranged + SeqIO.write(record, f_out, 'fastq') + +os.system('pigz ' + output_fq) + +with open("versions.yml", "w") as out_f: + out_f.write("!{process_name}" + ":\n") + out_f.write(" python: " + platform.python_version() + "\n") + out_f.write(" biopython: " + Bio.__version__ + "\n") \ No newline at end of file diff --git a/modules/local/whole_read_analysis/pairwise_samplesheet_check/main.nf b/modules/local/whole_read_analysis/pairwise_samplesheet_check/main.nf new file mode 100644 index 0000000..b24e1b1 --- /dev/null +++ b/modules/local/whole_read_analysis/pairwise_samplesheet_check/main.nf @@ -0,0 +1,22 @@ +process PAIRWISE_SAMPLESHEET_CHECK { + tag "$samplesheet" + label 'process_single' + + conda "conda-forge::python=3.10.4" + container "docker.io/python:3.10.4" + + input: + path samplesheet + + output: + path '*.valid.csv' , emit: csv + path "versions.yml", emit: versions + + when: + task.ext.when == null || task.ext.when + + shell: + process_name = task.process + output = task.ext.output ?: 'pairwise_samplesheet.valid.csv' + template 'pairwise_samplesheet_check.py' +} diff --git a/modules/local/whole_read_analysis/pairwise_samplesheet_check/meta.yml b/modules/local/whole_read_analysis/pairwise_samplesheet_check/meta.yml new file mode 100644 index 0000000..14ddd54 --- /dev/null +++ b/modules/local/whole_read_analysis/pairwise_samplesheet_check/meta.yml @@ -0,0 +1,20 @@ +name: pairwise_samplesheet_check +description: Checks a pairwise samplesheet recording IP and input samples for MACS3 peak calling +keywords: + - samplesheet +input: + - samplesheet: + type: file + description: Input samplesheet to check + pattern: "*.{csv}" +output: + - csv: + type: file + description: Validated samplesheet file + pattern: "*.csv" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@hanzhong-bai" diff --git a/modules/local/whole_read_analysis/pairwise_samplesheet_check/templates/pairwise_samplesheet_check.py b/modules/local/whole_read_analysis/pairwise_samplesheet_check/templates/pairwise_samplesheet_check.py new file mode 100644 index 0000000..531cb48 --- /dev/null +++ b/modules/local/whole_read_analysis/pairwise_samplesheet_check/templates/pairwise_samplesheet_check.py @@ -0,0 +1,170 @@ +#!/usr/bin/env python + +import os +import sys +import errno +import argparse +import platform + +def make_dir(path): + if len(path) > 0: + try: + os.makedirs(path) + except OSError as exception: + if exception.errno != errno.EEXIST: + raise exception + + +def print_error(error, context="Line", context_str=""): + error_str = "ERROR: Please check samplesheet -> {}".format(error) + if context != "" and context_str != "": + error_str = "ERROR: Please check samplesheet -> {}\n{}: '{}'".format( + error, context.strip(), context_str.strip() + ) + print(error_str) + sys.exit(1) + + +def dump_versions(process_name): + with open("versions.yml", "w") as out_f: + out_f.write(process_name + ":\n") + out_f.write(" python: " + platform.python_version() + "\n") + + +def check_samplesheet(process_name, samplesheet, output): + """ + This function checks that the samplesheet follows the following structure: + + group,replicate,control_group,control_replicate + WT_BRD4_plus,1,WT_No_Ab,1 + WT_BRD4_plus,2,WT_No_Ab,2 + WT_FUS_plus,1,WT_No_Ab,1 + WT_FUS_plus,2,WT_No_Ab,2 + """ + + # Dump version file + dump_versions(process_name) + + rows = [] + ip_rows = [] + samples = [] + + with open(samplesheet, "r") as fin: + ## Check header + MIN_COLS = 4 + HEADER = ["group", "replicate", "control_group", "control_replicate"] + # HEADER_LEN = len(HEADER) + header = [x.strip('"') for x in fin.readline().strip().split(",")] + ACTUAL_HEADER_LEN = len(header) + + if header[: len(HEADER)] != HEADER: + print("ERROR: Please check samplesheet header -> {} != {}".format(",".join(header), ",".join(HEADER))) + sys.exit(1) + + ## Check sample entries + line_no = 1 + for line in fin: + lspl = [x.strip().strip('"') for x in line.strip().split(",")] + + ## Check if its just a blank line so we dont error + if line.strip() == "": + continue + + ## Check valid number of columns per row + if len(lspl) != ACTUAL_HEADER_LEN: + print_error( + "Invalid number of columns (found {} should be {})! - line no. {}".format( + len(lspl), len(HEADER), line_no + ), + "Line", + line, + ) + + ## Check valid number of populated columns per row + num_cols = len([x for x in lspl if x]) + if num_cols < MIN_COLS: + print_error( + "Invalid number of populated columns (minimum = {})!".format(MIN_COLS), + "Line", + line, + ) + + ## Check sample name entries + group, replicate, control_group, control_replicate = lspl[: len(HEADER)] + if group: + if group.find(" ") != -1: + print_error("Group entry contains spaces!", "Line", line) + else: + print_error("Group entry has not been specified!", "Line", line) + + if group: + if group.find(".") != -1: + print_error("Group entry contains dots!", "Line", line) + + if control_group: + if control_group.find(" ") != -1: + print_error("Control Group entry contains spaces!", "Line", line) + else: + print_error("Control Group entry has not been specified!", "Line", line) + + if control_group: + if control_group.find(".") != -1: + print_error("Control Group entry contains dots!", "Line", line) + + ## Check replicate entry is integer + if not replicate.isdigit(): + print_error("Replicate id not an integer", "Line", line) + replicate = int(replicate) + if replicate <= 0: + print_error("Replicate must be > 0", "Line", line) + + ## Check control_replicate entry is integer + if not control_replicate.isdigit(): + print_error("Control Replicate id not an integer", "Line", line) + control_replicate = int(control_replicate) + if control_replicate <= 0: + print_error("Control Replicate must be > 0", "Line", line) + + ## Check for duplicate entries + sample_info = (group, replicate, control_group, control_replicate) + if sample_info in rows: + print_error("Samplesheet contains duplicate rows!", "Line", line) + else: + rows.append(sample_info) + + ## Check that sample _info is not duplicated + ip_info = (group, replicate) + if ip_info in ip_rows: + print_error("Samplesheet contains duplicate IP rows!", "Line", line) + else: + ip_rows.append(ip_info) + + ## Create sample id and control_sample id + ## This id matches with the final id in meta (without _Txxx) + sample_id = "{}_R{}".format(group, replicate) + control_sample_id = "{}_R{}".format(control_group, control_replicate) + + # Save the sample id and control sample id in front of the row + lspl = [sample_id, control_sample_id] + lspl + samples.append(lspl) + + line_no += 1 + + # Write out the samplesheet in csv with header + make_dir(os.path.dirname(output)) + with open(output, "w") as fout: + output_header = ["id", "control_id"] + HEADER + fout.write(",".join(output_header) + "\n") + for sample in samples: + fout.write(",".join(sample) + "\n") + + +if __name__ == "__main__": + # Allows switching between nextflow templating and standalone python running using arguments + parser = argparse.ArgumentParser() + parser.add_argument("--process_name", default="!{process_name}") + parser.add_argument("--samplesheet", default="!{samplesheet}") + parser.add_argument("--output", default="!{output}") + args = parser.parse_args() + + check_samplesheet(args.process_name, args.samplesheet, args.output) \ No newline at end of file diff --git a/modules/local/whole_read_analysis/parse_pairwise_input/main.nf b/modules/local/whole_read_analysis/parse_pairwise_input/main.nf new file mode 100644 index 0000000..5a34f63 --- /dev/null +++ b/modules/local/whole_read_analysis/parse_pairwise_input/main.nf @@ -0,0 +1,22 @@ +process PARSE_PAIRWISE_INPUT { + tag "$samplesheet" + label 'process_single' + + conda "conda-forge::python=3.10.4" + container "docker.io/python:3.10.4" + + input: + path samplesheet + + output: + path '*.valid.csv' , emit: csv + path "versions.yml", emit: versions + + when: + task.ext.when == null || task.ext.when + + shell: + process_name = task.process + output = task.ext.output ?: 'pairwise_samplesheet.valid.csv' + template 'pairwise_samplesheet_check.py' +} diff --git a/modules/local/whole_read_analysis/parse_pairwise_input/meta.yml b/modules/local/whole_read_analysis/parse_pairwise_input/meta.yml new file mode 100644 index 0000000..ff53e7a --- /dev/null +++ b/modules/local/whole_read_analysis/parse_pairwise_input/meta.yml @@ -0,0 +1,20 @@ +name: sample_base_samplesheet_check +description: Checks a standard fastq-based samplesheet +keywords: + - samplesheet +input: + - samplesheet: + type: file + description: Input samplesheet to check + pattern: "*.{csv}" +output: + - csv: + type: file + description: Validated samplesheet file + pattern: "*.csv" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@chris-cheshire" diff --git a/modules/local/whole_read_analysis/parse_pairwise_input/templates/pairwise_samplesheet_check.py b/modules/local/whole_read_analysis/parse_pairwise_input/templates/pairwise_samplesheet_check.py new file mode 100644 index 0000000..8829862 --- /dev/null +++ b/modules/local/whole_read_analysis/parse_pairwise_input/templates/pairwise_samplesheet_check.py @@ -0,0 +1,166 @@ +#!/usr/bin/env python + +import os +import sys +import errno +import argparse +import platform + +def make_dir(path): + if len(path) > 0: + try: + os.makedirs(path) + except OSError as exception: + if exception.errno != errno.EEXIST: + raise exception + + +def print_error(error, context="Line", context_str=""): + error_str = "ERROR: Please check samplesheet -> {}".format(error) + if context != "" and context_str != "": + error_str = "ERROR: Please check samplesheet -> {}\n{}: '{}'".format( + error, context.strip(), context_str.strip() + ) + print(error_str) + sys.exit(1) + + +def dump_versions(process_name): + with open("versions.yml", "w") as out_f: + out_f.write(process_name + ":\n") + out_f.write(" python: " + platform.python_version() + "\n") + + +def check_samplesheet(process_name, samplesheet, output): + """ + This function checks that the samplesheet follows the following structure: + + group,replicate,control_group,control_replicate + WT_BRD4_plus,1,WT_No_Ab,1 + WT_BRD4_plus,2,WT_No_Ab,2 + WT_FUS_plus,1,WT_No_Ab,1 + WT_FUS_plus,2,WT_No_Ab,2 + """ + + # Dump version file + dump_versions(process_name) + + rows = [] + samples = [] + + with open(samplesheet, "r") as fin: + ## Check header + MIN_COLS = 4 + HEADER = ["group", "replicate", "control_group", "control_replicate"] + # HEADER_LEN = len(HEADER) + header = [x.strip('"') for x in fin.readline().strip().split(",")] + ACTUAL_HEADER_LEN = len(header) + + if header[: len(HEADER)] != HEADER: + print("ERROR: Please check samplesheet header -> {} != {}".format(",".join(header), ",".join(HEADER))) + sys.exit(1) + + ## Check sample entries + line_no = 1 + for line in fin: + lspl = [x.strip().strip('"') for x in line.strip().split(",")] + + ## Check if its just a blank line so we dont error + if line.strip() == "": + continue + + ## Check valid number of columns per row + if len(lspl) != ACTUAL_HEADER_LEN: + print_error( + "Invalid number of columns (found {} should be {})! - line no. {}".format( + len(lspl), len(HEADER), line_no + ), + "Line", + line, + ) + + ## Check valid number of populated columns per row + num_cols = len([x for x in lspl if x]) + if num_cols < MIN_COLS: + print_error( + "Invalid number of populated columns (minimum = {})!".format(MIN_COLS), + "Line", + line, + ) + + ## Check sample name entries + group, replicate, control_group, control_replicate = lspl[: len(HEADER)] + if group: + if group.find(" ") != -1: + print_error("Group entry contains spaces!", "Line", line) + else: + print_error("Group entry has not been specified!", "Line", line) + + if group: + if group.find(".") != -1: + print_error("Group entry contains dots!", "Line", line) + + if control_group: + if control_group.find(" ") != -1: + print_error("Control Group entry contains spaces!", "Line", line) + else: + print_error("Control Group entry has not been specified!", "Line", line) + + if control_group: + if control_group.find(".") != -1: + print_error("Control Group entry contains dots!", "Line", line) + + ## Check replicate entry is integer + if not replicate.isdigit(): + print_error("Replicate id not an integer", "Line", line) + replicate = int(replicate) + if replicate <= 0: + print_error("Replicate must be > 0", "Line", line) + + ## Check control_replicate entry is integer + if not control_replicate.isdigit(): + print_error("Control Replicate id not an integer", "Line", line) + control_replicate = int(control_replicate) + if control_replicate <= 0: + print_error("Control Replicate must be > 0", "Line", line) + + ## Check replicate and control_replicate are not the same + if replicate == control_replicate: + print_error("Replicate and Control Replicate must be different", "Line", line) + + ## Check for duplicate entries + sample_info = (group, replicate, control_group, control_replicate) + if sample_info in rows: + print_error("Samplesheet contains duplicate rows!", "Line", line) + else: + rows.append(sample_info) + + ## Create sample id and control_sample id + ## This id matches with the final id in meta (without _Txxx) + sample_id = "{}_R{}".format(group, replicate) + control_sample_id = "{}_R{}".format(control_group, control_replicate) + + # Save the sample id and control sample id in front of the row + lspl = [sample_id, control_sample_id] + lspl + samples.append(lspl) + + line_no += 1 + + # Write out the samplesheet in csv with header + make_dir(os.path.dirname(output)) + with open(output, "w") as fout: + output_header = ["id", "control_id"] + HEADER + fout.write(",".join(output_header) + "\n") + for sample in samples: + fout.write(",".join(sample) + "\n") + + +if __name__ == "__main__": + # Allows switching between nextflow templating and standalone python running using arguments + parser = argparse.ArgumentParser() + parser.add_argument("--process_name", default="!