1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
|
// ==========================================================================
// ALF - Alignment free sequence comparison
// ==========================================================================
// Copyright (c) 2006-2026, Knut Reinert, FU Berlin
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the distribution.
// * Neither the name of Knut Reinert or the FU Berlin nor the names of
// its contributors may be used to endorse or promote products derived
// from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
// ARE DISCLAIMED. IN NO EVENT SHALL KNUT REINERT OR THE FU BERLIN BE LIABLE
// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
// LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
// OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
// DAMAGE.
//
// ==========================================================================
// Author: Jonathan Goeke <goeke@molgen.mpg.de>
// ==========================================================================
// Alignment free sequence comparison.
//
// This application can be used to calculate pairwise scores of DNA Sequences
// without alignments.
//
// The following scores are implemented: N2, D2, D2Star, D2z.
// ==========================================================================
#include <iostream>
#include <seqan/basic.h>
#include <seqan/sequence.h>
#include <seqan/seq_io.h>
#include <seqan/misc/edit_environment.h>
#include <seqan/arg_parse.h>
#include <seqan/alignment_free.h>
using namespace seqan2;
using namespace std;
// TODO(holtgrew): Adapt parameters to naming conventions, i.e. use --parameter-name.
int main(int argc, const char * argv[])
{
// -----------------------------------------------------------------------
// Setup argument parser
// -----------------------------------------------------------------------
seqan2::ArgumentParser parser("alf");
// Set short description, version, date.
setShortDescription(parser, "Alignment free sequence comparison");
setVersion(parser, SEQAN_APP_VERSION " [" SEQAN_REVISION "]");
setDate(parser, SEQAN_DATE);
setCategory(parser, "Sequence Comparison");
// Usage line and description.
addUsageLine(parser, "[\\fIOPTIONS\\fP] \\fB-i\\fP \\fIIN.FASTA\\fP [\\fB-o\\fP \\fIOUT.TXT\\fP]");
addDescription(parser, "Compute pairwise similarity of sequences using alignment-free methods in \\fIIN.FASTA\\fP and write out tab-delimited matrix with pairwise scores to \\fIOUT.TXT\\fP.");
addOption(parser, seqan2::ArgParseOption("v", "verbose", "When given, details about the progress are printed to the screen."));
// Options Section: Input / Output parameters.
addSection(parser, "Input / Output");
addOption(parser, seqan2::ArgParseOption("i", "input-file", "Name of the multi-FASTA input file.", seqan2::ArgParseArgument::INPUT_FILE));
setValidValues(parser, "input-file", seqan2::SeqFileIn::getFileExtensions());
setRequired(parser, "input-file");
addOption(parser, seqan2::ArgParseOption("o", "output-file", "Name of the file to which the tab-delimtied matrix with pairwise scores will be written to. Default is to write to stdout.", seqan2::ArgParseArgument::OUTPUT_FILE));
setValidValues(parser, "output-file", "alf.tsv");
addSection(parser, "General Algorithm Parameters");
addOption(parser, seqan2::ArgParseOption("m", "method", "Select method to use.", seqan2::ArgParseArgument::STRING, "METHOD"));
setValidValues(parser, "method", "N2 D2 D2Star D2z");
setDefaultValue(parser, "method", "N2");
addOption(parser, seqan2::ArgParseOption("k", "k-mer-size", "Size of the k-mers.", seqan2::ArgParseArgument::INTEGER, "K"));
setDefaultValue(parser, "k-mer-size", "4");
addOption(parser, seqan2::ArgParseOption("mo", "bg-model-order", "Order of background Markov Model.", seqan2::ArgParseArgument::INTEGER, "ORDER"));
setDefaultValue(parser, "bg-model-order", "1");
addSection(parser, "N2 Algorithm Parameters");
// addText(parser, "The following parameters are only used in the N2 algorithm.");
addOption(parser, seqan2::ArgParseOption("rc", "reverse-complement", "Which strand to score. Use \\fIboth_strands\\fP to score both strands simultaneously.", seqan2::ArgParseArgument::STRING, "MODE"));
setValidValues(parser, "reverse-complement", "input both_strands mean min max");
setDefaultValue(parser, "reverse-complement", "input");
addOption(parser, seqan2::ArgParseOption("mm", "mismatches", "Number of mismatches, one of \\fI0\\fP and \\fI1\\fP. When \\fI1\\fP is used, N2 uses the k-mer-neighbour with one mismatch.", seqan2::ArgParseArgument::INTEGER, "MISMATCHES"));
setDefaultValue(parser, "mismatches", "0");
addOption(parser, seqan2::ArgParseOption("mmw", "mismatch-weight", "Real-valued weight of counts for words with mismatches.", seqan2::ArgParseArgument::DOUBLE, "WEIGHT"));
setDefaultValue(parser, "mismatch-weight", "0.1");
addOption(parser, seqan2::ArgParseOption("kwf", "k-mer-weights-file", "Print k-mer weights for every sequence to this file if given.", seqan2::ArgParseArgument::OUTPUT_FILE, "FILE.TXT"));
setValidValues(parser, "k-mer-weights-file", "txt");
addTextSection(parser, "Contact and References");
addListItem(parser, "For questions or comments, contact:", "Jonathan Goeke <goeke@molgen.mpg.de>");
addListItem(parser, "Please reference the following publication if you used ALF or the N2 method for your analysis:", "Jonathan Goeke, Marcel H. Schulz, Julia Lasserre, and Martin Vingron. Estimation of Pairwise Sequence Similarity of Mammalian Enhancers with Word Neighbourhood Counts. Bioinformatics (2012).");
addListItem(parser, "Project Homepage:", "https://www.seqan.de/apps/alf");
// Parse command line.
