Fixed to use dbifloret (generalizes the script so it doesn't have to be modfied by...

svn path=/; revision=489

diff --git a/interactome_scripts/inparanoid_output_parse.pl b/interactome_scripts/inparanoid_output_parse.pl
index f02373e5ac23ae238d09833affc61212adead72f..92d3a7a8d4523d2bd63afedb5dd9ae0922942728 100755 (executable)
--- a/interactome_scripts/inparanoid_output_parse.pl
+++ b/interactome_scripts/inparanoid_output_parse.pl
@@ -19,11 +19,25 @@ use strict;
 use warnings;
 
 use DBI;
-use Term::Screen::ReadLine;
 
 use Getopt::Long;
 my $new = '';
-GetOptions ('new' => \$new);
+my $strip = '';
+GetOptions ('new' => \$new, 'strip' => \$strip);
+
+
+# set up the database connection
+use lib "$ENV{HOME}/scripts/jaiswallab/interactome_scripts";
+
+use DbiFloret;
+
+my $dbh = DbiFloret::dbconnect;
+
+if($new) {
+               $database = $dbh->selectrow_array("select DATABASE()");
+               $dbh->do("drop database if exists $database");
+               $dbh->do("create database $database");
+}
 
 
 if(-e "$ENV{HOME}/scripts/jaiswallab/interactome_scripts/find_species.pl") {
@@ -36,35 +50,7 @@ if(-e "$ENV{HOME}/scripts/jaiswallab/interactome_scripts/find_species.pl") {
 
 my @files = glob("sqltable*");
 
-# define the database handle to be used 
-
-my $database;
-
-my $screen = Term::Screen::ReadLine->new();
-       # clear the screen
-       $screen->clrscr;
-       # ask for username
-       $screen->at(0,0)->puts("Username: ");
-       my $username = $screen->readline(ROW => 0, COL=>11);
-
-       # ask for password, replace character presses with stars
-       $screen->at(1,0)->puts("Password: ");
-       my $password = $screen->readline(ROW => 1, COL => 11, PASSWORD => 1);
-
-       $screen->at(2,0);
-       undef $screen;
-       if($new) {
-               $database = "";
-               my $dbh_temp = DBI->connect("DBI:mysql:$database;host=floret.cgrb.oregonstate.edu", $username, $password,
-               { RaiseError=> 1, AutoCommit=>1 }
-               ) or die "Failed to connect to database: $DBI::errstr";
-               $dbh_temp->do("drop database inparanoid_data");
-               $dbh_temp->do("create database inparanoid_data");
-               $dbh_temp->disconnect;
-       }
-       my $dbh = DBI->connect("DBI:mysql:inparanoid_data;host=floret.cgrb.oregonstate.edu", $username, $password,
-               { RaiseError=> 1, AutoCommit=>1 }
-               ) or die "Failed to connect to database: $DBI::errstr";
+
                
                
 my $clust_table = "clusters";
@@ -149,17 +135,27 @@ foreach my $input_file (@files) {
                $species = find_species($species);
                # the next line is no longer neccessary, future inparanoid runs will fix the gene headers before running
                #my $gene = find_gene($gene_header,$species);
-               # skip isomers that are not .1
-               next if ($gene =~ /\.[2-9]$/);
-               next if ($gene =~ /\.1[0-9]$/);
-               next if ($gene =~ /\.2[0-9]$/);
-               next if ($gene =~ /\.3[0-9]$/);
-               next if ($gene =~ /\.4[0-9]$/);
-               next if ($gene =~ /\.5[0-9]$/);
-               next if ($gene =~ /\.6[0-9]$/);
-               next if ($gene =~ /\.7[0-9]$/);
-               next if ($gene =~ /\.8[0-9]$/);
-               next if ($gene =~ /\.9[0-9]$/);
+               # skip isomers that are not .1 if asked
+               if ($strip) {
+                               if($species ne "Jatropha_curcas") { #Jatropha gene ids are .10, .20, .30, etc...
+                                       next if ($gene =~ /\.[2-9]$/);
+                                       next if ($gene =~ /\.1[0-9]$/);
+                                       next if ($gene =~ /\.2[0-9]$/);
+                                       next if ($gene =~ /\.3[0-9]$/);
+                                       next if ($gene =~ /\.4[0-9]$/);
+                                       next if ($gene =~ /\.5[0-9]$/);
+                                       next if ($gene =~ /\.6[0-9]$/);
+                                       next if ($gene =~ /\.7[0-9]$/);
+                                       next if ($gene =~ /\.8[0-9]$/);
+                                       next if ($gene =~ /\.9[0-9]$/);
+                               }
+                               
+                               # skip Maize genes that are not the first transcript
+                               if($species eq "Zea_mays") {
+                                               next if ($gene =~ /\_T0[2-9]$/);
+                                               next if ($gene =~ /\_T1[0-9]$/);
+                               }
+               }
        
                if(!defined($id_hash{$clust_id})) {
                        if ($clust_id ne $clust_id_prev) {