{process_name}") + parser.add_argument("--samplesheet", default="!{samplesheet}") + parser.add_argument("--output", default="!{output}") + args = parser.parse_args() + + check_samplesheet(args.process_name, args.samplesheet, args.output) \ No newline at end of file diff --git a/modules/nf-core/macs3/callpeak/environment.yml b/modules/nf-core/macs3/callpeak/environment.yml new file mode 100644 index 0000000..4aa6a32 --- /dev/null +++ b/modules/nf-core/macs3/callpeak/environment.yml @@ -0,0 +1,7 @@ +--- +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json +channels: + - conda-forge + - bioconda +dependencies: + - "bioconda::macs3=3.0.1" diff --git a/modules/nf-core/macs3/callpeak/main.nf b/modules/nf-core/macs3/callpeak/main.nf new file mode 100644 index 0000000..53a1a20 --- /dev/null +++ b/modules/nf-core/macs3/callpeak/main.nf @@ -0,0 +1,70 @@ + +process MACS3_CALLPEAK { + tag "$meta.id" + label 'process_medium' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/macs3:3.0.1--py311h0152c62_3': + 'biocontainers/macs3:3.0.1--py311h0152c62_3' }" + + input: + tuple val(meta), path(ipbam), path(controlbam) + val macs3_gsize + + output: + tuple val(meta), path("*.{narrowPeak,broadPeak}"), emit: peak + tuple val(meta), path("*.xls") , emit: xls + path "versions.yml" , emit: versions + + tuple val(meta), path("*.gappedPeak"), optional:true, emit: gapped + tuple val(meta), path("*.bed") , optional:true, emit: bed + tuple val(meta), path("*.bdg") , optional:true, emit: bdg + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + def args_list = args.tokenize() + def format = meta.single_end ? 'BAM' : 'BAMPE' + def control = controlbam ? "--control $controlbam" : '' + if(args_list.contains('--format')){ + def id = args_list.findIndexOf{it=='--format'} + format = args_list[id+1] + args_list.remove(id+1) + args_list.remove(id) + } + """ + macs3 \\ + callpeak \\ + ${args_list.join(' ')} \\ + --gsize $macs3_gsize \\ + --format $format \\ + --name $prefix \\ + --treatment $ipbam \\ + $control + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + macs3: \$(macs3 --version | sed -e "s/macs3 //g") + END_VERSIONS + """ + + stub: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + """ + touch ${prefix}.gappedPeak + touch ${prefix}.bed + touch ${prefix}.bdg + touch ${prefix}.narrowPeak + touch ${prefix}.xls + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + macs3: \$(macs3 --version | sed -e "s/macs3 //g") + END_VERSIONS + """ +} diff --git a/modules/nf-core/macs3/callpeak/meta.yml b/modules/nf-core/macs3/callpeak/meta.yml new file mode 100644 index 0000000..5d97a03 --- /dev/null +++ b/modules/nf-core/macs3/callpeak/meta.yml @@ -0,0 +1,97 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json +name: "macs3_callpeak" +description: Peak calling of enriched genomic regions of ChIP-seq and ATAC-seq experiments +keywords: + - alignment + - atac-seq + - chip-seq + - peak-calling +tools: + - macs3: + description: "Model Based Analysis for ChIP-Seq data" + homepage: "https://macs3-project.github.io/MACS/" + documentation: "https://macs3-project.github.io/MACS/" + tool_dev_url: "https://github.com/macs3-project/MACS/" + doi: "10.1101/496521" + licence: ["BSD-3-clause"] + identifier: "" + +input: + - - meta: + type: map + description: | + Groovy Map containing sample information + e.g. `[ id:'sample_1', single_end:false ]` + - ipbam: + type: file + description: The ChIP-seq treatment file + - controlbam: + type: file + description: The control file + - - macs3_gsize: + type: string + description: | + Effective genome size. It can be 1.0e+9 or 1000000000, + or shortcuts:'hs' for human (2,913,022,398), 'mm' for mouse + (2,652,783,500), 'ce' for C. elegans (100,286,401) + and 'dm' for fruitfly (142,573,017), Default:hs. +output: + - peak: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. `[ id:'sample1', single_end:false ]` + - "*.{narrowPeak,broadPeak}": + type: file + description: BED file containing annotated peaks + pattern: "*.gappedPeak,*.narrowPeak}" + - xls: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. `[ id:'sample1', single_end:false ]` + - "*.xls": + type: file + description: xls file containing annotated peaks + pattern: "*.xls" + - versions: + - versions.yml: + type: file + description: File containing software version + pattern: "versions.yml" + - gapped: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. `[ id:'sample1', single_end:false ]` + - "*.gappedPeak": + type: file + description: Optional BED file containing gapped peak + pattern: "*.gappedPeak" + - bed: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. `[ id:'sample1', single_end:false ]` + - "*.bed": + type: file + description: Optional BED file containing peak summits locations for every peak + pattern: "*.bed" + - bdg: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. `[ id:'sample1', single_end:false ]` + - "*.bdg": + type: file + description: Optional bedGraph files for input and treatment input samples + pattern: "*.bdg" +authors: + - "@JoseEspinosa" +maintainers: + - "@JoseEspinosa" diff --git a/modules/nf-core/macs3/callpeak/tests/bam.config b/modules/nf-core/macs3/callpeak/tests/bam.config new file mode 100644 index 0000000..217e310 --- /dev/null +++ b/modules/nf-core/macs3/callpeak/tests/bam.config @@ -0,0 +1,5 @@ +process { + withName: 'MACS3_CALLPEAK' { + ext.args = '--qval 0.1' + } +} \ No newline at end of file diff --git a/modules/nf-core/macs3/callpeak/tests/bed.config b/modules/nf-core/macs3/callpeak/tests/bed.config new file mode 100644 index 0000000..1944400 --- /dev/null +++ b/modules/nf-core/macs3/callpeak/tests/bed.config @@ -0,0 +1,5 @@ +process { + withName: 'MACS3_CALLPEAK' { + ext.args = '--format BED --qval 10 --nomodel --extsize 200' + } +} \ No newline at end of file diff --git a/modules/nf-core/macs3/callpeak/tests/main.nf.test b/modules/nf-core/macs3/callpeak/tests/main.nf.test new file mode 100644 index 0000000..4338c96 --- /dev/null +++ b/modules/nf-core/macs3/callpeak/tests/main.nf.test @@ -0,0 +1,113 @@ +nextflow_process { + + name "Test Process MACS3_CALLPEAK" + script "../main.nf" + process "MACS3_CALLPEAK" + + tag "modules" + tag "modules_nfcore" + tag "macs3" + tag "macs3/callpeak" + + test("homo_sapiens - callpeak - bed") { + + when { + config "./bed.config" + process { + """ + input[0] = [ + [ id:'test', single_end:false ], // meta map + [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/pacbio/bed/alz.ccs.fl.NEB_5p--NEB_Clontech_3p.flnc.clustered.singletons.merged.aligned_tc.bed', checkIfExists: true) ], + [] + ] + input[1] = 4000 + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + + } + + test("homo_sapiens - callpeak - bam") { + + when { + config "./bam.config" + process { + """ + input[0] = [ + [ id:'test', single_end:false ], // meta map + [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.name.sorted.bam', checkIfExists: true) ], + [] + ] + input[1] = 40000 + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + + } + + test("homo_sapiens - callpeak - control - bam") { + + when { + config "./bam.config" + process { + """ + input[0] = [ + [ id:'test', single_end:false ], // meta map + [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.name.sorted.bam', checkIfExists: true) ], + [ file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test2.paired_end.name.sorted.bam', checkIfExists: true) ] + ] + input[1] = 40000 + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + + } + + test("sarscov2 - bam - stub") { + + options "-stub" + + when { + process { + """ + input[0] = [ + [ id:'test', single_end:false ], // meta map + [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true) ], + [] + ] + input[1] = 40000 + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + + } + +} diff --git a/modules/nf-core/macs3/callpeak/tests/main.nf.test.snap b/modules/nf-core/macs3/callpeak/tests/main.nf.test.snap new file mode 100644 index 0000000..d6d9829 --- /dev/null +++ b/modules/nf-core/macs3/callpeak/tests/main.nf.test.snap @@ -0,0 +1,358 @@ +{ + "homo_sapiens - callpeak - bam": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.narrowPeak:md5,2e4da1c1704595e12aaf99cc715ad70c" + ] + ], + "1": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.xls:md5,221852e4639574d2f53cf1917efa4922" + ] + ], + "2": [ + "versions.yml:md5,cb33970f9aaa0730733abe2fd9cb2b74" + ], + "3": [ + + ], + "4": [ + [ + { + "id": "test", + "single_end": false + }, + "test_summits.bed:md5,26f0f97b6c14dbca129e947a58067c82" + ] + ], + "5": [ + + ], + "bdg": [ + + ], + "bed": [ + [ + { + "id": "test", + "single_end": false + }, + "test_summits.bed:md5,26f0f97b6c14dbca129e947a58067c82" + ] + ], + "gapped": [ + + ], + "peak": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.narrowPeak:md5,2e4da1c1704595e12aaf99cc715ad70c" + ] + ], + "versions": [ + "versions.yml:md5,cb33970f9aaa0730733abe2fd9cb2b74" + ], + "xls": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.xls:md5,221852e4639574d2f53cf1917efa4922" + ] + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "24.04.2" + }, + "timestamp": "2024-07-22T17:04:31.629715" + }, + "sarscov2 - bam - stub": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": false + }, + "test.narrowPeak:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "1": [ + [ + { + "id": "test", + "single_end": false + }, + "test.xls:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "2": [ + "versions.yml:md5,cb33970f9aaa0730733abe2fd9cb2b74" + ], + "3": [ + [ + { + "id": "test", + "single_end": false + }, + "test.gappedPeak:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "4": [ + [ + { + "id": "test", + "single_end": false + }, + "test.bed:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "5": [ + [ + { + "id": "test", + "single_end": false + }, + "test.bdg:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "bdg": [ + [ + { + "id": "test", + "single_end": false + }, + "test.bdg:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "bed": [ + [ + { + "id": "test", + "single_end": false + }, + "test.bed:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "gapped": [ + [ + { + "id": "test", + "single_end": false + }, + "test.gappedPeak:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "peak": [ + [ + { + "id": "test", + "single_end": false + }, + "test.narrowPeak:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "versions": [ + "versions.yml:md5,cb33970f9aaa0730733abe2fd9cb2b74" + ], + "xls": [ + [ + { + "id": "test", + "single_end": false + }, + "test.xls:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "24.04.2" + }, + "timestamp": "2024-07-22T17:04:58.589844" + }, + "homo_sapiens - callpeak - control - bam": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.narrowPeak:md5,653e1108cc57ca07d0f60fc0f4fb8ba3" + ] + ], + "1": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.xls:md5,9fce04613bdc9c8372a9f884aa0d5aa6" + ] + ], + "2": [ + "versions.yml:md5,cb33970f9aaa0730733abe2fd9cb2b74" + ], + "3": [ + + ], + "4": [ + [ + { + "id": "test", + "single_end": false + }, + "test_summits.bed:md5,4f3c7c53a1d730d90d1b3dd9d3197af4" + ] + ], + "5": [ + + ], + "bdg": [ + + ], + "bed": [ + [ + { + "id": "test", + "single_end": false + }, + "test_summits.bed:md5,4f3c7c53a1d730d90d1b3dd9d3197af4" + ] + ], + "gapped": [ + + ], + "peak": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.narrowPeak:md5,653e1108cc57ca07d0f60fc0f4fb8ba3" + ] + ], + "versions": [ + "versions.yml:md5,cb33970f9aaa0730733abe2fd9cb2b74" + ], + "xls": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.xls:md5,9fce04613bdc9c8372a9f884aa0d5aa6" + ] + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "24.04.2" + }, + "timestamp": "2024-07-22T17:04:44.063426" + }, + "homo_sapiens - callpeak - bed": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.narrowPeak:md5,10e7d4747f8a2513e5ebb04856a51673" + ] + ], + "1": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.xls:md5,14efbf7137623df5aaf282b506ac9601" + ] + ], + "2": [ + "versions.yml:md5,cb33970f9aaa0730733abe2fd9cb2b74" + ], + "3": [ + + ], + "4": [ + [ + { + "id": "test", + "single_end": false + }, + "test_summits.bed:md5,28833eeb7816688f0d698f51670be946" + ] + ], + "5": [ + + ], + "bdg": [ + + ], + "bed": [ + [ + { + "id": "test", + "single_end": false + }, + "test_summits.bed:md5,28833eeb7816688f0d698f51670be946" + ] + ], + "gapped": [ + + ], + "peak": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.narrowPeak:md5,10e7d4747f8a2513e5ebb04856a51673" + ] + ], + "versions": [ + "versions.yml:md5,cb33970f9aaa0730733abe2fd9cb2b74" + ], + "xls": [ + [ + { + "id": "test", + "single_end": false + }, + "test_peaks.xls:md5,14efbf7137623df5aaf282b506ac9601" + ] + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "24.04.2" + }, + "timestamp": "2024-07-22T17:04:16.697163" + } +} \ No newline at end of file diff --git a/modules/nf-core/ucsc/bedgraphtobigwig/environment.yml b/modules/nf-core/ucsc/bedgraphtobigwig/environment.yml new file mode 100644 index 0000000..27868a4 --- /dev/null +++ b/modules/nf-core/ucsc/bedgraphtobigwig/environment.yml @@ -0,0 +1,5 @@ +channels: + - conda-forge + - bioconda +dependencies: + - bioconda::ucsc-bedgraphtobigwig=469 diff --git a/modules/nf-core/ucsc/bedgraphtobigwig/main.nf b/modules/nf-core/ucsc/bedgraphtobigwig/main.nf new file mode 100644 index 0000000..81cdee9 --- /dev/null +++ b/modules/nf-core/ucsc/bedgraphtobigwig/main.nf @@ -0,0 +1,49 @@ +process UCSC_BEDGRAPHTOBIGWIG { + tag "$meta.id" + label 'process_single' + + // WARN: Version information not provided by tool on CLI. Please update version string below when bumping container versions. + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/ucsc-bedgraphtobigwig:469--h9b8f530_0' : + 'biocontainers/ucsc-bedgraphtobigwig:469--h9b8f530_0' }" + + input: + tuple val(meta), path(bedgraph) + path sizes + + output: + tuple val(meta), path("*.bigWig"), emit: bigwig + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + def VERSION = '469' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions. + """ + bedGraphToBigWig \\ + $bedgraph \\ + $sizes \\ + ${prefix}.bigWig + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + ucsc: $VERSION + END_VERSIONS + """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}" + def VERSION = '469' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions. + """ + touch ${prefix}.bigWig + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + ucsc: $VERSION + END_VERSIONS + """ +} diff --git a/modules/nf-core/ucsc/bedgraphtobigwig/meta.yml b/modules/nf-core/ucsc/bedgraphtobigwig/meta.yml new file mode 100755 index 0000000..5d42cbd --- /dev/null +++ b/modules/nf-core/ucsc/bedgraphtobigwig/meta.yml @@ -0,0 +1,49 @@ +name: ucsc_bedgraphtobigwig +description: Convert a bedGraph file to bigWig format. +keywords: + - bedgraph + - bigwig + - ucsc + - bedgraphtobigwig + - converter +tools: + - ucsc: + description: Convert a bedGraph file to bigWig format. + homepage: http://hgdownload.cse.ucsc.edu/admin/exe/ + documentation: https://genome.ucsc.edu/goldenPath/help/bigWig.html + licence: ["varies; see http://genome.ucsc.edu/license"] + identifier: "" +input: + - - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bedgraph: + type: file + description: bedGraph file + pattern: "*.{bedGraph}" + - - sizes: + type: file + description: chromosome sizes file + pattern: "*.{sizes}" +output: + - bigwig: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*.bigWig": + type: file + description: bigWig file + pattern: "*.{bigWig}" + - versions: + - versions.yml: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@drpatelh" +maintainers: + - "@drpatelh" diff --git a/modules/nf-core/ucsc/bedgraphtobigwig/tests/main.nf.test b/modules/nf-core/ucsc/bedgraphtobigwig/tests/main.nf.test new file mode 100644 index 0000000..94a799e --- /dev/null +++ b/modules/nf-core/ucsc/bedgraphtobigwig/tests/main.nf.test @@ -0,0 +1,53 @@ +nextflow_process { + + name "Test Process UCSC_BEDGRAPHTOBIGWIG" + script "../main.nf" + process "UCSC_BEDGRAPHTOBIGWIG" + tag "modules" + tag "modules_nfcore" + tag "ucsc" + tag "ucsc/bedgraphtobigwig" + + test("Should run without failures") { + when { + process { + """ + input[0] = Channel.of([ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + "genomics/sarscov2/illumina/bedgraph/test.bedgraph", checkIfExists: true) + ]) + input[1] = Channel.of(file(params.modules_testdata_base_path + "genomics/sarscov2/genome/genome.sizes", checkIfExists: true)) + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } + + test("stub") { + options "-stub" + when { + process { + """ + input[0] = Channel.of([ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + "genomics/sarscov2/illumina/bedgraph/test.bedgraph", checkIfExists: true) + ]) + input[1] = Channel.of(file(params.modules_testdata_base_path + "genomics/sarscov2/genome/genome.sizes", checkIfExists: true)) + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } +} diff --git a/modules/nf-core/ucsc/bedgraphtobigwig/tests/main.nf.test.snap b/modules/nf-core/ucsc/bedgraphtobigwig/tests/main.nf.test.snap new file mode 100644 index 0000000..7c731f6 --- /dev/null +++ b/modules/nf-core/ucsc/bedgraphtobigwig/tests/main.nf.test.snap @@ -0,0 +1,68 @@ +{ + "stub": { + "content": [ + { + "0": [ + [ + { + "id": "test" + }, + "test.bigWig:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "1": [ + "versions.yml:md5,db26514184acfdf220bb2f061382cf8c" + ], + "bigwig": [ + [ + { + "id": "test" + }, + "test.bigWig:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "versions": [ + "versions.yml:md5,db26514184acfdf220bb2f061382cf8c" + ] + } + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.04.4" + }, + "timestamp": "2024-10-18T10:47:58.558813949" + }, + "Should run without failures": { + "content": [ + { + "0": [ + [ + { + "id": "test" + }, + "test.bigWig:md5,910ecc7f57e3bbd5fac5a8edba4f615d" + ] + ], + "1": [ + "versions.yml:md5,db26514184acfdf220bb2f061382cf8c" + ], + "bigwig": [ + [ + { + "id": "test" + }, + "test.bigWig:md5,910ecc7f57e3bbd5fac5a8edba4f615d" + ] + ], + "versions": [ + "versions.yml:md5,db26514184acfdf220bb2f061382cf8c" + ] + } + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.04.4" + }, + "timestamp": "2024-10-18T10:47:36.476844229" + } +} \ No newline at end of file diff --git a/modules/nf-core/ucsc/bedgraphtobigwig/tests/tags.yml b/modules/nf-core/ucsc/bedgraphtobigwig/tests/tags.yml new file mode 100644 index 0000000..481e8b8 --- /dev/null +++ b/modules/nf-core/ucsc/bedgraphtobigwig/tests/tags.yml @@ -0,0 +1,2 @@ +ucsc/bedgraphtobigwig: + - modules/nf-core/ucsc/bedgraphtobigwig/** diff --git a/nextflow.config b/nextflow.config index 8c471a2..4da12f8 100644 --- a/nextflow.config +++ b/nextflow.config @@ -81,16 +81,20 @@ params { clippy_params = "" icount_peaks_params = "" peka_params = "" + + // Whole read analysis params + whole_read_analysis = false + pairwise_samplesheet= null + macs_gsize = "hs" + macs3_params = "--keep-dup all --nomodel --extsize 30 --bdg" } // Load base.config by default for all pipelines includeConfig 'conf/base.config' -// Load pipeline switching config -includeConfig 'conf/logic.config' - profiles { debug { process.beforeScript = 'echo $HOSTNAME' } + crick { includeConfig 'conf/crick.config' } conda { conda.enabled = true docker.enabled = false @@ -159,8 +163,12 @@ profiles { test_flow_genome { includeConfig 'conf/test_flow_genome.config' } test_full { includeConfig 'conf/test_full.config' } test_full_small { includeConfig 'conf/test_full_small.config' } + test_artr_seq { includeConfig 'conf/test_artr_seq.config' } } +// Load pipeline switching config +includeConfig 'conf/logic.config' + // Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile // Will not be used unless Apptainer / Docker / Podman / Singularity are enabled // Set to your registry if you have a mirror of containers diff --git a/nf-test.config b/nf-test.config index d8e70a7..651d67b 100644 --- a/nf-test.config +++ b/nf-test.config @@ -2,7 +2,8 @@ config { testsDir "tests" workDir ".nf-test" - configFile "tests/nf_test/nextflow.config" + configFile "tests/subworkflows/local/parse_pairwise_input/test.config" profile "" + // libDir "tests/lib" } diff --git a/subworkflows/local/parse_pairwise_input/main.nf b/subworkflows/local/parse_pairwise_input/main.nf new file mode 100644 index 0000000..cdbe71e --- /dev/null +++ b/subworkflows/local/parse_pairwise_input/main.nf @@ -0,0 +1,33 @@ +/* + * Get sample id from pairwise samplesheet and check if compatible with fastq samplesheet + * Then create channel of pairwise ids for bam file channel reorganisation before MACS3 peak calling + * Subworkflow goal is to create pairwise channels of sample id that match metadata + */ + +include { PAIRWISE_SAMPLESHEET_CHECK } from '../../../modules/local/whole_read_analysis/pairwise_samplesheet_check/main.nf' + +workflow PARSE_PAIRWISE_INPUT { + take: + samplesheet // file: /path/to/samplesheet.csv + + main: + ch_versions = Channel.empty() + + /* + * MODULE: Check the samplesheet for errors + */ + PAIRWISE_SAMPLESHEET_CHECK ( + samplesheet + ) + + /* + * CHANNEL: Split the validated pairwise samplesheet into a channel + */ + ch_pairwise_samples = PAIRWISE_SAMPLESHEET_CHECK.out.csv + .splitCsv ( header:true, sep:"," ) + .map { row -> [row.id, row.control_id] } + + emit: + pairwise = ch_pairwise_samples // channel: [ id, control_id ] + versions = ch_versions // channel: [ versions.yml ] +} diff --git a/subworkflows/local/parse_pairwise_input/meta.yml b/subworkflows/local/parse_pairwise_input/meta.yml new file mode 100644 index 0000000..b809fb8 --- /dev/null +++ b/subworkflows/local/parse_pairwise_input/meta.yml @@ -0,0 +1,30 @@ +name: parse_pairwise_input +description: | + Get sample id from pairwise samplesheet and check if compatible with fastq samplesheet + Then create channel of pairwise ids for bam file channel reorganisation before MACS3 peak calling + Subworkflow goal is to create pairwise channels of sample id that match metadata + +keywords: + +modules: + - nf-core/samtools/view + - local/whole_read_analysis/pairwise_samplesheet_check + - nf-core/bedtools/bamtobed + - nf-core/bedtools/genomecov +input: + - samplesheet: + type: file + description: Pairwise samplesheet + pattern: "*pairwise_samplesheet.csv" +output: + - pairwise: + type: list + description: | + Groovy list containing pairwise sample information + e.g. [ id, control_id ] + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@hanzhong-bai" diff --git a/subworkflows/local/prep_whole_read/default.config b/subworkflows/local/prep_whole_read/default.config new file mode 100644 index 0000000..4b0cc0a --- /dev/null +++ b/subworkflows/local/prep_whole_read/default.config @@ -0,0 +1,49 @@ +process { + + withName: BEDTOOLS_SHIFT { + ext.args = '-m 1 -p -1' + } + + withName: BEDTOOLS_GENOMECOV_POS { + ext.args = '-dz -strand + -5' + } + + withName: BEDTOOLS_GENOMECOV_NEG { + ext.args = '-dz -strand - -5' + } + + withName: SELECT_BED_POS { + ext.cmd1 = 'awk \'{OFS="\\t"}{print \$1, \$2, \$2+1, ".", \$3, "+"}\'' + ext.suffix = '.pos' + ext.ext = 'bed' + } + + withName: SELECT_BED_NEG { + ext.cmd1 = 'awk \'{OFS="\\t"}{print \$1, \$2, \$2+1, ".", \$3, "-"}\'' + ext.suffix = '.neg' + ext.ext = 'bed' + } + + withName: MERGE_AND_SORT { + ext.cmd1 = 'sort -k1,1 -k2,2n' + ext.suffix = '.sorted' + ext.ext = 'bed' + } + + withName: CROSSLINK_COVERAGE { + ext.cmd1 = 'awk \'{OFS = "\t"}{if (\$6 == "+") {print \$1, \$2, \$3, \$5} else {print \$1, \$2, \$3, -\$5}}\' | sort -k1,1 -k2,2n' + ext.suffix = '.sorted' + ext.ext = 'bedgraph' + } + + withName: CROSSLINK_NORMCOVERAGE { + ext.cmd1 = """ + awk -v total=\$CMD2 \'{printf "%s\\t%i\\t%i\\t%s\\t%f\\t%s\\n", \$1, \$2, \$3, \$4, 1000000*\$5/total, \$6}\' | + awk \'{OFS = "\t"}{if (\$6 == "+") {print \$1, \$2, \$3, \$5} else {print \$1, \$2, \$3, -\$5}}\' | + sort -k1,1 -k2,2n + """ + ext.cmd2 = 'awk \'BEGIN {total=0} {total=total+\$5} END {print total}\'' + ext.suffix = '.norm.sorted' + ext.ext = 'bedgraph' + } +} diff --git a/subworkflows/local/prep_whole_read/main.nf b/subworkflows/local/prep_whole_read/main.nf new file mode 100644 index 0000000..38eabe7 --- /dev/null +++ b/subworkflows/local/prep_whole_read/main.nf @@ -0,0 +1,96 @@ +/* Split bam files into plus and minus strand bam files for MACS3 peak calling +* Also convert the bam file to bed format and calculate (normalised) coverage tracks in bedgraph format + +* Update: The new workflow generates bigwig files from positive and negative strand bedgraph files +*/ + +/* +* MODULES +*/ +include { SAMTOOLS_VIEW as SAMTOOLS_VIEW_PLUS } from '../../../modules/nf-core/samtools/view/main' +include { SAMTOOLS_VIEW as SAMTOOLS_VIEW_MINUS } from '../../../modules/nf-core/samtools/view/main' + +include { BEDTOOLS_BAMTOBED } from '../../../modules/nf-core/bedtools/bamtobed/main.nf' +include { BEDTOOLS_GENOMECOV as BEDTOOLS_GENOMECOV_POS } from '../../../modules/nf-core/bedtools/genomecov/main.nf' +include { BEDTOOLS_GENOMECOV as BEDTOOLS_GENOMECOV_NEG } from '../../../modules/nf-core/bedtools/genomecov/main.nf' + +include { UCSC_BEDGRAPHTOBIGWIG as BIGWIG_POS } from '../../../modules/nf-core/ucsc/bedgraphtobigwig/main.nf' +include { UCSC_BEDGRAPHTOBIGWIG as BIGWIG_NEG } from '../../../modules/nf-core/ucsc/bedgraphtobigwig/main.nf' + +workflow PREP_WHOLE_READ { + take: + bam // channel: [ val(meta), [ bam ] ] + bai // channel: [ val(meta), [ bai ] ] + fai // channel: [ fai ] + run_bigwig // boolean: run bigwig conversion + + main: + ch_versions = Channel.empty() + + /* + * MODULE: split BAM file into plus and minus strand files + */ + ch_bam = bam.join(bai, by: [0], remainder: true) + .map { meta, bam, bai -> [ meta, bam, bai ] } + + SAMTOOLS_VIEW_PLUS ( + ch_bam, + [[],[]], + [] + ) + ch_versions = ch_versions.mix(SAMTOOLS_VIEW_PLUS.out.versions) + + SAMTOOLS_VIEW_MINUS ( + ch_bam, + [[],[]], + [] + ) + + /* + * MODULE: Convert input BAM file to BED format + */ + BEDTOOLS_BAMTOBED ( + bam + ) + ch_versions = ch_versions.mix(BEDTOOLS_BAMTOBED.out.versions) + + /* + * MODULE: Report depth on the pos/neg strand, using whole interval as bedgraph output + */ + BEDTOOLS_GENOMECOV_POS ( + BEDTOOLS_BAMTOBED.out.bed.map{ [ it[0], it[1], 1 ] }, + fai, + 'pos.bedgraph' + ) + ch_versions = ch_versions.mix(BEDTOOLS_GENOMECOV_POS.out.versions) + + BEDTOOLS_GENOMECOV_NEG ( + BEDTOOLS_BAMTOBED.out.bed.map{ [ it[0], it[1], 1 ] }, + fai, + 'neg.bedgraph' + ) + + /* + * MODULE: Convert BED file to bigwig format + */ + if (run_bigwig) { + ch_chrom_sizes = Channel.fromPath(params.chrom_sizes) + BIGWIG_POS ( + BEDTOOLS_GENOMECOV_POS.out.genomecov, + ch_chrom_sizes.collect() + ) + ch_versions = ch_versions.mix(BIGWIG_POS.out.versions) + + BIGWIG_NEG ( + BEDTOOLS_GENOMECOV_NEG.out.genomecov, + ch_chrom_sizes.collect() + ) + } + + emit: + bam_plus = SAMTOOLS_VIEW_PLUS.out.bam // channel: [ val(meta), [ bam ] ] + bam_minus = SAMTOOLS_VIEW_MINUS.out.bam // channel: [ val(meta), [ bam ] ] + + bed = BEDTOOLS_BAMTOBED.out.bed // channel: [ val(meta), [ bed ] ] + versions = ch_versions // channel: [ versions.yml ] +} diff --git a/subworkflows/local/prep_whole_read/meta.yml b/subworkflows/local/prep_whole_read/meta.yml new file mode 100644 index 0000000..6bdc6dd --- /dev/null +++ b/subworkflows/local/prep_whole_read/meta.yml @@ -0,0 +1,62 @@ +name: prep_whole_read +description: | + Split bam files into plus and minus strand bam files for MACS3 peak calling + Also convert the bam file to bed format and calculate (normalised) coverage tracks in bedgraph format +keywords: + - samtools + - bedtools + - macs3 + - coverage + - fai + - bam +modules: + - nf-core/samtools/view + - goodwright/linux/command + - nf-core/bedtools/bamtobed + - nf-core/bedtools/genomecov +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [id:FUS_KO_BRD4_plus_R2, group:FUS_KO_BRD4_plus, replicate:2, single_end:true] + - bam: + type: file + description: BAM file + pattern: "*.bam" + - fai: + type: file + description: FAI file + pattern: "*.fai" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam_plus: + type: file + description: BAM file containing reads on the plus strand + pattern: "*_plus.bam" + - bam_minus: + type: file + description: BAM file containing reads on the minus strand + pattern: "*_minus.bam" + - bed: + type: file + description: Bedfile containing the crosslink depths at genomic positions + pattern: "*.bed" + - coverage: + type: file + description: The crosslinks bed file turned into a bedgraph coverage file. + pattern: "*.bedgraph" + - coverage_norm: + type: file + description: The crosslinks bed file turned into a bedgraph coverage file normalised against total count + pattern: "*.bedgraph" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@chris-cheshire" diff --git a/tests/ARTR-seq/input_data/pairwise_peak_calling.csv b/tests/ARTR-seq/input_data/pairwise_peak_calling.csv new file mode 100644 index 0000000..44ffc77 --- /dev/null +++ b/tests/ARTR-seq/input_data/pairwise_peak_calling.csv @@ -0,0 +1,11 @@ +group,replicate,control_group,control_replicate +WT_BRD4_plus,1,WT_No_Ab,1 +WT_BRD4_plus,2,WT_No_Ab,2 +WT_FUS_plus,1,WT_No_Ab,1 +WT_FUS_plus,2,WT_No_Ab,2 +WT_FUS_plus,1,FUS_KO_FUS,1 +WT_FUS_plus,2,FUS_KO_FUS,2 +M3_KO_BRD4_plus,1,M3_KO_No_Ab,1 +M3_KO_BRD4_plus,2,M3_KO_No_Ab,2 +FUS_KO_BRD4_plus,1,FUS_KO_No_Ab,1 +FUS_KO_BRD4_plus,2,FUS_KO_No_Ab,2 diff --git a/tests/ARTR-seq/input_data/pairwise_peak_calling_for_testing.csv b/tests/ARTR-seq/input_data/pairwise_peak_calling_for_testing.csv new file mode 100644 index 0000000..991b0a8 --- /dev/null +++ b/tests/ARTR-seq/input_data/pairwise_peak_calling_for_testing.csv @@ -0,0 +1,3 @@ +group,replicate,control_group,control_replicate +WT_BRD4_plus,1,WT_No_Ab,1 +WT_BRD4_plus,2,WT_No_Ab,2 diff --git a/tests/ARTR-seq/input_data/sample_sheet.csv b/tests/ARTR-seq/input_data/sample_sheet.csv new file mode 100644 index 0000000..5736d38 --- /dev/null +++ b/tests/ARTR-seq/input_data/sample_sheet.csv @@ -0,0 +1,17 @@ +group,replicate,fastq_1,fastq_2 +WT_BRD4_plus,1,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A9_S347_L008_R1_001.fastq.gz, +WT_BRD4_plus,2,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A10_S348_L008_R1_001.fastq.gz, +WT_No_Ab,1,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A11_S349_L008_R1_001.fastq.gz, +WT_No_Ab,2,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A12_S350_L008_R1_001.fastq.gz, +WT_FUS_plus,1,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A13_S351_L008_R1_001.fastq.gz, +WT_FUS_plus,2,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A14_S352_L008_R1_001.fastq.gz, +M3_KO_BRD4_plus,1,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A15_S353_L008_R1_001.fastq.gz, +M3_KO_BRD4_plus,2,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A16_S354_L008_R1_001.fastq.gz, +M3_KO_No_Ab,1,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A17_S355_L008_R1_001.fastq.gz, +M3_KO_No_Ab,2,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A18_S356_L008_R1_001.fastq.gz, +FUS_KO_BRD4_plus,1,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A19_S357_L008_R1_001.fastq.gz, +FUS_KO_BRD4_plus,2,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A20_S358_L008_R1_001.fastq.gz, +FUS_KO_No_Ab,1,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A21_S359_L008_R1_001.fastq.gz, +FUS_KO_No_Ab,2,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A22_S360_L008_R1_001.fastq.gz, +FUS_KO_FUS,1,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A23_S361_L008_R1_001.fastq.gz, +FUS_KO_FUS,2,/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq/BAI7152A24_S362_L008_R1_001.fastq.gz, diff --git a/tests/ARTR-seq/input_data/sample_sheet_for_testing.csv b/tests/ARTR-seq/input_data/sample_sheet_for_testing.csv new file mode 100644 index 0000000..af8c226 --- /dev/null +++ b/tests/ARTR-seq/input_data/sample_sheet_for_testing.csv @@ -0,0 +1,5 @@ +group,replicate,fastq_1,fastq_2 +WT_BRD4_plus,1,tests/ARTR-seq/input_data/subsampled/WT_BRD4_plus_1_subsampled_100000.fastq.gz, +WT_BRD4_plus,2,tests/ARTR-seq/input_data/subsampled/WT_BRD4_plus_2_subsampled_100000.fastq.gz, +WT_No_Ab,1,tests/ARTR-seq/input_data/subsampled/WT_No_Ab_1_subsampled_100000.fastq.gz, +WT_No_Ab,2,tests/ARTR-seq/input_data/subsampled/WT_No_Ab_2_subsampled_100000.fastq.gz, \ No newline at end of file diff --git a/tests/ARTR-seq/input_data/subsampled/WT_BRD4_plus_1_subsampled_100000.fastq.gz b/tests/ARTR-seq/input_data/subsampled/WT_BRD4_plus_1_subsampled_100000.fastq.gz new file mode 100644 index 0000000..15c8429 Binary files /dev/null and b/tests/ARTR-seq/input_data/subsampled/WT_BRD4_plus_1_subsampled_100000.fastq.gz differ diff --git a/tests/ARTR-seq/input_data/subsampled/WT_BRD4_plus_2_subsampled_100000.fastq.gz b/tests/ARTR-seq/input_data/subsampled/WT_BRD4_plus_2_subsampled_100000.fastq.gz new file mode 100644 index 0000000..5eb879f Binary files /dev/null and b/tests/ARTR-seq/input_data/subsampled/WT_BRD4_plus_2_subsampled_100000.fastq.gz differ diff --git a/tests/ARTR-seq/input_data/subsampled/WT_No_Ab_1_subsampled_100000.fastq.gz b/tests/ARTR-seq/input_data/subsampled/WT_No_Ab_1_subsampled_100000.fastq.gz new file mode 100644 index 0000000..454d43c Binary files /dev/null and b/tests/ARTR-seq/input_data/subsampled/WT_No_Ab_1_subsampled_100000.fastq.gz differ diff --git a/tests/ARTR-seq/input_data/subsampled/WT_No_Ab_2_subsampled_100000.fastq.gz b/tests/ARTR-seq/input_data/subsampled/WT_No_Ab_2_subsampled_100000.fastq.gz new file mode 100644 index 0000000..2537589 Binary files /dev/null and b/tests/ARTR-seq/input_data/subsampled/WT_No_Ab_2_subsampled_100000.fastq.gz differ diff --git a/tests/ARTR-seq/logs/API_upload_20240924_9527900.out b/tests/ARTR-seq/logs/API_upload_20240924_9527900.out new file mode 100644 index 0000000..5a942ff --- /dev/null +++ b/tests/ARTR-seq/logs/API_upload_20240924_9527900.out @@ -0,0 +1,4 @@ +Traceback (most recent call last): + File "/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/script/API_upload.py", line 1, in + import flowbio +ModuleNotFoundError: No module named 'flowbio' diff --git a/tests/ARTR-seq/logs/API_upload_20240924_9527919.out b/tests/ARTR-seq/logs/API_upload_20240924_9527919.out new file mode 100644 index 0000000..f0c7f22 --- /dev/null +++ b/tests/ARTR-seq/logs/API_upload_20240924_9527919.out @@ -0,0 +1,93 @@ +usage: conda [-h] [--no-plugins] [-V] COMMAND ... +conda: error: argument COMMAND: invalid choice: 'activate' (choose from 'clean', 'compare', 'config', 'create', 'info', 'init', 'install', 'list', 'notices', 'package', 'remove', 'uninstall', 'rename', 'run', 'search', 'update', 'upgrade', 'build', 'content-trust', 'convert', 'debug', 'develop', 'doctor', 'index', 'inspect', 'metapackage', 'render', 'skeleton', 'verify', 'pack', 'server', 'token', 'repo', 'env') + 0%| | 0/779 [00:00", line 3, in raise_from + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 461, in _make_request + httplib_response = conn.getresponse() + ^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 1378, in getresponse + response.begin() + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 318, in begin + version, status, reason = self._read_status() + ^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 287, in _read_status + raise RemoteDisconnected("Remote end closed connection without" +http.client.RemoteDisconnected: Remote end closed connection without response + +During handling of the above exception, another exception occurred: + +Traceback (most recent call last): + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/requests/adapters.py", line 486, in send + resp = conn.urlopen( + ^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 798, in urlopen + retries = retries.increment( + ^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/util/retry.py", line 550, in increment + raise six.reraise(type(error), error, _stacktrace) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/packages/six.py", line 769, in reraise + raise value.with_traceback(tb) + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 714, in urlopen + httplib_response = self._make_request( + ^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 466, in _make_request + six.raise_from(e, None) + File "", line 3, in raise_from + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 461, in _make_request + httplib_response = conn.getresponse() + ^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 1378, in getresponse + response.begin() + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 318, in begin + version, status, reason = self._read_status() + ^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 287, in _read_status + raise RemoteDisconnected("Remote end closed connection without" +urllib3.exceptions.ProtocolError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response')) + +During handling of the above exception, another exception occurred: + +Traceback (most recent call last): + File "/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/script/API_upload.py", line 18, in + sample = client.upload_sample( + ^^^^^^^^^^^^^^^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/flowbio/upload.py", line 89, in upload_sample + resp = self.execute(UPLOAD_SAMPLE, retries=retries, variables={ + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/flowbio/client.py", line 25, in execute + resp = super().execute(*args, **kwargs) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/kirjava/client.py", line 75, in execute + response = self.request_with_retries( + ^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/kirjava/client.py", line 117, in request_with_retries + if attempts > retries: raise e + ^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/kirjava/client.py", line 109, in request_with_retries + response = self.session.request( + ^^^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/requests/sessions.py", line 589, in request + resp = self.send(prep, **send_kwargs) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/requests/sessions.py", line 703, in send + r = adapter.send(request, **kwargs) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/requests/adapters.py", line 501, in send + raise ConnectionError(err, request=request) +requests.exceptions.ConnectionError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response')) diff --git a/tests/ARTR-seq/logs/API_upload_20240924_9529902.out b/tests/ARTR-seq/logs/API_upload_20240924_9529902.out new file mode 100644 index 0000000..ef1d3af --- /dev/null +++ b/tests/ARTR-seq/logs/API_upload_20240924_9529902.out @@ -0,0 +1,85 @@ +usage: conda [-h] [--no-plugins] [-V] COMMAND ... +conda: error: argument COMMAND: invalid choice: 'activate' (choose from 'clean', 'compare', 'config', 'create', 'info', 'init', 'install', 'list', 'notices', 'package', 'remove', 'uninstall', 'rename', 'run', 'search', 'update', 'upgrade', 'build', 'content-trust', 'convert', 'debug', 'develop', 'doctor', 'index', 'inspect', 'metapackage', 'render', 'skeleton', 'pack', 'server', 'verify', 'repo', 'token', 'env') + 0%| | 0/428 [00:00", line 3, in raise_from + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 461, in _make_request + httplib_response = conn.getresponse() + ^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 1378, in getresponse + response.begin() + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 318, in begin + version, status, reason = self._read_status() + ^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 287, in _read_status + raise RemoteDisconnected("Remote end closed connection without" +http.client.RemoteDisconnected: Remote end closed connection without response + +During handling of the above exception, another exception occurred: + +Traceback (most recent call last): + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/requests/adapters.py", line 486, in send + resp = conn.urlopen( + ^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 798, in urlopen + retries = retries.increment( + ^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/util/retry.py", line 550, in increment + raise six.reraise(type(error), error, _stacktrace) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/packages/six.py", line 769, in reraise + raise value.with_traceback(tb) + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 714, in urlopen + httplib_response = self._make_request( + ^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 466, in _make_request + six.raise_from(e, None) + File "", line 3, in raise_from + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/urllib3/connectionpool.py", line 461, in _make_request + httplib_response = conn.getresponse() + ^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 1378, in getresponse + response.begin() + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 318, in begin + version, status, reason = self._read_status() + ^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/http/client.py", line 287, in _read_status + raise RemoteDisconnected("Remote end closed connection without" +urllib3.exceptions.ProtocolError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response')) + +During handling of the above exception, another exception occurred: + +Traceback (most recent call last): + File "/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/script/API_upload.py", line 18, in + sample = client.upload_sample( + ^^^^^^^^^^^^^^^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/flowbio/upload.py", line 89, in upload_sample + resp = self.execute(UPLOAD_SAMPLE, retries=retries, variables={ + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/flowbio/client.py", line 25, in execute + resp = super().execute(*args, **kwargs) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/kirjava/client.py", line 75, in execute + response = self.request_with_retries( + ^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/kirjava/client.py", line 117, in request_with_retries + if attempts > retries: raise e + ^^^^^^^ + File "/camp/home/baih/.local/lib/python3.11/site-packages/kirjava/client.py", line 109, in request_with_retries + response = self.session.request( + ^^^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/requests/sessions.py", line 589, in request + resp = self.send(prep, **send_kwargs) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/requests/sessions.py", line 703, in send + r = adapter.send(request, **kwargs) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/camp/apps/eb/software/Anaconda3/2023.09-0/lib/python3.11/site-packages/requests/adapters.py", line 501, in send + raise ConnectionError(err, request=request) +requests.exceptions.ConnectionError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response')) diff --git a/tests/ARTR-seq/script/API_upload.py b/tests/ARTR-seq/script/API_upload.py new file mode 100644 index 0000000..355ccf0 --- /dev/null +++ b/tests/ARTR-seq/script/API_upload.py @@ -0,0 +1,30 @@ +import flowbio +import os + +client = flowbio.Client() +client.login("hanzhong", "H5HUeHc!5rDaRzs") + + +# sample dir path +sample_dir = "/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq" + +# Loop through samples A9 to A24 +for i in range(12, 25): + sample_name = f"BAI7152A{i}" + reads1 = os.path.join(sample_dir, f"{sample_name}_S{i+338}_L008_R1_001.fastq.gz") + reads2 = os.path.join(sample_dir, f"{sample_name}_S{i+338}_L008_R2_001.fastq.gz") # Assuming paired-end reads + + # Upload sample + sample = client.upload_sample( + sample_name, + reads1, + reads2, # Optional + progress=True, + metadata={ + "Category": "CLIP", + "Organism": "Human", + "Project": "ARTR-seq-20240924", + "5' Barcode Sequence": "NNNNNGGG" + } + ) + print(sample) diff --git a/tests/ARTR-seq/script/API_upload_sbatch.sh b/tests/ARTR-seq/script/API_upload_sbatch.sh new file mode 100644 index 0000000..57b90ca --- /dev/null +++ b/tests/ARTR-seq/script/API_upload_sbatch.sh @@ -0,0 +1,14 @@ +#!/bin/bash +#SBATCH --job-name=API_upload +#SBATCH --time=12:00:00 # Set the maximum runtime (e.g., 12 hour) +#SBATCH --ntasks=1 # Number of tasks (usually 1 for a single script) +#SBATCH --cpus-per-task=1 # Number of CPU cores per task +#SBATCH --mem=6G # Memory per node (e.g., 4GB) +#SBATCH --nodes=1 +#SBATCH --output=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/logs/API_upload_20240924_%j.out + + +# Run the Python script +ml Anaconda3/2023.09-0 +conda activate flow +python3 /nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/script/API_upload.py \ No newline at end of file diff --git a/tests/ARTR-seq/script/ARTR-seq-bash.sh b/tests/ARTR-seq/script/ARTR-seq-bash.sh new file mode 100644 index 0000000..2ebbd27 --- /dev/null +++ b/tests/ARTR-seq/script/ARTR-seq-bash.sh @@ -0,0 +1,53 @@ +#!/bin/sh +#SBATCH --job-name="ARTRseq_HeLa_results" +#SBATCH --time=12:00:00 +#SBATCH --nodes=1 +#SBATCH --output=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/v1.3/clipseq/tests/ARTR-seq_20240925/logs/1st_run_20240925-%A.out + +ml purge +ml Anaconda3/2023.09-0 +ml Nextflow/23.04.4 +ml Singularity/3.11.3 +# ml Graphviz/2.38.0-foss-2016b + +# the pipeline also has a "libraryDir = '/flask/apps/containers/all-singularity-images'" in the config file, which searches for the singularity images on nemo +export NXF_SINGULARITY_CACHEDIR=/camp/lab/ulej/home/shared/singularity +cd /nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/v1.3/clipseq + +# Input Parameters +input_dir="/nemo/stp/sequencing/inputs/instruments/fastq/20240807_LH00442_0034_A22MYGKLT3/fastq/PM24162" +outdir="/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/v1.3/clipseq/tests/ARTR-seq_20240925/output" +sample_sheet=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/v1.3/clipseq/tests/ARTR-seq_20240925/data/sample_sheet.csv + +genome_fasta="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/GRCh38.primary_assembly.genome.fa" +smRNA_fasta="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/flow_bio_additional_ref/Homo_sapiens.GRCh38.smrna.fasta" +genome_gtf="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/gencode.v44.primary_assembly.annotation.gtf" + +# Pipeline Parameters +# here we remove 3 nucleotides from the 5' end of read 1 and the 3' end of read 2, which are bias introduced by MMLV +# also remove 4 nucleotides from the 3' end of read 1 and the 5' end of read 2, which are bias introduced by random RT priming +trimgalore_params="--fastqc --length 10 -q 20 --clip_r1 3 --three_prime_clip_r1 4" +# Here it's the bowtie2 alignment parameters, basically we allow 2 mismatches and 100 alignments, and we only keep the best alignment +# Note that the --best and --strata do not work in pared-end mode, but here we are only interested in the unaligned reads so it's fine +# Also note that ARTR-seq used bowtie2 -n mode with seed legnth 15 () +bowtie_params="-v 2 -m 100 --norc --best --strata" +# Here we use the STAR parameters in CLIP-seq, which allow multimappers and basically a classic encode RNA-seq pipeline. +# Note the alignEndsType is EndToEnd, which prevents soft-clipping, since we hard-clipped the reads in the previous step +star_params="--outFilterMultimapNmax 100 --outFilterMultimapScoreRange 1 --outSAMattributes All --alignSJoverhangMin 8 --alignSJDBoverhangMin 1 --outFilterType BySJout --alignIntronMin 20 --alignIntronMax 1000000 --outFilterScoreMin 10 --alignEndsType EndToEnd --twopassMode Basic" +umi_header_format="NNNNN" +umi_separator="_" + +nextflow run main.nf -resume \ +-profile crick \ +-N pelusobai@gmail.com \ +--outdir $outdir \ +--samplesheet $sample_sheet \ +--fasta $genome_fasta \ +--smrna_fasta $smRNA_fasta \ +--gtf $genome_gtf \ +--move_umi_to_header true \ +--umi_header_format "${umi_header_format}" \ +--trimgalore_params "${trimgalore_params}" \ +--bowtie_params "${bowtie_params}" \ +--star_params "${star_params}" \ +--umi_separator "${umi_separator}" \ No newline at end of file diff --git a/tests/ARTR-seq/script/ARTR-seq-hanzhong-samples.sh b/tests/ARTR-seq/script/ARTR-seq-hanzhong-samples.sh new file mode 100644 index 0000000..a909d20 --- /dev/null +++ b/tests/ARTR-seq/script/ARTR-seq-hanzhong-samples.sh @@ -0,0 +1,95 @@ +#!