Renamed script names and fixed some errors in tutorial

fortune9 · Jul 12, 2015 · eb22f22 · eb22f22
1 parent 1133fcc
commit eb22f22
Show file tree

Hide file tree

Showing 10 changed files with 86 additions and 59 deletions.
diff --git a/Changes b/Changes
@@ -1,5 +1,14 @@
 Revision history for Bio-CUA
 
+1.04    Thu May 28 10:37:37 EDT 2015
+        1. Update Tutorial.pod by correcting format errors and reword
+        sentences.
+		2. Change program names as follows:
+		   build_cai_param.pl -> cai_codon.pl
+		   build_tai_param.pl -> tai_codon.pl
+		   calculate_CUB.pl   -> cub_seq.pl
+		The new names reflect the functions of the programs better.
+
 1.03    Wed May 20 13:25:29 EDT 2015
         1. Add option --fop-param to calculate_CUB.pl so that the
 		program can compute the metric Fop.

diff --git a/MANIFEST b/MANIFEST
@@ -1,6 +1,6 @@
-bin/build_cai_param.pl
-bin/build_tai_param.pl
-bin/calculate_CUB.pl
+bin/cai_codon.pl
+bin/tai_codon.pl
+bin/cub_seq.pl
 Changes
 ignore.txt
 lib/Bio/CUA.pm

diff --git a/Makefile.PL b/Makefile.PL
@@ -11,9 +11,9 @@ WriteMakefile(
     ABSTRACT_FROM    => 'lib/Bio/CUA.pm',
     LICENSE          => 'gpl_3',
 	#PL_FILES         => {'other.PL' => ''}, # files run during compilation 
-	EXE_FILES        => ["bin/build_cai_param.pl",
-	                     "bin/build_tai_param.pl",
-						 "bin/calculate_CUB.pl"
+	EXE_FILES        => ["bin/cai_codon.pl",
+	                     "bin/tai_codon.pl",
+						 "bin/cub_seq.pl"
 	                    ], # files in bin directory
     MIN_PERL_VERSION => 5.006,
     CONFIGURE_REQUIRES => {

diff --git a/README b/README
@@ -1,6 +1,6 @@
 1. Bio-CUA
 
-Version: 1.01
+This is a Perl software package for analyzing codon usage bias.
 
 2. Purpose
 
@@ -57,6 +57,11 @@ perldoc command.
 
     perldoc Bio::CUA
 
+You can also find a tutorial on the CPAN, which is also accessible
+through
+
+    perldoc Bio::CUA::Tutorial
+
 You can also look for information at:
 
     RT, CPAN's request tracker (report bugs here)
@@ -93,6 +98,6 @@ along with this program.  If not, see L<http://www.gnu.org/licenses/>.
 
 6. CITATION
 
-Zhenguo Zhang and Daven C. Presgraves, CUA: a Flexible Codon Usage
-Analyzer (In preparation)
+Zhenguo Zhang, CUA: a Flexible and
+Comprehensive Codon Usage Analyzer (In preparation)
 
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 ##1. Bio-CUA
 
-Version: 1.01
+This is a Perl software package for analyzing codon usage bias.
 
 ##2. Purpose
 
@@ -57,6 +57,11 @@ perldoc command.
 
     perldoc Bio::CUA
 
+You can also find a tutorial on the CPAN, which is also accessible
+through
+
+    perldoc Bio::CUA::Tutorial
+
 You can also look for information at:
 
     RT, CPAN's request tracker (report bugs here)
@@ -93,6 +98,6 @@ along with this program.  If not, see L<http://www.gnu.org/licenses/>.
 
 ##6. CITATION
 
-Zhenguo Zhang and Daven C. Presgraves, CUA: a Flexible Codon Usage
-Analyzer (In preparation)
+Zhenguo Zhang, CUA: a Flexible and
+Comprehensive Codon Usage Analyzer (In preparation)
 
diff --git a/bin/build_cai_param.pl → bin/cai_codon.pl b/bin/build_cai_param.pl → bin/cai_codon.pl
@@ -350,7 +350,7 @@ sub usage
 -o/--out-file: the file to store the result. Default is standard output.
 
