Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use dbNSFP 4.9 academic version in Protein Function pipeline #1127

Open
wants to merge 3 commits into
base: postreleasefix/114
Choose a base branch
from
+31 −6
Open

Use dbNSFP 4.9 academic version in Protein Function pipeline #1127

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
93d76d8
Use dbNSFP 4.9 academic version in Protein Function pipeline
nakib103 Oct 29, 2024
eaa1364
Update annotation adapter
nakib103 Nov 6, 2024
2588ce6
Update tests
nakib103 Nov 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions modules/Bio/EnsEMBL/Variation/Pipeline/ProteinFunction/ProteinFunction_conf.pm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -217,12 +217,12 @@ sub default_options {
dbnsfp_max_workers => 50,
dbnsfp_working => $self->o('species_dir').'/dbnsfp_working',
dbnsfp_annotation => { GRCh37 =>
{ file => $self->o('variation_data') . '/dbNSFP/4.9c/dbNSFP4.9c_grch37.gz',
version => '4.9c',
{ file => $self->o('variation_data') . '/dbNSFP/4.9a/dbNSFP4.9a_grch37.gz',
version => '4.9a',
},
GRCh38 =>
{ file => $self->o('variation_data') . '/dbNSFP/4.9c/dbNSFP4.9c_grch38.gz',
version => '4.9c',
{ file => $self->o('variation_data') . '/dbNSFP/4.9a/dbNSFP4.9a_grch38.gz',
version => '4.9a',
}
},
cadd_run_type => NONE,
Expand Down
25 changes: 24 additions & 1 deletion modules/Bio/EnsEMBL/Variation/Utils/DbNSFPProteinFunctionAnnotation.pm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ sub new {

my $self = $class->SUPER::new(@_);

my @versions = ('3.5a', '4.0a', '4.1a', '4.2a', '4.3a', '4.4a', '4.5c', '4.6c', '4.7c', '4.8c', '4.9c');
my @versions = ('3.5a', '4.0a', '4.1a', '4.2a', '4.3a', '4.4a', '4.5c', '4.6c', '4.7c', '4.8c', '4.9c', '4.9a');
if (! grep {$_ eq $self->annotation_file_version} @versions) {
die "dbNSFP version " . $self->annotation_file_version . " is not supported.";
}
Expand Down Expand Up @@ -357,6 +357,29 @@ my $column_names = {
},
},
},
'4.9a' => {
assembly_unspecific => {
chr => '#chr',
ref => 'ref',
refcodon => 'refcodon',
alt => 'alt',
aaalt => 'aaalt',
aaref => 'aaref',
revel_score => 'REVEL_score',
meta_lr_score => 'MetaLR_score',
meta_lr_pred => 'MetaLR_pred',
mutation_assessor_score => 'MutationAssessor_rankscore',
mutation_assessor_pred => 'MutationAssessor_pred',
},
'assembly_specific' => {
'GRCh37' => {
pos => 'hg19_pos(1-based)'
},
'GRCh38' => {
pos => 'pos(1-based)'
},
},
},
};

sub load_predictions_for_triplets {
Expand Down
4 changes: 3 additions & 1 deletion modules/t/protein_function_utils.t
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ my $triplet = {
'aa' => 'G'
};

my @file_versions = ('3.5a', '4.0a', '4.1a', '4.2a', '4.3a', '4.4a', '4.5c', '4.6c', '4.7c', '4.8c', '4.9c');
my @file_versions = ('3.5a', '4.0a', '4.1a', '4.2a', '4.3a', '4.4a', '4.5c', '4.6c', '4.7c', '4.8c', '4.9c', '4.9a');
my @assemblies = ('GRCh37', 'GRCh38');
my $expected_results = {
'GRCh37' => {
Expand All @@ -97,6 +97,7 @@ my $expected_results = {
'4.7c' => { 'dbnsfp_mutation_assessor' => { '21' => { 'A' => { 'high' => '0.99996' }, 'S' => { 'high' => '0.99244' }, 'D' => { 'high' => '0.99996' }, 'C' => { 'high' => '0.99996' }, 'R' => { 'high' => '0.99996' }, 'V' => { 'high' => '0.99996' }}}, 'dbnsfp_meta_lr' => { '21' => { 'A' => { 'damaging' => '0.9814' },'S' => {'damaging' => '0.9798'},'D' => {'damaging' => '0.9836'},'C' => {'damaging' => '0.9836'},'R' => {'damaging' => '0.9814'},'V' => {'damaging' => '0.9814'}}},},
'4.8c' => { 'dbnsfp_mutation_assessor' => { '21' => { 'A' => { 'high' => '0.99996' }, 'S' => { 'high' => '0.99244' }, 'D' => { 'high' => '0.99996' }, 'C' => { 'high' => '0.99996' }, 'R' => { 'high' => '0.99996' }, 'V' => { 'high' => '0.99996' }}}, 'dbnsfp_meta_lr' => { '21' => { 'A' => { 'damaging' => '0.9814' },'S' => {'damaging' => '0.9798'},'D' => {'damaging' => '0.9836'},'C' => {'damaging' => '0.9836'},'R' => {'damaging' => '0.9814'},'V' => {'damaging' => '0.9814'}}},},
'4.9c' => { 'dbnsfp_mutation_assessor' => { '21' => { 'A' => { 'high' => '0.99996' }, 'S' => { 'high' => '0.99244' }, 'D' => { 'high' => '0.99996' }, 'C' => { 'high' => '0.99996' }, 'R' => { 'high' => '0.99996' }, 'V' => { 'high' => '0.99996' }}}, 'dbnsfp_meta_lr' => { '21' => { 'A' => { 'damaging' => '0.9814' },'S' => {'damaging' => '0.9798'},'D' => {'damaging' => '0.9836'},'C' => {'damaging' => '0.9836'},'R' => {'damaging' => '0.9814'},'V' => {'damaging' => '0.9814'}}},},
'4.9a' => { 'dbnsfp_revel' => { '21' => { 'A' => { 'likely disease causing' => '0.940' }, 'S' => { 'likely disease causing' => '0.943' }, 'D' => { 'likely disease causing' => '0.908' }, 'C' => { 'likely disease causing' => '0.901' }, 'R' => { 'likely disease causing' => '0.944' }, 'V' => { 'likely disease causing' => '0.965' }}}, 'dbnsfp_mutation_assessor' => { '21' => { 'A' => { 'high' => '0.99996' }, 'S' => { 'high' => '0.99244' }, 'D' => { 'high' => '0.99996' }, 'C' => { 'high' => '0.99996' }, 'R' => { 'high' => '0.99996' }, 'V' => { 'high' => '0.99996' }}}, 'dbnsfp_meta_lr' => { '21' => { 'A' => { 'damaging' => '0.9814' },'S' => {'damaging' => '0.9798'},'D' => {'damaging' => '0.9836'},'C' => {'damaging' => '0.9836'},'R' => {'damaging' => '0.9814'},'V' => {'damaging' => '0.9814'}}},},
},

