Mercurial > repos > deepakjadmin > mayatool3_test3
diff mayachemtools/docs/modules/html/code/SequenceFileUtil.html @ 0:73ae111cf86f draft
Uploaded
| author | deepakjadmin |
|---|---|
| date | Wed, 20 Jan 2016 11:55:01 -0500 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mayachemtools/docs/modules/html/code/SequenceFileUtil.html Wed Jan 20 11:55:01 2016 -0500 @@ -0,0 +1,938 @@ +<html> +<head> +<title>MayaChemTools:Code:SequenceFileUtil.pm</title> +<meta http-equiv="content-type" content="text/html;charset=utf-8"> +<link rel="stylesheet" type="text/css" href="../../../css/MayaChemToolsCode.css"> +</head> +<body leftmargin="20" rightmargin="20" topmargin="10" bottommargin="10"> +<br/> +<center> +<a href="http://www.mayachemtools.org" title="MayaChemTools Home"><img src="../../../images/MayaChemToolsLogo.gif" border="0" alt="MayaChemTools"></a> +</center> +<br/> +<pre> +<a name="package-SequenceFileUtil-"></a> 1 <span class="k">package </span><span class="i">SequenceFileUtil</span><span class="sc">;</span> + 2 <span class="c">#</span> + 3 <span class="c"># $RCSfile: SequenceFileUtil.pm,v $</span> + 4 <span class="c"># $Date: 2015/02/28 20:47:18 $</span> + 5 <span class="c"># $Revision: 1.33 $</span> + 6 <span class="c">#</span> + 7 <span class="c"># Author: Manish Sud <msud@san.rr.com></span> + 8 <span class="c">#</span> + 9 <span class="c"># Copyright (C) 2015 Manish Sud. All rights reserved.</span> + 10 <span class="c">#</span> + 11 <span class="c"># This file is part of MayaChemTools.</span> + 12 <span class="c">#</span> + 13 <span class="c"># MayaChemTools is free software; you can redistribute it and/or modify it under</span> + 14 <span class="c"># the terms of the GNU Lesser General Public License as published by the Free</span> + 15 <span class="c"># Software Foundation; either version 3 of the License, or (at your option) any</span> + 16 <span class="c"># later version.</span> + 17 <span class="c">#</span> + 18 <span class="c"># MayaChemTools is distributed in the hope that it will be useful, but without</span> + 19 <span class="c"># any warranty; without even the implied warranty of merchantability of fitness</span> + 20 <span class="c"># for a particular purpose. See the GNU Lesser General Public License for more</span> + 21 <span class="c"># details.</span> + 22 <span class="c">#</span> + 23 <span class="c"># You should have received a copy of the GNU Lesser General Public License</span> + 24 <span class="c"># along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or</span> + 25 <span class="c"># write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,</span> + 26 <span class="c"># Boston, MA, 02111-1307, USA.</span> + 27 <span class="c">#</span> + 28 + 29 <span class="k">use</span> <span class="w">strict</span><span class="sc">;</span> + 30 <span class="k">use</span> <span class="w">Exporter</span><span class="sc">;</span> + 31 <span class="k">use</span> <span class="w">Text::ParseWords</span><span class="sc">;</span> + 32 <span class="k">use</span> <span class="w">TextUtil</span><span class="sc">;</span> + 33 <span class="k">use</span> <span class="w">FileUtil</span><span class="sc">;</span> + 34 + 35 <span class="k">use</span> <span class="w">vars</span> <span class="q">qw(@ISA @EXPORT @EXPORT_OK %EXPORT_TAGS)</span><span class="sc">;</span> + 36 + 37 <span class="i">@ISA</span> = <span class="q">qw(Exporter)</span><span class="sc">;</span> + 38 <span class="i">@EXPORT</span> = <span class="q">qw(AreSequenceLengthsIdentical CalcuatePercentSequenceIdentity CalculatePercentSequenceIdentityMatrix GetLongestSequence GetShortestSequence GetSequenceLength IsGapResidue IsSupportedSequenceFile IsClustalWSequenceFile IsPearsonFastaSequenceFile IsMSFSequenceFile ReadSequenceFile RemoveSequenceGaps RemoveSequenceAlignmentGapColumns WritePearsonFastaSequenceFile)</span><span class="sc">;</span> + 39 <span class="i">@EXPORT_OK</span> = <span class="q">qw()</span><span class="sc">;</span> + 40 + 41 <span class="i">%EXPORT_TAGS</span> = <span class="s">(</span><span class="w">all</span> <span class="cm">=></span> <span class="s">[</span><span class="i">@EXPORT</span><span class="cm">,</span> <span class="i">@EXPORT_OK</span><span class="s">]</span><span class="s">)</span><span class="sc">;</span> + 42 + 43 <span class="c"># Compare lengths of all sequences...</span> +<a name="AreSequenceLengthsIdentical-"></a> 44 <span class="k">sub </span><span class="m">AreSequenceLengthsIdentical</span> <span class="s">{</span> + 45 <span class="k">my</span><span class="s">(</span><span class="i">$SequencesDataRef</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 46 <span class="k">my</span><span class="s">(</span><span class="i">$Status</span><span class="cm">,</span> <span class="i">$ID</span><span class="cm">,</span> <span class="i">$FirstID</span><span class="cm">,</span> <span class="i">$FirstSeqLen</span><span class="cm">,</span> <span class="i">$FirstDifferentLenID</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="s">)</span><span class="sc">;</span> + 47 + 48 <span class="i">$Status</span> = <span class="n">1</span><span class="sc">;</span> + 49 <span class="i">$FirstID</span> = <span class="q">''</span><span class="sc">;</span> + 50 <span class="i">$FirstDifferentLenID</span> = <span class="q">''</span><span class="sc">;</span> + 51 + 52 <span class="j">ID:</span> <span class="k">for</span> <span class="i">$ID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$SequencesDataRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 53 <span class="k">if</span> <span class="s">(</span>!<span class="i">$FirstID</span><span class="s">)</span> <span class="s">{</span> + 54 <span class="i">$FirstID</span> = <span class="i">$ID</span><span class="sc">;</span> + 55 <span class="i">$FirstSeqLen</span> = <span class="k">length</span><span class="s">(</span><span class="i">$SequencesDataRef</span>->{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="s">)</span><span class="sc">;</span> + 56 <span class="k">next</span> <span class="j">ID</span><span class="sc">;</span> + 57 <span class="s">}</span> + 58 <span class="i">$SeqLen</span> = <span class="k">length</span><span class="s">(</span><span class="i">$SequencesDataRef</span>->{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="s">)</span><span class="sc">;</span> + 59 <span class="k">if</span> <span class="s">(</span><span class="i">$SeqLen</span> != <span class="i">$FirstSeqLen</span><span class="s">)</span> <span class="s">{</span> + 60 <span class="i">$Status</span> = <span class="n">0</span><span class="sc">;</span> + 61 <span class="i">$FirstDifferentLenID</span> = <span class="i">$ID</span><span class="sc">;</span> + 62 <span class="k">last</span> <span class="j">ID</span><span class="sc">;</span> + 63 <span class="s">}</span> + 64 <span class="s">}</span> + 65 <span class="k">return</span> <span class="s">(</span><span class="i">$Status</span><span class="s">)</span><span class="sc">;</span> + 66 <span class="s">}</span> + 67 + 68 <span class="c"># Calculate percent identity between two sequences. By default, gaps are ignored.</span> +<a name="CalcuatePercentSequenceIdentity-"></a> 69 <span class="k">sub </span><span class="m">CalcuatePercentSequenceIdentity</span> <span class="s">{</span> + 70 <span class="k">my</span><span class="s">(</span><span class="i">$Sequence1</span><span class="cm">,</span> <span class="i">$Sequence2</span><span class="cm">,</span> <span class="i">$PercentIdentity</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="cm">,</span> <span class="i">$Precision</span><span class="s">)</span><span class="sc">;</span> + 71 + 72 <span class="i">$PercentIdentity</span> = <span class="q">''</span><span class="sc">;</span> + 73 <span class="i">$Precision</span> = <span class="n">1</span><span class="sc">;</span> + 74 <span class="i">$IgnoreGaps</span> = <span class="n">1</span><span class="sc">;</span> + 75 <span class="k">if</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">4</span><span class="s">)</span> <span class="s">{</span> + 76 <span class="s">(</span><span class="i">$Sequence1</span><span class="cm">,</span> <span class="i">$Sequence2</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="cm">,</span> <span class="i">$Precision</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 77 <span class="s">}</span> + 78 <span class="k">elsif</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">3</span><span class="s">)</span> <span class="s">{</span> + 79 <span class="s">(</span><span class="i">$Sequence1</span><span class="cm">,</span> <span class="i">$Sequence2</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 80 <span class="s">}</span> + 81 <span class="k">elsif</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">2</span><span class="s">)</span> <span class="s">{</span> + 82 <span class="s">(</span><span class="i">$Sequence1</span><span class="cm">,</span> <span class="i">$Sequence2</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 83 <span class="s">}</span> + 84 <span class="k">else</span> <span class="s">{</span> + 85 <span class="k">return</span> <span class="i">$PercentIdentity</span><span class="sc">;</span> + 86 <span class="s">}</span> + 87 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="i">IsNotEmpty</span><span class="s">(</span><span class="i">$Sequence1</span><span class="s">)</span> && <span class="i">IsNotEmpty</span><span class="s">(</span><span class="i">$Sequence2</span><span class="s">)</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 88 <span class="k">return</span> <span class="i">$PercentIdentity</span><span class="sc">;</span> + 89 <span class="s">}</span> + 90 <span class="k">my</span><span class="s">(</span><span class="i">$Index</span><span class="cm">,</span> <span class="i">$Identity</span><span class="cm">,</span> <span class="i">$Sequence1Len</span><span class="cm">,</span> <span class="i">$Sequence2Len</span><span class="cm">,</span> <span class="i">$Residue1</span><span class="cm">,</span> <span class="i">$Residue2</span><span class="cm">,</span> <span class="i">$ResMatchCount</span><span class="cm">,</span> <span class="i">$ResCount</span><span class="s">)</span><span class="sc">;</span> + 91 + 92 <span class="i">$Sequence1Len</span> = <span class="k">length</span><span class="s">(</span><span class="i">$Sequence1</span><span class="s">)</span><span class="sc">;</span> + 93 <span class="i">$Sequence2Len</span> = <span class="k">length</span><span class="s">(</span><span class="i">$Sequence2</span><span class="s">)</span><span class="sc">;</span> + 94 + 95 <span class="i">$ResMatchCount</span> = <span class="n">0</span><span class="sc">;</span> + 96 <span class="i">$ResCount</span> = <span class="n">0</span><span class="sc">;</span> + 97 <span class="j">RESIDUE:</span> <span class="k">for</span> <span class="i">$Index</span> <span class="s">(</span><span class="n">0</span> .. <span class="s">(</span><span class="i">$Sequence1Len</span> - <span class="n">1</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 98 <span class="i">$Residue1</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$Sequence1</span><span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span><span class="sc">;</span> + 99 <span class="i">$Residue2</span> = <span class="s">(</span><span class="i">$Index</span> < <span class="i">$Sequence2Len</span><span class="s">)</span> ? <span class="k">substr</span><span class="s">(</span><span class="i">$Sequence2</span><span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span> <span class="co">:</span> <span class="q">''</span><span class="sc">;</span> + 100 <span class="k">if</span> <span class="s">(</span><span class="i">$IgnoreGaps</span><span class="s">)</span> <span class="s">{</span> + 101 <span class="k">if</span> <span class="s">(</span><span class="i">$Residue1</span> !~ <span class="q">/[A-Z]/i</span> || <span class="i">$Residue2</span> !