 -h/--help: show this help message. For more detailed information, run
-'perldoc build_cai_param.pl'
+'perldoc cai_codon.pl'
 
 Author:  Zhenguo Zhang
 Contact: zhangz.sci\@gmail.com
@@ -366,7 +366,7 @@ sub usage
 
 =head1 NAME
 
-build_cai_param.pl - a program to calculate CAI for each codon
+cai_codon.pl - a program to calculate CAI for each codon
 
 =head1 VERSION
 
@@ -379,14 +379,14 @@ =head1 SYNOPSIS
 L<http://search.cpan.org/dist/Bio-CUA/>
 
 # calculate codon CAI by choosing the top 200 highly expressed genes
-build_cai_param.pl -i seqs.fasta -e gene_expression.tsv -s 200 -o CAI_top200
+cai_codon.pl -i seqs.fasta -e gene_expression.tsv -s 200 -o CAI_top200
 
 # the same as above but normalize RSCUs with expected RSCUs under even
 # codon usage
-build_cai_param.pl -i seqs.fasta -e gene_expression.tsv -s 200 -o CAI_top200.by_mean -m mean
+cai_codon.pl -i seqs.fasta -e gene_expression.tsv -s 200 -o CAI_top200.by_mean -m mean
 
 # normalize RSCUs by RSCUs derived from bottom 1000 lowely expressed genes
-build_cai_param.pl -i seqs.fasta -e gene_expression.tsv -s 200 -o CAI_top200.b1000 -b 1000
+cai_codon.pl -i seqs.fasta -e gene_expression.tsv -s 200 -o CAI_top200.b1000 -b 1000
 
 =head1 OPTIONS
 

diff --git a/bin/calculate_CUB.pl → bin/cub_seq.pl b/bin/calculate_CUB.pl → bin/cub_seq.pl
@@ -7,7 +7,7 @@
 use Bio::CUA::CodonTable;
 use Getopt::Long;
 
-our $VERSION = 0.11;
+our $VERSION = 0.12;
 my @args = @ARGV;
 my $sep = "\t";
 my $seqIO_pkg;
@@ -187,13 +187,13 @@ sub usage
 	print <<USAGE;
 Usage: $0 [options]
 
-This program computes CUB indices and additional sequence statistics
-for each sequence. Available CUB indices are ENC, CAI, tAI, Fop.
+This program computes CUB metrics and additional sequence statistics
+for each sequence. Available CUB metrics are ENC, CAI, tAI, Fop.
 
 Options:
 
 -s/--seq-file: file containing sequences in fasta format, from which
-CUB indices are computed.
+CUB metrics are computed.
 
 -g/--gc-id:  genetic code table ID used for deriving amino acids for
 sequences in input file. Default is 1, i.e., standard table
@@ -228,7 +228,7 @@ sub usage
 -o/--out:  the file to store the results. Default is to standard output.
 
 -h/--help: show this message. For more details, run 
-'perldoc calculate_CUB.pl'
+'perldoc cub_seq.pl'
 
 Author:  Zhenguo Zhang
 Contact: zhangz.sci\@gmail.com
@@ -245,30 +245,30 @@ sub usage
 
 =head1 NAME
 
-calculate_CUB.pl - a program to calculate sequence codon usage bias
+cub_seq.pl - a program to calculate sequence codon usage bias
 metrics and other sequence parameters.
 
 =head1 VERSION
 
-VERSION: 0.11
+VERSION: 0.12
 
 =head1 SYNOPSIS
 
-This program computes CUB indices for each sequence; the types of
-computed CUB indices depend on the provided options (see below).
+This program computes CUB metrics for each sequence; the types of
+computed CUB metrics depend on the provided options (see below).
 
-In addition to CUB indices, the program also computes some other
+In addition to CUB metrics, the program also computes some other
 features such as counts of amino acids, GC-content of the whole
 sequence and the 3rd codon positions.
 
