Parent Directory
| 
Revision Log
Revision 1.3 - (view) (download) (as text)
| 1 : | parrello | 1.1 | #!/usr/bin/perl -w |
| 2 : | |||
| 3 : | package ContigDNA; | ||
| 4 : | |||
| 5 : | use strict; | ||
| 6 : | use Tracer; | ||
| 7 : | use FIG; | ||
| 8 : | use Genome; | ||
| 9 : | |||
| 10 : | =head1 Contig DNA manipulation object | ||
| 11 : | |||
| 12 : | =head2 Introduction | ||
| 13 : | |||
| 14 : | This method creates a pseudo-FIG object for use by the B<FullLocation> object. It | ||
| 15 : | supports the L</contig_ln> and L</dna_seq> methods. | ||
| 16 : | |||
| 17 : | Note that it keeps all the data structures in memory, so it should not be used except for | ||
| 18 : | a few genomes with small number of gen | ||
| 19 : | |||
| 20 : | =cut | ||
| 21 : | |||
| 22 : | =head2 Public Methods | ||
| 23 : | |||
| 24 : | =head3 new | ||
| 25 : | |||
| 26 : | parrello | 1.2 | my $cdna = ContigDNA->new($genID1 => $file1, $genID2 => $file, ... $genIDN => $fileN ); |
| 27 : | parrello | 1.1 | |
| 28 : | Construct a new pseudo-FIG object from a set of FASTA files. The incoming parameters come | ||
| 29 : | in pairs. The first of each pair is the ID of a genome; the second is the name of a FASTA | ||
| 30 : | file containing the contig data. | ||
| 31 : | |||
| 32 : | =over 4 | ||
| 33 : | |||
| 34 : | =item genID1, genID2, ... genIDN | ||
| 35 : | |||
| 36 : | IDs of the genomes whose contigs are to be read into memory. | ||
| 37 : | |||
| 38 : | =item file1, file2, ... fileN | ||
| 39 : | |||
| 40 : | Names of the FASTA files containing the genome data. | ||
| 41 : | |||
| 42 : | parrello | 1.3 | =back |
| 43 : | |||
| 44 : | parrello | 1.1 | =cut |
| 45 : | |||
| 46 : | sub new { | ||
| 47 : | # Get the parameters. | ||
| 48 : | my ($class, %files) = @_; | ||
| 49 : | # Create the object. | ||
| 50 : | my $retVal = { }; | ||
| 51 : | # Loop through the genomes. | ||
| 52 : | for my $genID (keys %files) { | ||
| 53 : | # Get the name of this genome's FASTA file. | ||
| 54 : | my $file = $files{$genID}; | ||
| 55 : | # Read it in using the Genome object. | ||
| 56 : | my $genomeData = Genome->new($genID, $file, ""); | ||
| 57 : | # Put it in the hash. | ||
| 58 : | $retVal->{$genID} = $genomeData; | ||
| 59 : | } | ||
| 60 : | # Bless and return it. | ||
| 61 : | bless $retVal, $class; | ||
| 62 : | return $retVal; | ||
| 63 : | } | ||
| 64 : | |||
| 65 : | =head3 dna_seq | ||
| 66 : | |||
| 67 : | parrello | 1.2 | my $sequence = $sfxlate->dna_seq($genomeID, @locations); |
| 68 : | parrello | 1.1 | |
| 69 : | Return the sequence represented by a list of locations. The locations | ||
| 70 : | should be in the standard form I<contigID>C<_>I<begin>I<dir>I<end>. | ||
| 71 : | |||
| 72 : | =over 4 | ||
| 73 : | |||
| 74 : | =item genomeID | ||
| 75 : | |||
| 76 : | ID of the relevant genome. | ||
| 77 : | |||
| 78 : | =item location1, location2, ... locationN | ||
| 79 : | |||
| 80 : | List of locations to be included in the DNA sequence. | ||
| 81 : | |||
| 82 : | =item RETURN | ||
| 83 : | |||
| 84 : | Returns a string specifying the DNA nucleotides in the specified locations. | ||
| 85 : | |||
| 86 : | =back | ||
| 87 : | |||
| 88 : | =cut | ||
| 89 : | #: Return Type $; | ||
| 90 : | sub dna_seq { | ||
| 91 : | # Get the parameters. | ||
| 92 : | my ($self, $genomeID, @locations) = @_; | ||
| 93 : | # Get the Genome object. | ||
| 94 : | my $genome = $self->{$genomeID}; | ||
| 95 : | # Start the return string. | ||
| 96 : | my $retVal = ""; | ||
| 97 : | # Loop through the locations. | ||
| 98 : | for my $location (@locations) { | ||
| 99 : | # Get the DNA. | ||
| 100 : | my $dna = $genome->GetLocation($location); | ||
| 101 : | # Add it to the return string. | ||
| 102 : | $retVal .= $dna; | ||
| 103 : | } | ||
| 104 : | # Return the result. | ||
| 105 : | return $retVal; | ||
| 106 : | } | ||
| 107 : | |||
| 108 : | =head3 contig_ln | ||
| 109 : | |||
| 110 : | parrello | 1.2 | my $length = $sfxlate->contig_ln($genomeID, $contig); |
| 111 : | parrello | 1.1 | |
| 112 : | Return the length of the specified contig. | ||
| 113 : | |||
| 114 : | =over 4 | ||
| 115 : | |||
| 116 : | =item genomeID | ||
| 117 : | |||
| 118 : | ID of the genome to which the contig belongs. | ||
| 119 : | |||
| 120 : | =item contigID | ||
| 121 : | |||
| 122 : | ID of the contig whose length is desired. | ||
| 123 : | |||
| 124 : | =item RETURN | ||
| 125 : | |||
| 126 : | Returns the length (in base pairs) of the specified contig in the specified | ||
| 127 : | genome. | ||
| 128 : | |||
| 129 : | =back | ||
| 130 : | |||
| 131 : | =cut | ||
| 132 : | #: Return Type $; | ||
| 133 : | sub contig_ln { | ||
| 134 : | my($self, $genomeID, $contigID) = @_; | ||
| 135 : | my $genome = $self->{$genomeID}; | ||
| 136 : | return $genome->ContigLen($contigID); | ||
| 137 : | } | ||
| 138 : | |||
| 139 : | 1; | ||
| 140 : |
| MCS Webmaster | ViewVC Help |
| Powered by ViewVC 1.0.3 |