~ <span class="q">/[A-Z]/i</span><span class="s">)</span> <span class="s">{</span> + 102 <span class="k">next</span> <span class="j">RESIDUE</span><span class="sc">;</span> + 103 <span class="s">}</span> + 104 <span class="s">}</span> + 105 <span class="k">if</span> <span class="s">(</span><span class="i">$Residue1</span> <span class="k">eq</span> <span class="i">$Residue2</span><span class="s">)</span> <span class="s">{</span> + 106 <span class="i">$ResMatchCount</span>++<span class="sc">;</span> + 107 <span class="s">}</span> + 108 <span class="i">$ResCount</span>++<span class="sc">;</span> + 109 <span class="s">}</span> + 110 <span class="i">$Identity</span> = <span class="i">$ResCount</span> ? <span class="s">(</span><span class="i">$ResMatchCount</span>/<span class="i">$ResCount</span><span class="s">)</span> <span class="co">:</span> <span class="n">0.0</span><span class="sc">;</span> + 111 <span class="i">$PercentIdentity</span> = <span class="k">sprintf</span><span class="s">(</span><span class="q">"%.${Precision}f"</span><span class="cm">,</span> <span class="s">(</span><span class="i">$Identity</span> * <span class="n">100</span><span class="s">)</span><span class="s">)</span><span class="sc">;</span> + 112 + 113 <span class="k">return</span> <span class="i">$PercentIdentity</span><span class="sc">;</span> + 114 <span class="s">}</span> + 115 + 116 <span class="c"># Calculate pairwise identify matrix for all the sequences and return a reference</span> + 117 <span class="c"># to a hash with the following keys:</span> + 118 <span class="c">#</span> + 119 <span class="c"># {IDs} - Sequence IDs</span> + 120 <span class="c"># {Count} - Number of IDs</span> + 121 <span class="c"># {PercentIdentity}{$RowID}{$ColID} - Percent identify for a pair of sequences</span> + 122 <span class="c">#</span> +<a name="CalculatePercentSequenceIdentityMatrix-"></a> 123 <span class="k">sub </span><span class="m">CalculatePercentSequenceIdentityMatrix</span> <span class="s">{</span> + 124 <span class="k">my</span><span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="cm">,</span> <span class="cm">,</span> <span class="i">$Precision</span><span class="cm">,</span> <span class="i">$ID</span><span class="cm">,</span> <span class="i">$RowID</span><span class="cm">,</span> <span class="i">$ColID</span><span class="cm">,</span> <span class="i">$RowIDSeq</span><span class="cm">,</span> <span class="i">$ColIDSeq</span><span class="cm">,</span> <span class="i">$PercentIdentity</span><span class="cm">,</span> <span class="i">%IdentityMatrixData</span><span class="s">)</span><span class="sc">;</span> + 125 + 126 <span class="i">$IgnoreGaps</span> = <span class="n">1</span><span class="sc">;</span> + 127 <span class="i">$Precision</span> = <span class="n">1</span><span class="sc">;</span> + 128 <span class="k">if</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">3</span><span class="s">)</span> <span class="s">{</span> + 129 <span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="cm">,</span> <span class="i">$Precision</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 130 <span class="s">}</span> + 131 <span class="k">elsif</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">2</span><span class="s">)</span> <span class="s">{</span> + 132 <span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 133 <span class="s">}</span> + 134 <span class="k">else</span> <span class="s">{</span> + 135 <span class="s">(</span><span class="i">$SequencesDataRef</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 136 <span class="s">}</span> + 137 + 138 <span class="i">%IdentityMatrixData</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 139 <span class="i">@</span>{<span class="i">$IdentityMatrixData</span>{<span class="w">IDs</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 140 <span class="i">%</span>{<span class="i">$IdentityMatrixData</span>{<span class="w">PercentIdentity</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 141 <span class="i">$IdentityMatrixData</span>{<span class="w">Count</span>} = <span class="n">0</span><span class="sc">;</span> + 142 + 143 <span class="k">for</span> <span class="i">$ID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$SequencesDataRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 144 <span class="k">push</span> <span class="i">@</span>{<span class="i">$IdentityMatrixData</span>{<span class="w">IDs</span>}}<span class="cm">,</span> <span class="i">$ID</span><span class="sc">;</span> + 145 <span class="i">$IdentityMatrixData</span>{<span class="w">Count</span>} += <span class="n">1</span><span class="sc">;</span> + 146 <span class="s">}</span> + 147 <span class="c"># Initialize and calculate percent identity data values...</span> + 148 <span class="k">for</span> <span class="i">$RowID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$SequencesDataRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 149 <span class="i">%</span>{<span class="i">$IdentityMatrixData</span>{<span class="w">PercentIdentity</span>}{<span class="i">$RowID</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 150 <span class="i">$RowIDSeq</span> = <span class="i">$SequencesDataRef</span>->{<span class="w">Sequence</span>}{<span class="i">$RowID</span>}<span class="sc">;</span> + 151 <span class="k">for</span> <span class="i">$ColID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$SequencesDataRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 152 <span class="i">$IdentityMatrixData</span>{<span class="i">$RowID</span>}{<span class="i">$ColID</span>} = <span class="q">''</span><span class="sc">;</span> + 153 <span class="i">$ColIDSeq</span> = <span class="i">$SequencesDataRef</span>->{<span class="w">Sequence</span>}{<span class="i">$ColID</span>}<span class="sc">;</span> + 154 <span class="i">$PercentIdentity</span> = <span class="i">CalcuatePercentSequenceIdentity</span><span class="s">(</span><span class="i">$RowIDSeq</span><span class="cm">,</span> <span class="i">$ColIDSeq</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="cm">,</span> <span class="i">$Precision</span><span class="s">)</span><span class="sc">;</span> + 155 <span class="i">$IdentityMatrixData</span>{<span class="w">PercentIdentity</span>}{<span class="i">$RowID</span>}{<span class="i">$ColID</span>} = <span class="i">$PercentIdentity</span><span class="sc">;</span> + 156 <span class="s">}</span> + 157 <span class="s">}</span> + 158 <span class="k">return</span> \<span class="i">%IdentityMatrixData</span><span class="sc">;</span> + 159 <span class="s">}</span> + 160 + 161 <span class="c"># Retrieve information about shortest sequence...</span> +<a name="GetShortestSequence-"></a> 162 <span class="k">sub </span><span class="m">GetShortestSequence</span> <span class="s">{</span> + 163 <span class="k">my</span><span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="cm">,</span> <span class="i">$ID</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span><span class="sc">;</span> + 164 + 165 <span class="i">$IgnoreGaps</span> = <span class="n">1</span><span class="sc">;</span> + 166 <span class="k">if</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">2</span><span class="s">)</span> <span class="s">{</span> + 167 <span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 168 <span class="s">}</span> + 169 <span class="k">else</span> <span class="s">{</span> + 170 <span class="s">(</span><span class="i">$SequencesDataRef</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 171 <span class="s">}</span> + 172 + 173 <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span> = <span class="i">_GetShortestOrLongestSequence</span><span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="q">'Shortest'</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span><span class="sc">;</span> + 174 <span class="k">return</span> <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span><span class="sc">;</span> + 175 <span class="s">}</span> + 176 + 177 <span class="c"># Retrieve information about longest sequence..</span> +<a name="GetLongestSequence-"></a> 178 <span class="k">sub </span><span class="m">GetLongestSequence</span> <span class="s">{</span> + 179 <span class="k">my</span><span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="cm">,</span> <span class="i">$ID</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span><span class="sc">;</span> + 180 + 181 <span class="i">$IgnoreGaps</span> = <span class="n">1</span><span class="sc">;</span> + 182 <span class="k">if</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">2</span><span class="s">)</span> <span class="s">{</span> + 183 <span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 184 <span class="s">}</span> + 185 <span class="k">else</span> <span class="s">{</span> + 186 <span class="s">(</span><span class="i">$SequencesDataRef</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 187 <span class="s">}</span> + 188 + 189 <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span> = <span class="i">_GetShortestOrLongestSequence</span><span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="q">'Longest'</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span><span class="sc">;</span> + 190 <span class="k">return</span> <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span><span class="sc">;</span> + 191 <span class="s">}</span> + 192 + 193 <span class="c"># Get sequence length...</span> +<a name="GetSequenceLength-"></a> 194 <span class="k">sub </span><span class="m">GetSequenceLength</span> <span class="s">{</span> + 195 <span class="k">my</span><span class="s">(</span><span class="i">$Seq</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span><span class="sc">;</span> + 196 + 197 <span class="i">$SeqLen</span> = <span class="q">''</span><span class="sc">;</span> <span class="i">$IgnoreGaps</span> = <span class="n">1</span><span class="sc">;</span> + 198 <span class="k">if</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">2</span><span class="s">)</span> <span class="s">{</span> + 199 <span class="s">(</span><span class="i">$Seq</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 200 <span class="s">}</span> + 201 <span class="k">else</span> <span class="s">{</span> + 202 <span class="s">(</span><span class="i">$Seq</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 203 <span class="s">}</span> + 204 <span class="k">if</span> <span class="s">(</span><span class="i">$IgnoreGaps</span><span class="s">)</span> <span class="s">{</span> + 205 <span class="k">my</span><span class="s">(</span><span class="i">$Index</span><span class="cm">,</span> <span class="i">$Residue</span><span class="s">)</span><span class="sc">;</span> + 206 <span class="i">$SeqLen</span> = <span class="n">0</span><span class="sc">;</span> + 207 <span class="k">for</span> <span class="i">$Index</span> <span class="s">(</span><span class="n">0</span> .. <span class="s">(</span><span class="k">length</span><span class="s">(</span><span class="i">$Seq</span><span class="s">)</span> - <span class="n">1</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 208 <span class="i">$Residue</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$Seq</span><span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span><span class="sc">;</span> + 209 <span class="k">if</span> <span class="s">(</span><span class="i">$Residue</span> =~ <span class="q">/[A-Z]/i</span><span class="s">)</span> <span class="s">{</span> + 210 <span class="i">$SeqLen</span>++<span class="sc">;</span> + 211 <span class="s">}</span> + 212 <span class="s">}</span> + 213 <span class="s">}</span> + 214 <span class="k">else</span> <span class="s">{</span> + 215 <span class="i">$SeqLen</span> = <span class="k">length</span><span class="s">(</span><span class="i">$Seq</span><span class="s">)</span><span class="sc">;</span> + 216 <span class="s">}</span> + 217 + 218 <span class="k">return</span> <span class="i">$SeqLen</span><span class="sc">;</span> + 219 <span class="s">}</span> + 220 + 221 <span class="c"># Is it a gap residue...