CI
6a030faa77
Build pipeline: viash-hub.craftbox.v0.1-4f4mc
Source commit: 373be82129
Source message: Bump viash to 0.9.0-RC7 (#6)
102 lines
3.2 KiB
YAML
102 lines
3.2 KiB
YAML
name: csv2fasta
|
|
description: |
|
|
Convert two columns from a CSV file to FASTA entries. The CSV file can
|
|
contain an optional header and each row (other than the header) becomes
|
|
a single FASTA record. One of the two columns will be used as the names
|
|
for the FASTA entries, while the other become the sequences. The sequences
|
|
column must only contain characters that are valid IUPAC notation for
|
|
nucleotides or a group thereof (wildcard characters).
|
|
argument_groups:
|
|
- name: Inputs
|
|
arguments:
|
|
- name: --input
|
|
type: file
|
|
direction: input
|
|
example: barcodes.csv
|
|
description: CSV file to be processed.
|
|
required: true
|
|
- name: --header
|
|
type: boolean_true
|
|
description: |
|
|
Parse the first line of the CSV file as a header.
|
|
- name: "CSV dialect options"
|
|
description: |
|
|
Options that can be used to override the automatically detected
|
|
dialect of the CSV file.
|
|
arguments:
|
|
- name: --delimiter
|
|
type: string
|
|
description: |
|
|
Overwrite the column delimiter character.
|
|
- name: --quote_character
|
|
type: string
|
|
description: |
|
|
Overwrite the character used to denote the start and end of a quoted item.
|
|
- name: "CSV column arguments"
|
|
description: |
|
|
Parameters for the selection of columns from the CSV file.
|
|
Only required when your CSV file contains more than 2 columns,
|
|
otherwise the first column will be used for the FASTA header
|
|
and the second for the FASTA nucleotide sequences. This default
|
|
can still be overwritten by using the options below.
|
|
arguments:
|
|
- name: --sequence_column
|
|
type: string
|
|
description: |
|
|
Name of the column containing the sequences. Implies 'header'.
|
|
Cannot be used together with 'sequence_column_index'.
|
|
required: false
|
|
- name: "--name_column"
|
|
type: string
|
|
description: |
|
|
Name of the column describing the FASTA headers. Implies 'header'.
|
|
Cannot be used together with 'name_column_index'.
|
|
required: false
|
|
- name: "--sequence_column_index"
|
|
type: integer
|
|
min: 0
|
|
description: |
|
|
Index of the column to use as the FASTA sequences, counter from the left and
|
|
starting from 0. Cannot be used in combination with the 'sequence_column' argument.
|
|
required: false
|
|
- name: "--name_column_index"
|
|
type: integer
|
|
min: 0
|
|
description: |
|
|
Index of the column to use as the FASTA headers, counter from the left and
|
|
starting from 0. Cannot be used in combination with 'name_column'.
|
|
required: false
|
|
- name: Outputs
|
|
arguments:
|
|
- name: "--output"
|
|
type: file
|
|
example: barcodes.fasta
|
|
direction: output
|
|
description: Output fasta file.
|
|
|
|
resources:
|
|
- type: python_script
|
|
path: script.py
|
|
test_resources:
|
|
- type: python_script
|
|
path: test_csv2fasta.py
|
|
|
|
engines:
|
|
- type: docker
|
|
image: python:slim
|
|
setup:
|
|
- type: apt
|
|
packages:
|
|
- procps
|
|
- type: python
|
|
packages:
|
|
- dnaio
|
|
test_setup:
|
|
- type: python
|
|
packages:
|
|
- pytest
|
|
- viashpy
|
|
|
|
runners:
|
|
- type: executable
|
|
- type: nextflow |