Massive reorganization.

README

@@ -1,20 +1,29 @@
-These are the scripts I write as I do my work. You're free to use them but please cite me if you do.
+This repo contains visualization and analysis scripts that I've written to help me perform
+phylogenomic analyses. Almost all are written in Perl. Some require the Bioperl package.
 
-Notes:
-Many of the scripts require subfuncs.pl and circlegraph.pl, so unless you are
-planning to always call the scripts from the main directory, you might want to add
-this directory to your $PERL5LIB variable.
+Scripts that require the Bioperl package will either call the Bio package directly or require
+subfunctions that are in the file bioperl_subfuncs.pl. It might be easiest if you include
+this directory in your $PERL5LIB path so that the various subfunction files are easy for
+the interpreter to find.
 
 CircleGraph.pm is an object-oriented package that makes it easier to draw graphs along
-a circle. It makes postscript objects.
+a circle. It makes postscript objects and uses the Postscript::Simple package.
 
-subfuncs.pl is a random hodgepodge of utility functions.
+subfuncs.pl is a random hodgepodge of utility functions. As I write more of them, I may
+move some to more specific subfunction files to reduce overhead.
+
+bioperl_subfuncs.pl has helper functions that require Bioperl packages.
 
 circlegraph.pl has helper functions that draw specific kinds of circular graphs.
 
 The subdirs contain scripts for various tasks:
-- converting: helper scripts to convert files from one format to another
+- analysis: scripts that perform various analyses on datasets.
+    introgression: scripts to calculate statistics for introgression analysis.
+    selection: scripts that use Bioperl, PAML, HyPhy to analyze selection on genes.
+- converting: scripts to convert files from one format to another or to combine files
+  in various ways.
+- filtering: scripts that reduce complexity.
 - parsing: uses Bioperl to slice and dice sequence files in various ways.
 - plastome: scripts that take input about the plastome and draw circle graphs to
   represent that data.
-- selection_analysis: scripts that use Bioperl, PAML, HyPhy to analyze selection on genes.
+- reporting: scripts that take vcf or sequence files and report statistics about them.

reporting/vcf_to_depth.pl

@@ -0,0 +1,62 @@
+use File::Basename;
+use Getopt::Long;
+use Pod::Usage;
+require "subfuncs.pl";
+
+if (@ARGV == 0) {
+    pod2usage(-verbose => 1);
+}
+
+my $runline = "running " . basename($0) . " " . join (" ", @ARGV) . "\n";
+
+my $samplefile = 0;
+my $help = 0;
+my $outfile = "";
+
+GetOptions ('samples|input|vcf=s' => \$samplefile,
+            'outputfile=s' => \$outfile,
+            'help|?' => \$help) or pod2usage(-msg => "GetOptions failed.", -exitval => 2);
+
+if ($help) {
+    pod2usage(-verbose => 1);
+}
+
+print $runline;
+
+my @samples = @{sample_list ($samplefile)};
+if ($samplefile =~ /(.*?)\.vcf$/) {
+	@samples = ($1);
+}
+
+foreach my $sample (@samples) {
+	$name = basename($sample);
+	my $vcf_file = $sample . ".vcf";
+	if ($outfile ne "") {
+		vcf_to_depth ($vcf_file,$outfile);
+	} else {
+		vcf_to_depth ($vcf_file);
+	}
+}
+
+
+__END__
+
+=head1 NAME
+
+vcf_to_depth
+
+=head1 SYNOPSIS
+
+vcf_to_depth -samplefile -output [-threshold]
+
+=head1 OPTIONS
+
+  -samples|input|vcf:   name of sample or list of samples to convert
+  -outputfile:      optional: prefix of output fasta file
+
+=head1 DESCRIPTION
+
+Generates a summary file with the read depths of each position in the inputted vcf file(s).
+
+=cut
+

subfuncs.pl

@@ -501,5 +501,36 @@ sub meld_sequence_files {
 	return meld_matrices (\@matrixnames, \%matrices);
 }
 
+
+=head1
+
+B<String $out_file meld_matrices ( String $vcf_file, [String $out_file] )>
+
+Generates a summary file with the read depths of each position in the inputted vcf file.
+
+$vcf_file:  A vcf file.
+
+=cut
+
+
+
+sub vcf_to_depth {
+	my $vcf_file = shift;
+	my $out_file = shift;
+
+	$vcf_file =~ /(.+)(\.vcf)/;
+	my $basename = $1;
+
+	if ($out_file == 0) {
+		$out_file = "$basename.depth";
+	}
+
+	system ("awk 'BEGIN {OFS=\"\\t\"} /^.*?\\t(.*?)\\t/ {print \$1,\$2,\$8}' $vcf_file | awk 'BEGIN {OFS=\"\\t\"} {sub(/DP=/,\"\",\$3);sub(/;.*/,\"\",\$3);print \$1,\$2,\$3}' - > $out_file");
+
+	return $out_file;
+}
+
+
+
 # must return 1 for the file overall.
 1;