1
0
Fork 0
mirror of https://github.com/MillironX/taxprofiler.git synced 2024-11-13 07:23:10 +00:00

Add pep_input_base_dir to workflow. Just need to update modules

This commit is contained in:
Rafal Stepien 2022-09-15 12:31:49 -04:00
parent 5f3eee9a4a
commit 768f9980d8
5 changed files with 17 additions and 15 deletions

View file

@ -67,16 +67,14 @@ On release, automated continuous integration tests run the pipeline on a full-si
> - If you are using `singularity`, please use the [`nf-core download`](https://nf-co.re/tools/#downloading-pipelines-for-offline-use) command to download images first, before running the pipeline. Setting the [`NXF_SINGULARITY_CACHEDIR` or `singularity.cacheDir`](https://www.nextflow.io/docs/latest/singularity.html?#singularity-docker-hub) Nextflow options enables you to store and re-use the images from a central location for future pipeline runs.
> - If you are using `conda`, it is highly recommended to use the [`NXF_CONDA_CACHEDIR` or `conda.cacheDir`](https://www.nextflow.io/docs/latest/conda.html) settings to store the environments in a central location for future pipeline runs.
4. You can also run the pipeline using PEP format as an input by running following command:
```console
nextflow run main.nf -profile test_pep,docker --outdir <OUTDIR>
```
5. Start running your own analysis!
4. Start running your own analysis!
```console
nextflow run nf-core/taxprofiler --input samplesheet.csv --databases database.csv --outdir <OUTDIR> --run_<TOOL1> --run_<TOOL1> -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
```
Note pipeline supports both CSV and PEP input sample sheets. Find out more [here](http://pep.databio.org/en/2.1.0/specification/).
## Documentation
The nf-core/taxprofiler pipeline comes with documentation about the pipeline [usage](https://nf-co.re/taxprofiler/usage), [parameters](https://nf-co.re/taxprofiler/parameters) and [output](https://nf-co.re/taxprofiler/output).

View file

@ -33,15 +33,15 @@ properties:
]
fastq1:
type: ["string", "null"]
description: "FASTQ file for read 1."
description: "Optional FASTQ file for read 1 of paired-end sequenced libraries."
pattern: "^[\\S]+.(fq\\.gz|fastq\\.gz)$"
fastq2:
type: ["string", "null"]
description: "FASTQ file for read 2."
description: "Optional FASTQ file for read 2 of paired-end sequenced libraries."
pattern: "^[\\S]+.(fq\\.gz|fastq\\.gz)$"
fasta:
type: ["string", "null"]
description: "Path to FASTA file."
description: "Optional FASTA file."
pattern: "^[\\S]+.(fa\\.gz|fasta\\.gz)$"
required:
- sample

View file

@ -22,6 +22,10 @@ This samplesheet is then specified on the command line as follows:
--input '[path to samplesheet file]' --databases '[path to database sheet file]'
```
Note pipeline supports both CSV and PEP input sample sheets. Find out more [here](http://pep.databio.org/en/2.1.0/specification/).
When using PEP as an input, the `samplesheet.csv` must be placed in the same folder
as `config.yaml` file. A path to `samplesheet.csv` within the config must be absolute.
### Multiple runs of the same sample
The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate different runs FASTQ files of the same sample before performing profiling, when `--perform_runmerging` is supplied. Below is an example for the same sample sequenced across 3 lanes:

View file

@ -9,11 +9,11 @@ include { EIDO_CONVERT } from '../../modules/nf-core/modules/eido/convert/main'
workflow INPUT_CHECK {
take:
samplesheet_or_pep_config // file: /path/to/samplesheet.csv or /path/to/pep/config.yaml
base_dir // file: path to PEP directory
ch_pep_input_base_dir
main:
EIDO_VALIDATE ( samplesheet_or_pep_config, file("$projectDir/assets/samplesheet_schema.yaml") )
converted_samplesheet = EIDO_CONVERT ( samplesheet_or_pep_config, "csv" )
EIDO_VALIDATE ( samplesheet_or_pep_config, file("$projectDir/assets/samplesheet_schema.yaml"), ch_pep_input_base_dir )
converted_samplesheet = EIDO_CONVERT ( samplesheet_or_pep_config, "csv", ch_pep_input_base_dir )
parsed_samplesheet = SAMPLESHEET_CHECK ( converted_samplesheet.samplesheet_converted )
.csv
.splitCsv ( header:true, sep:',' )

View file

@ -19,18 +19,18 @@ for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true
// Check mandatory parameters
if (params.input) {
ch_input = file(params.input)
ch_input_basedir = []
ch_pep_input_base_dir = []
} else if (params.pep) {
if ( params.pep.startsWith("http://") || params.pep.startsWith("https://") ) {
ch_input = file(params.pep)
ch_input_basedir = []
ch_pep_input_base_dir = []
}
else {
ch_input = file(params.pep)
ch_input_basedir = new File(params.pep).getParent()
ch_pep_input_base_dir = new File(params.pep).getParent()
}
} else {
@ -117,7 +117,7 @@ workflow TAXPROFILER {
SUBWORKFLOW: Read in samplesheet, validate and stage input files
*/
INPUT_CHECK (
ch_input, ch_input_basedir
ch_input, ch_pep_input_base_dir
)
ch_versions = ch_versions.mix(INPUT_CHECK.out.versions)