/bin/sh +#SBATCH --job-name="ARTRseq_test" +#SBATCH --time=12:00:00 +#SBATCH --nodes=1 +#SBATCH --output=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/logs/ARTR_seq_hanzhong_20241101-%A.out + +ml purge +ml Anaconda3/2023.09-0 +ml Nextflow/23.04.4 +ml Singularity/3.11.3 +# ml Graphviz/2.38.0-foss-2016b + +# the pipeline also has a "libraryDir = '/flask/apps/containers/all-singularity-images'" in the config file, which searches for the singularity images on nemo +export NXF_SINGULARITY_CACHEDIR=/camp/lab/ulej/home/shared/singularity +cd /nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq + +# Input Parameters +outdir="/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/output_hanzhong_samples" +sample_sheet=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/input_data/sample_sheet.csv +pairwise_samplesheet=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/input_data/pairwise_peak_calling.csv + +# Reference Parameters +fasta="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/GRCh38.primary_assembly.genome.fa" +smRNA_fasta="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/flow_bio_additional_ref/Homo_sapiens.GRCh38.smrna.fasta" +genome_gtf="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/gencode.v44.primary_assembly.annotation.gtf" + +target_genome_index=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/index/star +smrna_genome_index=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/index/bowtie +fasta_fai=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/GRCh38.primary_assembly.genome.fa.fai +filtered_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered.gtf +chrom_sizes=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/GRCh38.primary_assembly.genome.fa.sizes +smrna_fasta_fai=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/Homo_sapiens.GRCh38.smrna.fasta.fai +smrna_chrom_sizes=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/Homo_sapiens.GRCh38.smrna.fasta.sizes +longest_transcript=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/longest_transcript.txt +longest_transcript_fai=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/longest_transcript.fai +longest_transcript_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/longest_transcript.gtf +seg_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_seg.gtf +seg_filt_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_seg.gtf +seg_resolved_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_seg_genicOtherfalse.resolved.gtf +seg_resolved_gtf_genic=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_seg_genicOthertrue.resolved.gtf +regions_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_regions.gtf +regions_filt_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_regions.gtf.gz +regions_resolved_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_regions_genicOtherfalse.resolved.gtf +regions_resolved_gtf_genic=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_regions_genicOthertrue.resolved.gtf + +# Pipeline Parameters +# here we remove 3 nucleotides from the 5' end of read 1 and the 3' end of read 2, which are bias introduced by MMLV +# also remove 4 nucleotides from the 3' end of read 1 and the 5' end of read 2, which are bias introduced by random RT priming +trimgalore_params="--fastqc --length 10 -q 20 --clip_r1 3 --three_prime_clip_r1 4" +# Here it's the bowtie2 alignment parameters, basically we allow 2 mismatches and 100 alignments, and we only keep the best alignment +# Note that the --best and --strata do not work in pared-end mode, but here we are only interested in the unaligned reads so it's fine +# Also note that ARTR-seq used bowtie2 -n mode with seed legnth 15 () +bowtie_params="-v 2 -m 100 --norc --best --strata" +# Here we use the STAR parameters in CLIP-seq, which allow multimappers and basically a classic encode RNA-seq pipeline. +# Note the alignEndsType is EndToEnd, which prevents soft-clipping, since we hard-clipped the reads in the previous step +star_params="--outFilterMultimapNmax 100 --outFilterMultimapScoreRange 1 --outSAMattributes All --alignSJoverhangMin 8 --alignSJDBoverhangMin 1 --outFilterType BySJout --alignIntronMin 20 --alignIntronMax 1000000 --outFilterScoreMin 10 --alignEndsType EndToEnd --twopassMode Basic" +macs3_params="--keep-dup all --nomodel --extsize 30 --bdg -g hs" +umi_header_format="NNNNN" +umi_separator="_" + +nextflow run main.nf -resume \ +-profile crick \ +-N pelusobai@gmail.com \ +--whole_read_analysis true \ +--outdir $outdir \ +--samplesheet $sample_sheet \ +--pairwise_samplesheet $pairwise_samplesheet \ +--fasta $fasta \ +--smrna_fasta $smRNA_fasta \ +--gtf $genome_gtf \ +--target_genome_index $target_genome_index \ +--smrna_genome_index $smrna_genome_index \ +--fasta_fai $fasta_fai \ +--filtered_gtf $filtered_gtf \ +--chrom_sizes $chrom_sizes \ +--smrna_fasta_fai $smrna_fasta_fai \ +--smrna_chrom_sizes $smrna_chrom_sizes \ +--longest_transcript $longest_transcript \ +--longest_transcript_fai $longest_transcript_fai \ +--longest_transcript_gtf $longest_transcript_gtf \ +--seg_gtf $seg_gtf \ +--seg_filt_gtf $seg_filt_gtf \ +--seg_resolved_gtf $seg_resolved_gtf \ +--seg_resolved_gtf_genic $seg_resolved_gtf_genic \ +--regions_gtf $regions_gtf \ +--regions_filt_gtf $regions_filt_gtf \ +--regions_resolved_gtf $regions_resolved_gtf \ +--regions_resolved_gtf_genic $regions_resolved_gtf_genic \ +--move_umi_to_header true \ +--umi_header_format "${umi_header_format}" \ +--trimgalore_params "${trimgalore_params}" \ +--bowtie_params "${bowtie_params}" \ +--star_params "${star_params}" \ +--macs3_params "${macs3_params}" \ +--umi_separator "${umi_separator}" \ No newline at end of file diff --git a/tests/ARTR-seq/script/ARTR-seq-test.sh b/tests/ARTR-seq/script/ARTR-seq-test.sh new file mode 100644 index 0000000..9d9bc11 --- /dev/null +++ b/tests/ARTR-seq/script/ARTR-seq-test.sh @@ -0,0 +1,95 @@ +#!/bin/sh +#SBATCH --job-name="ARTRseq_test" +#SBATCH --time=12:00:00 +#SBATCH --nodes=1 +#SBATCH --output=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/logs/ARTR_seq_test_20241024-%A.out + +ml purge +ml Anaconda3/2023.09-0 +ml Nextflow/23.04.4 +ml Singularity/3.11.3 +# ml Graphviz/2.38.0-foss-2016b + +# the pipeline also has a "libraryDir = '/flask/apps/containers/all-singularity-images'" in the config file, which searches for the singularity images on nemo +export NXF_SINGULARITY_CACHEDIR=/camp/lab/ulej/home/shared/singularity +cd /nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq + +# Input Parameters +outdir="/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/output" +sample_sheet=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/input_data/sample_sheet_for_testing.csv +pairwise_samplesheet=/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/tests/ARTR-seq/input_data/pairwise_peak_calling_for_testing.csv + +# Reference Parameters +fasta="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/GRCh38.primary_assembly.genome.fa" +smRNA_fasta="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/flow_bio_additional_ref/Homo_sapiens.GRCh38.smrna.fasta" +genome_gtf="/nemo/lab/ulej/home/users/baih/Reference/Gencode_reference_files/Human/GRCh38.v44/gencode.v44.primary_assembly.annotation.gtf" + +target_genome_index=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/index/star +smrna_genome_index=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/index/bowtie +fasta_fai=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/GRCh38.primary_assembly.genome.fa.fai +filtered_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered.gtf +chrom_sizes=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/GRCh38.primary_assembly.genome.fa.sizes +smrna_fasta_fai=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/Homo_sapiens.GRCh38.smrna.fasta.fai +smrna_chrom_sizes=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/Homo_sapiens.GRCh38.smrna.fasta.sizes +longest_transcript=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/longest_transcript.txt +longest_transcript_fai=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/longest_transcript.fai +longest_transcript_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/longest_transcript.gtf +seg_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_seg.gtf +seg_filt_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_seg.gtf +seg_resolved_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_seg_genicOtherfalse.resolved.gtf +seg_resolved_gtf_genic=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_seg_genicOthertrue.resolved.gtf +regions_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_regions.gtf +regions_filt_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_regions.gtf.gz +regions_resolved_gtf=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_regions_genicOtherfalse.resolved.gtf +regions_resolved_gtf_genic=/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/gencode_filtered_regions_genicOthertrue.resolved.gtf + +# Pipeline Parameters +# here we remove 3 nucleotides from the 5' end of read 1 and the 3' end of read 2, which are bias introduced by MMLV +# also remove 4 nucleotides from the 3' end of read 1 and the 5' end of read 2, which are bias introduced by random RT priming +trimgalore_params="--fastqc --length 10 -q 20 --clip_r1 3 --three_prime_clip_r1 4" +# Here it's the bowtie2 alignment parameters, basically we allow 2 mismatches and 100 alignments, and we only keep the best alignment +# Note that the --best and --strata do not work in pared-end mode, but here we are only interested in the unaligned reads so it's fine +# Also note that ARTR-seq used bowtie2 -n mode with seed legnth 15 () +bowtie_params="-v 2 -m 100 --norc --best --strata" +# Here we use the STAR parameters in CLIP-seq, which allow multimappers and basically a classic encode RNA-seq pipeline. +# Note the alignEndsType is EndToEnd, which prevents soft-clipping, since we hard-clipped the reads in the previous step +star_params="--outFilterMultimapNmax 100 --outFilterMultimapScoreRange 1 --outSAMattributes All --alignSJoverhangMin 8 --alignSJDBoverhangMin 1 --outFilterType BySJout --alignIntronMin 20 --alignIntronMax 1000000 --outFilterScoreMin 10 --alignEndsType EndToEnd --twopassMode Basic" +macs3_params="--keep-dup all --nomodel --extsize 30 --bdg -g hs" +umi_header_format="NNNNN" +umi_separator="_" + +nextflow run main.nf -resume \ +-profile crick \ +-N pelusobai@gmail.com \ +--whole_read_analysis true \ +--outdir $outdir \ +--samplesheet $sample_sheet \ +--pairwise_samplesheet $pairwise_samplesheet \ +--fasta $fasta \ +--smrna_fasta $smRNA_fasta \ +--gtf $genome_gtf \ +--target_genome_index $target_genome_index \ +--smrna_genome_index $smrna_genome_index \ +--fasta_fai $fasta_fai \ +--filtered_gtf $filtered_gtf \ +--chrom_sizes $chrom_sizes \ +--smrna_fasta_fai $smrna_fasta_fai \ +--smrna_chrom_sizes $smrna_chrom_sizes \ +--longest_transcript $longest_transcript \ +--longest_transcript_fai $longest_transcript_fai \ +--longest_transcript_gtf $longest_transcript_gtf \ +--seg_gtf $seg_gtf \ +--seg_filt_gtf $seg_filt_gtf \ +--seg_resolved_gtf $seg_resolved_gtf \ +--seg_resolved_gtf_genic $seg_resolved_gtf_genic \ +--regions_gtf $regions_gtf \ +--regions_filt_gtf $regions_filt_gtf \ +--regions_resolved_gtf $regions_resolved_gtf \ +--regions_resolved_gtf_genic $regions_resolved_gtf_genic \ +--move_umi_to_header true \ +--umi_header_format "${umi_header_format}" \ +--trimgalore_params "${trimgalore_params}" \ +--bowtie_params "${bowtie_params}" \ +--star_params "${star_params}" \ +--macs3_params "${macs3_params}" \ +--umi_separator "${umi_separator}" \ No newline at end of file diff --git a/tests/ARTR-seq/script/sample_prep.py b/tests/ARTR-seq/script/sample_prep.py new file mode 100644 index 0000000..774766e --- /dev/null +++ b/tests/ARTR-seq/script/sample_prep.py @@ -0,0 +1,22 @@ +import os +import pandas as pd + +# Define the directory path +sample_dir = "/nemo/lab/ulej/data/STPs/babs/inputs/hanzhong.bai/asf/PM24162/20240807_LH00442_0034_A22MYGKLT3/fastq" + +# Create a DataFrame with the specified columns +df = pd.DataFrame(columns=["group", "replicate", "fastq_1", "fastq_2"]) + +# Loop through samples A9 to A24 +for i in range(9, 25): + sample_name = f"BAI7152A{i}" + fastq_1 = os.path.join(sample_dir, f"{sample_name}_S{i+338}_L008_R1_001.fastq.gz") + replicate = 2 - (i % 2) + df = df.append({"group": "", "replicate": replicate, "fastq_1": fastq_1, "fastq_2": ""}, ignore_index=True) + +# Save the DataFrame as a CSV file +output_csv = "sample_sheet.csv" +df.to_csv(output_csv, index=False) + +print(f"Sample sheet created: {output_csv}") + diff --git a/tests/data/samplesheets/pairwise-multi-se-with-merge.csv b/tests/data/samplesheets/pairwise-multi-se-with-merge.csv new file mode 100644 index 0000000..e8ed592 --- /dev/null +++ b/tests/data/samplesheets/pairwise-multi-se-with-merge.csv @@ -0,0 +1,2 @@ +group,replicate,control_group,control_replicate +sample_1,1,sample_2,1 diff --git a/tests/subworkflows/local/parse_pairwise_input/main.nf.test b/tests/subworkflows/local/parse_pairwise_input/main.nf.test new file mode 100644 index 0000000..894250b --- /dev/null +++ b/tests/subworkflows/local/parse_pairwise_input/main.nf.test @@ -0,0 +1,37 @@ +nextflow_workflow { + + name "Test Workflow PARSE_PAIRWISE_INPUT" + script "subworkflows/local/parse_pairwise_input/main.nf" + config "tests/subworkflows/local/parse_pairwise_input/test.config" + profile "singularity" + workflow "PARSE_PAIRWISE_INPUT" + + test("Should run without failures") { + + when { + params { + // define parameters here. Example: + outdir = "${projectDir}/tests/subworkflows/local/parse_pairwise_input/output" + } + workflow { + """ + // define inputs of the workflow here. Example: + input[0] = file("${projectDir}/tests/subworkflows/local/parse_pairwise_input/pairwise_peak_calling_for_testing.csv") + """ + } + } + + then { + assert workflow.success + assert snapshot(workflow.out).match() + + // asseert the pairwise channel contains [WT_BRD4_plus_R1,WT_No_Ab_R1] + with(workflow.out.pairwise) { + assert size() == 2 + assert contains(['WT_BRD4_plus_R1', 'WT_No_Ab_R1']) + } + } + + } + +} diff --git a/tests/subworkflows/local/parse_pairwise_input/main.nf.test.snap b/tests/subworkflows/local/parse_pairwise_input/main.nf.test.snap