Skip to content

Update phenotype pipeline for G2P #1182

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

Update phenotype pipeline for G2P #1182

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
14 changes: 4 additions & 10 deletions modules/Bio/EnsEMBL/Variation/Pipeline/PhenotypeAnnotation/ImportG2P.pm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,24 +93,19 @@ sub fetch_input {
$self->errFH($errFH);
$self->pipelogFH($pipelogFH);




#get input file G2P:

# Get input file G2P
my $dateStrURL = strftime("%d_%m_%Y", localtime);

for (keys %input_files_url){
my $file = $dateStrURL.$_.".csv.gz";
print $logFH "Found files (".$workdir."/".$file."), will skip new fetch\n" if -e $workdir."/".$file;
my $resHTTPcode = qx{curl -L -w %{http_code} -X GET $input_files_url{$_} -o $workdir/$file} unless -e $workdir."/".$file;
print $errFH "WARNING: File cound not be retrieved (HTTP code: $resHTTPcode)" if defined($resHTTPcode) && $resHTTPcode != 200;

}

gunzip "<$workdir/*.csv.gz>" => "<$workdir/#1.csv>"
or die "gunzip failed: $GunzipError\n";

my @rows;
my $g2p_csv = $dateStrURL."DDG2P.csv";
my $csv = Text::CSV->new ({ binary => 1, sep_char => "," });
Expand All @@ -123,16 +118,13 @@ sub fetch_input {
close $infile;
}


open my $fh, ">>:encoding(utf8)", "$workdir/$g2p_csv";
foreach my $line (@rows) {
next if $line->[0] =~ /^gene symbol/;
$csv->say ($fh, $line);
}
close $fh or die "$workdir/$g2p_csv: $!";



unlink glob "$workdir/*.csv.gz"; # to remove the csv.gz file.
$self->param('ddg2p_file', $g2p_csv);
}
Expand Down Expand Up @@ -220,6 +212,7 @@ sub parse_input_file {
while (my $content = $csv->getline_hr ($fh)) {

# get data from the line
my $g2p_id = $content->{"g2p id"};
my $symbol = $content->{"gene symbol"};
my $allelic = $content->{"allelic requirement"};
my $phen = $content->{"disease name"};
Expand Down Expand Up @@ -259,6 +252,7 @@ sub parse_input_file {
'seq_region_end' => $gene->seq_region_end,
'seq_region_strand' => $gene->seq_region_strand,
'inheritance_type' => $allelic,
'g2p_stable_id' => $g2p_id,
'pubmed_id' => $pubmeds,
'accessions' => \@accns,
'g2p_confidence' => $confidence_category,
Expand Down