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
|
#include <iostream>
#include <seqan/arg_parse.h>
#include <seqan/seq_io.h>
#include "common.h"
#include "GeneModel.hpp"
#include "FilterFusions.hpp"
seqan::ArgumentParser::ParseResult
parseCommandLine(ProgramOptions & options, int argc, char const ** argv) {
seqan::ArgumentParser parser("pizzly");
// We require one argument.
seqan::addArgument(parser, seqan::ArgParseArgument(
seqan::ArgParseArgument::STRING, "FUSION"));
// Define Options
seqan::addOption(parser, seqan::ArgParseOption(
"k", "", "k-mer size used in kallisto",
seqan::ArgParseArgument::INTEGER, "K"));
seqan::addOption(parser, seqan::ArgParseOption(
"a", "align-score", "Maximum number of mismatches allowed (default: 2)",
seqan::ArgParseArgument::INTEGER, "ALIGN_SCORE"));
seqan::addOption(parser, seqan::ArgParseOption(
"i", "insert-size", "Maximum fragment size of library (default: 400)",
seqan::ArgParseArgument::INTEGER, "INSERT_SIZE"));
seqan::addOption(parser, seqan::ArgParseOption(
"o", "output", "Prefix for output files",
seqan::ArgParseArgument::STRING, "OUTPUT_PREFIX"));
seqan::addOption(parser, seqan::ArgParseOption(
"G", "gtf", "Annotation in GTF format",
seqan::ArgParseArgument::STRING, "GTF"));
seqan::addOption(parser, seqan::ArgParseOption(
"C", "cache", "File for caching annotation (created if not present, otherwise reused from previous runs)",
seqan::ArgParseArgument::STRING, "cache"));
seqan::addOption(parser, seqan::ArgParseOption(
"F", "fasta", "Fasta reference",
seqan::ArgParseArgument::STRING, "FASTA"));
seqan::addOption(parser, seqan::ArgParseOption(
"", "ignore-protein", "Ignore any protein coding information in annotation"));
seqan::setRequired(parser, "k");
seqan::setRequired(parser, "o");
seqan::setRequired(parser, "F");
seqan::setVersion(parser, std::string(PIZZLY_VERSION));
// Parse command line.
seqan::ArgumentParser::ParseResult res = seqan::parse(parser, argc, argv);
// Only extract options if the program will continue after parseCommandLine()
if (res != seqan::ArgumentParser::PARSE_OK)
return res;
// Extract option values.
getOptionValue(options.k, parser, "k");
getOptionValue(options.alignScore, parser, "align-score");
getOptionValue(options.insertSize, parser, "insert-size");
getOptionValue(options.gtf, parser, "gtf");
getOptionValue(options.fasta, parser, "fasta");
getOptionValue(options.cache, parser, "cache");
getOptionValue(options.outprefix, parser, "output");
getArgumentValue(options.fusionFile, parser, 0);
if (seqan::isSet(parser, "ignore-protein")) {
options.ignoreProtein = true;
}
return seqan::ArgumentParser::PARSE_OK;
}
int main(int argc, char const ** argv)
{
// Parse the command line.
ProgramOptions options;
seqan::ArgumentParser::ParseResult res = parseCommandLine(options, argc, argv);
// If parsing was not successful then exit with code 1 if there were errors.
// Otherwise, exit with code 0 (e.g. help was printed).
if (res != seqan::ArgumentParser::PARSE_OK)
return res == seqan::ArgumentParser::PARSE_ERROR;
// parse GTF file
Transcriptome trx;
if (options.cache.empty()) {
parseGTF(trx, options.gtf, options);
} else {
std::ifstream in(options.cache);
if (in.good()) {
std::cerr << "Opening cached file ... ";
loadTranscriptome(trx,in, options);
std::cerr << "loaded " << trx.genes.size() << " genes and " << trx.trxToGeneId.size() << " transcripts" << std::endl;
in.close();
} else {
parseGTF(trx, options.gtf, options);
in.close();
std::ofstream out(options.cache);
writeTranscriptome(trx,out);
out.close();
}
in.close();
}
parseFasta(trx, options.fasta);
int numTxpSeqFound = 0;
int numProt = 0;
for (const auto &it : trx.seqs) {
if (trx.trxToGeneId.find(it.first) != trx.trxToGeneId.end()) {
numTxpSeqFound++;
}
}
for (const auto &git : trx.genes) {
for (const auto &it : git.second.transcripts) {
if (it.second.type == BioType::PROTEIN) {
numProt++;
}
}
}
if (numTxpSeqFound == 0) {
std::cerr << "Error, could not find any transcript sequences check that the ids in the FASTA file and GTF file match" << std::endl;
exit(1);
} else if (numTxpSeqFound != trx.seqs.size()) {
std::cerr << "Warning: could not find annotations for " << (trx.seqs.size() - numTxpSeqFound) << " transcripts\n" << std::endl;
}
if (!options.ignoreProtein && numProt == 0) {
std::cerr << "Warning: the annotation contains no protein coding information\n"
<< " pizzly will probably not report any fusions, consider finding\n"
<< " a better annotation or run again with --ignore-protein option.\n" << std::endl;
}
// filter fusion edges
processFusions(trx,options);
return 0;
}
|