</span> +<a name="IsGapResidue-"></a> 222 <span class="k">sub </span><span class="m">IsGapResidue</span> <span class="s">{</span> + 223 <span class="k">my</span><span class="s">(</span><span class="i">$Residue</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 224 <span class="k">my</span><span class="s">(</span><span class="i">$Status</span><span class="s">)</span><span class="sc">;</span> + 225 + 226 <span class="i">$Status</span> = <span class="s">(</span><span class="i">$Residue</span> !~ <span class="q">/[A-Z]/i</span> <span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span> + 227 + 228 <span class="k">return</span> <span class="i">$Status</span><span class="sc">;</span> + 229 <span class="s">}</span> + 230 + 231 <span class="c"># Is it a supported sequence file?</span> + 232 <span class="c">#</span> + 233 <span class="c"># Supported seqence formats are:</span> + 234 <span class="c">#</span> + 235 <span class="c"># ALN/ClustalW .aln</span> + 236 <span class="c"># GCG/MSF .msf</span> + 237 <span class="c"># PILEUP/MSF .msf</span> + 238 <span class="c"># Fasts(Pearson) .fasta, .fta</span> + 239 <span class="c"># NBRF/PIR .pir</span> + 240 <span class="c">#</span> +<a name="IsSupportedSequenceFile-"></a> 241 <span class="k">sub </span><span class="m">IsSupportedSequenceFile</span> <span class="s">{</span> + 242 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 243 <span class="k">my</span><span class="s">(</span><span class="i">$Status</span><span class="cm">,</span> <span class="i">$SequenceFormat</span><span class="s">)</span><span class="sc">;</span> + 244 <span class="i">$Status</span> = <span class="n">0</span><span class="sc">;</span> <span class="i">$SequenceFormat</span> = <span class="q">'NotSupported'</span><span class="sc">;</span> + 245 + 246 <span class="j">SEQFORMAT:</span> <span class="s">{</span> + 247 <span class="k">if</span> <span class="s">(</span><span class="i">IsClustalWSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span><span class="i">$Status</span> = <span class="n">1</span><span class="sc">;</span> <span class="i">$SequenceFormat</span> = <span class="q">'ClustalW'</span><span class="sc">;</span> <span class="k">last</span> <span class="j">SEQFORMAT</span><span class="s">}</span> + 248 <span class="k">if</span> <span class="s">(</span><span class="i">IsPearsonFastaSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span><span class="i">$Status</span> = <span class="n">1</span><span class="sc">;</span> <span class="i">$SequenceFormat</span> = <span class="q">'Pearson'</span><span class="sc">;</span> <span class="k">last</span> <span class="j">SEQFORMAT</span><span class="s">}</span> + 249 <span class="k">if</span> <span class="s">(</span><span class="i">IsPIRFastaSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span><span class="i">$Status</span> = <span class="n">1</span><span class="sc">;</span> <span class="i">$SequenceFormat</span> = <span class="q">'PIR'</span><span class="sc">;</span> <span class="k">last</span> <span class="j">SEQFORMAT</span><span class="s">}</span> + 250 <span class="k">if</span> <span class="s">(</span><span class="i">IsMSFSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span><span class="i">$Status</span> = <span class="n">1</span><span class="sc">;</span> <span class="i">$SequenceFormat</span> = <span class="q">'MSF'</span><span class="sc">;</span> <span class="k">last</span> <span class="j">SEQFORMAT</span><span class="s">}</span> + 251 <span class="i">$Status</span> = <span class="n">0</span><span class="sc">;</span> <span class="i">$SequenceFormat</span> = <span class="q">'NotSupported'</span><span class="sc">;</span> + 252 <span class="s">}</span> + 253 <span class="k">return</span> <span class="s">(</span><span class="i">$Status</span><span class="cm">,</span> <span class="i">$SequenceFormat</span><span class="s">)</span><span class="sc">;</span> + 254 <span class="s">}</span> + 255 + 256 <span class="c"># Is it a ClustalW multiple sequence sequence file...</span> +<a name="IsClustalWSequenceFile-"></a> 257 <span class="k">sub </span><span class="m">IsClustalWSequenceFile</span> <span class="s">{</span> + 258 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 259 <span class="k">my</span><span class="s">(</span><span class="i">$Status</span><span class="cm">,</span> <span class="i">$Line</span><span class="s">)</span><span class="sc">;</span> + 260 + 261 <span class="i">$Status</span> = <span class="n">0</span><span class="sc">;</span> + 262 + 263 <span class="k">open</span> <span class="w">SEQUENCEFILE</span><span class="cm">,</span> <span class="q">"$SequenceFile"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Couldn't open $SequenceFile: $!\n"</span><span class="sc">;</span> + 264 <span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*SEQUENCEFILE</span><span class="s">)</span><span class="sc">;</span> + 265 <span class="i">$Status</span> = <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/(ClustalW|Clustal W|Clustal)/i</span> <span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span> + 266 <span class="k">close</span> <span class="w">SEQUENCEFILE</span><span class="sc">;</span> + 267 + 268 <span class="k">return</span> <span class="i">$Status</span><span class="sc">;</span> + 269 <span class="s">}</span> + 270 + 271 <span class="c"># Is it a valid Pearson fasta sequence or alignment file?</span> + 272 <span class="c">#</span> +<a name="IsPearsonFastaSequenceFile-"></a> 273 <span class="k">sub </span><span class="m">IsPearsonFastaSequenceFile</span> <span class="s">{</span> + 274 <span class="k">my</span><span class="s">(</span><span class="i">$FastaFile</span><span class="cm">,</span> <span class="i">$Line</span><span class="cm">,</span> <span class="i">$Status</span><span class="s">)</span><span class="sc">;</span> + 275 + 276 <span class="s">(</span><span class="i">$FastaFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 277 <span class="i">$Status</span> = <span class="n">0</span><span class="sc">;</span> + 278 + 279 <span class="k">open</span> <span class="w">FASTAFILE</span><span class="cm">,</span> <span class="q">"$FastaFile"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Couldn't open $FastaFile: $!\n"</span><span class="sc">;</span> + 280 <span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*FASTAFILE</span><span class="s">)</span><span class="sc">;</span> + 281 + 282 <span class="c"># First line starts with > and the fourth character is not ';'; otherwise, it's</span> + 283 <span class="c"># PIR FASTA format.</span> + 284 <span class="k">if</span> <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/^>/</span><span class="s">)</span> <span class="s">{</span> + 285 <span class="k">my</span><span class="s">(</span><span class="i">$FourthChar</span><span class="s">)</span><span class="sc">;</span> + 286 <span class="i">$FourthChar</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$Line</span><span class="cm">,</span> <span class="n">3</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span><span class="sc">;</span> + 287 <span class="i">$Status</span> = <span class="s">(</span><span class="i">$FourthChar</span> !~ <span class="q">/\;/</span><span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span> + 288 <span class="s">}</span> + 289 <span class="k">close</span> <span class="w">FASTAFILE</span><span class="sc">;</span> + 290 + 291 <span class="k">return</span> <span class="i">$Status</span><span class="sc">;</span> + 292 <span class="s">}</span> + 293 + 294 <span class="c"># Is it a valid NBRF/PIR fasta sequence or alignment file?</span> + 295 <span class="c">#</span> +<a name="IsPIRFastaSequenceFile-"></a> 296 <span class="k">sub </span><span class="m">IsPIRFastaSequenceFile</span> <span class="s">{</span> + 297 <span class="k">my</span><span class="s">(</span><span class="i">$FastaFile</span><span class="cm">,</span> <span class="i">$Line</span><span class="cm">,</span> <span class="i">$Status</span><span class="s">)</span><span class="sc">;</span> + 298 + 299 <span class="s">(</span><span class="i">$FastaFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 300 <span class="i">$Status</span> = <span class="n">0</span><span class="sc">;</span> + 301 + 302 <span class="k">open</span> <span class="w">FASTAFILE</span><span class="cm">,</span> <span class="q">"$FastaFile"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Couldn't open $FastaFile: $!\n"</span><span class="sc">;</span> + 303 <span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*FASTAFILE</span><span class="s">)</span><span class="sc">;</span> + 304 + 305 <span class="c"># First line starts with > and the fourth character is ';'; otherwise, it's</span> + 306 <span class="c"># a Pearson FASTA format.</span> + 307 <span class="k">if</span> <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/^>/</span><span class="s">)</span> <span class="s">{</span> + 308 <span class="k">my</span><span class="s">(</span><span class="i">$FourthChar</span><span class="s">)</span><span class="sc">;</span> + 309 <span class="i">$FourthChar</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$Line</span><span class="cm">,</span> <span class="n">3</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span><span class="sc">;</span> + 310 <span class="i">$Status</span> = <span class="s">(</span><span class="i">$FourthChar</span> =~ <span class="q">/\;/</span><span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span> + 311 <span class="s">}</span> + 312 <span class="k">close</span> <span class="w">FASTAFILE</span><span class="sc">;</span> + 313 + 314 <span class="k">return</span> <span class="i">$Status</span><span class="sc">;</span> + 315 <span class="s">}</span> + 316 + 317 <span class="c"># Is it a valid MSF sequence or alignment file?</span> + 318 <span class="c">#</span> +<a name="IsMSFSequenceFile-"></a> 319 <span class="k">sub </span><span class="m">IsMSFSequenceFile</span> <span class="s">{</span> + 320 <span class="k">my</span><span class="s">(</span><span class="i">$MSFFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 321 + 322 <span class="k">open</span> <span class="w">MSFFILE</span><span class="cm">,</span> <span class="q">"$MSFFile"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Couldn't open $MSFFile: $!\n"</span><span class="sc">;</span> + 323 + 324 <span class="k">my</span><span class="s">(</span><span class="i">$Line</span><span class="cm">,</span> <span class="i">$Status</span><span class="s">)</span><span class="sc">;</span> + 325 + 326 <span class="i">$Status</span> = <span class="n">0</span><span class="sc">;</span> + 327 <span class="c"># Find a line that contains MSF: keyword and ends with '..'</span> + 328 <span class="j">LINE:</span> <span class="k">while</span> <span class="s">(</span><span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*MSFFILE</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 329 <span class="i">$Line</span> = <span class="i">RemoveLeadingWhiteSpaces</span><span class="s">(</span><span class="i">$Line</span><span class="s">)</span><span class="sc">;</span> + 330 <span class="k">if</span> <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/MSF:/i</span> && <span class="i">$Line</span> =~ <span class="q">/\.\.[ ]*$/</span><span class="s">)</span> <span class="s">{</span> + 331 <span class="i">$Status</span> = <span class="n">1</span><span class="sc">;</span> + 332 <span class="k">last</span> <span class="j">LINE</span><span class="sc">;</span> + 333 <span class="s">}</span> + 334 <span class="k">elsif</span> <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/(!!AA_MULTIPLE_ALIGNMENT|!!NA_MULTIPLE_ALIGNMENT|PILEUP)/i</span><span class="s">)</span> <span class="s">{</span> + 335 <span class="c"># Pileup MSF...</span> + 336 <span class="i">$Status</span> = <span class="n">1</span><span class="sc">;</span> + 337 <span class="k">last</span> <span class="j">LINE</span><span class="sc">;</span> + 338 <span class="s">}</span> + 339 <span class="s">}</span> + 340 <span class="k">close</span> <span class="w">MSFFILE</span><span class="sc">;</span> + 341 + 342 <span class="k">return</span> <span class="i">$Status</span><span class="sc">;</span> + 343 <span class="s">}</span> + 344 + 345 <span class="c"># Read sequence or sequence alignment file...