81672aadf156d034a3fd95a1fd76c258070da064 angie Tue Nov 24 14:06:45 2020 -0800 Increase tolerance for BioSample IDs not found. (Checked some on the NCBI website... just not found.) diff --git src/hg/utils/otto/sarscov2phylo/gbMetadataAddBioSample.pl src/hg/utils/otto/sarscov2phylo/gbMetadataAddBioSample.pl index a36967d..db3798a 100755 --- src/hg/utils/otto/sarscov2phylo/gbMetadataAddBioSample.pl +++ src/hg/utils/otto/sarscov2phylo/gbMetadataAddBioSample.pl @@ -71,27 +71,27 @@ if (! $gbName) { $gbName = $bName; } elsif (($gbName eq '1' || $gbName eq 'NA') && length($bName) > length($gbName)) { $gbName = $bName; } elsif ($gbName eq 'nasopharyngeal' && $bName =~ m/\d/) { $gbName = $bName; } if (! $gbGeo) { $gbGeo = $bCountry; } print join("\t", $gbAcc, $bAcc, $gbDate, $gbGeo, $host, $gbName, $completeness, $len); } else { # BioSample file doesn't have info for this BioSample accession print STDERR "Missing BioSample info for $bAcc\n"; $missingCount++; - if ($missingCount >= 100) { + if ($missingCount >= 1000) { die "Too many missing BioSamples, quitting.\n"; } # Pass through as-is print; } } else { # No associated BioSample, just pass through as-is print; } }