From a670aed1c935aaff76aba43d84aa89124fbeb7fb Mon Sep 17 00:00:00 2001
From: Robrecht Cannoodt <rcannood@gmail.com>
Date: Thu, 4 Jul 2024 15:59:16 +0200
Subject: [PATCH] add missing metadata

---
 .../config.vsh.yaml                           | 14 ++++
 .../bd_rhapsody_make_reference/help.txt       | 66 +++++++++++++++++++
 2 files changed, 80 insertions(+)
 create mode 100644 src/bd_rhapsody/bd_rhapsody_make_reference/help.txt

diff --git a/src/bd_rhapsody/bd_rhapsody_make_reference/config.vsh.yaml b/src/bd_rhapsody/bd_rhapsody_make_reference/config.vsh.yaml
index 5f7c35bd..4554bc34 100644
--- a/src/bd_rhapsody/bd_rhapsody_make_reference/config.vsh.yaml
+++ b/src/bd_rhapsody/bd_rhapsody_make_reference/config.vsh.yaml
@@ -9,6 +9,13 @@ description: |
   
   - STAR index
   - Filtered GTF file
+keywords: [genome, reference, index, align]
+links:
+  repository: https://bitbucket.org/CRSwDev/cwl/src/master/v2.2.1/Extra_Utilities/
+  documentation: https://bd-rhapsody-bioinfo-docs.genomics.bd.com/resources/extra_utilities.html#make-rhapsody-reference
+license: Unknown
+requirements:
+  commands: [ "cwl-runner" ]
 argument_groups:
   - name: Inputs
     arguments:
@@ -101,14 +108,17 @@ argument_groups:
         example: --limitGenomeGenerateRAM 48000 --genomeSAindexNbases 11
         info:
           config_key: Extra_STAR_params
+
 resources:
   - type: python_script
     path: script.py
   - path: make_rhap_reference_2.2.1_nodocker.cwl
+
 test_resources:
   - type: bash_script
     path: test.sh
   - path: test_data
+
 engines:
   - type: docker
     image: bdgenomics/rhapsody:2.2.1
@@ -117,6 +127,10 @@ engines:
         packages: [procps]
       - type: python
         packages: [cwlref-runner, cwl-runner]
+      - type: docker
+        run: |
+          echo "bdgenomics/rhapsody: 2.2.1" > /var/software_versions.txt
+
 runners:
   - type: executable
   - type: nextflow
diff --git a/src/bd_rhapsody/bd_rhapsody_make_reference/help.txt b/src/bd_rhapsody/bd_rhapsody_make_reference/help.txt
new file mode 100644
index 00000000..cd038b25
--- /dev/null
+++ b/src/bd_rhapsody/bd_rhapsody_make_reference/help.txt
@@ -0,0 +1,66 @@
+```bash
+cwl-runner src/bd_rhapsody/bd_rhapsody_make_reference/make_rhap_reference_2.2.1_nodocker.cwl --help
+```
+
+usage: src/bd_rhapsody/bd_rhapsody_make_reference/make_rhap_reference_2.2.1_nodocker.cwl
+       [-h] [--Archive_prefix ARCHIVE_PREFIX]
+       [--Extra_STAR_params EXTRA_STAR_PARAMS]
+       [--Extra_sequences EXTRA_SEQUENCES] [--Filtering_off] --Genome_fasta
+       GENOME_FASTA --Gtf GTF [--Maximum_threads MAXIMUM_THREADS]
+       [--Mitochondrial_Contigs MITOCHONDRIAL_CONTIGS] [--WTA_Only]
+       [job_order]
+
+The Reference Files Generator creates an archive containing Genome Index and
+Transcriptome annotation files needed for the BD Rhapsodyâ„¢ Sequencing
+Analysis Pipeline. The app takes as input one or more FASTA and GTF files and
+produces a compressed archive in the form of a tar.gz file. The archive
+contains:\n - STAR index\n - Filtered GTF file
+
+positional arguments:
+  job_order             Job input json file
+
+options:
+  -h, --help            show this help message and exit
+  --Archive_prefix ARCHIVE_PREFIX
+                        A prefix for naming the compressed archive file
+                        containing the Reference genome index and annotation
+                        files. The default value is constructed based on the
+                        input Reference files.
+  --Extra_STAR_params EXTRA_STAR_PARAMS
+                        Additional parameters to pass to STAR when building
+                        the genome index. Specify exactly like how you would
+                        on the command line. Example: --limitGenomeGenerateRAM
+                        48000 --genomeSAindexNbases 11
+  --Extra_sequences EXTRA_SEQUENCES
+                        Additional sequences in FASTA format to use when
+                        building the STAR index. (E.g. phiX genome)
+  --Filtering_off       By default the input Transcript Annotation files are
+                        filtered based on the gene_type/gene_biotype
+                        attribute. Only features having the following
+                        attribute values are are kept: - protein_coding -
+                        lncRNA (lincRNA and antisense for Gencode <
+                        v31/M22/Ensembl97) - IG_LV_gene - IG_V_gene -
+                        IG_V_pseudogene - IG_D_gene - IG_J_gene -
+                        IG_J_pseudogene - IG_C_gene - IG_C_pseudogene -
+                        TR_V_gene - TR_V_pseudogene - TR_D_gene - TR_J_gene -
+                        TR_J_pseudogene - TR_C_gene If you have already pre-
+                        filtered the input Annotation files and/or wish to
+                        turn-off the filtering, please set this option to
+                        True.
+  --Genome_fasta GENOME_FASTA
+                        Reference genome file in FASTA format. The BD
+                        Rhapsodyâ„¢ Sequencing Analysis Pipeline uses GRCh38
+                        for Human and GRCm39 for Mouse.
+  --Gtf GTF             Transcript annotation files in GTF format. The BD
+                        Rhapsodyâ„¢ Sequencing Analysis Pipeline uses Gencode
+                        v42 for Human and M31 for Mouse.
+  --Maximum_threads MAXIMUM_THREADS
+                        The maximum number of threads to use in the pipeline.
+                        By default, all available cores are used.
+  --Mitochondrial_Contigs MITOCHONDRIAL_CONTIGS
+                        Names of the Mitochondrial contigs in the provided
+                        Reference Genome. Fragments originating from contigs
+                        other than these are identified as 'nuclear fragments'
+                        in the ATACseq analysis pipeline.
+  --WTA_Only            Build a WTA only index, otherwise builds a WTA + ATAC
+                        index.