millironx/taxprofiler
1
0
Fork 0
mirror of https://github.com/MillironX/taxprofiler.git synced 2024-11-25 22:59:56 +00:00
Code Issues Releases Packages Activity

Fix metadata manipulaton for malt

Browse source
This commit is contained in:
James Fellows Yates 2022-06-10 19:33:37 +02:00
parent 621b6a3d09
commit e0ad49ebc9
1 changed files with 15 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
subworkflows/local/profiling.nf
View file

@ -61,25 +61,29 @@ workflow PROFILING {
// MALT: We groupTuple to have all samples in one channel for MALT as database // MALT: We groupTuple to have all samples in one channel for MALT as database
// loading takes a long time, so we only want to run it once per database // loading takes a long time, so we only want to run it once per database
// TODO document somewhere we only accept illumina short reads for MALT?
ch_input_for_malt = ch_input_for_profiling.malt ch_input_for_malt = ch_input_for_profiling.malt
.filter { it[0]['instrument_platform'] == 'ILLUMINA' } .filter { it[0]['instrument_platform'] == 'ILLUMINA' }
.map { .map {
meta, reads, db_meta, db -> meta, reads, db_meta, db ->
def new_meta = meta.clone()
def new_db_meta = db_meta.clone()
// Add the saving of alignments in SAM format to params // Reset entire input meta for MALT to just database name,
// as we don't run run on a per-sample basis due to huge datbaases
// so all samples are in one run and so sample-specific metadata
// unnecessary. Set as database name to prevent `null` job ID and prefix.
def temp_meta = [ id: meta['db_name'] ]
// Extend database parameters to specify whether to save alignments or not
def new_db_meta = db_meta.clone()
def sam_format = params.malt_save_reads ? ' --alignments ./ -za false' : "" def sam_format = params.malt_save_reads ? ' --alignments ./ -za false' : ""
new_db_meta['db_params'] = db_meta['db_params'] + sam_format new_db_meta['db_params'] = db_meta['db_params'] + sam_format
// As MALT has huge databases, we don't run on a per-sample basis but multiple // Combine reduced sample metadata with updated database parameters metadata,
// samples at once. This replaces the ID of the particular process with the // make sure id is db_name for publishing purposes.
// db_name instead to prevent `null` in job name, and in publishDir) def new_meta = temp_meta + new_db_meta
def updated_meta = new_meta + new_db_meta new_meta['id'] = new_meta['db_name']
updated_meta['id'] = updated_meta['db_name']
[ new_meta, reads, db ]
[ updated_meta, reads, db ]
} }
.groupTuple(by: [0,2]) .groupTuple(by: [0,2])
.multiMap { .multiMap {