name: abundant_sequences
version: 0.0.2
output_asset_class: abundant_sequences
description: |
  Abundant sequences in the FASTA format -- PhiX spike-in, Poly(A),
  Poly(C) and adapter sequences. Commonly used for contamination
  screening in sequencing experiments.
input_files:
  phix:
    description: PhiX sequences in FASTA format
  polyA:
    description: Poly(A) sequences in FASTA format
  polyC:
    description: Poly(C) sequences in FASTA format
  adapter_contam:
    description: Adapter sequences in FASTA format
input_params: null
input_assets: null
docker_image: null
command_templates:
  - cp {{values.files["phix"]}} {{values.output_folder}}/{{values.genome_digest}}_phix.fa
  - cp {{values.files["polyA"]}} {{values.output_folder}}/{{values.genome_digest}}_polyA.fa
  - cp {{values.files["polyC"]}} {{values.output_folder}}/{{values.genome_digest}}_polyC.fa
  - cp {{values.files["adapter_contam"]}} {{values.output_folder}}/{{values.genome_digest}}_adapter_contam.fa
default_asset: "default"

tags:
- contamination
- qc
- spike-in
outputs:
- pattern: '*_phix.fa'
  description: PhiX spike-in sequence
- pattern: '*_polyA.fa'
  description: Poly(A) sequence
- pattern: '*_polyC.fa'
  description: Poly(C) sequence
- pattern: '*_adapter_contam.fa'
  description: Adapter contamination sequence
test:
  commands:
  - test -f {output_dir}/{genome}_phix.fa
  - test -f {output_dir}/{genome}_polyA.fa
  - test -f {output_dir}/{genome}_polyC.fa
  - test -f {output_dir}/{genome}_adapter_contam.fa
resources:
  memory: 1GB
  disk: 1GB
  time: 10m
metadata:
  author: nsheff
  created: '2026-05-20'
  license: BSD-2-Clause
