name: prokka
description: Whole genome annotation of small genomes (bacterial, archeal, viral)
keywords:
  - annotation
  - fasta
  - prokka
tools:
  - prokka:
      description: Rapid annotation of prokaryotic genomes
      homepage: https://github.com/tseemann/prokka
      doi: "10.1093/bioinformatics/btu153"
      licence: ["GPL v2"]

input:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - fasta:
      type: file
      description: |
        FASTA file to be annotated. Has to contain at least a non-empty string dummy value.
  - proteins:
      type: file
      description: FASTA file of trusted proteins to first annotate from (optional)
  - prodigal_tf:
      type: file
      description: Training file to use for Prodigal (optional)

output:
  - meta:
      type: map
      description: |
        Groovy Map containing sample information
        e.g. [ id:'test', single_end:false ]
  - versions:
      type: file
      description: File containing software versions
      pattern: "versions.yml"
  - gff:
      type: file
      description: annotation in GFF3 format, containing both sequences and annotations
      pattern: "*.{gff}"
  - gbk:
      type: file
      description: annotation in GenBank format, containing both sequences and annotations
      pattern: "*.{gbk}"
  - fna:
      type: file
      description: nucleotide FASTA file of the input contig sequences
      pattern: "*.{fna}"
  - faa:
      type: file
      description: protein FASTA file of the translated CDS sequences
      pattern: "*.{faa}"
  - ffn:
      type: file
      description: nucleotide FASTA file of all the prediction transcripts (CDS, rRNA, tRNA, tmRNA, misc_RNA)
      pattern: "*.{ffn}"
  - sqn:
      type: file
      description: an ASN1 format "Sequin" file for submission to Genbank
      pattern: "*.{sqn}"
  - fsa:
      type: file
      description: nucleotide FASTA file of the input contig sequences, used by "tbl2asn" to create the .sqn file
      pattern: "*.{fsa}"
  - tbl:
      type: file
      description: feature Table file, used by "tbl2asn" to create the .sqn file
      pattern: "*.{tbl}"
  - err:
      type: file
      description: unacceptable annotations - the NCBI discrepancy report.
      pattern: "*.{err}"
  - log:
      type: file
      description: contains all the output that Prokka produced during its run
      pattern: "*.{log}"
  - txt:
      type: file
      description: statistics relating to the annotated features found
      pattern: "*.{txt}"
  - tsv:
      type: file
      description: tab-separated file of all features (locus_tag,ftype,len_bp,gene,EC_number,COG,product)
      pattern: "*.{tsv}"

authors:
  - "@rpetit3"