Merge pull request #4 from chriswyatt1/working

Working

bin/get_fasta_largest_isoform.TrinityMS.pl

@@ -4,9 +4,14 @@
 use FindBin;
 use lib ("$FindBin::RealBin/PerlLib");
 use Getopt::Std;
+use Bio::SeqIO;
 
+# This script reads in a fasta file and produces the longest transcript for each gene (if present in ensembl, trinity or basic headers are present). 
+# This is to stop multiple isoforms of the same gene going through. 
+# If you wish all genes/isoforms to go through, use "basic"
+# It then prints out the longest isoform for each gene, or all genes. 
 
-die "Please specify (1)fasta file (2) nucl type (ensembl, trinity)\n" unless(@ARGV==2);
+die "Please specify (1)fasta file (2) nucl type (ensembl, trinity, basic)\n" unless(@ARGV==2);
 
 my $fastafile = $ARGV[0];
 my $nucl_type = $ARGV[1];
@@ -19,7 +24,6 @@
 if ($nucl_type eq "trinity"){
 
 
-use Bio::SeqIO;
 my $seqio = Bio::SeqIO->new(-file => "$fastafile", '-format' => 'Fasta');
 my %fastadictionary=();
 my @headersplit=();
@@ -49,7 +53,7 @@
 
 foreach my $key ( sort keys %fastadictionary){
 	if ($fastadictionary{$key} eq "Sequenceunavailable"){
-
+		#Do nothing
 	}
 	else{
 		print $outhandle ">$key\n$fastadictionary{$key}\n";
@@ -61,7 +65,6 @@
 
 if ($nucl_type eq "ensembl"){
 
-use Bio::SeqIO;
 my $seqio = Bio::SeqIO->new(-file => "$fastafile", '-format' => 'Fasta');
 my %fastadictionary=();
 my @headersplit=();
@@ -87,20 +90,53 @@
 
 }
 
-print "Now print new fasta with one main protein per gene.\n";
+#print "Now print new fasta with one main protein per gene.\n";
 
 foreach my $key ( sort keys %fastadictionary){
 	if ($fastadictionary{$key} eq "Sequenceunavailable"){
-
+		#Do nothing
 	}
 	else{
 		print $outhandle ">$key\n$fastadictionary{$key}\n";
-	}
-
+	}	
+}
+
+}
+
+
+if ($nucl_type eq "basic"){
+
+my $seqio = Bio::SeqIO->new(-file => "$fastafile", '-format' => 'Fasta');
+my %fastadictionary=();
+my @headersplit=();
+while (my $seq = $seqio->next_seq){ ## selects one sequence at a time
+        ## set variables for THIS sequence
+        my $id = $seq->display_id;
+        my $string = $seq->seq;
+        my $len=length($string);
+        if ($fastadictionary{$id}){
+                my $len_old=length($fastadictionary{$id});
+                if ($len >= $len_old){
+                        $fastadictionary{$id}=$string;
+                }
+        }
+	else{
+             	$fastadictionary{$id}=$string;
+        }
 }
 
+print "Now print new fasta with one main protein per gene.\n";
+
+foreach my $key ( sort keys %fastadictionary){
+        if ($fastadictionary{$key} eq "Sequenceunavailable"){
+                #Do nothing
+        }
+        else{
+                print $outhandle ">$key\n$fastadictionary{$key}\n";
+        }
 }
 
+}
 
 print "Finished:  input lines, output lines\n";
 

conf/base.config

@@ -0,0 +1,67 @@
+// Setting default labels with associated resource allocation
+process {
+
+    // Default resources are same as single label for any unlabelled processes that may be added
+    cpus   = { check_max( 1    * task.attempt, 'cpus'   ) }
+    memory = { check_max( 2.GB * task.attempt, 'memory' ) }
+    time   = { check_max( 1.h  * task.attempt, 'time'   ) }
+
+    // If error is due to timeout or exceeding resource limits then retry
+    errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
+    maxRetries    = 1
+    // Do not allow any errors when retrying
+    maxErrors     = '-1'
+
+    withLabel:process_single {
+        cpus   = { check_max( 1    * task.attempt, 'cpus'   ) }
+        memory = { check_max( 2.GB * task.attempt, 'memory' ) }
+        time   = { check_max( 1.h  * task.attempt, 'time'   ) }
+    }
+    withLabel:process_low {
+        cpus   = { check_max( 2     * task.attempt, 'cpus'    ) }
+        memory = { check_max( 4.GB  * task.attempt, 'memory'  ) }
+        time   = { check_max( 2.h   * task.attempt, 'time'    ) }
+    }
+    withLabel:process_medium {
+        cpus   = { check_max( 4     * task.attempt, 'cpus'    ) }
+        memory = { check_max( 8.GB  * task.attempt, 'memory'  ) }
+        time   = { check_max( 4.h   * task.attempt, 'time'    ) }
+    }
+    withLabel:process_high {
+        cpus   = { check_max( 8     * task.attempt, 'cpus'    ) }
+        memory = { check_max( 12.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 8.h   * task.attempt, 'time'    ) }
+    }
+    withLabel:process_long {
+        time   = { check_max( 24.h  * task.attempt, 'time'    ) }
+    }
+    withLabel:process_high_memory {
+        memory = { check_max( 64.GB * task.attempt, 'memory' ) }
+    }
+    withLabel:process_med_memory {
+        memory = { check_max( 20.GB * task.attempt, 'memory' ) }
+    }
+    withLabel:download_nr {
+        memory = 12.GB
+        cpus = 2
+        time = 24.h
+    }
+    withLabel:blastdb {
+        memory = 40.GB
+        cpus = 4
+        time = 8.h
+    }
+    withLabel:blast {
+        memory = 40.GB
+        cpus = 4
+        time = 8.h
+    }
+    withLabel:error_ignore {
+        errorStrategy = 'ignore'
+    }
+    withLabel:error_retry {
+        errorStrategy = 'retry'
+        maxRetries    = 2
+    }
+
+}