nf-core_modules/modules/gstama/collapse/meta.yml

name: GSTAMA_COLLAPSE
description: Collapse redundant transcript models in Iso-Seq data.
keywords:
  - tama_collapse.py
  - isoseq
  - nanopore
  - long-read
  - transcriptome
  - gene model
  - TAMA
tools:
  - tama_collapse.py:
      description: Collapse similar gene model
      homepage: https://github.com/sguizard/gs-tama
      documentation: https://github.com/GenomeRIK/tama/wiki
      tool_dev_url: https://github.com/sguizard/gs-tama
      doi: 10.1186/s12864-020-07123-7
      licence: GNU GPL3

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test' ]
  - bam:
      type: file
      description: A sorted BAM or sam file of aligned reads
      pattern: "*.{bam,sam}"
  - fasta:
      type: file
      description: A fasta file of the genome used for the mapping
      pattern: "*.{fasta,fa}"

output:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test' ]
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"
  - bed:
      type: file
      description: a bed12 format file containing the final collapsed version of your transcriptome
      pattern: "*.bed"
  - bed_trans_reads:
      type: file
      description: This file uses bed12 format to show the transcript model for each read based on the mapping prior to collapsing. This only contains the reads which were accepted according to the defined thresholds. You can use this file to see if there were any strange occurrences during collapsing. It also contains the relationships between reads and collapsed transcript models. The 1st subfield in the 4th column shows the final transcript ID and the 2nd subfield in the 4th column shows the read ID. If you used no_cap mode for collapsing there may be multiple lines for a single read. This happens when a 5' degraded read can match to multiple 5' longer transcript models.
      pattern: "*_trans_read.bed"
  - local_density_error:
      type: file
      description: This file contains the log of filtering for local density error around the splice junctions ("-lde")
      pattern: "*_local_density_error.txt"
  - polya:
      type: file
      description: This file contains the reads with potential poly A truncation.
      pattern: "*_polya.txt"
  - read:
      type: file
      description: This file contains information for all mapped reads from the input SAM/BAM file. It shows both accepted and discarded reads and should match the number of mapped reads in your SAM/BAM file
      pattern: "*_read.txt"
  - strand_check:
      type: file
      description: This file shows instances where the sam flag strand information contrasted the GMAP strand information.
      pattern: "*_strand_check.txt"
  - trans_report:
      type: file
      description: This file contains collapsing information for each transcript.
      pattern: "*_trans_report.txt"
  - varcov:
      type: file
      description: This file contains the coverage information for each variant detected.
      pattern: "*_varcov.txt"
  - variants:
      type: file
      description: This file contains the variants called. Variants are only called if 5 or more reads show the variant at a specific locus. If you would like to change the threshold, please make an issue about this in the Github repo.
      pattern: "*_variants.txt"

authors:
  - "@sguizard"