Skip to content

Commit

Permalink
Merge pull request #858 from mgcam/fix_should_run4review_check
Browse files Browse the repository at this point in the history
Fixed a bug in the autoqc function package.
  • Loading branch information
jmtcsngr authored Oct 9, 2024
2 parents 479fea3 + 1447857 commit 7dc20a0
Show file tree
Hide file tree
Showing 7 changed files with 64 additions and 17 deletions.
3 changes: 3 additions & 0 deletions Changes
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
LIST OF CHANGES
---------------

- The runfolder_path attribute is passed to the constructor of the review
autoqc check object when deciding whether this check should run.

release 68.5.1 (2024-10-04)
- Added .github/dependabot.yml file to auto-update GitHub actions
- Following a release on 07/09/2024, see https://metacpan.org/dist/App-perlbrew/changes,
Expand Down
1 change: 1 addition & 0 deletions MANIFEST
Original file line number Diff line number Diff line change
Expand Up @@ -1041,6 +1041,7 @@ t/data/release/config/haplotype_caller_on_study_specific_reference/product_relea
t/data/release/config/notify_off/product_release.yml
t/data/release/config/notify_on/product_release.yml
t/data/release/config/qc_review/product_release.yml
t/data/release/config/qc_review_default/product_release.yml
t/data/release/config/pp_archival/product_release.yml
t/data/release/config/pp_archival/product_release_no_array.yml
t/data/release/config/pp_archival/product_release_no_filters.yml
Expand Down
3 changes: 2 additions & 1 deletion lib/npg_pipeline/function/autoqc.pm
Original file line number Diff line number Diff line change
Expand Up @@ -318,6 +318,7 @@ sub _should_run {
$init_hash{'is_paired_read'} = $self->is_paired_read() ? 1 : 0;
} elsif ($self->qc_to_run() eq 'review') {
$init_hash{'product_conf_file_path'} = $self->product_conf_file_path;
$init_hash{'runfolder_path'} = $self->runfolder_path;
} elsif ($self->qc_to_run() eq 'genotype') {
my $ref_fasta = npg_pipeline::cache::reference->instance()
->get_path($product, q(fasta), $self->repository());
Expand Down Expand Up @@ -416,7 +417,7 @@ Marina Gourtovaia
=head1 LICENSE AND COPYRIGHT
Copyright (C) 2018,2019,2020 Genome Research Ltd.
Copyright (C) 2018,2019,2020,2024 Genome Research Ltd.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
Expand Down
36 changes: 27 additions & 9 deletions t/20-function-autoqc.t
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,8 @@ my $archive_dir = $hiseq_rf->{'archive_path'};
my $rf_path = $hiseq_rf->{'runfolder_path'};
fcopy('t/data/run_params/runParameters.hiseq.xml', "$rf_path/runParameters.xml")
or die 'Fail to copy run param file';
fcopy('t/data/run_params/RunInfo.hiseq.rr.xml', "$rf_path/RunInfo.xml")
or die 'Fail to copy run info file';

my $default = {
default => {
Expand Down Expand Up @@ -509,7 +511,7 @@ subtest 'genotype and gc_fraction and bcfstats' => sub {

my $qc = npg_pipeline::function::autoqc->new($init);

# create products with the characteristics being tested
# create products with the characteristics being tested
my $plexed_lane_lims = st::api::lims->new(id_run => 14043, position => 6);
my $library_lane_lims = st::api::lims->new(id_run => 14043, position => 1);
my $plex0_lims = st::api::lims->new(id_run => 8747, position => 6, tag_index => 0);
Expand Down Expand Up @@ -574,7 +576,7 @@ subtest 'genotype and gc_fraction and bcfstats' => sub {
};

subtest 'review' => sub {
plan tests => 6;
plan tests => 8;

local $ENV{NPG_CACHED_SAMPLESHEET_FILE} = 't/data/samplesheet_8747.csv';

Expand Down Expand Up @@ -602,20 +604,19 @@ subtest 'review' => sub {
);

