added missing files

[biopieces.git] / code_perl / Maasha / Seq.pm

diff --git a/code_perl/Maasha/Seq.pm b/code_perl/Maasha/Seq.pm
index 12839653b5fbb4dec3b992401c22eda77edce6b9..4d6c7997665eb2ff19d4e2e44b6c035de841dbd4 100644 (file)
--- a/code_perl/Maasha/Seq.pm
+++ b/code_perl/Maasha/Seq.pm
@@ -28,6 +28,7 @@ package Maasha::Seq;
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
 
 
+use warnings;
 use strict;
 use POSIX qw( islower );
 use Maasha::Common;
@@ -64,11 +65,11 @@ sub seq_guess_type
     }
 
     if ( $count = $check_seq =~ tr/FLPQIEflpqie// and $count > 0 ) {
-        return "protein";
+        return "PROTEIN";
     } elsif ( $count = $check_seq =~ tr/Uu// and $count > 0 ) {
-        return "rna";
+        return "RNA";
     } else {
-        return "dna";
+        return "DNA";
     }
 }
 
@@ -779,6 +780,56 @@ sub seq_generate
 }
 
 
+sub seq_insert
+{
+    # Martin A. Hansen, June 2009.
+
+    # Randomly duplicates a given number of residues in a given sequence.
+
+    my ( $seq,          # sequence to mutate
+         $insertions,   # number of residues to insert
+       ) = @_;
+
+    # Returns a string.
+
+    my ( $i, $pos );
+
+    for ( $i = 0; $i < $insertions; $i++ )
+    {
+        $pos = int( rand( length $seq ) );
+
+        substr $seq, $pos, 0, substr $seq , $pos, 1;
+    }
+
+    return $seq;
+}
+
+
+sub seq_delete
+{
+    # Martin A. Hansen, June 2009.
+
+    # Randomly deletes a given number of residues from a given sequence.
+
+    my ( $seq,         # sequence to mutate
+         $deletions,   # number of residues to delete
+       ) = @_;
+
+    # Returns a string.
+
+    my ( $i, $pos );
+
+    for ( $i = 0; $i < $deletions; $i++ )
+    {
+        $pos = int( rand( length $seq ) );
+
+        substr $seq, $pos, 1, '';
+    }
+
+    return $seq;
+}
+
+
 sub seq_mutate
 {
     # Martin A. Hansen, June 2009.
@@ -863,26 +914,30 @@ sub seq_alph
 {
     # Martin A. Hansen, May 2007.
 
-    # returns a requested alphabet
+    # Returns a requested sequence alphabet.
 
     my ( $type,   # alphabet type
        ) = @_;
 
     # returns list
 
-    my ( @alph );
+    my ( %alph_hash, $alph );
+
+    %alph_hash = (
+        DNA      => [ qw(A T C G) ],
+        DNA_AMBI => [ qw(A G C U T R Y W S M K H D V B N) ],
+        RNA      => [ qw(A U C G) ],
+        RNA_AMBI => [ qw(A G C U T R Y W S M K H D V B N) ],
+        PROTEIN  => [ qw(F L S Y C W P H Q R I M T N K V A D E G) ],
+    );
 
-    if ( $type =~ /^dna$/i ) {
-        @alph = qw( A T C G );
-    } elsif ( $type =~ /^rna$/i ) {
-        @alph = qw( A U C G );
-    } elsif ( $type =~ /^prot/i ) {
-        @alph = qw( F L S Y C W P H Q R I M T N K V A D E G );
+    if ( exists $alph_hash{ uc $type } ) {
+        $alph = $alph_hash{ uc $type };
     } else {
         die qq(ERROR: Unknown alphabet type: "$type"\n);
     }
 
-    return wantarray ? @alph : \@alph;
+    return wantarray ? @{ $alph } : $alph;
 }
 
 
@@ -899,7 +954,7 @@ sub seq_analyze
 
     my ( %analysis, @chars, @chars_lc, $char, %char_hash, $gc, $at, $lc, $max, $res_sum, @indels, %indel_hash );
 
-    $analysis{ "SEQ_TYPE" } = uc Maasha::Seq::seq_guess_type( $seq );
+    $analysis{ "SEQ_TYPE" } = Maasha::Seq::seq_guess_type( $seq );
     $analysis{ "SEQ_LEN" }  = length $seq;
 
     @indels = qw( - ~ . _ );
@@ -954,7 +1009,7 @@ sub seq_analyze
     map { $analysis{ "RES[$_]" } = $indel_hash{ $_ } } @indels;
 
     $analysis{ "MIX_INDEX" } = sprintf( "%.2f", $max / $analysis{ "SEQ_LEN" } );
-    $analysis{ "MELT_TEMP" } = sprintf( "%.2f", 4 * $gc + 2 * $at );
+    #$analysis{ "MELT_TEMP" } = sprintf( "%.2f", 4 * $gc + 2 * $at );
 
     return wantarray ? %analysis : \%analysis;
 }