| 1 |
/* BaitFisher (version 1.2.8) a program for designing DNA target enrichment baits |
| 2 |
* Copyright 2013-2016 by Christoph Mayer |
| 3 |
* |
| 4 |
* This source file is part of the BaitFisher-package. |
| 5 |
* |
| 6 |
* This program is free software: you can redistribute it and/or modify |
| 7 |
* it under the terms of the GNU General Public License as published by |
| 8 |
* the Free Software Foundation, either version 3 of the License, or |
| 9 |
* (at your option) any later version. |
| 10 |
* |
| 11 |
* This program is distributed in the hope that it will be useful, |
| 12 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 13 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 14 |
* GNU General Public License for more details. |
| 15 |
* |
| 16 |
* You should have received a copy of the GNU General Public License |
| 17 |
* along with BaitFisher. If not, see <http://www.gnu.org/licenses/>. |
| 18 |
* |
| 19 |
* |
| 20 |
* For any enquiries send an Email to Christoph Mayer |
| 21 |
* [email protected] |
| 22 |
* |
| 23 |
* When publishing work that is based on the results please cite: |
| 24 |
* Mayer et al. 2016: BaitFisher: A software package for multi-species target DNA enrichment probe design |
| 25 |
* |
| 26 |
*/ |
| 27 |
#include "faststring2.h" |
| 28 |
#include <iostream> |
| 29 |
#include <list> |
| 30 |
|
| 31 |
#include "CFile/CFile2_1.h" |
| 32 |
#include "CSequences2.h" |
| 33 |
#include "CSequence_Mol2_1.h" |
| 34 |
|
| 35 |
#include "bait-fisher-helper.h" |
| 36 |
|
| 37 |
using namespace std; |
| 38 |
|
| 39 |
// Extract species (taxon) name from transcript name: |
| 40 |
faststring extract_taxon_name(faststring sequence_name, char delim, unsigned short field_num) |
| 41 |
{ |
| 42 |
list<faststring> container; char delim_cstring[2]; |
| 43 |
|
| 44 |
delim_cstring[0] = delim; |
| 45 |
delim_cstring[1] = '\0'; |
| 46 |
|
| 47 |
split(container, sequence_name, delim_cstring); |
| 48 |
|
| 49 |
// If the field number (0 based) is not smaller the number of fields, we have a problem. |
| 50 |
if (!(field_num < container.size() ) ) |
| 51 |
{ |
| 52 |
cerr << "ERROR: In extract_taxon_name: Found unexpected number of fields in a sequence name: " << sequence_name << endl; |
| 53 |
cerr << "I tried to extract field number " << field_num << " as specified in the parameter file or given as default value." << endl; |
| 54 |
cerr << "But this field does not exist." << endl; |
| 55 |
exit(-3); |
| 56 |
} |
| 57 |
|
| 58 |
list<faststring>::iterator it = container.begin(); |
| 59 |
unsigned short i; |
| 60 |
|
| 61 |
for (i=0; i<field_num; ++i) |
| 62 |
++it; |
| 63 |
|
| 64 |
return *it; |
| 65 |
} |
| 66 |
|
| 67 |
|
| 68 |
// Extract gene name from transcript name: |
| 69 |
faststring extract_gene_name(faststring sequence_name, char delim, unsigned short field_num) |
| 70 |
{ |
| 71 |
list<faststring> container; |
| 72 |
char delim_cstring[2]; |
| 73 |
|
| 74 |
|
| 75 |
|
| 76 |
delim_cstring[0] = delim; |
| 77 |
delim_cstring[1] = '\0'; |
| 78 |
|
| 79 |
split(container, sequence_name, delim_cstring); |
| 80 |
|
| 81 |
// If the field number (0 based) is not smaller the number of fields, we have a problem. |
| 82 |
if (!(field_num < container.size() ) ) |
| 83 |
{ |
| 84 |
cerr << "ERROR: In extract_gene_name: Found unexpected number of fields in a sequence name: " << sequence_name << endl; |
| 85 |
cerr << "I tried to extract field number " << field_num << " as specified in the parameter file or given as default value." << endl; |
| 86 |
cerr << "But this field does not exist." << endl; |
| 87 |
exit(-3); |
| 88 |
} |
| 89 |
|
| 90 |
list<faststring>::iterator it = container.begin(); |
| 91 |