</span> +<a name="ReadSequenceFile-"></a> 346 <span class="k">sub </span><span class="m">ReadSequenceFile</span> <span class="s">{</span> + 347 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 348 + 349 <span class="k">if</span> <span class="s">(</span><span class="i">IsPearsonFastaSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 350 <span class="k">return</span> <span class="i">ReadPearsonFastaSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="sc">;</span> + 351 <span class="s">}</span> + 352 <span class="k">elsif</span> <span class="s">(</span><span class="i">IsPIRFastaSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 353 <span class="k">return</span> <span class="i">ReadPIRFastaSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="sc">;</span> + 354 <span class="s">}</span> + 355 <span class="k">elsif</span> <span class="s">(</span><span class="i">IsMSFSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 356 <span class="k">return</span> <span class="i">ReadMSFSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="sc">;</span> + 357 <span class="s">}</span> + 358 <span class="k">elsif</span> <span class="s">(</span><span class="i">IsClustalWSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 359 <span class="k">return</span> <span class="i">ReadClustalWSequenceFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="sc">;</span> + 360 <span class="s">}</span> + 361 <span class="k">else</span> <span class="s">{</span> + 362 <span class="k">return</span> <span class="k">undef</span><span class="sc">;</span> + 363 <span class="s">}</span> + 364 <span class="s">}</span> + 365 + 366 <span class="c"># Read file and setup alignment data...</span> +<a name="ReadClustalWSequenceFile-"></a> 367 <span class="k">sub </span><span class="m">ReadClustalWSequenceFile</span> <span class="s">{</span> + 368 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 369 + 370 <span class="k">return</span> <span class="i">_ReadFileAndSetupSequencesData</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="cm">,</span> <span class="q">'ClustalW'</span><span class="s">)</span><span class="sc">;</span> + 371 <span class="s">}</span> + 372 + 373 <span class="c"># Read file and setup alignment data...</span> +<a name="ReadPearsonFastaSequenceFile-"></a> 374 <span class="k">sub </span><span class="m">ReadPearsonFastaSequenceFile</span> <span class="s">{</span> + 375 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 376 + 377 <span class="k">return</span> <span class="i">_ReadFileAndSetupSequencesData</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="cm">,</span> <span class="q">'Pearson'</span><span class="s">)</span><span class="sc">;</span> + 378 <span class="s">}</span> + 379 + 380 <span class="c"># Read file and setup alignment data...</span> +<a name="ReadPIRFastaSequenceFile-"></a> 381 <span class="k">sub </span><span class="m">ReadPIRFastaSequenceFile</span> <span class="s">{</span> + 382 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 383 + 384 <span class="k">return</span> <span class="i">_ReadFileAndSetupSequencesData</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="cm">,</span> <span class="q">'PIR'</span><span class="s">)</span><span class="sc">;</span> + 385 <span class="s">}</span> + 386 + 387 + 388 <span class="c"># Read file and setup sequence data...</span> +<a name="ReadMSFSequenceFile-"></a> 389 <span class="k">sub </span><span class="m">ReadMSFSequenceFile</span> <span class="s">{</span> + 390 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 391 + 392 <span class="k">return</span> <span class="i">_ReadFileAndSetupSequencesData</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="cm">,</span> <span class="q">'MSF'</span><span class="s">)</span><span class="sc">;</span> + 393 <span class="s">}</span> + 394 + 395 <span class="c"># Write out a Pearson FASTA file...</span> +<a name="WritePearsonFastaSequenceFile-"></a> 396 <span class="k">sub </span><span class="m">WritePearsonFastaSequenceFile</span> <span class="s">{</span> + 397 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFileName</span><span class="cm">,</span> <span class="i">$SequenceDataRef</span><span class="cm">,</span> <span class="i">$MaxLength</span><span class="cm">,</span> <span class="i">$ID</span><span class="cm">,</span> <span class="i">$Description</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$WrappedSequence</span><span class="s">)</span><span class="sc">;</span> + 398 + 399 <span class="i">$MaxLength</span> = <span class="n">80</span><span class="sc">;</span> + 400 <span class="k">if</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">3</span><span class="s">)</span> <span class="s">{</span> + 401 <span class="s">(</span><span class="i">$SequenceFileName</span><span class="cm">,</span> <span class="i">$SequenceDataRef</span><span class="cm">,</span> <span class="i">$MaxLength</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 402 <span class="s">}</span> + 403 <span class="k">elsif</span> <span class="s">(</span><span class="i">@_</span> == <span class="n">2</span><span class="s">)</span> <span class="s">{</span> + 404 <span class="s">(</span><span class="i">$SequenceFileName</span><span class="cm">,</span> <span class="i">$SequenceDataRef</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 405 <span class="s">}</span> + 406 <span class="k">open</span> <span class="w">SEQUENCEFILE</span><span class="cm">,</span> <span class="q">">$SequenceFileName"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Can't open $SequenceFileName: $!\n"</span><span class="sc">;</span> + 407 <span class="k">for</span> <span class="i">$ID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$SequenceDataRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 408 <span class="i">$Description</span> = <span class="i">$SequenceDataRef</span>->{<span class="w">Description</span>}{<span class="i">$ID</span>}<span class="sc">;</span> + 409 <span class="i">$Sequence</span> = <span class="i">$SequenceDataRef</span>->{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="sc">;</span> + 410 <span class="i">$WrappedSequence</span> = <span class="i">WrapText</span><span class="s">(</span><span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$MaxLength</span><span class="cm">,</span> <span class="q">"\n"</span><span class="s">)</span><span class="sc">;</span> + 411 + 412 <span class="c"># Description also contains ID...</span> + 413 <span class="k">print</span> <span class="i">SEQUENCEFILE</span> <span class="q">">$Description\n"</span><span class="sc">;</span> + 414 <span class="k">print</span> <span class="i">SEQUENCEFILE</span> <span class="q">"$WrappedSequence\n"</span><span class="sc">;</span> + 415 <span class="s">}</span> + 416 <span class="k">close</span> <span class="w">SEQUENCEFILE</span><span class="sc">;</span> + 417 <span class="s">}</span> + 418 + 419 <span class="c"># Get ID, Sequence and Length for smallest or longest sequence</span> +<a name="_GetShortestOrLongestSequence-"></a> 420 <span class="k">sub </span><span class="m">_GetShortestOrLongestSequence</span> <span class="s">{</span> + 421 <span class="k">my</span><span class="s">(</span><span class="i">$SequencesDataRef</span><span class="cm">,</span> <span class="i">$SequenceType</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 422 <span class="k">my</span><span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Seq</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="cm">,</span> <span class="i">$FirstID</span><span class="cm">,</span> <span class="i">$FirstSeqLen</span><span class="cm">,</span> <span class="i">$CurrentID</span><span class="cm">,</span> <span class="i">$CurrentSeq</span><span class="cm">,</span> <span class="i">$CurrentSeqLen</span><span class="cm">,</span> <span class="i">$CurrentDescription</span><span class="s">)</span><span class="sc">;</span> + 423 + 424 <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Seq</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="s">)</span> = <span class="s">(</span><span class="q">''</span><span class="cm">,</span> <span class="q">''</span><span class="cm">,</span> <span class="q">''</span><span class="s">)</span><span class="sc">;</span> + 425 <span class="i">$FirstID</span> = <span class="q">''</span><span class="sc">;</span> + 426 + 427 <span class="j">ID:</span> <span class="k">for</span> <span class="i">$CurrentID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$SequencesDataRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 428 <span class="i">$CurrentSeq</span> = <span class="i">$IgnoreGaps</span> ? <span class="i">RemoveSequenceGaps</span><span class="s">(</span><span class="i">$SequencesDataRef</span>->{<span class="w">Sequence</span>}{<span class="i">$CurrentID</span>}<span class="s">)</span> <span class="co">:</span> <span class="i">$SequencesDataRef</span>->{<span class="w">Sequence</span>}{<span class="i">$CurrentID</span>}<span class="sc">;</span> + 429 <span class="i">$CurrentSeqLen</span> = <span class="i">GetSequenceLength</span><span class="s">(</span><span class="i">$CurrentSeq</span><span class="cm">,</span> <span class="i">$IgnoreGaps</span><span class="s">)</span><span class="sc">;</span> + 430 <span class="i">$CurrentDescription</span> = <span class="i">$SequencesDataRef</span>->{<span class="w">Description</span>}{<span class="i">$CurrentID</span>}<span class="sc">;</span> + 431 <span class="k">if</span> <span class="s">(</span>!<span class="i">$FirstID</span><span class="s">)</span> <span class="s">{</span> + 432 <span class="i">$FirstID</span> = <span class="i">$ID</span><span class="sc">;</span> <span class="i">$FirstSeqLen</span> = <span class="i">$CurrentSeqLen</span><span class="sc">;</span> + 433 <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Seq</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span> = <span class="s">(</span><span class="i">$CurrentID</span><span class="cm">,</span> <span class="i">$CurrentSeq</span><span class="cm">,</span> <span class="i">$CurrentSeqLen</span><span class="cm">,</span> <span class="i">$CurrentDescription</span><span class="s">)</span><span class="sc">;</span> + 434 <span class="k">next</span> <span class="j">ID</span><span class="sc">;</span> + 435 <span class="s">}</span> + 436 <span class="k">if</span> <span class="s">(</span><span class="i">$CurrentSeqLen</span> != <span class="i">$SeqLen</span><span class="s">)</span> <span class="s">{</span> + 437 <span class="k">if</span> <span class="s">(</span><span class="s">(</span><span class="i">$SequenceType</span> =~ <span class="q">/Shortest/i</span><span class="s">)</span> && <span class="s">(</span><span class="i">$CurrentSeqLen</span> < <span class="i">$SeqLen</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 438 <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Seq</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span> = <span class="s">(</span><span class="i">$CurrentID</span><span class="cm">,</span> <span class="i">$CurrentSeq</span><span class="cm">,</span> <span class="i">$CurrentSeqLen</span><span class="cm">,</span> <span class="i">$CurrentDescription</span><span class="s">)</span><span class="sc">;</span> + 439 <span class="s">}</span> + 440 <span class="k">elsif</span> <span class="s">(</span><span class="s">(</span><span class="i">$SequenceType</span> =~ <span class="q">/Longest/i</span><span class="s">)</span> && <span class="s">(</span><span class="i">$CurrentSeqLen</span> > <span class="i">$SeqLen</span><span class="s">)</span> <span class="s">)</span> <span class="s">{</span> + 441 <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Seq</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span> = <span class="s">(</span><span class="i">$CurrentID</span><span class="cm">,</span> <span class="i">$CurrentSeq</span><span class="cm">,</span> <span class="i">$CurrentSeqLen</span><span class="cm">,</span> <span class="i">$CurrentDescription</span><span class="s">)</span><span class="sc">;</span> + 442 <span class="s">}</span> + 443 <span class="s">}</span> + 444 <span class="s">}</span> + 445 <span class="k">return</span> <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Seq</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Description</span><span class="s">)</span><span class="sc">;</span> + 446 <span class="s">}</span> + 447 + 448 <span class="c"># Remove gaps in the sequence and return new sequence...