Skip to content

added sigfig option for output #854

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

Open
jamie-m-a wants to merge 1 commit into
base: postreleasefix/116
Choose a base branch
from
Open

added sigfig option for output #854

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
38 changes: 22 additions & 16 deletions pLI.pm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,11 @@ pLI - Add pLI score to the output
./vep -i variants.vcf --plugin pLI,values_file.txt
./vep -i variants.vcf --plugin pLI,values_file.txt,transcript # to check for the transcript score.

By default, scores are formatted to two decimal places. To format scores
to three significant figures instead, add the sigfig parameter:
./vep -i variants.vcf --plugin pLI,sigfig
./vep -i variants.vcf --plugin pLI,values_file.txt,transcript,sigfig

gnomAD v4 release expanded the scale of pLI score calculation. The file can be downloaded from -
https://gnomad.broadinstitute.org/downloads#v4-constraint (Constraint metrics TSV)
To use the data you can follow the same procedure as above but needs to change the column number to accordingly.
Expand All @@ -83,7 +88,6 @@ use DBI;
use base qw(Bio::EnsEMBL::Variation::Utils::BaseVepPlugin);
use List::MoreUtils qw/zip/;


my %include_columns = (
"transcript" => {
"name" => "pLI_transcript_value"
Expand All @@ -96,13 +100,17 @@ sub new {
my $class = shift;

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

my $file = $self->params->[0];

my %scores;

my @params = @{$self->params};
my $sigfig = grep { $_ eq 'sigfig' } @params;
@params = grep { $_ ne 'sigfig' } @params;

my $file = $params[0];
my $value = defined($params[1]) ? $params[1] : 'gene';
my $score_format = $sigfig ? '%.3g' : '%.2f';
$self->{option} = $value;

my $value = $self->params->[1] if (defined ($self->params->[1]));
my %scores;

if(!$file) {
my $plugin_dir = $INC{'pLI.pm'};
Expand Down Expand Up @@ -134,7 +142,7 @@ sub new {
chomp;
my ($gene, $score) = split;
next if $score eq 'pLI';
$scores{lc($gene)} = sprintf("%.2f", $score);
$scores{lc($gene)} = sprintf($score_format, $score);
}
close $fh;
}
Expand All @@ -145,33 +153,33 @@ sub new {
chomp;
my ($transcript, $score) = split;
next if $score eq "pLI";
$scores{lc($transcript)} = sprintf("%.2f", $score) ;
$scores{lc($transcript)} = sprintf($score_format, $score);
}
close $fh;
}

if (!defined ($self->params->[1]) || defined($self->params->[1]) eq 'gene' ){
if ($value eq 'gene') {
die "Error: File does not have a gene column\n" unless grep {$_ eq "gene"} @{$self->{headers}};
$self->{header}{$include_columns{"gene"}{"name"}} = "pLI value by gene";
open my $fh, "<", $file;
while (<$fh>) {
chomp;
my ($gene, $score) = split;
next if $score eq 'pLI';
$scores{lc($gene)} = sprintf("%.2f", $score);
$scores{lc($gene)} = sprintf($score_format, $score);
}
close $fh;
}

if ( defined($self->params->[1]) && $self->params->[1] eq 'transcript') {
if ($value eq 'transcript') {
die "Error: Could not find transcript in the headers\n" unless grep {$_ eq "transcript"} @{$self->{headers}};
$self->{header}{$include_columns{"transcript"}{"name"}} = "pLI value by transcript";
open my $fh, "<", $file;
while (<$fh>) {
chomp;
my ($transcript, $score) = split;
next if $score eq "pLI";
$scores{lc($transcript)} = sprintf("%.2f", $score) ;
$scores{lc($transcript)} = sprintf($score_format, $score);
}
close $fh;
}
Expand All @@ -180,7 +188,6 @@ sub new {

$self->{scores} = \%scores;


return $self;


Expand All @@ -204,13 +211,13 @@ sub run {
my $transcript = $tva->transcript;
return {} unless $transcript;

if (!defined ($self->params->[1]) || defined($self->{option}) eq "gene") {
if ($self->{option} eq "gene") {
my $symbol = $tva->transcript->{_gene_symbol} || $tva->transcript->{_gene_hgnc};
return {} unless $symbol;
return $self->{scores}->{lc($symbol)} ? { $include_columns{"gene"}{"name"} => $self->{scores}->{lc($symbol)}} : {};
}

if (defined($self->{option}) eq "transcript" || defined ($self->params->[1]) ) {
if ($self->{option} eq "transcript") {
my $transcript = $tva->transcript->stable_id;
return {} unless $transcript;
return $self->{scores}->{lc($transcript)} ? { $include_columns{"transcript"}{"name"} => $self->{scores}->{lc($transcript)}} : {};
Expand All @@ -221,4 +228,3 @@ sub run {


1;