unsigned short i; |
| 92 |
|
| 93 |
for (i=0; i<field_num; ++i) |
| 94 |
++it; |
| 95 |
|
| 96 |
#ifdef SHORTEN_GENENAME_AFTER_MINUS |
| 97 |
faststring pre, post; |
| 98 |
it->backwards_search_divide_at_break_at('-', delim, pre, post); |
| 99 |
return pre; |
| 100 |
#else |
| 101 |
return *it; |
| 102 |
#endif |
| 103 |
} |
| 104 |
|
| 105 |
// (1) Read alignment. |
| 106 |
// (2) Provide pointer to specific sequence (the one for which the name is specified, see (3)) as well as to the full alignment. |
| 107 |
// (3) If species_name_query is not empty, find the sequence with this name. |
| 108 |
// If species_name_query is an empty string, assign NULL to pseq. |
| 109 |
// (4) Important: The CSequence_Mol and CSequences2 objects need to be deleted by the user of this function when not used any more. |
| 110 |
// Version 2: Read full alignment and return both: full alignment and requested sequence. |
| 111 |
void read_alignment_sequence_of_species2(faststring alignment_file, |
| 112 |
faststring species_name_query, |
| 113 |
CSequence_Mol*& pseq, |
| 114 |
CSequences2*& pseqs, |
| 115 |
unsigned& pseq_index, |
| 116 |
char delim, |
| 117 |
unsigned short field_num) |
| 118 |
{ |
| 119 |
CFile infile; |
| 120 |
// unsigned count_seq=0; |
| 121 |
CSequences2* tmp_pseqs; |
| 122 |
|
| 123 |
|
| 124 |
// fputs("Reading alignment file: ", stderr); |
| 125 |
// fputs(alignment_file.c_str(), stderr); |
| 126 |
// fputs(".\n", stderr); |
| 127 |
|
| 128 |
infile.ffopen(alignment_file.c_str()); |
| 129 |
if ( infile.fail() ) |
| 130 |
{ |
| 131 |
fprintf(stderr, "Sorry! The input file \n \"%s\"\ncould not be opened. I guess it does not exist.\n", |
| 132 |
alignment_file.c_str()); |
| 133 |
exit(-1); |
| 134 |
} |
| 135 |
|
| 136 |
CSequence_Mol::processing_flag pflag = CSequence_Mol::processing_flag(0); |
| 137 |
// Convert all nucleotides to upper case letters and ambig to Ns. |
| 138 |
pflag = CSequence_Mol::processing_flag(pflag | CSequence_Mol::convert_toupper | CSequence_Mol::convert_ambig2N); |
| 139 |
tmp_pseqs = new CSequences2(CSequence_Mol::dna); |
| 140 |
|
| 141 |
++DEBUG_COUNT_NEW_ALIGNMENT_FROM_FILE; |
| 142 |
|
| 143 |
tmp_pseqs->read_from_Fasta_File(infile, pflag, 0, -1, false); |
| 144 |
infile.ffclose(); |
| 145 |
|
| 146 |
|
| 147 |
// fputsf("Alignment file has been read successfully.\n", stderr); |
| 148 |
|
| 149 |
pseqs = tmp_pseqs; |
| 150 |
|
| 151 |
|
| 152 |
if (species_name_query.empty() ) |
| 153 |
{ |
| 154 |
pseq = NULL; |
| 155 |
pseq_index = -1u; |
| 156 |
} |
| 157 |
else |
| 158 |
{ |
| 159 |
// Find sequence with taxon name equal to species_name_query |
| 160 |
unsigned i, N; |
| 161 |
N = pseqs->GetTaxaNum(); |
| 162 |
|
| 163 |
for (i=0; i<N; ++i) |
| 164 |
{ |
| 165 |
const char* seq_name = pseqs->get_Seq_Name(i); |
| 166 |
|
| 167 |
if (seq_name == NULL) |
| 168 |
{ |
| 169 |
cerr << "INTERNAL ERROR: Could not retrieve sequence name for sequence of index: " |
| 170 |
<< i << " in read_transcript_sequence_of_species2." << endl; |
| 171 |
exit(-5); |
| 172 |
} |
| 173 |
|
| 174 |
faststring species_name = extract_taxon_name(seq_name, delim, field_num); |
| 175 |
|
| 176 |
// cout << "Index: " << i << " " << N << endl; |
| 177 |
// cout << "Comparing: " << species_name << " " << species_name_query << endl; |
| 178 |
|
| 179 |
if (species_name == species_name_query) |
| 180 |
break; |
| 181 |
} |
| 182 |
if (i == N) // There is no sequence with species name equal to the one we search for. |
| 183 |
{ |
| 184 |
pseq = NULL; |
| 185 |
pseq_index = -1u; |
| 186 |
} |
| 187 |
else |
| 188 |
{ |
| 189 |
pseq = pseqs->get_seq_by_index(i); |
| 190 |
pseq_index = i; |
| 191 |
} |
| 192 |
} |
| 193 |
} |