</span> +<a name="RemoveSequenceGaps-"></a> 449 <span class="k">sub </span><span class="m">RemoveSequenceGaps</span> <span class="s">{</span> + 450 <span class="k">my</span><span class="s">(</span><span class="i">$Seq</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 451 <span class="k">my</span><span class="s">(</span><span class="i">$SeqWithoutGaps</span><span class="cm">,</span> <span class="i">$SeqLen</span><span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="i">$Residue</span><span class="s">)</span><span class="sc">;</span> + 452 + 453 <span class="i">$SeqWithoutGaps</span> = <span class="q">''</span><span class="sc">;</span> + 454 <span class="i">$SeqLen</span> = <span class="k">length</span><span class="s">(</span><span class="i">$Seq</span><span class="s">)</span><span class="sc">;</span> + 455 <span class="k">for</span> <span class="i">$Index</span> <span class="s">(</span><span class="n">0</span> .. <span class="s">(</span><span class="i">$SeqLen</span> - <span class="n">1</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 456 <span class="i">$Residue</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$Seq</span><span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span><span class="sc">;</span> + 457 <span class="k">if</span> <span class="s">(</span><span class="i">$Residue</span> =~ <span class="q">/[A-Z]/i</span><span class="s">)</span> <span class="s">{</span> + 458 <span class="i">$SeqWithoutGaps</span> .= <span class="i">$Residue</span><span class="sc">;</span> + 459 <span class="s">}</span> + 460 <span class="s">}</span> + 461 + 462 <span class="k">return</span> <span class="i">$SeqWithoutGaps</span><span class="sc">;</span> + 463 <span class="s">}</span> + 464 + 465 <span class="c"># Using input alignment data map ref containing following keys, generate</span> + 466 <span class="c"># a new hash with same set of keys after residue columns containg only</span> + 467 <span class="c"># gaps have been removed:</span> + 468 <span class="c">#</span> + 469 <span class="c"># {IDs} : Array of IDs in order as they appear in file</span> + 470 <span class="c"># {Count}: ID count...</span> + 471 <span class="c"># {Description}{$ID} : Description data...</span> + 472 <span class="c"># {Sequence}{$ID} : Sequence data...</span> + 473 <span class="c">#</span> +<a name="RemoveSequenceAlignmentGapColumns-"></a> 474 <span class="k">sub </span><span class="m">RemoveSequenceAlignmentGapColumns</span> <span class="s">{</span> + 475 <span class="k">my</span><span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$AlignmentDataMapRef</span><span class="cm">,</span> <span class="i">%NewAlignmentDataMap</span><span class="s">)</span><span class="sc">;</span> + 476 + 477 <span class="s">(</span><span class="i">$AlignmentDataMapRef</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 478 + 479 <span class="i">%NewAlignmentDataMap</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 480 <span class="i">@</span>{<span class="i">$NewAlignmentDataMap</span>{<span class="w">IDs</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 481 <span class="i">%</span>{<span class="i">$NewAlignmentDataMap</span>{<span class="w">Description</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 482 <span class="i">%</span>{<span class="i">$NewAlignmentDataMap</span>{<span class="w">Sequence</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 483 <span class="i">$NewAlignmentDataMap</span>{<span class="w">Count</span>} = <span class="n">0</span><span class="sc">;</span> + 484 + 485 <span class="c"># Transfer ID and count information...</span> + 486 <span class="k">for</span> <span class="i">$ID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$AlignmentDataMapRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 487 <span class="k">push</span> <span class="i">@</span>{<span class="i">$NewAlignmentDataMap</span>{<span class="w">IDs</span>}}<span class="cm">,</span> <span class="i">$ID</span><span class="sc">;</span> + 488 <span class="i">$NewAlignmentDataMap</span>{<span class="w">Description</span>}{<span class="i">$ID</span>} = <span class="i">$AlignmentDataMapRef</span>->{<span class="w">Description</span>}{<span class="i">$ID</span>}<span class="sc">;</span> + 489 <span class="i">$NewAlignmentDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} = <span class="q">''</span><span class="sc">;</span> + 490 <span class="i">$NewAlignmentDataMap</span>{<span class="w">Count</span>} += <span class="n">1</span><span class="sc">;</span> + 491 <span class="s">}</span> + 492 + 493 <span class="c"># Go over residue columns and transfer the data...</span> + 494 <span class="k">my</span><span class="s">(</span><span class="i">$FirstID</span><span class="cm">,</span> <span class="i">$FirstSeq</span><span class="cm">,</span> <span class="i">$FirstSeqLen</span><span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="i">$Res</span><span class="cm">,</span> <span class="i">$GapColumn</span><span class="s">)</span><span class="sc">;</span> + 495 + 496 <span class="i">$FirstID</span> = <span class="i">$AlignmentDataMapRef</span>->{<span class="w">IDs</span>}[<span class="n">0</span>]<span class="sc">;</span> + 497 <span class="i">$FirstSeq</span> = <span class="i">$AlignmentDataMapRef</span>->{<span class="w">Sequence</span>}{<span class="i">$FirstID</span>}<span class="sc">;</span> + 498 <span class="i">$FirstSeqLen</span> = <span class="k">length</span><span class="s">(</span><span class="i">$FirstSeq</span><span class="s">)</span><span class="sc">;</span> + 499 + 500 <span class="j">RES:</span> <span class="k">for</span> <span class="i">$Index</span> <span class="s">(</span><span class="n">0</span> .. <span class="s">(</span><span class="i">$FirstSeqLen</span> - <span class="n">1</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 501 <span class="c"># Is this a gap column?</span> + 502 <span class="i">$GapColumn</span> = <span class="n">1</span><span class="sc">;</span> + 503 <span class="j">ID:</span> <span class="k">for</span> <span class="i">$ID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$AlignmentDataMapRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 504 <span class="i">$Res</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$AlignmentDataMapRef</span>->{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span><span class="sc">;</span> + 505 <span class="k">if</span> <span class="s">(</span><span class="i">$Res</span> =~ <span class="q">/[A-Z]/i</span><span class="s">)</span> <span class="s">{</span> + 506 <span class="i">$GapColumn</span> = <span class="n">0</span><span class="sc">;</span> + 507 <span class="k">last</span> <span class="j">ID</span><span class="sc">;</span> + 508 <span class="s">}</span> + 509 <span class="s">}</span> + 510 <span class="k">if</span> <span class="s">(</span><span class="i">$GapColumn</span><span class="s">)</span> <span class="s">{</span> + 511 <span class="k">next</span> <span class="j">RES</span><span class="sc">;</span> + 512 <span class="s">}</span> + 513 <span class="c"># Transfer this residue...</span> + 514 <span class="k">for</span> <span class="i">$ID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$AlignmentDataMapRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 515 <span class="i">$Res</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$AlignmentDataMapRef</span>->{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span><span class="sc">;</span> + 516 <span class="i">$NewAlignmentDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} .= <span class="i">$Res</span><span class="sc">;</span> + 517 <span class="s">}</span> + 518 <span class="s">}</span> + 519 + 520 <span class="k">return</span> <span class="s">(</span>\<span class="i">%NewAlignmentDataMap</span><span class="s">)</span><span class="sc">;</span> + 521 <span class="s">}</span> + 522 + 523 <span class="c">#</span> + 524 <span class="c"># Read sequences file and return a reference to hash with the following keys:</span> + 525 <span class="c">#</span> + 526 <span class="c"># {IDs} - Array of sequence IDs</span> + 527 <span class="c"># {Count} - Number of sequences</span> + 528 <span class="c"># {Description}{$ID} - Sequence description</span> + 529 <span class="c"># {Sequence}{$ID} - Sequence for a specific ID</span> + 530 <span class="c"># {InputFileType} - Sequence file format</span> + 531 <span class="c"># {ConservedAnnotation} - Conserved residue annonation</span> + 532 <span class="c">#</span> + 533 <span class="c"># Note:</span> + 534 <span class="c"># . Conserved residue annotation either exist in the input sequence alignment file or set</span> + 535 <span class="c"># for a file containing same number of residues for all the sequence using the following</span> + 536 <span class="c"># notation: * - Residue conserved; ' ' - Residue not conserved.</span> + 537 <span class="c">#</span> +<a name="_ReadFileAndSetupSequencesData-"></a> 538 <span class="k">sub </span><span class="m">_ReadFileAndSetupSequencesData</span> <span class="s">{</span> + 539 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="cm">,</span> <span class="i">$SequenceType</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 540 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceDataMapRef</span><span class="s">)</span><span class="sc">;</span> + 541 + 542 <span class="i">$SequenceDataMapRef</span> = <span class="k">undef</span><span class="sc">;</span> + 543 + 544 <span class="c"># Read sequence file...</span> + 545 <span class="i">$SequenceDataMapRef</span> = <span class="q">''</span><span class="sc">;</span> + 546 <span class="k">if</span> <span class="s">(</span><span class="i">$SequenceType</span> =~ <span class="q">/^ClustalW$/i</span><span class="s">)</span> <span class="s">{</span> + 547 <span class="i">$SequenceDataMapRef</span> = <span class="i">_ReadClustalWFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="sc">;</span> + 548 <span class="s">}</span> + 549 <span class="k">elsif</span> <span class="s">(</span><span class="i">$SequenceType</span> =~ <span class="q">/^Pearson$/i</span><span class="s">)</span> <span class="s">{</span> + 550 <span class="i">$SequenceDataMapRef</span> = <span class="i">_ReadPearsonFastaFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="sc">;</span> + 551 <span class="s">}</span> + 552 <span class="k">elsif</span> <span class="s">(</span><span class="i">$SequenceType</span> =~ <span class="q">/^PIR$/i</span><span class="s">)</span> <span class="s">{</span> + 553 <span class="i">$SequenceDataMapRef</span> = <span class="i">_ReadPIRFastaFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="sc">;</span> + 554 <span class="s">}</span> + 555 <span class="k">elsif</span> <span class="s">(</span><span class="i">$SequenceType</span> =~ <span class="q">/^MSF$/i</span><span class="s">)</span> <span class="s">{</span> + 556 <span class="i">$SequenceDataMapRef</span> = <span class="i">_ReadMSFFile</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span><span class="sc">;</span> + 557 <span class="s">}</span> + 558 <span class="k">else</span> <span class="s">{</span> + 559 <span class="k">return</span> <span class="i">$SequenceDataMapRef</span><span class="sc">;</span> + 560 <span class="s">}</span> + 561 + 562 <span class="k">if</span> <span class="s">(</span><span class="k">exists</span> <span class="i">$SequenceDataMapRef</span>->{<span class="w">ConservedAnnotation</span>}<span class="s">)</span> <span class="s">{</span> + 563 <span class="k">return</span> <span class="s">(</span><span class="i">$SequenceDataMapRef</span><span class="s">)</span><span class="sc">;</span> + 564 <span class="s">}</span> + 565 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="s">(</span><span class="i">$SequenceDataMapRef</span>->{<span class="w">Count</span>} > <span class="n">1</span><span class="s">)</span> && <span class="s">(</span><span class="i">AreSequenceLengthsIdentical</span><span class="s">(</span><span class="i">$SequenceDataMapRef</span><span class="s">)</span><span class="s">)</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 566 <span class="k">return</span> <span class="s">(</span><span class="i">$SequenceDataMapRef</span><span class="s">)</span><span class="sc">;</span> + 567 <span class="s">}</span> + 568 + 569 <span class="c"># Use the first sequence to setup an empty ConservedAnnotation key...