$da = $qc->create();
ok ($da && (@{$da} == 11), '11 definitions returned');
ok ($da && (@{$da} == 10), '10 definitions returned');
my %definitions = map { $_->composition->freeze2rpt => $_ } @{$da};
my @expected_rpt_lists = qw/ 8747:1:1 8747:1:2 8747:1:3
8747:2:4 8747:2:5 8747:2:6
8747:3:7 8747:3:8 8747:3:9
8747:7
8747:8 /;
8747:7 /;
is_deeply ([sort keys %definitions], \@expected_rpt_lists,
'definitions are for correct entities');

my $d = $definitions{'8747:8'};
my $expected_command = q{qc --check=review --rpt_list="8747:8" } .
qq{--filename_root=8747_8 --qc_out=$archive_dir/lane8/qc } .
qq{--qc_in=$archive_dir/lane8/qc --conf_path=t/data/release/config/qc_review } .
my $d = $definitions{'8747:7'};
my $expected_command = q{qc --check=review --rpt_list="8747:7" } .
qq{--filename_root=8747_7 --qc_out=$archive_dir/lane7/qc } .
qq{--qc_in=$archive_dir/lane7/qc --conf_path=t/data/release/config/qc_review } .
qq{--runfolder_path=$rf_path};
is ($d->command, $expected_command, 'correct command for lane-level job');

Expand All @@ -625,6 +626,23 @@ subtest 'review' => sub {
qq{--qc_in=$archive_dir/lane1/plex1/qc --conf_path=t/data/release/config/qc_review } .
qq{--runfolder_path=$rf_path};
is ($d->command, $expected_command, 'correct command for plex-level job');

$qc = npg_pipeline::function::autoqc->new(
qc_to_run => 'review',
is_indexed => 1,
id_run => 8747,
runfolder_path => $rf_path,
timestamp => q{today},
conf_path => q{t/data/release/config/qc_review_default},
resource => $default
);

$da = $qc->create();
ok ($da && (@{$da} == 6), '6 definitions returned');
%definitions = map { $_->composition->freeze2rpt => $_ } @{$da};
@expected_rpt_lists = map { "8747:$_:168"} qw/1 2 3 4 5 6/;
is_deeply ([sort keys %definitions], \@expected_rpt_lists,
'definitions are for correct entities');
};

subtest 'interop' => sub {
Expand Down
14 changes: 8 additions & 6 deletions t/data/release/config/qc_review/product_release.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,19 +5,21 @@ default:
study:
- study_id: "1713"
robo_qc:
qc_type: "mqc"
criteria:
- applicability_criteria:
lims:
- library_type:
- "Agilent Pulldown"
lims:
library_type:
- "Agilent Pulldown"
acceptance_criteria:
- "criteria1"
- study_id: "2410"
robo_qc:
qc_type: "mqc"
criteria:
- applicability_criteria:
lims:
- library_type:
- "Custom"
lims:
library_type:
- "Custom"
acceptance_criteria:
- "criteria2"
22 changes: 22 additions & 0 deletions t/data/release/config/qc_review_default/product_release.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
---
common:
irods: &no_irods
enable: false
default:
irods: &default_irods
enable: true
data_deletion:
staging_deletion_delay: 30
markdup_method: "biobambam"
gbs_pipeline: &gbs_pipeline_accessible
allowed: true
robo_qc:
qc_type: "mqc"
criteria:
- applicability_criteria:
lims:
is_control: 1
sequencing_run:
platform_HiSeq: 1
acceptance_criteria:
- "sequence_error.pass"
2 changes: 1 addition & 1 deletion t/data/samplesheet_8747.csv
Original file line number Diff line number Diff line change
Expand Up @@ -34,5 +34,5 @@ Lane,Sample_ID,Sample_Name,GenomeFolder,Index,bait_name,default_library_type,def
6,6093530,ERS183155,,TTAATC,,qPCR only,GCCAATGT,,[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected],[email protected] [email protected] [email protected] [email protected] [email protected],[email protected] [email protected],[email protected],,0,0,,,dag1_wt3 6093530,zebrafish,7955,S4301,82,ZF molecular phenotype,standard,,,from:70 to:270,ERS183155,,Danio rerio,,3%27 end enriched mRNA from morphologically normal sibling embryos from dag1 knockout incross 3. A 6 base indexing sequence (TTAATC) is bases 5 to 10 of read 1 followed by polyT. More information describing the mutant phenotype can be found at the Wellcome Trust Sanger Institute Zebrafish Mutation Project website http%3A%2F%2Fwww.sanger.ac.uk%2Fcgi-bin%2FProjects%2FD_rerio%2Fzmp%2Fsearch.pl%3Fq%3Dzmp_phD,,1503354,dag1_wt3,Zebrafish dag1 wt3,Danio_rerio (zv9),,168,ERP001559,1,0,0,Total RNA was extracted from wild type and mutant zebrafish embryos. Double stranded cDNA representing the 3%27 ends of transcripts was made by a variety of methods%2C including polyT priming and 3%27 pull down on magentic beads. Some samples included indexing test experiments where a sequence barcode was placed within one of the sequence reads.. This data is part of a pre-publication release. For information on the proper use of pre-publication data shared by the Wellcome Trust Sanger Institute (including details of any publication moratoria)%2C please see http%3A%2F%2Fwww.sanger.ac.uk%2Fdatasharing%2F,82,ZF molecular phenotype,,,Zebrafish transcript profiling,6,
6,4405872,phiX_for_spiked_buffers,,ACAACGCAAT,,,ACAACGCAAT,,[email protected] [email protected],[email protected],[email protected],[email protected],,1,0,,,PhiX (10Jan12),,,,,,standard,,,,,,,,,,1255141,phiX_for_spiked_buffers,,,,168,,1,0,0,None,198,Illumina Controls,,,,168,
7,6101639,EGAN00001085924,,,,Custom,,,[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected],[email protected] [email protected] [email protected] [email protected] [email protected],[email protected] [email protected] [email protected] [email protected],[email protected],,0,0,6103057,0,PD4845a-RNA_rnaseq 6101639,Human,9606,S0814,1177,CGP Core Sequencing 10%2F12 to 09%2F13,standard,pass,4683991,from:175 to:225,EGAN00001085924,,Homo sapiens,,,,1505636,PD4845a-RNA_rnaseq,PD4845a-RNA,,,168,EGAS00001000377,1,0,0,We propose to definitively characterise the somatic genetics of triple negative breast cancer through generation of comprehensive catalogues of somatic mutations in breast cancer cases by high coverage genome sequencing coupled with integrated transcriptomic and methylation analyses.,2410,Triple Negative Breast Cancer RNA Sequencing,Homo_sapiens (CGP_GRCh37.NCBI.allchr_MT),,Triple Negative Breast Cancer RNA Sequencing,,
8,6101640,EGAN00001085925,,,,Custom,,,[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected],[email protected] [email protected] [email protected] [email protected] [email protected],[email protected] [email protected] [email protected] [email protected],[email protected],,0,0,6103058,0,PD4845a-RNA2_rnaseq 6101640,Human,9606,S0814,1177,CGP Core Sequencing 10%2F12 to 09%2F13,standard,pass,4683992,from:175 to:225,EGAN00001085925,,Homo sapiens,,,,1505637,PD4845a-RNA2_rnaseq,PD4845a-RNA2,,,168,EGAS00001000377,1,0,0,We propose to definitively characterise the somatic genetics of triple negative breast cancer through generation of comprehensive catalogues of somatic mutations in breast cancer cases by high coverage genome sequencing coupled with integrated transcriptomic and methylation analyses.,2410,Triple Negative Breast Cancer RNA Sequencing,Homo_sapiens (CGP_GRCh37.NCBI.allchr_MT),,Triple Negative Breast Cancer RNA Sequencing,,
8,6101640,EGAN00001085925,,,,Custom2,,,[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected],[email protected] [email protected] [email protected] [email protected] [email protected],[email protected] [email protected] [email protected] [email protected],[email protected],,0,0,6103058,0,PD4845a-RNA2_rnaseq 6101640,Human,9606,S0814,1177,CGP Core Sequencing 10%2F12 to 09%2F13,standard,pass,4683992,from:175 to:225,EGAN00001085925,,Homo sapiens,,,,1505637,PD4845a-RNA2_rnaseq,PD4845a-RNA2,,,168,EGAS00001000377,1,0,0,We propose to definitively characterise the somatic genetics of triple negative breast cancer through generation of comprehensive catalogues of somatic mutations in breast cancer cases by high coverage genome sequencing coupled with integrated transcriptomic and methylation analyses.,2410,Triple Negative Breast Cancer RNA Sequencing,Homo_sapiens (CGP_GRCh37.NCBI.allchr_MT),,Triple Negative Breast Cancer RNA Sequencing,,

0 comments on commit 7dc20a0

Please sign in to comment.