millironx/taxprofiler
1
0
Fork 0
mirror of https://github.com/MillironX/taxprofiler.git synced 2024-11-22 12:29:54 +00:00
Code Issues Releases Packages Activity

Add database sheet validation

Browse source
This commit is contained in:
James Fellows Yates 2022-12-12 11:03:40 +01:00
parent 07bd989bc6
commit 460f3ca157
2 changed files with 25 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
subworkflows/local/db_check.nf
View file

@ -11,14 +11,22 @@ workflow DB_CHECK {
main: main:
ch_versions = Channel.empty() ch_versions = Channel.empty()
// TODO: make database sheet check // special check to check _between_ rows, for which we must group rows together
// Checks: Channel.fromPath(dbsheet)
// 1) no duplicates, .splitCsv ( header:true, sep:',' )
.map {[it.tool, it.db_name] }
.groupTuple()
.map {
tool, db_name ->
def unique_names = db_name.unique(false)
if ( unique_names.size() < db_name.size() ) exit 1, "[nf-core/taxprofiler] ERROR: Each database for a tool must have a unique name, duplicated detected. Tool: ${tool}, Database name: ${unique_names}"
}
// normal checks for within-row validity, so can be moved to separate functions
parsed_samplesheet = Channel.fromPath(dbsheet) parsed_samplesheet = Channel.fromPath(dbsheet)
.splitCsv ( header:true, sep:',' ) .splitCsv ( header:true, sep:',' )
.map { .map {
validate_db_sheet(it) validate_db_rows(it)
create_db_channels(it) create_db_channels(it)
} }
@ -40,21 +48,22 @@ workflow DB_CHECK {
versions = ch_versions // channel: [ versions.yml ] versions = ch_versions // channel: [ versions.yml ]
} }
def validate_db_sheet(LinkedHashMap row){ def validate_db_rows(LinkedHashMap row){
// check minimum number of columns // check minimum number of columns
if (row.size() < 4) exit 1, "[nf-core/taxprofiler] error: Invalid database input sheet - malformed row (e.g. missing column). See documentation for more information. Error in: ${row}, " if (row.size() < 4) exit 1, "[nf-core/taxprofiler] ERROR: Invalid database input sheet - malformed row (e.g. missing column). See documentation for more information. Error in: ${row}"
// all columns there // all columns there
def expected_headers = ['tool', 'db_name', 'db_params', 'db_path'] def expected_headers = ['tool', 'db_name', 'db_params', 'db_path']
if ( !row.keySet().containsAll(expected_headers) ) exit 1, "[nf-core/taxprofiler] error: Invalid database input sheet - malformed column names. Please check input TSV. Column names should be: ${expected_keys.join(", ")}" if ( !row.keySet().containsAll(expected_headers) ) exit 1, "[nf-core/taxprofiler] ERROR: Invalid database input sheet - malformed column names. Please check input TSV. Column names should be: ${expected_keys.join(", ")}"
// valid tools specified// TIFNISIH LIST // valid tools specified// TIFNISIH LIST
def expected_tools = [ "bracken", "centrifuge", "diamond", "kaiju", "kraken2", "malt", "metaphlan3" ] def expected_tools = [ "bracken", "centrifuge", "diamond", "kaiju", "kraken2", "krakenuniq", "malt", "metaphlan3", "motus" ]
if ( !expected_tools.contains(row.tool) ) exit 1, "[nf-core/taxprofiler] ERROR: Invalid tool name. Please see documentation for all supported profilers. Error in: ${row}"
// detect quotes in params // detect quotes in params
if ( row.db_params.contains('"') ) exit 1, "[nf-core/taxprofiler] error: Invalid database db_params entry. No quotes allowed. Error in: ${row}" if ( row.db_params.contains('"') ) exit 1, "[nf-core/taxprofiler] ERROR: Invalid database db_params entry. No quotes allowed. Error in: ${row}"
if ( row.db_params.contains("'") ) exit 1, "[nf-core/taxprofiler] error: Invalid database db_params entry. No quotes allowed. Error in: ${row}" if ( row.db_params.contains("'") ) exit 1, "[nf-core/taxprofiler] ERROR: Invalid database db_params entry. No quotes allowed. Error in: ${row}"
} }
@ -66,7 +75,7 @@ def create_db_channels(LinkedHashMap row) {
def array = [] def array = []
if (!file(row.db_path, type: 'dir').exists()) { if (!file(row.db_path, type: 'dir').exists()) {
exit 1, "ERROR: Please check input samplesheet -> database could not be found!\n${row.db_path}" exit 1, "ERROR: Please check input samplesheet -> database path could not be found!\n${row.db_path}"
} }
array = [ meta, file(row.db_path) ] array = [ meta, file(row.db_path) ]

10
subworkflows/local/profiling.nf
View file

@ -41,14 +41,14 @@ workflow PROFILING {
} }
.combine(databases) .combine(databases)
.branch { .branch {
malt: it[2]['tool'] == 'malt'
kraken2: it[2]['tool'] == 'kraken2' || it[2]['tool'] == 'bracken' // to reuse the kraken module to produce the input data for bracken
metaphlan3: it[2]['tool'] == 'metaphlan3'
centrifuge: it[2]['tool'] == 'centrifuge' centrifuge: it[2]['tool'] == 'centrifuge'
kaiju: it[2]['tool'] == 'kaiju'
diamond: it[2]['tool'] == 'diamond' diamond: it[2]['tool'] == 'diamond'
motus: it[2]['tool'] == 'motus' kaiju: it[2]['tool'] == 'kaiju'
kraken2: it[2]['tool'] == 'kraken2' || it[2]['tool'] == 'bracken' // to reuse the kraken module to produce the input data for bracken
krakenuniq: it[2]['tool'] == 'krakenuniq' krakenuniq: it[2]['tool'] == 'krakenuniq'
malt: it[2]['tool'] == 'malt'
metaphlan3: it[2]['tool'] == 'metaphlan3'
motus: it[2]['tool'] == 'motus'
unknown: true unknown: true
} }