</span> + 570 <span class="c"># And mark fully conserved residues...</span> + 571 <span class="c">#</span> + 572 <span class="k">my</span><span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$FirstSequence</span><span class="cm">,</span> <span class="i">$FirstSeqLen</span><span class="cm">,</span> <span class="i">$Res</span><span class="cm">,</span> <span class="i">$FirstRes</span><span class="cm">,</span> <span class="i">$ResConserved</span><span class="cm">,</span> <span class="i">$Index</span><span class="s">)</span><span class="sc">;</span> + 573 <span class="i">$ID</span> = <span class="i">$SequenceDataMapRef</span>->{<span class="w">IDs</span>}[<span class="n">0</span>]<span class="sc">;</span> + 574 <span class="i">$FirstSequence</span> = <span class="i">$SequenceDataMapRef</span>->{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="sc">;</span> + 575 <span class="i">$FirstSeqLen</span> = <span class="k">length</span><span class="s">(</span><span class="i">$FirstSequence</span><span class="s">)</span><span class="sc">;</span> + 576 <span class="i">$SequenceDataMapRef</span>->{<span class="w">ConservedAnnotation</span>} = <span class="q">''</span><span class="sc">;</span> + 577 <span class="k">for</span> <span class="i">$Index</span> <span class="s">(</span><span class="n">0</span> .. <span class="s">(</span><span class="i">$FirstSeqLen</span> - <span class="n">1</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 578 <span class="i">$FirstRes</span> = <span class="q">''</span><span class="sc">;</span> + 579 <span class="i">$ResConserved</span> = <span class="n">1</span><span class="sc">;</span> + 580 <span class="j">ID:</span> <span class="k">for</span> <span class="i">$ID</span> <span class="s">(</span><span class="i">@</span>{<span class="i">$SequenceDataMapRef</span>->{<span class="w">IDs</span>}}<span class="s">)</span> <span class="s">{</span> + 581 <span class="i">$Sequence</span> = <span class="i">$SequenceDataMapRef</span>->{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="sc">;</span> + 582 <span class="i">$Res</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$Index</span><span class="cm">,</span> <span class="n">1</span><span class="s">)</span><span class="sc">;</span> + 583 <span class="k">if</span> <span class="s">(</span>!<span class="i">$FirstRes</span><span class="s">)</span> <span class="s">{</span> + 584 <span class="i">$FirstRes</span> = <span class="i">$Res</span><span class="sc">;</span> + 585 <span class="k">next</span> <span class="j">ID</span><span class="sc">;</span> + 586 <span class="s">}</span> + 587 <span class="k">if</span> <span class="s">(</span><span class="s">(</span><span class="i">$Res</span> !~ <span class="q">/[A-Z]/i</span><span class="s">)</span> || <span class="s">(</span><span class="i">$Res</span> <span class="k">ne</span> <span class="i">$FirstRes</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 588 <span class="i">$ResConserved</span> = <span class="n">0</span><span class="sc">;</span> + 589 <span class="k">last</span> <span class="j">ID</span><span class="sc">;</span> + 590 <span class="s">}</span> + 591 <span class="s">}</span> + 592 <span class="k">if</span> <span class="s">(</span><span class="i">$ResConserved</span><span class="s">)</span> <span class="s">{</span> + 593 <span class="i">$SequenceDataMapRef</span>->{<span class="w">ConservedAnnotation</span>} .= <span class="q">'*'</span><span class="sc">;</span> + 594 <span class="s">}</span> + 595 <span class="k">else</span> <span class="s">{</span> + 596 <span class="i">$SequenceDataMapRef</span>->{<span class="w">ConservedAnnotation</span>} .= <span class="q">' '</span><span class="sc">;</span> + 597 <span class="s">}</span> + 598 <span class="s">}</span> + 599 + 600 <span class="k">return</span> <span class="s">(</span><span class="i">$SequenceDataMapRef</span><span class="s">)</span><span class="sc">;</span> + 601 <span class="s">}</span> + 602 + 603 <span class="c"># Read sequence data in ClustalW multiple sequence alignment file and</span> + 604 <span class="c"># return a reference to hash with these keys and values:</span> + 605 <span class="c">#</span> + 606 <span class="c"># {IDs} - Array of sequence IDs</span> + 607 <span class="c"># {Count} - Number of sequences</span> + 608 <span class="c"># {Description}{$ID} - Sequence description</span> + 609 <span class="c"># {Sequence}{$ID} - Sequence for a specific ID</span> + 610 <span class="c"># {InputFileType} - Sequence file format</span> + 611 <span class="c"># {ConservedAnnotation} - Conserved residue annonations: space, *, : , .</span> + 612 <span class="c">#</span> + 613 <span class="c">#</span> + 614 <span class="c">#</span> + 615 <span class="c"># And based on ClustalW/X manual, here is what the ConservedAnnonations mean:</span> + 616 <span class="c">#</span> + 617 <span class="c"># '*' indicates positions which have a single, fully conserved residue</span> + 618 <span class="c">#</span> + 619 <span class="c"># ':' indicates that one of the following 'strong' groups is fully conserved: STA</span> + 620 <span class="c"># NEQK NHQK NDEQ QHRK MILV MILF HY FYW</span> + 621 + 622 <span class="c"># '.' indicates that one of the following 'weaker' groups is fully conserved:</span> + 623 <span class="c"># CSA ATV SAG STNK STPA SGND SNDEQK NDEQHK NEQHRK FVLIM HFY</span> + 624 <span class="c">#</span> + 625 <span class="c"># These are all the positively scoring groups that occur in the Gonnet Pam250</span> + 626 <span class="c"># matrix. The strong and weak groups are defined as strong score >0.5 and weak</span> + 627 <span class="c"># score =<0.5 respectively.</span> + 628 <span class="c">#</span> +<a name="_ReadClustalWFile-"></a> 629 <span class="k">sub </span><span class="m">_ReadClustalWFile</span> <span class="s">{</span> + 630 <span class="k">my</span><span class="s">(</span><span class="i">$SequenceFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 631 <span class="k">my</span><span class="s">(</span><span class="i">%SequencesDataMap</span><span class="s">)</span><span class="sc">;</span> + 632 + 633 <span class="c"># Initialize data...</span> + 634 <span class="i">%SequencesDataMap</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 635 <span class="i">@</span>{<span class="i">$SequencesDataMap</span>{<span class="w">IDs</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 636 <span class="i">%</span>{<span class="i">$SequencesDataMap</span>{<span class="w">Description</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 637 <span class="i">%</span>{<span class="i">$SequencesDataMap</span>{<span class="w">Sequence</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 638 <span class="i">$SequencesDataMap</span>{<span class="w">Count</span>} = <span class="n">0</span><span class="sc">;</span> + 639 <span class="i">$SequencesDataMap</span>{<span class="w">ConservedAnnotation</span>} = <span class="q">''</span><span class="sc">;</span> + 640 <span class="i">$SequencesDataMap</span>{<span class="w">InputFileType</span>} = <span class="q">'ClustalW'</span><span class="sc">;</span> + 641 + 642 <span class="k">open</span> <span class="w">SEQUENCEFILE</span><span class="cm">,</span> <span class="q">"$SequenceFile"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Couldn't open $SequenceFile: $!\n"</span><span class="sc">;</span> + 643 + 644 <span class="k">my</span><span class="s">(</span><span class="i">$Line</span><span class="cm">,</span> <span class="i">$LineLength</span><span class="cm">,</span> <span class="i">$AnnotationStart</span><span class="cm">,</span> <span class="i">$AnnotationLength</span><span class="cm">,</span> <span class="i">$Annotation</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$SequenceLength</span><span class="cm">,</span> <span class="i">$ID</span><span class="cm">,</span> <span class="i">$IDIndex</span><span class="s">)</span><span class="sc">;</span> + 645 + 646 <span class="c"># Ignore the header line...</span> + 647 <span class="i">$Line</span> = <span class="q"><SEQUENCEFILE></span><span class="sc">;</span> + 648 + 649 <span class="j">LINE:</span> <span class="k">while</span> <span class="s">(</span><span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*SEQUENCEFILE</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 650 <span class="k">if</span> <span class="s">(</span><span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/^[ \*\:\.]/</span><span class="s">)</span> && <span class="s">(</span><span class="i">$Line</span> !~ <span class="q">/[A-Z]/i</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 651 <span class="c"># Annotation for sequences: fully conserverd, weaker or stronger group conserverd.</span> + 652 <span class="c"># Extract it and save...</span> + 653 <span class="i">$LineLength</span> = <span class="k">length</span><span class="s">(</span><span class="i">$Line</span><span class="s">)</span><span class="sc">;</span> + 654 <span class="i">$AnnotationStart</span> = <span class="i">$LineLength</span> - <span class="i">$SequenceLength</span><span class="sc">;</span> + 655 <span class="i">$AnnotationLength</span> = <span class="i">$SequenceLength</span><span class="sc">;</span> + 656 <span class="i">$Annotation</span> = <span class="k">substr</span><span class="s">(</span><span class="i">$Line</span><span class="cm">,</span> <span class="i">$AnnotationStart</span><span class="cm">,</span> <span class="i">$AnnotationLength</span><span class="s">)</span><span class="sc">;</span> + 657 <span class="i">$SequencesDataMap</span>{<span class="w">ConservedAnnotation</span>} .= <span class="i">$Annotation</span><span class="sc">;</span> + 658 <span class="s">}</span> + 659 <span class="k">else</span> <span class="s">{</span> + 660 <span class="c"># Extract ID and sequences...</span> + 661 <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="s">)</span>= <span class="i">$Line</span> =~ <span class="q">/^[ ]*(.*?)[ ]+(.*?)[ 01-9]*$/</span><span class="sc">;</span> + 662 <span class="i">$Sequence</span> =~ <span class="q">s/ //g</span><span class="sc">;</span> + 663 <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="i">$ID</span> && <span class="i">$Sequence</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 664 <span class="k">next</span> <span class="j">LINE</span><span class="sc">;</span> + 665 <span class="s">}</span> + 666 + 667 <span class="k">if</span> <span class="s">(</span><span class="k">exists</span> <span class="i">$SequencesDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="s">)</span> <span class="s">{</span> + 668 <span class="c"># Append to existing alignment value...</span> + 669 <span class="i">$SequenceLength</span> = <span class="k">length</span><span class="s">(</span><span class="i">$Sequence</span><span class="s">)</span><span class="sc">;</span> + 670 <span class="i">$SequencesDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} .= <span class="i">$Sequence</span><span class="sc">;</span> + 671 <span class="s">}</span> + 672 <span class="k">else</span> <span class="s">{</span> + 673 <span class="c"># New alignment data...