Merge pull request #64 from nf-core/Organise_script_comments

Scripts updated

bin/busco_2_table.py

@@ -1,4 +1,8 @@
 #!/usr/bin/python3
+
+# Written by Chris Wyatt and released under the MIT license. 
+# Converts a group of busco outputs to a table to plot on a tree
+
 import pandas as pd
 import argparse
 

bin/fasta_topIsoform.pl

@@ -1,4 +1,8 @@
 #!/usr/bin/perl
+
+# Written by Chris Wyatt and released under the MIT license. 
+# Extract isoform from a list of isoforms you want to get
+
 use warnings;
 use strict;
 use Getopt::Std;
@@ -11,19 +15,17 @@
 my $outfile="$fastafile\.nucl.longest.fa";
 
 open(my $outhandle, ">", $outfile)   or die "Could not open $outfile \n";
-
 open(my $inhandle,  "<", $hitlist)   or die "Could not open $hitlist \n";
 
-
-
 use Bio::SeqIO;
 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
+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;
 	$id=~ s/rna-//g;
@@ -49,7 +51,3 @@
 	$HIT{$sp[1]}="y";
 	$len_prots++;
 }
-
-
-
-

bin/gff_to_genetranshash.2.pl

@@ -2,10 +2,11 @@
 use warnings;
 use strict;
 
+# Written by Chris Wyatt and released under the MIT license. 
+# Converts gff file to a hash of genes
 
 print "Please be in folder with *noquest.gff3 file\n\n";
 
-
 my $in_gfffile=`ls *noquest.gff3`;
 chomp $in_gfffile;
 my @namesplit=split(/\./, $in_gfffile);
@@ -39,7 +40,6 @@
         #print "$line\n";
         if ($split[2] eq "mRNA"){
             my $length=$split[4]-$split[3];
-
             #Do different split if AUGUSTUS or NCBI
             if ($split[1] eq "AUGUSTUS"){
                 #Its an AUGUSTUS GFF
@@ -97,7 +97,6 @@
                 $Gene_tran_hash{$gene}=$tran;
             }
 
-
             #Add to longest, if longest
             if ($longest{$gene}){
                 my @old=split("\t", $longest{$gene});
@@ -109,7 +108,6 @@
                 $longest{$gene}="$tran\t$length";
             }
 
-
         }
     }
 }

bin/gtf2gff.pl

@@ -1,5 +1,5 @@
 #!/usr/bin/perl
-#
+# Script taken from : https://github.com/Gaius-Augustus/Augustus/blob/955ce1731e9bdd1c670216ed3c514f978c033891/scripts/gtf2gff.pl
 # format convert a gtf file
 #
 # This script is used by the braker.pl pipeline.

bin/plot_tree_summary.R

@@ -1,4 +1,8 @@
 #!/usr/bin/Rscript
+
+# Written by Chris Wyatt and released under the MIT license. 
+# Prints a tree with QUAST N50 results on tips of branches
+
 # Load necessary libraries
 if (!requireNamespace("argparse", quietly = TRUE)) {
   install.packages("argparse")

bin/plot_tree_summary2.R

@@ -1,4 +1,8 @@
 #!/usr/bin/Rscript
+
+# Written by Chris Wyatt and released under the MIT license. 
+# Plots the phylogenetic tree with BUSCO result in pie charts
+
 # Load necessary libraries
 if (!requireNamespace("argparse", quietly = TRUE)) {
   install.packages("argparse")

bin/prot_fasta_to_longest.pl

@@ -1,4 +1,8 @@
 #!/usr/bin/perl
+
+# Written by Chris Wyatt and released under the MIT license. 
+# Prints out longest unique protein 
+
 use warnings;
 use strict;
 use lib '/opt/conda/lib/perl5/site_perl';
@@ -42,7 +46,7 @@
 
 
 while (my $seq = $seqio->next_seq){ ## selects one sequence at a time
-   	## set variables for THIS sequence
+    ## set variables for THIS sequence
     my $id = $seq->id;
     chomp $id;
     print "here $id\n";
@@ -57,8 +61,6 @@
     if ($longest{$id}){
         print $outhandle ">$iso2gene{$id}\n$string\n";
     }
-
-
 }
 
 

bin/quast_2_table.py

@@ -1,4 +1,7 @@
 #!/usr/bin/python3
+
+# Written by Chris Wyatt and released under the MIT license. Converts a group of quast outputs to a table to plot on a tree
+
 import pandas as pd
 import argparse
 import os