'GRCh38' => {
Expand All @@ -118,6 +119,7 @@ my $expected_results = {
'4.7c' => { 'dbnsfp_mutation_assessor' => { '21' => { 'A' => { 'high' => '0.99996' }, 'S' => { 'high' => '0.99244' }, 'D' => { 'high' => '0.99996' }, 'C' => { 'high' => '0.99996' }, 'R' => { 'high' => '0.99996' }, 'V' => { 'high' => '0.99996' }}}, 'dbnsfp_meta_lr' => { '21' => { 'A' => { 'damaging' => '0.9814' },'S' => {'damaging' => '0.9798'},'D' => {'damaging' => '0.9836'},'C' => {'damaging' => '0.9836'},'R' => {'damaging' => '0.9814'},'V' => {'damaging' => '0.9814'}}},},
'4.8c' => { 'dbnsfp_mutation_assessor' => { '21' => { 'A' => { 'high' => '0.99996' }, 'S' => { 'high' => '0.99244' }, 'D' => { 'high' => '0.99996' }, 'C' => { 'high' => '0.99996' }, 'R' => { 'high' => '0.99996' }, 'V' => { 'high' => '0.99996' }}}, 'dbnsfp_meta_lr' => { '21' => { 'A' => { 'damaging' => '0.9814' },'S' => {'damaging' => '0.9798'},'D' => {'damaging' => '0.9836'},'C' => {'damaging' => '0.9836'},'R' => {'damaging' => '0.9814'},'V' => {'damaging' => '0.9814'}}},},
'4.9c' => { 'dbnsfp_mutation_assessor' => { '21' => { 'A' => { 'high' => '0.99996' }, 'S' => { 'high' => '0.99244' }, 'D' => { 'high' => '0.99996' }, 'C' => { 'high' => '0.99996' }, 'R' => { 'high' => '0.99996' }, 'V' => { 'high' => '0.99996' }}}, 'dbnsfp_meta_lr' => { '21' => { 'A' => { 'damaging' => '0.9814' },'S' => {'damaging' => '0.9798'},'D' => {'damaging' => '0.9836'},'C' => {'damaging' => '0.9836'},'R' => {'damaging' => '0.9814'},'V' => {'damaging' => '0.9814'}}},},
'4.9a' => { 'dbnsfp_revel' => { '21' => { 'A' => { 'likely disease causing' => '0.940' }, 'S' => { 'likely disease causing' => '0.943' }, 'D' => { 'likely disease causing' => '0.908' }, 'C' => { 'likely disease causing' => '0.901' }, 'R' => { 'likely disease causing' => '0.944' }, 'V' => { 'likely disease causing' => '0.965' }}}, 'dbnsfp_mutation_assessor' => { '21' => { 'A' => { 'high' => '0.99996' }, 'S' => { 'high' => '0.99244' }, 'D' => { 'high' => '0.99996' }, 'C' => { 'high' => '0.99996' }, 'R' => { 'high' => '0.99996' }, 'V' => { 'high' => '0.99996' }}}, 'dbnsfp_meta_lr' => { '21' => { 'A' => { 'damaging' => '0.9814' },'S' => {'damaging' => '0.9798'},'D' => {'damaging' => '0.9836'},'C' => {'damaging' => '0.9836'},'R' => {'damaging' => '0.9814'},'V' => {'damaging' => '0.9814'}}},},
}
};

Expand Down