bin/load_sequence_metadata_protocol.pl

   1 #! /usr/bin/perl
   2
   3 =head1
   4 load_sequence_metadata_protocol.pl - create a new sequence metadata protocol
   5
   6 =head1 SYNOPSIS
   7 This script uses the CXGN::Genotype::SequenceMetadata package to create a new
   8 Sequence Metadata Protocol in the nd_protocol table and store its sequence
   9 metadata protocol props in the nd_protocolprop table.
  10
  11 =head1 COMMAND-LINE OPTIONS
  12   ARGUMENTS
  13  -H host name (required) e.g. "localhost"
  14  -D database name (required) e.g. "cxgn_cassava"
  15  -U database username (required)
  16  -P database password (optional, default=prompt user for password)
  17  -t Sequence Metadata Type ID, cvterm_id of term from 'sequence_metadata_types' CV (required)
  18  -n protocol name (required)
  19  -d protocol description (required)
  20  -r reference genome name (required)
  21  -s score description (optional)
  22  -a attribute names and descriptions (optional)
  23     Example: "ID=marker name,Locus=gene name,pvalue=p value"
  24  -l external link definitions (optional)
  25     Example: "JBrowse=https://wheat.pw.usda.gov/jb/?data=/ggds/whe-iwgsc2018&loc={{Locus}},Knetminer=https://knetminer.rothamsted.ac.uk/wheatknet/genepage?keyword={{Trait}}&list={{Locus}}"
  26
  27 =head1 AUTHOR
  28     David Waring <djw64@cornell.edu>
  29
  30 =cut
  31
  32 use strict;
  33
  34 use Getopt::Std;
  35 use Data::Dumper;
  36
  37 use Bio::Chado::Schema;
  38 use CXGN::Genotype::SequenceMetadata;
  39
  40
  41 # Read CLI Options
  42 our ($opt_H, $opt_D, $opt_U, $opt_P, $opt_t, $opt_n, $opt_d, $opt_r, $opt_s, $opt_a, $opt_l);
  43 getopts('H:D:U:P:t:n:d:r:s:a:l:');
  44
  45
  46 # Check for required arguments
  47 if ( !$opt_H || !$opt_U || !$opt_D ) {
  48     die "ERROR: Database options -H, -D, and -U are required!\n";
  49 }
  50 if ( !$opt_t ) {
  51     die "ERROR: Sequence Metadata Type is required!\n";
  52 }
  53 if ( !$opt_n ) {
  54     die "ERROR: Sequence Metadata Protocol name is required!\n";
  55 }
  56 if ( !$opt_d ) {
  57     die "ERROR: Sequence Metadata Protocol description is required!\n";
  58 }
  59 if ( !$opt_r ) {
  60     die "ERROR: Reference genome name is required!\n";
  61 }
  62
  63
  64 # Connect to DB
  65 my $pass = $opt_P;
  66 if ( !$opt_P ) {
  67     print "Password for $opt_H / $opt_D: \n";
  68     my $pw = <>;
  69     chomp($pw);
  70     $pass = $pw;
  71 }
  72 print STDERR "Connecting to database...\n";
  73 my $dsn = 'dbi:Pg:database='.$opt_D.";host=".$opt_H.";port=5432";
  74 my $schema = Bio::Chado::Schema->connect($dsn, $opt_U, $pass);
  75
  76
  77 # Parse attributes
  78 my %attributes = ();
  79 if ( defined $opt_a && $opt_a ne '' ) {
  80     my @as = split(',', $opt_a);
  81     foreach my $a (@as) {
  82         my @vs = split('=', $a);
  83         my $n = $vs[0];
  84         my $d = $vs[1];
  85         $attributes{$n} = $d;
  86     }
  87 }
  88
  89 # Parse links
  90 my %links = ();
  91 if ( defined $opt_l && $opt_l ne '' ) {
  92     my @ls = split(',', $opt_l);
  93     foreach my $l (@ls) {
  94         my @vs = split('=', $l);
  95         my $t = $vs[0];
  96         my $u = $vs[1];
  97         $links{$t} = $u;
  98     }
  99 }
 100
 101 # Create Protocol
 102 my $smd = CXGN::Genotype::SequenceMetadata->new(bcs_schema => $schema, type_id => $opt_t);
 103 my %args = (
 104     protocol_name => $opt_n,
 105     protocol_description => $opt_d,
 106     reference_genome => $opt_r,
 107     score_description => $opt_s,
 108     attributes => \%attributes,
 109     links => \%links
 110 );
 111 my $results = $smd->create_protocol(\%args);
 112
 113 print STDERR "Results:\n";
 114 print STDERR Dumper $results;