2ae2c57f81bed91b2474771b896de8bc885b6b21
angie
  Wed Sep 8 12:04:46 2021 -0700
Don't prepend country and append year if isolate name (e.g. from BioSample) already includes those.

diff --git src/hg/utils/otto/sarscov2phylo/fixNcbiFastaNames.pl src/hg/utils/otto/sarscov2phylo/fixNcbiFastaNames.pl
index 099f6d3..e1a96a3 100755
--- src/hg/utils/otto/sarscov2phylo/fixNcbiFastaNames.pl
+++ src/hg/utils/otto/sarscov2phylo/fixNcbiFastaNames.pl
@@ -6,39 +6,43 @@
 sub usage() {
   print STDERR "usage: $0 ncbi_dataset.plusBioSample.tsv [fasta]\n";
   exit 1;
 }
 
 # Read in metadata for GenBank virus sequences, then stream through fasta; if header already
 # has a well-formed country/isolate/year name after the accession then keep that, otherwise
 # add from metadata.
 
 sub makeName($$$$) {
   my ($host, $country, $isolate, $year) = @_;
   my @components = ();
   if ($host) {
     push @components, $host;
   }
+  if ($isolate =~ m@^[A-Za-z]+/.*/\d+$@) {
+    push @components, $isolate;
+  } else {
     if ($country) {
       push @components, $country;
     }
     if ($isolate) {
       push @components, $isolate;
     }
     if ($year) {
       push @components, $year;
     }
+  }
   return join('/', @components);
 }
 
 # Replace non-human host scientific names with common names
 my %sciToCommon = ( 'Canis lupus familiaris' => 'canine',
                     'Felis catus' => 'cat',
                     'Mustela lutreola' => 'mink', # Netherlands
                     'Neovison vison' => 'mink',   # Denmark
                     'Panthera leo' => 'lion',
                     'Panthera tigris' => 'tiger',
                     'Panthera tigris jacksoni' => 'tiger'
                   );
 
 my $gbMetadataFile = shift @ARGV;