new file mode 100644 index 0000000..92a4634 --- /dev/null +++ b/tests/subworkflows/local/parse_pairwise_input/main.nf.test.snap @@ -0,0 +1,39 @@ +{ + "Should run without failures": { + "content": [ + { + "0": [ + [ + "WT_BRD4_plus_R1", + "WT_No_Ab_R1" + ], + [ + "WT_BRD4_plus_R2", + "WT_No_Ab_R2" + ] + ], + "1": [ + + ], + "pairwise": [ + [ + "WT_BRD4_plus_R1", + "WT_No_Ab_R1" + ], + [ + "WT_BRD4_plus_R2", + "WT_No_Ab_R2" + ] + ], + "versions": [ + + ] + } + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "23.04.4" + }, + "timestamp": "2024-10-08T14:41:40.966647" + } +} \ No newline at end of file diff --git a/tests/subworkflows/local/parse_pairwise_input/output/04_whole_read/transcriptome/versions.yml b/tests/subworkflows/local/parse_pairwise_input/output/04_whole_read/transcriptome/versions.yml new file mode 120000 index 0000000..cbc997a --- /dev/null +++ b/tests/subworkflows/local/parse_pairwise_input/output/04_whole_read/transcriptome/versions.yml @@ -0,0 +1 @@ +/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/.nf-test/tests/9de90743697f22402207661d7290f0ef/work/d2/b005ec8916e667e67e3b6cbc424cdf/versions.yml \ No newline at end of file diff --git a/tests/subworkflows/local/parse_pairwise_input/pairwise_peak_calling_for_testing.csv b/tests/subworkflows/local/parse_pairwise_input/pairwise_peak_calling_for_testing.csv new file mode 100644 index 0000000..991b0a8 --- /dev/null +++ b/tests/subworkflows/local/parse_pairwise_input/pairwise_peak_calling_for_testing.csv @@ -0,0 +1,3 @@ +group,replicate,control_group,control_replicate +WT_BRD4_plus,1,WT_No_Ab,1 +WT_BRD4_plus,2,WT_No_Ab,2 diff --git a/tests/subworkflows/local/parse_pairwise_input/test.config b/tests/subworkflows/local/parse_pairwise_input/test.config new file mode 100644 index 0000000..81009f7 --- /dev/null +++ b/tests/subworkflows/local/parse_pairwise_input/test.config @@ -0,0 +1,22 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Nextflow config file for module tests +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Defines input files and everything required to run a fast and simple pipeline test. + nextflow run {{ name }} -profile test, +---------------------------------------------------------------------------------------- +*/ + +process { + errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' } +} + +params { + config_profile_name = 'Test profile' + config_profile_description = 'Minimal test dataset to check pipeline function' + + // Limit resources so that this can run on GitHub Actions + max_cpus = 4 + max_memory = '6.GB' + max_time = '6.h' +} \ No newline at end of file diff --git a/tests/subworkflows/local/prep_whole_read/GRCh38.primary_assembly.genome.fa.fai b/tests/subworkflows/local/prep_whole_read/GRCh38.primary_assembly.genome.fa.fai new file mode 100644 index 0000000..f45b3a9 --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/GRCh38.primary_assembly.genome.fa.fai @@ -0,0 +1,194 @@ +chr1 248956422 8 60 61 +chr2 242193529 253105712 60 61 +chr3 198295559 499335808 60 61 +chr4 190214555 700936301 60 61 +chr5 181538259 894321107 60 61 +chr6 170805979 1078885012 60 61 +chr7 159345973 1252537766 60 61 +chr8 145138636 1414539514 60 61 +chr9 138394717 1562097136 60 61 +chr10 133797422 1702798442 60 61 +chr11 135086622 1838825832 60 61 +chr12 133275309 1976163908 60 61 +chr13 114364328 2111660483 60 61 +chr14 107043718 2227930894 60 61 +chr15 101991189 2336758684 60 61 +chr16 90338345 2440449737 60 61 +chr17 83257441 2532293732 60 61 +chr18 80373285 2616938808 60 61 +chr19 58617616 2698651658 60 61 +chr20 64444167 2758246245 60 61 +chr21 46709983 2823764492 60 61 +chr22 50818468 2871252985 60 61 +chrX 156040895 2922918436 60 61 +chrY 57227415 3081560021 60 61 +chrM 16569 3139741236 60 61 +GL000008.2 209709 3139758105 60 61 +GL000009.2 201709 3139971333 60 61 +GL000194.1 191469 3140176427 60 61 +GL000195.1 182896 3140371111 60 61 +GL000205.2 185591 3140557079 60 61 +GL000208.1 92689 3140745787 60 61 +GL000213.1 164239 3140840044 60 61 +GL000214.1 137718 3141007044 60 61 +GL000216.2 176608 3141147081 60 61 +GL000218.1 161147 3141326656 60 61 +GL000219.1 179198 3141490512 60 61 +GL000220.1 161802 3141672720 60 61 +GL000221.1 155397 3141837242 60 61 +GL000224.1 179693 3141995252 60 61 +GL000225.1 211173 3142177963 60 61 +GL000226.1 15008 3142392679 60 61 +KI270302.1 2274 3142407961 60 61 +KI270303.1 1942 3142410296 60 61 +KI270304.1 2165 3142412294 60 61 +KI270305.1 1472 3142414519 60 61 +KI270310.1 1201 3142416039 60 61 +KI270311.1 12399 3142417284 60 61 +KI270312.1 998 3142429913 60 61 +KI270315.1 2276 3142430951 60 61 +KI270316.1 1444 3142433288 60 61 +KI270317.1 37690 3142434780 60 61 +KI270320.1 4416 3142473122 60 61 +KI270322.1 21476 3142477635 60 61 +KI270329.1 1040 3142499492 60 61 +KI270330.1 1652 3142500573 60 61 +KI270333.1 2699 3142502276 60 61 +KI270334.1 1368 3142505043 60 61 +KI270335.1 1048 3142506457 60 61 +KI270336.1 1026 3142507546 60 61 +KI270337.1 1121 3142508613 60 61 +KI270338.1 1428 3142509776 60 61 +KI270340.1 1428 3142511251 60 61 +KI270362.1 3530 3142512726 60 61 +KI270363.1 1803 3142516338 60 61 +KI270364.1 2855 3142518195 60 61 +KI270366.1 8320 3142521121 60 61 +KI270371.1 2805 3142529603 60 61 +KI270372.1 1650 3142532478 60 61 +KI270373.1 1451 3142534179 60 61 +KI270374.1 2656 3142535678 60 61 +KI270375.1 2378 3142538402 60 61 +KI270376.1 1136 3142540843 60 61 +KI270378.1 1048 3142542021 60 61 +KI270379.1 1045 3142543110 60 61 +KI270381.1 1930 3142544196 60 61 +KI270382.1 4215 3142546182 60 61 +KI270383.1 1750 3142550491 60 61 +KI270384.1 1658 3142552294 60 61 +KI270385.1 990 3142554003 60 61 +KI270386.1 1788 3142555033 60 61 +KI270387.1 1537 3142556874 60 61 +KI270388.1 1216 3142558460 60 61 +KI270389.1 1298 3142559720 60 61 +KI270390.1 2387 3142561063 60 61 +KI270391.1 1484 3142563513 60 61 +KI270392.1 971 3142565045 60 61 +KI270393.1 1308 3142566056 60 61 +KI270394.1 970 3142567409 60 61 +KI270395.1 1143 3142568419 60 61 +KI270396.1 1880 3142569605 60 61 +KI270411.1 2646 3142571540 60 61 +KI270412.1 1179 3142574254 60 61 +KI270414.1 2489 3142575476 60 61 +KI270417.1 2043 3142578030 60 61 +KI270418.1 2145 3142580131 60 61 +KI270419.1 1029 3142582335 60 61 +KI270420.1 2321 3142583405 60 61 +KI270422.1 1445 3142585788 60 61 +KI270423.1 981 3142587281 60 61 +KI270424.1 2140 3142588302 60 61 +KI270425.1 1884 3142590501 60 61 +KI270429.1 1361 3142592440 60 61 +KI270435.1 92983 3142593847 60 61 +KI270438.1 112505 3142688403 60 61 +KI270442.1 392061 3142802807 60 61 +KI270448.1 7992 3143201426 60 61 +KI270465.1 1774 3143209575 60 61 +KI270466.1 1233 3143211402 60 61 +KI270467.1 3920 3143212679 60 61 +KI270468.1 4055 3143216688 60 61 +KI270507.1 5353 3143220834 60 61 +KI270508.1 1951 3143226300 60 61 +KI270509.1 2318 3143228307 60 61 +KI270510.1 2415 3143230687 60 61 +KI270511.1 8127 3143233166 60 61 +KI270512.1 22689 3143241452 60 61 +KI270515.1 6361 3143264543 60 61 +KI270516.1 1300 3143271034 60 61 +KI270517.1 3253 3143272379 60 61 +KI270518.1 2186 3143275710 60 61 +KI270519.1 138126 3143277956 60 61 +KI270521.1 7642 3143418408 60 61 +KI270522.1 5674 3143426201 60 61 +KI270528.1 2983 3143431993 60 61 +KI270529.1 1899 3143435049 60 61 +KI270530.1 2168 3143437003 60 61 +KI270538.1 91309 3143439231 60 61 +KI270539.1 993 3143532085 60 61 +KI270544.1 1202 3143533118 60 61 +KI270548.1 1599 3143534364 60 61 +KI270579.1 31033 3143536013 60 61 +KI270580.1 1553 3143567587 60 61 +KI270581.1 7046 3143569189 60 61 +KI270582.1 6504 3143576376 60 61 +KI270583.1 1400 3143583012 60 61 +KI270584.1 4513 3143584459 60 61 +KI270587.1 2969 3143589071 60 61 +KI270588.1 6158 3143592113 60 61 +KI270589.1 44474 3143598397 60 61 +KI270590.1 4685 3143643636 60 61 +KI270591.1 5796 3143648423 60 61 +KI270593.1 3041 3143654339 60 61 +KI270706.1 175055 3143657454 60 61 +KI270707.1 32032 3143835450 60 61 +KI270708.1 127682 3143868039 60 61 +KI270709.1 66860 3143997873 60 61 +KI270710.1 40176 3144065871 60 61 +KI270711.1 42210 3144106740 60 61 +KI270712.1 176043 3144149677 60 61 +KI270713.1 40745 3144328678 60 61 +KI270714.1 41717 3144370126 60 61 +KI270715.1 161471 3144412562 60 61 +KI270716.1 153799 3144576748 60 61 +KI270717.1 40062 3144733134 60 61 +KI270718.1 38054 3144773887 60 61 +KI270719.1 176845 3144812599 60 61 +KI270720.1 39050 3144992415 60 61 +KI270721.1 100316 3145032139 60 61 +KI270722.1 194050 3145134150 60 61 +KI270723.1 38115 3145331458 60 61 +KI270724.1 39555 3145370232 60 61 +KI270725.1 172810 3145410470 60 61 +KI270726.1 43739 3145586184 60 61 +KI270727.1 448248 3145630675 60 61 +KI270728.1 1872759 3146086417 60 61 +KI270729.1 280839 3147990412 60 61 +KI270730.1 112551 3148275955 60 61 +KI270731.1 150754 3148390405 60 61 +KI270732.1 41543 3148543695 60 61 +KI270733.1 179772 3148585954 60 61 +KI270734.1 165050 3148768746 60 61 +KI270735.1 42811 3148936570 60 61 +KI270736.1 181920 3148980118 60 61 +KI270737.1 103838 3149165093 60 61 +KI270738.1 99375 3149270685 60 61 +KI270739.1 73985 3149371740 60 61 +KI270740.1 37240 3149446982 60 61 +KI270741.1 157432 3149484866 60 61 +KI270742.1 186739 3149644945 60 61 +KI270743.1 210658 3149834820 60 61 +KI270744.1 168472 3150049012 60 61 +KI270745.1 41891 3150220315 60 61 +KI270746.1 66486 3150262928 60 61 +KI270747.1 198735 3150330546 60 61 +KI270748.1 93321 3150532617 60 61 +KI270749.1 158759 3150627517 60 61 +KI270750.1 148850 3150788945 60 61 +KI270751.1 150742 3150940299 60 61 +KI270752.1 27745 3151093577 60 61 +KI270753.1 62944 3151121808 60 61 +KI270754.1 40191 3151185825 60 61 +KI270755.1 36723 3151226709 60 61 +KI270756.1 79590 3151264068 60 61 +KI270757.1 71251 3151345008 60 61 diff --git a/tests/subworkflows/local/prep_whole_read/WT_BRD4_plus_R1.unique_genome.dedup.subsampled.bam b/tests/subworkflows/local/prep_whole_read/WT_BRD4_plus_R1.unique_genome.dedup.subsampled.bam new file mode 100644 index 0000000..c49eb6a Binary files /dev/null and b/tests/subworkflows/local/prep_whole_read/WT_BRD4_plus_R1.unique_genome.dedup.subsampled.bam differ diff --git a/tests/subworkflows/local/prep_whole_read/WT_BRD4_plus_R1.unique_genome.dedup.subsampled.bam.bai b/tests/subworkflows/local/prep_whole_read/WT_BRD4_plus_R1.unique_genome.dedup.subsampled.bam.bai new file mode 100644 index 0000000..80ebba4 Binary files /dev/null and b/tests/subworkflows/local/prep_whole_read/WT_BRD4_plus_R1.unique_genome.dedup.subsampled.bam.bai differ diff --git a/tests/subworkflows/local/prep_whole_read/main.nf.test b/tests/subworkflows/local/prep_whole_read/main.nf.test new file mode 100644 index 0000000..4249c9f --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/main.nf.test @@ -0,0 +1,43 @@ +nextflow_workflow { + + name "Test Workflow PREP_WHOLE_READ" + script "subworkflows/local/prep_whole_read/main.nf" + config "tests/subworkflows/local/prep_whole_read/test.config" + workflow "PREP_WHOLE_READ" + + test("genome whole read analysis") { + + when { + params { + // define parameters here. Example: + outdir = "${projectDir}/tests/subworkflows/local/prep_whole_read/output" + } + workflow { + """ + // define inputs of the workflow here. Example: + + input[0] = channel.of( + tuple( + [id: 'WT_BRD4_plus_R1', group: 'WT_BRD4_plus', replicate: 1, single_end: true], + file("${projectDir}/tests/subworkflows/local/prep_whole_read/WT_BRD4_plus_R1.unique_genome.dedup.subsampled.bam") + ) + ) + input[1] = channel.of( + tuple( + [id: 'WT_BRD4_plus_R1', group: 'WT_BRD4_plus', replicate: 1, single_end: true], + file("${projectDir}/tests/subworkflows/local/prep_whole_read/WT_BRD4_plus_R1.unique_genome.dedup.subsampled.bam.bai") + ) + ) + input[2] = file("${projectDir}/tests/subworkflows/local/prep_whole_read/GRCh38.primary_assembly.genome.fa.fai") + """ + } + } + + then { + assert workflow.success + assert snapshot(workflow.out).match() + } + + } + +} diff --git a/tests/subworkflows/local/prep_whole_read/main.nf.test.snap b/tests/subworkflows/local/prep_whole_read/main.nf.test.snap new file mode 100644 index 0000000..4f3df1e --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/main.nf.test.snap @@ -0,0 +1,91 @@ +{ + "genome whole read analysis": { + "content": [ + { + "0": [ + [ + { + "id": "WT_BRD4_plus_R1", + "group": "WT_BRD4_plus", + "replicate": 1, + "single_end": true + }, + "WT_BRD4_plus_R1_unique_transcriptome_plus.bam:md5,ae127b2cac380fe339aeec891d6b9a8b" + ] + ], + "1": [ + [ + { + "id": "WT_BRD4_plus_R1", + "group": "WT_BRD4_plus", + "replicate": 1, + "single_end": true + }, + "WT_BRD4_plus_R1_unique_transcriptome_neg.bam:md5,5e78995bc09ceb1697cae6089cd92948" + ] + ], + "2": [ + [ + { + "id": "WT_BRD4_plus_R1", + "group": "WT_BRD4_plus", + "replicate": 1, + "single_end": true + }, + "WT_BRD4_plus_R1.bed:md5,4154ae3205761247f0d34369bd35ef24" + ] + ], + "3": [ + "versions.yml:md5,521d4bdfc9cd894d9f308f289f6b4d12", + "versions.yml:md5,72c64a635a623b2727531efef33bb2a9", + "versions.yml:md5,965df4a8dc27b395932172b6566f6c49", + "versions.yml:md5,b0349334704ce14fbbe846c940ffa7dc" + ], + "bam_minus": [ + [ + { + "id": "WT_BRD4_plus_R1", + "group": "WT_BRD4_plus", + "replicate": 1, + "single_end": true + }, + "WT_BRD4_plus_R1_unique_transcriptome_neg.bam:md5,5e78995bc09ceb1697cae6089cd92948" + ] + ], + "bam_plus": [ + [ + { + "id": "WT_BRD4_plus_R1", + "group": "WT_BRD4_plus", + "replicate": 1, + "single_end": true + }, + "WT_BRD4_plus_R1_unique_transcriptome_plus.bam:md5,ae127b2cac380fe339aeec891d6b9a8b" + ] + ], + "bed": [ + [ + { + "id": "WT_BRD4_plus_R1", + "group": "WT_BRD4_plus", + "replicate": 1, + "single_end": true + }, + "WT_BRD4_plus_R1.bed:md5,4154ae3205761247f0d34369bd35ef24" + ] + ], + "versions": [ + "versions.yml:md5,521d4bdfc9cd894d9f308f289f6b4d12", + "versions.yml:md5,72c64a635a623b2727531efef33bb2a9", + "versions.yml:md5,965df4a8dc27b395932172b6566f6c49", + "versions.yml:md5,b0349334704ce14fbbe846c940ffa7dc" + ] + } + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.04.4" + }, + "timestamp": "2024-10-24T09:25:08.105192974" + } +} \ No newline at end of file diff --git a/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1.norm.transcriptome.cmd.bedgraph b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1.norm.transcriptome.cmd.bedgraph new file mode 120000 index 0000000..65b34d6 --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1.norm.transcriptome.cmd.bedgraph @@ -0,0 +1 @@ +/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/.nf-test/tests/9de90743697f22402207661d7290f0ef/work/42/c228bcbd0d01754fcb588380b69ba1/WT_BRD4_plus_R1.norm.transcriptome.cmd.bedgraph \ No newline at end of file diff --git a/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1.transcriptome.cmd.bedgraph b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1.transcriptome.cmd.bedgraph new file mode 120000 index 0000000..06bc6f5 --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1.transcriptome.cmd.bedgraph @@ -0,0 +1 @@ +/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/.nf-test/tests/9de90743697f22402207661d7290f0ef/work/b7/fa433febd5cb247e5a6c5c50f78515/WT_BRD4_plus_R1.transcriptome.cmd.bedgraph \ No newline at end of file diff --git a/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1_unique_transcriptome_neg.bam b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1_unique_transcriptome_neg.bam new file mode 120000 index 0000000..61ab71a --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1_unique_transcriptome_neg.bam @@ -0,0 +1 @@ +/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/.nf-test/tests/9de90743697f22402207661d7290f0ef/work/21/1c631abc7432beffabf512ef965207/WT_BRD4_plus_R1_unique_transcriptome_neg.bam \ No newline at end of file diff --git a/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1_unique_transcriptome_plus.bam b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1_unique_transcriptome_plus.bam new file mode 120000 index 0000000..bc3e1a8 --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/WT_BRD4_plus_R1_unique_transcriptome_plus.bam @@ -0,0 +1 @@ +/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/.nf-test/tests/9de90743697f22402207661d7290f0ef/work/9a/2e6bec2c7be93d1a5b3c402ed8728d/WT_BRD4_plus_R1_unique_transcriptome_plus.bam \ No newline at end of file diff --git a/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/versions.yml b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/versions.yml new file mode 120000 index 0000000..fbe6ae4 --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/output/04_whole_read/transcriptome/versions.yml @@ -0,0 +1 @@ +/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/.nf-test/tests/9de90743697f22402207661d7290f0ef/work/19/6b35205c44dce41e180a289b55604a/versions.yml \ No newline at end of file diff --git a/tests/subworkflows/local/prep_whole_read/test.config b/tests/subworkflows/local/prep_whole_read/test.config new file mode 100644 index 0000000..cc0ca17 --- /dev/null +++ b/tests/subworkflows/local/prep_whole_read/test.config @@ -0,0 +1,322 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Nextflow config file for module tests +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Defines input files and everything required to run a fast and simple pipeline test. + nextflow run {{ name }} -profile test, +---------------------------------------------------------------------------------------- +*/ + +// Global default params, used in configs +params { + config_profile_name = 'Test profile' + config_profile_description = 'Minimal test dataset to check pipeline function' + + outdir = "${projectDir}/tests/subworkflows/local/prep_whole_read/output" + tracedir = "${params.outdir}/pipeline_info" + publish_dir_mode = 'symlink' + monochrome_logs = false + debug = false + ignore_params = "run_genome_prep,run_input_check,run_trim_galore_fastqc,run_alignment,run_read_filter,run_umi_dedup,run_calc_crosslinks,run_peak_calling,run_reporting,only_input,only_genome,only_trimming,only_alignment,only_filtering,only_dedup,only_crosslinks,only_peakcalling" + multiqc_title = null + + // Max resource options + max_memory = '32.GB' + max_cpus = 8 + max_time = '6.h' + + // Input params + samplesheet = null + fasta = null + smrna_fasta = null + gtf = null + target_genome_index = null + smrna_genome_index = null + fasta_fai = null + filtered_gtf = null + chrom_sizes = "/nemo/lab/ulej/home/users/baih/Reference/clip-seq_prepared_genomes/00_genome/GRCh38.primary_assembly.genome.fa.sizes" + smrna_fasta_fai = null + smrna_chrom_sizes = null + longest_transcript = null + longest_transcript_fai = null + longest_transcript_gtf = null + seg_gtf = null + seg_filt_gtf = null + seg_resolved_gtf = null + seg_resolved_gtf_genic = null + regions_gtf = null + regions_filt_gtf = null + regions_resolved_gtf = null + regions_resolved_gtf_genic = null + + // logic params + only_moveumitoheader = false + only_input = false + only_genome = false + only_trimming = false + only_alignment = false + only_filtering = false + only_dedup = false + only_crosslinks = false + only_peakcalling = false + skip_fastqc = false + skip_trimming = false + skip_umi_dedupe = false + + // Output params + save_reference = true + save_indexes = true + save_merged_fastq = true + save_trimmed = true + save_align_intermed = true + save_unaligned_res = true + + // Pipeline params + encode_eclip = false + move_umi_to_header = false + umi_header_format = null + save_unaligned = true // DO NOT CHANGE + umi_separator = "rbc:" + paraclu_min_value = 10 + trimgalore_params = "--fastqc --length 10 -q 20" + bowtie_params = "-v 2 -m 100 --norc --best --strata" + star_params = "--outFilterMultimapNmax 100 --outFilterMultimapScoreRange 1 --outSAMattributes All --alignSJoverhangMin 8 --alignSJDBoverhangMin 1 --outFilterType BySJout --alignIntronMin 20 --alignIntronMax 1000000 --outFilterScoreMin 10 --alignEndsType Extend5pOfRead1 --twopassMode Basic" + clippy_params = "" + icount_peaks_params = "" + peka_params = "" + + // Whole read analysis params + whole_read_analysis = false + pairwise_samplesheet= null + macs_gsize = "hs" + macs3_params = "--keep-dup all --nomodel --extsize 30 --bdg" +} + +// Process specifics settings +process { + // WHOLE READ PREPARATION + withName: 'BEDTOOLS_BAMTOBED' { + ext.args = '-split' + publishDir = [ + enabled: false + ] + } + + + withName: 'BEDTOOLS_GENOMECOV_POS' { + ext.args = '-bg -strand +' + publishDir = [ + enabled: false + ] + } + + withName: 'BEDTOOLS_GENOMECOV_NEG' { + ext.args = '-bg -strand -' + publishDir = [ + enabled: false + ] + } + + // Transcriptome + withName: 'SAMTOOLS_VIEW_PLUS' { + ext.prefix = { "${meta.id}_unique_transcriptome_plus" } + ext.args = "-F 16 --output-fmt bam" + publishDir = [ + path: { "${params.outdir}/04_whole_read/transcriptome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'SAMTOOLS_VIEW_MINUS' { + ext.prefix = { "${meta.id}_unique_transcriptome_neg" } + ext.args = "-f 16 --output-fmt bam" + publishDir = [ + path: { "${params.outdir}/04_whole_read/transcriptome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'BIGWIG_POS' { + ext.prefix = { "${meta.id}.transcriptome.pos" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/transcriptome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } + + withName: 'BIGWIG_NEG' { + ext.prefix = { "${meta.id}.transcriptome.neg" } + publishDir = [ + path: { "${params.outdir}/04_whole_read/transcriptome" }, + mode: "${params.publish_dir_mode}", + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + } +} + +// Load base.config by default for all pipelines +includeConfig '/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/conf/base.config' + +// Load pipeline switching config +includeConfig '/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/conf/logic.config' + +profiles { + debug { process.beforeScript = 'echo $HOSTNAME' } + crick { includeConfig '/nemo/lab/ulej/home/users/baih/PM24162/goodwright_clipseq/clipseq/conf/crick.config' } + conda { + conda.enabled = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + mamba { + conda.enabled = true + conda.useMamba = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + docker { + docker.enabled = true + docker.userEmulation = true + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + singularity { + singularity.enabled = true + singularity.autoMounts = true + docker.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + podman { + podman.enabled = true + docker.enabled = false + singularity.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + shifter { + shifter.enabled = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + charliecloud.enabled = false + } + charliecloud { + charliecloud.enabled = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + } + gitpod { + executor.name = 'local' + executor.cpus = 16 + executor.memory = 60.GB + } + arm { + docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64' + } +} + +// Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile +// Will not be used unless Apptainer / Docker / Podman / Singularity are enabled +// Set to your registry if you have a mirror of containers +apptainer.registry = 'quay.io' +docker.registry = 'quay.io' +podman.registry = 'quay.io' +singularity.registry = 'quay.io' + +// Export these variables to prevent local Python/R libraries from conflicting with those in the container +// The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container. +// See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable. + +env { + PYTHONNOUSERSITE = 1 + R_PROFILE_USER = "/.Rprofile" + R_ENVIRON_USER = "/.Renviron" + JULIA_DEPOT_PATH = "/usr/local/share/julia" +} + +// Capture exit codes from upstream processes when piping +process.shell = ['/bin/bash', '-euo', 'pipefail'] + +def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') +timeline { + enabled = true + file = "${params.tracedir}/execution_timeline_${trace_timestamp}.html" +} +report { + enabled = true + file = "${params.tracedir}/execution_report_${trace_timestamp}.html" +} +trace { + enabled = true + file = "${params.tracedir}/execution_trace_${trace_timestamp}.txt" +} +dag { + enabled = true + file = "${params.tracedir}/pipeline_dag_${trace_timestamp}.html" +} + +manifest { + name = 'goodwright/clipseq' + author = '' + homePage = 'https://github.com/goodwright/clipseq' + description = '' + mainScript = 'main.nf' + nextflowVersion = '!>=22.10.1' + version = '1.0dev' + doi = '' +} + + + + + +// Function to ensure that resource requirements don't go beyond +// a maximum limit +def check_max(obj, type) { + if (type == 'memory') { + try { + if (obj.compareTo(params.max_memory as nextflow.util.MemoryUnit) == 1) + return params.max_memory as nextflow.util.MemoryUnit + else + return obj + } catch (all) { + println " ### ERROR ### Max memory '${params.max_memory}' is not valid! Using default value: $obj" + return obj + } + } else if (type == 'time') { + try { + if (obj.compareTo(params.max_time as nextflow.util.Duration) == 1) + return params.max_time as nextflow.util.Duration + else + return obj + } catch (all) { + println " ### ERROR ### Max time '${params.max_time}' is not valid! Using default value: $obj" + return obj + } + } else if (type == 'cpus') { + try { + return Math.min( obj, params.max_cpus as int ) + } catch (all) { + println " ### ERROR ### Max cpus '${params.max_cpus}' is not valid! Using default value: $obj" + return obj + } + } +} + +// Nextflow settings +nextflow.enable.configProcessNamesValidation = false \ No newline at end of file