</span> + 674 <span class="i">$SequencesDataMap</span>{<span class="w">Count</span>} += <span class="n">1</span><span class="sc">;</span> + 675 <span class="k">push</span> <span class="i">@</span>{<span class="i">$SequencesDataMap</span>{<span class="w">IDs</span>}}<span class="cm">,</span> <span class="i">$ID</span><span class="sc">;</span> + 676 <span class="i">$SequencesDataMap</span>{<span class="w">Description</span>}{<span class="i">$ID</span>} = <span class="i">$ID</span><span class="sc">;</span> + 677 <span class="i">$SequencesDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} = <span class="i">$Sequence</span><span class="sc">;</span> + 678 <span class="i">$SequenceLength</span> = <span class="k">length</span><span class="s">(</span><span class="i">$Sequence</span><span class="s">)</span><span class="sc">;</span> + 679 <span class="s">}</span> + 680 <span class="s">}</span> + 681 <span class="s">}</span> + 682 <span class="k">close</span> <span class="w">SEQUENCEFILE</span><span class="sc">;</span> + 683 <span class="k">return</span> <span class="s">(</span>\<span class="i">%SequencesDataMap</span><span class="s">)</span><span class="sc">;</span> + 684 <span class="s">}</span> + 685 + 686 <span class="c"># Read Pearson fasta file and return a reference to hash with these keys:</span> + 687 <span class="c">#</span> + 688 <span class="c"># {IDs} - Array of sequence IDs</span> + 689 <span class="c"># {Count} - Number of sequences</span> + 690 <span class="c"># {Description}{$ID} - Sequence description</span> + 691 <span class="c"># {Sequence}{$ID} - Sequence for a specific ID</span> + 692 <span class="c"># {InputFileType} - Sequence file format</span> + 693 <span class="c"># {ConservedAnnotation} - Conserved residue annonation</span> + 694 <span class="c">#</span> +<a name="_ReadPearsonFastaFile-"></a> 695 <span class="k">sub </span><span class="m">_ReadPearsonFastaFile</span> <span class="s">{</span> + 696 <span class="k">my</span><span class="s">(</span><span class="i">$FastaFileName</span><span class="cm">,</span> <span class="i">$ID</span><span class="cm">,</span> <span class="i">$Description</span><span class="cm">,</span> <span class="i">$Line</span><span class="cm">,</span> <span class="i">$IgnoreID</span><span class="cm">,</span> <span class="i">@LineWords</span><span class="cm">,</span> <span class="i">%FastaDataMap</span><span class="s">)</span><span class="sc">;</span> + 697 + 698 <span class="s">(</span><span class="i">$FastaFileName</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 699 + 700 <span class="i">%FastaDataMap</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 701 <span class="i">@</span>{<span class="i">$FastaDataMap</span>{<span class="w">IDs</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 702 <span class="i">%</span>{<span class="i">$FastaDataMap</span>{<span class="w">Description</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 703 <span class="i">%</span>{<span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 704 <span class="i">$FastaDataMap</span>{<span class="w">Count</span>} = <span class="n">0</span><span class="sc">;</span> + 705 <span class="i">$FastaDataMap</span>{<span class="w">InputFileType</span>} = <span class="q">'Pearson'</span><span class="sc">;</span> + 706 + 707 <span class="k">open</span> <span class="w">FASTAFILE</span><span class="cm">,</span> <span class="q">"$FastaFileName"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Couldn't open $FastaFileName: $!\n"</span><span class="sc">;</span> + 708 <span class="i">$ID</span> = <span class="q">''</span><span class="sc">;</span> + 709 <span class="i">$IgnoreID</span> = <span class="n">0</span><span class="sc">;</span> + 710 <span class="j">LINE:</span> <span class="k">while</span> <span class="s">(</span><span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*FASTAFILE</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 711 <span class="k">if</span> <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/^\>/</span><span class="s">)</span> <span class="s">{</span> + 712 <span class="c"># Start of a new ID...</span> + 713 <span class="i">$Line</span> =~ <span class="q">s/^\>//</span><span class="sc">;</span> + 714 <span class="i">$Line</span> = <span class="i">RemoveLeadingWhiteSpaces</span><span class="s">(</span><span class="i">$Line</span><span class="s">)</span><span class="sc">;</span> + 715 <span class="i">@LineWords</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 716 <span class="i">@LineWords</span> = <span class="k">split</span> <span class="q">/ /</span><span class="cm">,</span> <span class="i">$Line</span><span class="sc">;</span> + 717 + 718 <span class="i">$ID</span> = <span class="i">$LineWords</span>[<span class="n">0</span>]<span class="sc">;</span> + 719 <span class="i">$ID</span> =~ <span class="q">s/ //g</span><span class="sc">;</span> + 720 <span class="i">$Description</span> = <span class="i">$Line</span><span class="sc">;</span> + 721 + 722 <span class="i">$IgnoreID</span> = <span class="n">0</span><span class="sc">;</span> + 723 <span class="k">if</span> <span class="s">(</span><span class="k">exists</span> <span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="s">)</span> <span class="s">{</span> + 724 <span class="i">$IgnoreID</span> = <span class="n">1</span><span class="sc">;</span> + 725 <span class="k">warn</span> <span class="q">"Warning: ID, $ID, in Fasta file already exists. Ignoring ID and sequence data...\n"</span><span class="sc">;</span> + 726 <span class="k">next</span> <span class="j">LINE</span><span class="sc">;</span> + 727 <span class="s">}</span> + 728 <span class="k">push</span> <span class="i">@</span>{<span class="i">$FastaDataMap</span>{<span class="w">IDs</span>}}<span class="cm">,</span> <span class="i">$ID</span><span class="sc">;</span> + 729 <span class="i">$FastaDataMap</span>{<span class="w">Description</span>}{<span class="i">$ID</span>} = <span class="i">$Description</span><span class="sc">;</span> + 730 <span class="i">$FastaDataMap</span>{<span class="w">Count</span>} += <span class="n">1</span><span class="sc">;</span> + 731 <span class="k">next</span> <span class="j">LINE</span><span class="sc">;</span> + 732 <span class="s">}</span> + 733 <span class="k">if</span> <span class="s">(</span><span class="i">$IgnoreID</span><span class="s">)</span> <span class="s">{</span> <span class="k">next</span> <span class="j">LINE</span><span class="sc">;</span> <span class="s">}</span> + 734 + 735 <span class="c"># Remove any spaces in the sequence...</span> + 736 <span class="i">$Line</span> =~ <span class="q">s/ //g</span><span class="sc">;</span> + 737 <span class="c"># Sequence data for active ID...</span> + 738 <span class="k">if</span> <span class="s">(</span><span class="k">exists</span> <span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="s">)</span> <span class="s">{</span> + 739 <span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} .= <span class="i">$Line</span><span class="sc">;</span> + 740 <span class="s">}</span> + 741 <span class="k">else</span> <span class="s">{</span> + 742 <span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} = <span class="i">$Line</span><span class="sc">;</span> + 743 <span class="s">}</span> + 744 <span class="s">}</span> + 745 <span class="k">close</span> <span class="w">FASTAFILE</span><span class="sc">;</span> + 746 <span class="k">return</span> \<span class="i">%FastaDataMap</span><span class="sc">;</span> + 747 <span class="s">}</span> + 748 + 749 <span class="c"># Read PIR fasta file and return a reference to hash with these keys:</span> + 750 <span class="c">#</span> + 751 <span class="c"># {IDs} - Array of sequence IDs</span> + 752 <span class="c"># {Count} - Number of sequences</span> + 753 <span class="c"># {Description}{$ID} - Sequence description</span> + 754 <span class="c"># {Sequence}{$ID} - Sequence for a specific ID</span> + 755 <span class="c"># {InputFileType} - Sequence file format</span> + 756 <span class="c"># {ConservedAnnotation} - Conserved residue annonation</span> + 757 <span class="c">#</span> + 758 <span class="c"># Format:</span> + 759 <span class="c"># A sequence in PIR format consists of:</span> + 760 <span class="c"># One line starting with</span> + 761 <span class="c"># a ">" (greater-than) sign, followed by</span> + 762 <span class="c"># a two-letter code describing the sequence type code (P1, F1, DL, DC, RL, RC, N3, N1 or XX), followed by</span> + 763 <span class="c"># a semicolon, followed by</span> + 764 <span class="c"># the sequence identification code (the database ID-code).</span> + 765 <span class="c"># One line containing a textual description of the sequence.</span> + 766 <span class="c"># One or more lines containing the sequence itself. The end of the</span> + 767 <span class="c"># sequence is marked by a "*" (asterisk) character.</span> + 768 <span class="c">#</span> + 769 <span class="c"># A file in PIR format may comprise more than one sequence.</span> + 770 <span class="c">#</span> + 771 <span class="c"># The PIR format is also often referred to as the NBRF format.</span> + 772 <span class="c">#</span> + 773 <span class="c"># Code SequenceType</span> + 774 <span class="c"># P1 Protein (complete)</span> + 775 <span class="c"># F1 Protein (fragment)</span> + 776 <span class="c"># DL DNA (linear)</span> + 777 <span class="c"># DC DNA (circular)</span> + 778 <span class="c"># RL RNA (linear)</span> + 779 <span class="c"># RC RNA (circular)</span> + 780 <span class="c"># N3 tRNA</span> + 781 <span class="c"># N1 Other functional RNA</span> + 782 <span class="c">#</span> + 783 +<a name="_ReadPIRFastaFile-"></a> 784 <span class="k">sub </span><span class="m">_ReadPIRFastaFile</span> <span class="s">{</span> + 785 <span class="k">my</span><span class="s">(</span><span class="i">$FastaFileName</span><span class="cm">,</span> <span class="i">$ID</span><span class="cm">,</span> <span class="i">$Description</span><span class="cm">,</span> <span class="i">$Line</span><span class="cm">,</span> <span class="i">$SequenceTypeCode</span><span class="cm">,</span> <span class="i">$ReadingSequenceData</span><span class="cm">,</span> <span class="i">%FastaDataMap</span><span class="s">)</span><span class="sc">;</span> + 786 + 787 <span class="s">(</span><span class="i">$FastaFileName</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 788 + 789 <span class="i">%FastaDataMap</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 790 <span class="i">@</span>{<span class="i">$FastaDataMap</span>{<span class="w">IDs</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 791 <span class="i">%</span>{<span class="i">$FastaDataMap</span>{<span class="w">Description</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 792 <span class="i">%</span>{<span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 793 <span class="i">%</span>{<span class="i">$FastaDataMap</span>{<span class="w">SequenceTypeCode</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 794 <span class="i">$FastaDataMap</span>{<span class="w">Count</span>} = <span class="n">0</span><span class="sc">;</span> + 795 <span class="i">$FastaDataMap</span>{<span class="w">InputFileType</span>} = <span class="q">'PIR'</span><span class="sc">;</span> + 796 + 797 <span class="k">open</span> <span class="w">FASTAFILE</span><span class="cm">,</span> <span class="q">"$FastaFileName"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Couldn't open $FastaFileName: $!\n"</span><span class="sc">;</span> + 798 <span class="i">$ID</span> = <span class="q">''</span><span class="sc">;</span> + 799 <span class="i">$ReadingSequenceData</span> = <span class="n">0</span><span class="sc">;</span> + 800 <span class="j">LINE:</span> <span class="k">while</span> <span class="s">(</span><span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*FASTAFILE</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 801 <span class="k">if</span> <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/^\>/</span><span class="s">)</span> <span class="s">{</span> + 802 <span class="c"># Start of a new ID...</span> + 803 <span class="i">$Line</span> =~ <span class="q">s/^\>//</span><span class="sc">;</span> + 804 <span class="i">$Line</span> = <span class="i">RemoveLeadingWhiteSpaces</span><span class="s">(</span><span class="i">$Line</span><span class="s">)</span><span class="sc">;</span> + 805 <span class="s">(</span><span class="i">$SequenceTypeCode</span><span class="cm">,</span> <span class="i">$ID</span><span class="s">)</span> = <span class="q">/^\>(.*?)\;(.*?)$/</span><span class="sc">;</span> + 806 + 807 <span class="c"># Use next line to retrieve sequence description...</span> + 808 <span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*FASTAFILE</span><span class="s">)</span><span class="sc">;</span> + 809 <span class="i">$Line</span> = <span class="i">RemoveLeadingWhiteSpaces</span><span class="s">(</span><span class="i">$Line</span><span class="s">)</span><span class="sc">;</span> + 810 <span class="i">$Description</span> = <span class="i">$Line</span><span class="sc">;</span> + 811 + 812 <span class="k">if</span> <span class="s">(</span><span class="k">exists</span> <span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="s">)</span> <span class="s">{</span> + 813 <span class="k">warn</span> <span class="q">"Warning: ID, $ID, in Fasta file already exists. Ignoring ID and sequence data...\n"</span><span class="sc">;</span> + 814 <span class="k">next</span> <span class="j">LINE</span><span class="sc">;</span> + 815 <span class="s">}</span> + 816 <span class="i">$ReadingSequenceData</span> = <span class="n">1</span><span class="sc">;</span> + 817 <span class="k">push</span> <span class="i">@</span>{<span class="i">$FastaDataMap</span>{<span class="w">IDs</span>}}<span class="cm">,</span> <span class="i">$ID</span><span class="sc">;</span> + 818 <span class="i">$FastaDataMap</span>{<span class="w">SequenceTypeCode</span>}{<span class="i">$ID</span>} = <span class="i">$SequenceTypeCode</span><span class="sc">;</span> + 819 <span class="i">$FastaDataMap</span>{<span class="w">Description</span>}{<span class="i">$ID</span>} = <span class="i">$Description</span><span class="sc">;</span> + 820 <span class="i">$FastaDataMap</span>{<span class="w">Count</span>} += <span class="n">1</span><span class="sc">;</span> + 821 <span class="k">next</span> <span class="j">LINE</span><span class="sc">;</span> + 822 <span class="s">}</span> + 823 <span class="k">if</span> <span class="s">(</span>!<span class="i">$ReadingSequenceData</span><span class="s">)</span> <span class="s">{</span> <span class="k">next</span> <span class="j">LINE</span><span class="sc">;</span> <span class="s">}</span> + 824 + 825 <span class="c"># Remove any spaces in the sequence...</span> + 826 <span class="i">$Line</span> =~ <span class="q">s/ //g</span><span class="sc">;</span> + 827 <span class="k">if</span> <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/[\*]$/</span><span class="s">)</span> <span class="s">{</span> + 828 <span class="c"># End of sequence...</span> + 829 <span class="i">$ReadingSequenceData</span> = <span class="n">0</span><span class="sc">;</span> + 830 <span class="i">$Line</span> =~ <span class="q">s/[\*]$//</span><span class="sc">;</span> + 831 <span class="s">}</span> + 832 <span class="c"># Sequence data for active ID...</span> + 833 <span class="k">if</span> <span class="s">(</span><span class="k">exists</span> <span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="s">)</span> <span class="s">{</span> + 834 <span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} .= <span class="i">$Line</span><span class="sc">;</span> + 835 <span class="s">}</span> + 836 <span class="k">else</span> <span class="s">{</span> + 837 <span class="i">$FastaDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} = <span class="i">$Line</span><span class="sc">;</span> + 838 <span class="s">}</span> + 839 <span class="s">}</span> + 840 <span class="k">close</span> <span class="w">FASTAFILE</span><span class="sc">;</span> + 841 <span class="k">return</span> \<span class="i">%FastaDataMap</span><span class="sc">;</span> + 842 <span class="s">}</span> + 843 + 844 <span class="c"># Read MSF file and return a reference to hash with these keys:</span> + 845 <span class="c">#</span> + 846 <span class="c"># {IDs} : Array of IDs in order as they appear in file</span> + 847 <span class="c"># {Count}: ID count...</span> + 848 <span class="c"># {Description}{$ID} : Description data...</span> + 849 <span class="c"># {Sequence}{$ID} : Sequence data...</span> + 850 <span class="c">#</span> +<a name="_ReadMSFFile-"></a> 851 <span class="k">sub </span><span class="m">_ReadMSFFile</span> <span class="s">{</span> + 852 <span class="k">my</span><span class="s">(</span><span class="i">$MSFFileName</span><span class="cm">,</span> <span class="i">$Line</span><span class="cm">,</span> <span class="i">@LineWords</span><span class="cm">,</span> <span class="i">%MSFDataMap</span><span class="s">)</span><span class="sc">;</span> + 853 + 854 <span class="s">(</span><span class="i">$MSFFileName</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> + 855 + 856 <span class="i">%MSFDataMap</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 857 <span class="i">@</span>{<span class="i">$MSFDataMap</span>{<span class="w">IDs</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 858 <span class="i">%</span>{<span class="i">$MSFDataMap</span>{<span class="w">Description</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 859 <span class="i">%</span>{<span class="i">$MSFDataMap</span>{<span class="w">Sequence</span>}} =<span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 860 <span class="i">$MSFDataMap</span>{<span class="w">Count</span>} = <span class="n">0</span><span class="sc">;</span> + 861 <span class="i">$MSFDataMap</span>{<span class="w">InputFileType</span>} = <span class="q">'MSF'</span><span class="sc">;</span> + 862 + 863 <span class="k">open</span> <span class="w">MSFFILE</span><span class="cm">,</span> <span class="q">"$MSFFileName"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Couldn't open $MSFFileName: $!\n"</span><span class="sc">;</span> + 864 + 865 <span class="c"># Collect sequences and IDs...</span> + 866 <span class="c">#</span> + 867 <span class="c"># '//' after the name fields indicates end of header list and start of sequence data.</span> + 868 <span class="c">#</span> + 869 <span class="k">my</span><span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Len</span><span class="cm">,</span> <span class="i">$Check</span><span class="cm">,</span> <span class="i">$Weight</span><span class="cm">,</span> <span class="i">$Sequence</span><span class="cm">,</span> <span class="i">$NameFieldsFound</span><span class="cm">,</span> <span class="i">%MSFIDsMap</span><span class="s">)</span><span class="sc">;</span> + 870 <span class="i">%MSFIDsMap</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> + 871 <span class="i">$NameFieldsFound</span> = <span class="n">0</span><span class="sc">;</span> + 872 <span class="j">LINE:</span> <span class="k">while</span> <span class="s">(</span><span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*MSFFILE</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 873 <span class="k">if</span> <span class="s">(</span><span class="i">$Line</span> =~ <span class="q">/Name:/</span><span class="s">)</span> <span class="s">{</span> + 874 <span class="i">$NameFieldsFound</span>++<span class="sc">;</span> + 875 <span class="s">(</span><span class="i">$ID</span><span class="cm">,</span> <span class="i">$Len</span><span class="cm">,</span> <span class="i">$Check</span><span class="cm">,</span> <span class="i">$Weight</span><span class="s">)</span> = <span class="i">$Line</span> =~ <span class="q">/^[ ]*Name:[ ]+(.*?)[ ]+Len:[ ]+(.*?)[ ]+Check:[ ]+(.*?)[ ]+Weight:[ ]+(.*?)[ ]*$/</span><span class="sc">;</span> + 876 <span class="k">if</span> <span class="s">(</span><span class="i">$ID</span> =~ <span class="q">/ /</span><span class="s">)</span> <span class="s">{</span> + 877 <span class="s">(</span><span class="i">$ID</span><span class="s">)</span> = <span class="i">$ID</span> =~ <span class="q">/^(.*?)[ ]+/</span> + 878 <span class="s">}</span> + 879 <span class="k">if</span> <span class="s">(</span><span class="k">exists</span> <span class="i">$MSFIDsMap</span>{<span class="i">$ID</span>}<span class="s">)</span> <span class="s">{</span> + 880 <span class="k">warn</span> <span class="q">"Warning: ID, $ID, in MSF file already exists. Ignoring ID and sequence data...\n"</span><span class="sc">;</span> + 881 <span class="k">next</span> <span class="j">LINE</span><span class="sc">;</span> + 882 <span class="s">}</span> + 883 <span class="i">$MSFIDsMap</span>{<span class="i">$ID</span>} = <span class="i">$ID</span><span class="sc">;</span> + 884 <span class="k">push</span> <span class="i">@</span>{<span class="i">$MSFDataMap</span>{<span class="w">IDs</span>}}<span class="cm">,</span> <span class="i">$ID</span><span class="sc">;</span> + 885 <span class="i">$MSFDataMap</span>{<span class="w">Description</span>}{<span class="i">$ID</span>} = <span class="i">$ID</span><span class="sc">;</span> + 886 <span class="i">$MSFDataMap</span>{<span class="w">Count</span>} += <span class="n">1</span><span class="sc">;</span> + 887 <span class="s">}</span> + 888 <span class="k">elsif</span> <span class="s">(</span> <span class="q">/\/\//</span> && <span class="i">$NameFieldsFound</span><span class="s">)</span> <span class="s">{</span> + 889 <span class="c"># End of header list...</span> + 890 <span class="k">last</span> <span class="j">LINE</span><span class="sc">;</span> + 891 <span class="s">}</span> + 892 <span class="s">}</span> + 893 <span class="c"># Collect all sequences...</span> + 894 <span class="c">#</span> + 895 <span class="k">my</span><span class="s">(</span><span class="i">$FirstField</span><span class="cm">,</span> <span class="i">$SecondField</span><span class="s">)</span><span class="sc">;</span> + 896 <span class="k">while</span> <span class="s">(</span><span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*MSFFILE</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> + 897 <span class="s">(</span><span class="i">$FirstField</span><span class="cm">,</span> <span class="i">$SecondField</span><span class="s">)</span> = <span class="i">$Line</span> =~ <span class="q">/^[ ]*(.*?)[ ]+(.*?)$/</span><span class="sc">;</span> + 898 <span class="k">if</span> <span class="s">(</span><span class="k">exists</span> <span class="i">$MSFIDsMap</span>{<span class="i">$FirstField</span>}<span class="s">)</span> <span class="s">{</span> + 899 <span class="c"># It's ID and sequence data...</span> + 900 <span class="i">$ID</span> = <span class="i">$FirstField</span><span class="sc">;</span> + 901 <span class="i">$Sequence</span> = <span class="i">$SecondField</span><span class="sc">;</span> + 902 <span class="c"># Take out spaces and leave the gap characters...</span> + 903 <span class="i">$Sequence</span> =~ <span class="q">s/ //g</span><span class="sc">;</span> + 904 <span class="k">if</span> <span class="s">(</span><span class="i">$MSFDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>}<span class="s">)</span> <span class="s">{</span> + 905 <span class="i">$MSFDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} .= <span class="i">$Sequence</span><span class="sc">;</span> + 906 <span class="s">}</span> + 907 <span class="k">else</span> <span class="s">{</span> + 908 <span class="i">$MSFDataMap</span>{<span class="w">Sequence</span>}{<span class="i">$ID</span>} = <span class="i">$Sequence</span><span class="sc">;</span> + 909 <span class="s">}</span> + 910 <span class="s">}</span> + 911 <span class="s">}</span> + 912 + 913 <span class="k">close</span> <span class="w">MSFFILE</span><span class="sc">;</span> + 914 <span class="k">return</span> \<span class="i">%MSFDataMap</span><span class="sc">;</span> + 915 <span class="s">}</span> + 916 + 917 +<a name="EOF-"></a></pre> +<p> </p> +<br /> +<center> +<img src="../../../images/h2o2.png"> +</center> +</body> +</html>