   # compute ENC, ENC_r, CAI, and tAI for each sequence in file cds.fa
-  summarize_cds_stat.pl --cai CAI_param.top_200 --tai tAI_param \
-  --enc enc,enc_r --seq cds.fa -o CUB_indice.tsv
+  cub_seq.pl --cai CAI_codon.top_200 --tai tAI_codon \
+  --enc enc,enc_r --seq cds.fa -o CUB_seq.tsv
 
   # the same as above but not output GC content, AA counts and protein
   # lengths
-  summarize_cds_stat.pl --cai CAI_param.top_200 --tai tAI_param \
-  --enc enc,enc_r --seq cds.fa -o CUB_indice.tsv --lite
+  cub_seq.pl --cai CAI_codon.top_200 --tai tAI_codon \
+  --enc enc,enc_r --seq cds.fa -o CUB_seq.tsv --lite
 
 =head1 OPTIONS
 
@@ -279,7 +279,7 @@ =head3 Mandatory options
 =item -s/--seq-file
 
 file containing sequences in fasta format, from which each sequence's
-CUB indices are computed.
+CUB metrics are computed.
 
 =back
 
@@ -298,14 +298,14 @@ =head3 Auxiliary options
 
 file containing tAI value for each codon in the
 format 'codon<tab>tAI_value', which can be produced by
-L<build_tai_param.pl>. If not given, tAI values would not be
+L<tai_codon.pl>. If not given, tAI values would not be
 computed.
 
 =item -c/--cai-param
 
 similar to --tai-param, except that CAI values are
 provided in the same format. This file may be produced by
-L<build_cai_param.pl>. If not given, CAI values would not be computed.
+L<cai_codon.pl>. If not given, CAI values would not be computed.
 
 =item -f/--fop-param
 
@@ -414,6 +414,10 @@ =head1 ACKNOWLEDGEMENTS
 
 =head1 UPDATES
 
+0.12 - Thu Jun  4 11:31:03 EDT 2015
+       
+	   1. update documentation
+
 0.11 - Thu May 21 16:00:28 EDT 2015
        
 	   1. modify/add option --base-comp and --lite.

diff --git a/bin/build_tai_param.pl → bin/tai_codon.pl b/bin/build_tai_param.pl → bin/tai_codon.pl
@@ -65,7 +65,7 @@ sub usage
 output.
 
 -h/--help: show this help message. For more detailed information, run
-'perldoc build_tai_param.pl'
+'perldoc tai_codon.pl'
 
 Author:  Zhenguo Zhang
 Contact: zhangz.sci\@gmail.com
@@ -81,7 +81,7 @@ sub usage
 
 =head1 NAME
 
-build_tai_param.pl - a program to calculate tAI of each codon
+tai_codon.pl - a program to calculate tAI of each codon
 
 =head1 VERSION
 
@@ -93,7 +93,7 @@ =head1 SYNOPSIS
 which is part of distribution L<http://search.cpan.org/dist/Bio-CUA/>
 
 # calculate tAI for drosophila melanogaster
-build_tai_param.pl -t dmel_tRNA_copy_number.tsv -o dmel_tAI.tsv
+tai_codon.pl -t dmel_tRNA_copy_number.tsv -o dmel_tAI.tsv
 
 # one can get tRNA copy numbers from the database
 # L<GtRNADB|http://gtrnadb.ucsc.edu/>
@@ -134,7 +134,7 @@ =head3 Auxiliary options:
 =item -h/--help
 
 show this help message. For more detailed information, run
-'perldoc build_tai_param.pl'
+'perldoc tai_codon.pl'
 
 =back
 

diff --git a/lib/Bio/CUA/CUB/Calculator.pm b/lib/Bio/CUA/CUB/Calculator.pm
@@ -46,6 +46,7 @@ use strict;
 use warnings;
 use parent qw/Bio::CUA::CUB/;
 use Bio::CUA::CodonTable;
+use Scalar::Util qw/blessed/;
 
 =head1 METHODS
 
@@ -480,7 +481,7 @@ sub _enc_factory
 
 	# a hash ref, codon => counts
 	my $codonList = $self->get_codon_list($seq) or return;
-	my $seqId = (ref($seq) and $seq->can('id'))? $seq->id : '';
+	my $seqId = (blessed($seq) and $seq->can('id'))? $seq->id : '';
 
 	# determine expected codon frequency if necessary
 	my $expectedCodonFreq;