|
3
|
1 /*
|
|
|
2 FASTX-toolkit - FASTA/FASTQ preprocessing tools.
|
|
|
3 Copyright (C) 2009 A. Gordon (gordon@cshl.edu)
|
|
|
4
|
|
|
5 This program is free software: you can redistribute it and/or modify
|
|
|
6 it under the terms of the GNU Affero General Public License as
|
|
|
7 published by the Free Software Foundation, either version 3 of the
|
|
|
8 License, or (at your option) any later version.
|
|
|
9
|
|
|
10 This program is distributed in the hope that it will be useful,
|
|
|
11 but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
13 GNU Affero General Public License for more details.
|
|
|
14
|
|
|
15 You should have received a copy of the GNU Affero General Public License
|
|
|
16 along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
17 */
|
|
|
18 #include <limits.h>
|
|
|
19 #include <stdio.h>
|
|
|
20 #include <stdlib.h>
|
|
|
21 #include <string.h>
|
|
|
22 #include <getopt.h>
|
|
|
23 #include <errno.h>
|
|
|
24 #include <err.h>
|
|
|
25
|
|
|
26 #include <config.h>
|
|
|
27
|
|
|
28 #include "fastx.h"
|
|
|
29 #include "fastx_args.h"
|
|
|
30
|
|
|
31 const char* usage=
|
|
|
32 "usage: fastx_reverse_complement [-h] [-r] [-z] [-v] [-i INFILE] [-o OUTFILE]\n" \
|
|
|
33 "\n" \
|
|
|
34 "version " VERSION "\n" \
|
|
|
35 " [-h] = This helpful help screen.\n" \
|
|
|
36 " [-z] = Compress output with GZIP.\n" \
|
|
|
37 " [-i INFILE] = FASTA/Q input file. default is STDIN.\n" \
|
|
|
38 " [-o OUTFILE] = FASTA/Q output file. default is STDOUT.\n" \
|
|
|
39 "\n";
|
|
|
40
|
|
|
41 FASTX fastx;
|
|
|
42
|
|
|
43 char reverse_complement_base ( const char input )
|
|
|
44 {
|
|
|
45 switch(input)
|
|
|
46 {
|
|
|
47 case 'N':
|
|
|
48 return 'N';
|
|
|
49 case 'n':
|
|
|
50 return 'n';
|
|
|
51 case 'A':
|
|
|
52 return 'T';
|
|
|
53 case 'T':
|
|
|
54 return 'A';
|
|
|
55 case 'G':
|
|
|
56 return 'C';
|
|
|
57 case 'C':
|
|
|
58 return 'G';
|
|
|
59 case 'a':
|
|
|
60 return 't';
|
|
|
61 case 't':
|
|
|
62 return 'a';
|
|
|
63 case 'g':
|
|
|
64 return 'c';
|
|
|
65 case 'c':
|
|
|
66 return 'g';
|
|
|
67 default:
|
|
|
68 errx(1,"Invalid nucleotide value (%c) in reverse_complement_base()", input );
|
|
|
69 }
|
|
|
70
|
|
|
71 }
|
|
|
72
|
|
|
73 void reverse_complement_fastx(FASTX* pFASTX)
|
|
|
74 {
|
|
|
75 int i,j ;
|
|
|
76 int length = strlen(pFASTX->nucleotides);
|
|
|
77
|
|
|
78 char temp_nuc;
|
|
|
79 int temp_qual;
|
|
|
80
|
|
|
81 for (i=0;i<length;i++)
|
|
|
82 pFASTX->nucleotides[i] = reverse_complement_base ( pFASTX->nucleotides[i] ) ;
|
|
|
83
|
|
|
84 i = 0 ;
|
|
|
85 j = length - 1 ;
|
|
|
86 while ( i < j ) {
|
|
|
87 //Swap the nucleotides
|
|
|
88 temp_nuc = pFASTX->nucleotides[i] ;
|
|
|
89 pFASTX->nucleotides[i] = pFASTX->nucleotides[j] ;
|
|
|
90 pFASTX->nucleotides[j] = temp_nuc;
|
|
|
91
|
|
|
92 //Swap the quality scores
|
|
|
93 if (pFASTX->read_fastq) {
|
|
|
94 temp_qual = pFASTX->quality[i];
|
|
|
95 pFASTX->quality[i] = pFASTX->quality[j];
|
|
|
96 pFASTX->quality[j] = temp_qual ;
|
|
|
97 }
|
|
|
98
|
|
|
99 //Advance to next position
|
|
|
100 i++;
|
|
|
101 j--;
|
|
|
102 }
|
|
|
103 }
|
|
|
104
|
|
|
105
|
|
|
106 int main(int argc, char* argv[])
|
|
|
107 {
|
|
|
108 fastx_parse_cmdline(argc, argv, "", NULL);
|
|
|
109
|
|
|
110 fastx_init_reader(&fastx, get_input_filename(),
|
|
|
111 FASTA_OR_FASTQ, ALLOW_N, REQUIRE_UPPERCASE);
|
|
|
112
|
|
|
113 fastx_init_writer(&fastx, get_output_filename(), OUTPUT_SAME_AS_INPUT, compress_output_flag());
|
|
|
114
|
|
|
115 while ( fastx_read_next_record(&fastx) ) {
|
|
|
116 reverse_complement_fastx(&fastx);
|
|
|
117 fastx_write_record(&fastx);
|
|
|
118 }
|
|
|
119
|
|
|
120 if ( verbose_flag() ) {
|
|
|
121 fprintf(get_report_file(), "Printing Reverse-Complement Sequences.\n" );
|
|
|
122 fprintf(get_report_file(), "Input: %zu reads.\n", num_input_reads(&fastx) ) ;
|
|
|
123 fprintf(get_report_file(), "Output: %zu reads.\n", num_output_reads(&fastx) ) ;
|
|
|
124 }
|
|
|
125 return 0;
|
|
|
126 }
|
