Output dexseq file [CW-6285]

CHANGELOG.md

@@ -6,20 +6,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 ### Changed
-- Updated to wf-template v5.6.1, changing:
+- Updated to wf-template v5.6.2, changing:
     - Reduce verbosity of debug logging from fastcat which can occasionally occlude errors found in FASTQ files during ingress.
     - Log banner art to say "EPI2ME" instead of "EPI2ME Labs" to match current branding. This has no effect on the workflow outputs.
     - pre-commit configuration to resolve an internal dependency problem with flake8. This has no effect on the workflow.
     - Stringtie updated to v2.2.3, which fixes stalling at transcriptome assembly step.
     - Gffcompare updated to v0.12.6, which fixes issue where ref_gene_id was assigned an nan value.
 ### Fixed
-- Updated to wf-template v5.6.1, fixing:
+- Updated to wf-template v5.6.2, fixing:
     - dacite.exceptions.WrongTypeError during report generation when barcode is null.
     - Sequence summary read length N50 incorrectly displayed minimum read length, it now correctly shows the N50.
     - Sequence summary component alignment and coverage plots failed to plot under some conditions.
 - Error in `deAnalysis` process - `mode(counts) %in% "numeric" is not TRUE` - caused by hyphens in sample sheet aliases.
 - Error in `deAnalysis` process - `values in 'transcripts$tx_strand' must be "+" or "-"`.
   - The workflow will now filter out any unstranded annotations from downstream analysis and log a warning.
+- Output the `results_dexseq.tsv` file when `--de_analysis` enabled.
 
 ## [v1.7.0]
 ### Changed

bin/workflow_glue/wfg_helpers/configure_igv.py

@@ -107,10 +107,11 @@ class TrackBuilder:
         if idx_basename == f"{basename}.gzi" and basename.endswith(".gz"):
             self.gzi = ref_index
 
-    def parse_fnames(self, fofn):
+    def parse_fnames(self, fofn, keep_track_order=False):
-        """Parse list with filenames and return them grouped.
+        """Parse list with filenames and set self with samples info per track.
 
         :param fofn: File with list of file names (one per line)
+        :param keep_track_order: Keep track order as in the list of file names.
         """
         tmp_samples = {}
         with open(fofn, "r") as f:
@@ -134,14 +135,18 @@ class TrackBuilder:
                             tmp_samples["NO_SAMPLE"] = SampleBundle(sample="NO_SAMPLE")
                         tmp_samples["NO_SAMPLE"].append(fname)
         # Re-order samples in dict and add them to the list, leaving
-        # NO_SAMPLE as last
+        # NO_SAMPLE
-        sorted_samples = (
+        samples = {
-            sorted([sample for sample in tmp_samples.keys() if sample != 'NO_SAMPLE'])
+            sample_name: sample_content
-        )
+            for sample_name, sample_content in tmp_samples.items()
-        if 'NO_SAMPLE' in tmp_samples.keys():
+            if sample_name != "NO_SAMPLE"
-            sorted_samples += ['NO_SAMPLE']
+        }
-        for sample in sorted_samples:
+        if not keep_track_order:
-            self.samples[sample] = tmp_samples[sample]
+            samples = dict(sorted(samples.items()))
+        # Add NO_SAMPLE as last
+        if "NO_SAMPLE" in tmp_samples.keys():
+            samples.update({"NO_SAMPLE": tmp_samples["NO_SAMPLE"]})
+        self.samples = samples
 
     def build_igv_json(self):
         """Ensure there is a reference genome."""
@@ -171,12 +176,22 @@ class TrackBuilder:
             bundle.process_data()
             # Add the bundled data to the tracks
             for fname, index, file_fmt in bundle.data_bundles:
+                # Check if there are custom opts per track
+                if sample != "NO_SAMPLE" and isinstance(
+                    self.extra_opts_lookups[file_fmt], list
+                ):
+                    sample_info = {}
+                    for e in self.extra_opts_lookups[file_fmt]:
+                        sample_info.update(e)
+                    extra_opts_lookups_track = sample_info[sample]
+                else:
+                    extra_opts_lookups_track = self.extra_opts_lookups[file_fmt]
                 self.add_track(
                     fname,
                     file_fmt,
                     sample_name=sample if sample != "NO_SAMPLE" else None,
                     index=index,
-                    extra_opts=self.extra_opts_lookups[file_fmt],
+                    extra_opts=extra_opts_lookups_track,
                 )
 
     def add_track(self, infile, file_fmt, sample_name=None, index=None, extra_opts={}):
@@ -325,7 +340,7 @@ def main(args):
     )
 
