nf-core · edmundmiller · Oct 12, 2022 · Aug 29, 2022 · Aug 31, 2022 · Aug 31, 2022
diff --git a/.github/workflows/local_modules.yml b/.github/workflows/local_modules.yml
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,14 +9,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - [[#28](https://github.com/nf-core/nascent/issues/28)] - Added DRAGMAP alignment
 - [[#64](https://github.com/nf-core/nascent/pull/64)] - Added CHM13 igenomes config
+- [[#39](https://github.com/nf-core/nascent/issues/39)] - Add PINTS for TSS identification
 
 ### `Fixed`
 
 - [[#33](https://github.com/nf-core/nascent/issues/33)] - groHMM works on full runs. Added the keep standard chromosomes function to standardize bam files.
 
 ### `Dependencies`
 
-- Updated Nextflow version to `v21.10.3`
+- Updated Nextflow version to `v21.10.6`
 
 ### `Deprecated`
 

diff --git a/CITATIONS.md b/CITATIONS.md
@@ -48,6 +48,10 @@
 
   > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
 
+- [PINTS](https://pints.yulab.org/)
+
+  > Yao, L., Liang, J., Ozer, A. et al. A comparison of experimental assays and analytical methods for genome-wide identification of active enhancers. Nat Biotechnol 40, 1056–1065 (2022). https://doi.org/10.1038/s41587-022-01211-7
+
 - [preseq](https://pubmed.ncbi.nlm.nih.gov/23435259/)
 
   > Daley T, Smith AD. Predicting the molecular complexity of sequencing libraries. Nat Methods. 2013 Apr;10(4):325-7. doi: 10.1038/nmeth.2375. Epub 2013 Feb 24. PubMed PMID: 23435259; PubMed Central PMCID: PMC3612374.

diff --git a/bin/bed2saf.py b/bin/bed2saf.py
diff --git a/conf/modules.config b/conf/modules.config
@@ -118,6 +118,7 @@ process {
     }
 
     withName: SUBREAD_FEATURECOUNTS_PREDICTED {
+        ext.prefix = { "${meta.id}-group_${annotation.baseName}-transcripts" }
         ext.args = "-F \"SAF\""
         publishDir = [
             path: { "${params.outdir}/${params.aligner}/featurecounts/predicted" },
@@ -126,26 +127,47 @@ process {
     }
 
     withName: GROHMM_PARAMETERTUNING {
-        ext.when = { params.transcript_identification == "grohmm" && !params.skip_tuning }
+        ext.when = { !params.skip_grohmm && !params.skip_tuning && params.assay_type == "GROseq" }
     }
 
     withName: GROHMM_TRANSCRIPTCALLING {
-        ext.when = { params.transcript_identification == "grohmm" }
+        ext.when = { !params.skip_grohmm && params.assay_type == "GROseq" }
     }
 
     withName: HOMER_FINDPEAKS {
-        ext.when = { params.transcript_identification == "homer" }
-        ext.args = "-style factor"
+        ext.when = { params.assay_type == "GROseq" }
+        // TODO Handle other assays
+        ext.args = "-style groseq"
     }
 
     withName: HOMER_MAKETAGDIRECTORY {
-        ext.when = { params.transcript_identification == "homer" }
+        ext.when = { params.assay_type == "GROseq" }
         ext.args = "-checkGC"
     }
 
     withName: HOMER_MAKEUCSCFILE {
-        ext.when = { params.transcript_identification == "homer" }
+        ext.when = { params.assay_type == "GROseq" }
         ext.args = "-strand separate"
     }
 
+    withName: PINTS_CALLER {
+        ext.args = { "--exp-type $params.assay_type" }
+        ext.singularity_pull_docker_container = true
+    }
+
+    withName: BEDTOOLS_SORT {
+        ext.prefix = { "${meta.id}_sorted" }
+    }
+
+    withName: BEDTOOLS_MERGE {
+        ext.args = "-header"
+        ext.prefix = { "${meta.id}_merged" }
+    }
+
+    withName: BEDTOOLS_INTERSECT_FILTER {
+        ext.when = { params.filter_bed }
+        ext.prefix = { "${meta.id}_filtered" }
+        ext.args = { no_overlap ? "-v": "" }
+    }
+
 }
diff --git a/conf/test.config b/conf/test.config
@@ -20,10 +20,21 @@ params {
     max_time   = '6.h'
 
     // Input data
-    input = "${baseDir}/assets/samplesheet.csv"
+    input = "${projectDir}/assets/samplesheet.csv"
 
     // Genome references
     fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/nascent/reference/GRCh38_chr21.fa'
     gtf = 's3://ngi-igenomes/igenomes/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf'
+
+    assay_type = "GROseq"
+    skip_grohmm = true
     tuning_file = "${projectDir}/tests/subworkflows/local/grohmm/tuningparams_small.csv"
+    filter_bed = "${projectDir}/tests/samplesheets/region.bed"
+}
+
+process {
+    // FIXME https://github.com/hyulab/PINTS/issues/12
+    withName: PINTS_CALLER {
+        ext.when = false
+    }
 }
diff --git a/conf/test_copro.config b/conf/test_copro.config
@@ -0,0 +1,23 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/nascent -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'CoPRO PINTS Test profile'
+    config_profile_description = 'Test dataset to check PINTS pipeline function(https://pints.yulab.org/tre_calling#part-iv-case-2)'
+
+    // Input data
+    input = "${projectDir}/tests/samplesheets/copro.csv"
+
+    genome = 'hg38'
+    assay_type = 'CoPRO'
+    filter_bed = "https://pints.yulab.org/ref/examples/promoters_1kb_tss_centered.bed.gz"
+}
diff --git a/conf/test_grocap.config b/conf/test_grocap.config
@@ -0,0 +1,23 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/nascent -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'GROcap PINTS Test profile'
+    config_profile_description = 'Test dataset to check PINTS pipeline function(https://pints.yulab.org/tre_calling#part-iii-case-1)'
+
+    // Input data
+    input = "${projectDir}/tests/samplesheets/grocap.csv"
+
+    genome = 'hg38'
+    assay_type = 'GROcap'
+    filter_bed = "https://pints.yulab.org/ref/examples/promoters_1kb_tss_centered.bed.gz"
+}