seqan2::ArgumentParser::ParseResult res = seqan2::parse(parser, argc, argv);
// Only extract options if the program will continue after parseCommandLine()
if (res != seqan2::ArgumentParser::PARSE_OK)
return (res == seqan2::ArgumentParser::PARSE_ERROR);
// Declare all parameters
String<char> kmerWeightsFileTmp;
String<char> inFileTmp;
String<char> outFileTmp;
getOptionValue(inFileTmp, parser, "input-file");
String<char, CStyle> inFile = inFileTmp;
getOptionValue(outFileTmp, parser, "output-file");
String<char, CStyle> outFile = outFileTmp;
String<char> method;
getOptionValue(method, parser, "method");
int kmerSize = 0;
getOptionValue(kmerSize, parser, "k-mer-size");
int bgModelOrder = 1;
getOptionValue(bgModelOrder, parser, "bg-model-order");
String<char> revComp;
getOptionValue(revComp, parser, "reverse-complement");
if (revComp == "input")
clear(revComp);
unsigned mismatches = 0;
getOptionValue(mismatches, parser, "mm");
double mismatchWeight = 0.1;
getOptionValue(mismatchWeight, parser, "mmw");
String<char, CStyle> kmerWeightsFile;
getOptionValue(kmerWeightsFileTmp, parser, "k-mer-weights-file");
kmerWeightsFile = kmerWeightsFileTmp;
bool verbose = isSet(parser, "verbose");
// Definition of type DNA string sets
typedef String<Dna5> TText;
typedef StringSet<TText> TStringSet;
// Definition of mxn two-dimensional matrix
typedef Matrix<double, 2> TMatrix;
TMatrix myMatrix; // myMatrix stores pairwise kmerScores
TStringSet mySequenceSet; // mySequenceSet stores all sequences from the multi-fasta file
if (inFile != "") // read in file
{
SeqFileIn seqFile;
open(seqFile, toCString(inFile));
StringSet<CharString> seqIDs;
readRecords(seqIDs, mySequenceSet, seqFile);
}
// Dispatch to alignment free comparisons with different scores.
if (method == "D2")
{
AFScore<D2> myScoreD2(kmerSize, verbose);
alignmentFreeComparison(myMatrix, mySequenceSet, myScoreD2);
}
else if (method == "D2z")
{
AFScore<D2z> myScoreD2z(kmerSize, bgModelOrder, verbose);
alignmentFreeComparison(myMatrix, mySequenceSet, myScoreD2z);
}
else if (method == "D2Star")
{
AFScore<D2Star> myScoreD2Star(kmerSize, bgModelOrder, verbose);
alignmentFreeComparison(myMatrix, mySequenceSet, myScoreD2Star);
}
else if (method == "N2")
{
AFScore<N2> myScoreN2(kmerSize, bgModelOrder, revComp, mismatches, mismatchWeight, kmerWeightsFile, verbose);
alignmentFreeComparison(myMatrix, mySequenceSet, myScoreN2);
}
// Write out resulting matrix; to file if file name was given, to stdout otherwise.
if (!empty(outFile))
{
ofstream myfile(outFile, std::ios::binary | std::ios::out);
myfile << myMatrix;
myfile.close();
}
else
{
std::cout << "\n" << myMatrix;
}
return 0;
}
|