     # Import files
-    igv_builder.parse_fnames(args.fofn)
+    igv_builder.parse_fnames(args.fofn, args.keep_track_order)
 
     # initialise the IGV options dict with the reference options
     igv_builder.build_igv_json()
@@ -335,7 +350,6 @@ def main(args):
         igv_builder.add_locus(args.locus)
 
     json.dump(igv_builder.igv_json, sys.stdout, indent=4)
-
     logger.info("Printed IGV config JSON to STDOUT.")
 
 
@@ -350,6 +364,11 @@ def argparser():
             "(one filename per line)"
         ),
     )
+    parser.add_argument(
+        "--keep-track-order",
+        action="store_true",
+        help="Keep track order as provided in fofn",
+    )
     parser.add_argument(
         "--locus",
         help="Locus string to set initial genomic coordinates to display in IGV",

lib/common.nf

@@ -28,6 +28,7 @@ process configure_igv {
         val locus_str
         val aln_extra_opts
         val var_extra_opts
+        val keep_track_order
     output: path "igv.json"
     script:
     // the locus argument just makes sure that the initial view in IGV shows something
@@ -43,6 +44,8 @@ process configure_igv {
         var_extra_opts ? new JsonBuilder(var_extra_opts).toPrettyString() : ""
     String var_extra_opts_arg = \
         var_extra_opts ? "--extra-vcf-opts extra-var-opts.json" : ""
+    String keep_track_order_arg = \
+        keep_track_order ? "--keep-track-order" : ""
     """
     # write out JSON files with extra options for the alignment and variant tracks
     echo '$aln_opts_json_str' > extra-aln-opts.json
@@ -53,6 +56,7 @@ process configure_igv {
         $locus_arg \
         $aln_extra_opts_arg \
         $var_extra_opts_arg \
+        $keep_track_order_arg \
     > igv.json
     """
 }

main.nf

@@ -919,6 +919,7 @@ workflow pipeline {
                 Channel.of(null), // igv locus
                 [displayMode: "SQUISHED", colorBy: "strand"], // bam extra opts
                 Channel.of(null), // vcf extra opts
+                Channel.of(false), // keep_track_order opts
                 )
 
             results = results.concat(igv_conf.map{ [it, null]})

nextflow.config

@@ -94,9 +94,9 @@ params {
         "--ref_genome 'wf-transcriptomes-demo/hg38_chr20.fa'",
         "--sample_sheet 'wf-transcriptomes-demo/sample_sheet.csv'",
       ]
-    agent = null
+      agent = null
-    container_sha = "shaaaf20a5a0e76f9e18bad21af639a6b69e4a31a2f"
+      container_sha = "shaaaf20a5a0e76f9e18bad21af639a6b69e4a31a2f"
-	common_sha = "sha1c69fd30053aad5d516e9567b3944384325a0fee"
+      common_sha = "sha72f3517dd994984e0e2da0b97cb3f23f8540be4b"
     }
 }
 

nextflow_schema.json

@@ -318,7 +318,8 @@
                 },
                 "store_dir": {
                     "type": "string",
-                    "hidden": true
+                    "hidden": true,
+                    "format" : "directory-path"
                 },
                 "disable_ping": {
                     "type": "boolean",

subworkflows/differential_expression.nf

@@ -192,7 +192,7 @@ workflow differential_expression {
             analysis.gene_counts, analysis.dge, analysis.dexseq,
             analysis.stageR, sample_sheet, merged, ref_annotation, merged_TPM, analysis.unflt_counts).collect()
         // Concat files required to be output to user without any changes
-        de_outputs_concat = analysis.cpm.concat(plotResults.out.dtu_plots, analysis.dge_pdf, analysis.dge_tsv,
+        de_outputs_concat = analysis.cpm.concat(analysis.dexseq, plotResults.out.dtu_plots, analysis.dge_pdf, analysis.dge_tsv,
         analysis.dtu_gene, analysis.dtu_transcript, analysis.dtu_stageR, analysis.dtu_pdf, merged_TPM).collect()
         collected_de_alignment_stats = mapped.align_stats.collect()
 emit: