| 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 |
#ifndef CSEQUENCE_CLUSTER_AND_CENTER_SEQUENCE |
| 28 |
#define CSEQUENCE_CLUSTER_AND_CENTER_SEQUENCE |
| 29 |
|
| 30 |
#include "DEBUG_STUFF.h" |
| 31 |
#include <set> |
| 32 |
#include <list> |
| 33 |
//#include "CTaxonNamesDictionary.h" // Has been used in earlier version, in which clusters where reported with unique sequence number. This intermediate step was not convenient for the user and is not used any more. |
| 34 |
#include <iostream> |
| 35 |
#include <fstream> |
| 36 |
#include "faststring2.h" |
| 37 |
#include "basic-DNA-RNA-AA-routines.h" |
| 38 |
#include <climits> |
| 39 |
#include "statistic_functions.h" |
| 40 |
#include "print_container.h" |
| 41 |
//#include "csv-toolbox.h" |
| 42 |
//#include "mydir.h" |
| 43 |
//#include "sequence-cluster-result-parser.h" |
| 44 |
#include "CSequences2.h" |
| 45 |
#include "CSequence_Mol2_1.h" |
| 46 |
#include "CDistance_matrix.h" |
| 47 |
#include "CSeqNameList.h" |
| 48 |
#include <vector> |
| 49 |
#include <ctime> |
| 50 |
|
| 51 |
|
| 52 |
// Prototypes of global functions implemented in csequence_cluster_and_center_sequence.cpp |
| 53 |
void recode_range(char * b, char *e); |
| 54 |
void back_recode_range(char * b, char *e); |
| 55 |
void recode_MSA(char **sequences, int num_taxa, int num_pos); |
| 56 |
void find_center_sequence(char **msa, char *consensus, |
| 57 |
char *variant, char *isAmbig, |
| 58 |
int len_variant, |
| 59 |
int pos_start, int num_taxa, |
| 60 |
int pos_start_msa, int pos_end_msa, |
| 61 |
int *distances, faststring &best_variant, |
| 62 |
int *p_best_maximum_distance); |
| 63 |
void find_center_sequence_for_msa_exhaustive(char **msa, faststring ¢er_seq, |
| 64 |
int num_taxa, |
| 65 |
int pos_start_msa, int pos_end_msa, |
| 66 |
double &mdist); |
| 67 |
|
| 68 |
void find_center_sequence_for_msa_heuristic(char **msa, faststring ¢er_seq, |
| 69 |
int num_taxa, |
| 70 |
int pos_start_msa, int pos_end_msa, |
| 71 |
double &mdist); |
| 72 |
|
| 73 |
|
| 74 |
class Csequence_loci_cluster_collection; |
| 75 |
|
| 76 |
class Csequence_cluster_and_center_sequence |
| 77 |
{ |
| 78 |
unsigned pos_start; // 0 based |
| 79 |
unsigned pos_end; // 0 based, after last element of range |
| 80 |
|
| 81 |
double max_dist_in_cluster; // Maximum distance within this cluster |
| 82 |
double max_dist_bait_to_msa; |
| 83 |
// This is not the threshold but the true maximum distance. |
| 84 |
|
| 85 |
std::set<short> taxon_set; // This is the set of sequence numbers in the cluster. |
| 86 |
// Sequence numbers are the numbers that can be used to access the sequences in the CSequences2 object |
| 87 |
// The sequences can be accessed from this class by following the *loci variable. |
| 88 |
faststring center_sequence; |
| 89 |
char **msa; // MSA of this cluster. In the assign function, the filter the sequences that belong to the cluster. |
| 90 |
|
| 91 |
Csequence_loci_cluster_collection *loci; // Via the loci we have access to the CSequnces2 object and the CTaxonNamesDictionary object. |
| 92 |
double CG_content; |
| 93 |
|
| 94 |
|
| 95 |
public: |
| 96 |
Csequence_cluster_and_center_sequence():pos_start(-1u-1), pos_end(-1u), max_dist_in_cluster(-1), msa(NULL), loci(NULL), CG_content(0) |
| 97 |
{} |
| 98 |
|
| 99 |
// Constructor: Never used, never tested. |
| 100 |
/* Csequence_cluster_and_center_sequence(unsigned P_pos_start, */ |
| 101 |
/* unsigned P_pos_end, */ |
| 102 |
/* double P_max_dist_in_cluster, */ |
| 103 |
/* std::set<short> P_taxon_set, */ |
| 104 |
/* Csequence_loci_cluster_collection *P_loci): */ |
| 105 |
/* pos_start(P_pos_start), pos_end(P_pos_end), max_dist_in_cluster(P_max_dist_in_cluster), max_dist_bait_to_msa(-1), */ |
| 106 |
/* taxon_set(P_taxon_set), msa(NULL), loci(P_loci), CG_content(0) */ |
| 107 |
/* {} */ |
| 108 |
|
| 109 |
~Csequence_cluster_and_center_sequence() |
| 110 |
{ |
| 111 |
if (msa) |
| 112 |
delete [] msa; |
| 113 |
else |
| 114 |
{ |
| 115 |
// We can get here if we destroy a default constructed object |
| 116 |
// that has not been assigned any data. That can happen. |
| 117 |
} |
| 118 |
} |
| 119 |
|
| 120 |
// The only function that is allowed to assign data to objects of this class. |
| 121 |
// The msa that is passed to this member function is not the msa that is being stored |
| 122 |
// in the object, since not all sequences belong to the cluster we deal with. |
| 123 |
void assign(unsigned P_pos_start, |
| 124 |
unsigned P_pos_end, |
| 125 |
double P_max_dist_in_cluster, |
| 126 |
std::set<short> &P_taxon_set, // Contains the indices of the sequences in P_msa that are copied to the msa array. |
| 127 |
Csequence_loci_cluster_collection *P_loci, |
| 128 |
char **P_msa) |
| 129 |
{ |
| 130 |
pos_start = P_pos_start; |
| 131 |
pos_end = P_pos_end; |
| 132 |
max_dist_in_cluster = P_max_dist_in_cluster; |
| 133 |
// We could swap the content of the two sets. This might be faster. |
| 134 |
taxon_set = P_taxon_set; |
| 135 |
loci = P_loci; |
| 136 |
|
| 137 |
std::set<short>::iterator it, it_end; |
| 138 |
|
| 139 |
it = taxon_set.begin(); |
| 140 |
it_end = taxon_set.end(); |
| 141 |
short i; |
| 142 |
|
| 143 |
if (msa) |
| 144 |
{ |
| 145 |
std::cerr << "WARNING: An existing msa is overwritten. This behaviour is not expected. " << std::endl; |
| 146 |
delete msa; |
| 147 |
} |
| 148 |
|
| 149 |
msa = new char * [taxon_set.size()]; |
| 150 |
|
| 151 |
i=0; |
| 152 |
while (it != it_end) |
| 153 |
{ |
| 154 |
msa[i] = P_msa[*it]; |
| 155 |
++i; |
| 156 |
++it; |
| 157 |
} |
| 158 |
} |
| 159 |
|
| 160 |
|
| 161 |
unsigned get_number_of_elements_in_cluster() |
| 162 |
{ |
| 163 |
return taxon_set.size(); |
| 164 |
} |
| 165 |
|
| 166 |
bool center_computed() |
| 167 |
{ |
| 168 |
return !center_sequence.empty(); |
| 169 |
} |
| 170 |
|
| 171 |
const faststring& get_center_sequence() |
| 172 |
{ |
| 173 |
return center_sequence; |
| 174 |
} |
| 175 |
|
| 176 |
double get_CG() |
| 177 |
{ |
| 178 |
return CG_content; |
| 179 |
} |
| 180 |
|
| 181 |
double get_max_dist_in_cluster() |
| 182 |
{ |
| 183 |
return max_dist_in_cluster; |
| 184 |
} |
| 185 |
|
| 186 |
double get_max_dist_bait_to_msa() |
| 187 |
{ |
| 188 |
return max_dist_bait_to_msa; |
| 189 |
} |
| 190 |
|
| 191 |
unsigned window_size() |
| 192 |
{ |
| 193 |
return pos_end - pos_start; |
| 194 |
} |
| 195 |
|
| 196 |
// Implemented in Csequence_cluster_and_center_sequence.cpp |
| 197 |
void compute_center(char); |
| 198 |
|
| 199 |
void print(std::ostream &os) |
| 200 |
{ |
| 201 |
os << "Cluster: " << pos_start+1 << " " << pos_end << " " |
| 202 |
<< max_dist_in_cluster << " "; |
| 203 |
print_container(os, taxon_set, "{", ",", "}\n"); |
| 204 |
|
| 205 |
if (msa != NULL) |
| 206 |
{ |
| 207 |
print_msa_backrecoded(os); |
| 208 |
} |
| 209 |
|
| 210 |
if (center_sequence.empty()) |
| 211 |
{ |
| 212 |
os << " ## Center sequenuence has not been computed yet." << std::endl; |
| 213 |
} |
| 214 |
else |
| 215 |
{ |
| 216 |
os << center_sequence << std::endl; |
| 217 |
} |
| 218 |
} |
| 219 |
|
| 220 |
void print_msa_backrecoded(std::ostream &os, int flag = 0) |
| 221 |
{ |
| 222 |
std::set<short>::iterator it; |
| 223 |
|
| 224 |
it = taxon_set.begin(); |
| 225 |
|
| 226 |
unsigned i; |
| 227 |
os << "Cluster MSA: " << pos_start+1 << " " << pos_end << std::endl; |
| 228 |
for (i=0; i<taxon_set.size(); ++i, ++it) |
| 229 |
{ |
| 230 |
faststring tmp( msa[i]+pos_start, msa[i]+pos_end); |
| 231 |
back_recode_range(tmp.begin(), tmp.end()); |
| 232 |
os.width(4); |
| 233 |
os << *it << " " << tmp << std::endl; |
| 234 |
} |
| 235 |
if (flag == 1) |
| 236 |
{ |
| 237 |
if (center_computed() ) |
| 238 |
{ |
| 239 |
os << "Cent " << center_sequence << std::endl; |
| 240 |
os << "Max dist: " << max_dist_bait_to_msa << std::endl; |
| 241 |
} |
| 242 |
else |
| 243 |
os << "Center sequence not computed." << std::endl; |
| 244 |
} |
| 245 |
} |
| 246 |
|
| 247 |
}; |
| 248 |
|
| 249 |
|
| 250 |
// Stores and handles all clusters for a specific bait window: |
| 251 |
|
| 252 |
class Csequence_loci_cluster_collection |
| 253 |
{ |
| 254 |
CSequences2 *seqs; |
| 255 |
unsigned pos_start; // 0 based |
| 256 |
unsigned pos_end; // 0 based, after last element of range |
| 257 |
double dist_threshold; // |
| 258 |
// CTaxonNamesDictionary &taxon_names_dict; |
| 259 |
std::vector<bool> valid_sequences; // Does the sequence with given index have Ns or gaps in this range? |
| 260 |
// Indices are the indices in the CSequences2 object. |
| 261 |
|
| 262 |
char** msa; // Pointer to a recoded copy of the data |
| 263 |
// pos_start and pos_end are the coordinates |
| 264 |
// in these sequences. |
| 265 |
|
| 266 |
std::list<Csequence_cluster_and_center_sequence> list_of_clusters; |
| 267 |
unsigned number_of_valid_sequences; |
| 268 |
|
| 269 |
|
| 270 |
|
| 271 |
public: |
| 272 |
CSequences2 *get_pointer_to_sequences() |
| 273 |
{ |
| 274 |
return seqs; |
| 275 |
} |
| 276 |
|
| 277 |
// CTaxonNamesDictionary& get_taxonNamesDictionary() |
| 278 |
// { |
| 279 |
// return taxon_names_dict; |
| 280 |
// } |
| 281 |
|
| 282 |
// Constructor: |
| 283 |
Csequence_loci_cluster_collection(unsigned P_pos_start, unsigned P_pos_end, CSequences2 *P_seqs, |
| 284 |
// CTaxonNamesDictionary &P_taxon_names_dict, |
| 285 |
double P_dist_threshold, |
| 286 |
char** P_msa): |
| 287 |
seqs(P_seqs), pos_start(P_pos_start), pos_end(P_pos_end), dist_threshold(P_dist_threshold), |
| 288 |
//taxon_names_dict(P_taxon_names_dict), |
| 289 |
valid_sequences(P_seqs->GetTaxaNum()), msa(P_msa) |
| 290 |
{ |
| 291 |
// std::cerr << "Call to constructor: Csequence_loci_cluster_collection " |
| 292 |
// << pos_start+1 << " " << pos_end << " " << dist_threshold << std::endl; |
| 293 |
|
| 294 |
unsigned i, N=seqs->GetTaxaNum(); |
| 295 |
CSequence_Mol* seq; |
| 296 |
|
| 297 |
number_of_valid_sequences = 0; |
| 298 |
|
| 299 |
// IMPORTANT: If this code should be uncommented, code further down needs to be uncommented as well. |
| 300 |
/* if (global_VERBOSITY > 200) */ |
| 301 |
/* { */ |
| 302 |
/* std::cerr << "#1 " << "Constructor: Csequence_loci_cluster_collection, range: " << pos_start+1 << " " << pos_end << std::endl; */ |
| 303 |
/* std::cerr << "#1 " << "Valid: "; */ |
| 304 |
/* } */ |
| 305 |
|
| 306 |
for (i=0; i<N; ++i) |
| 307 |
{ |
| 308 |
seq = seqs->get_seq_by_index(i); |
| 309 |
|
| 310 |
// Has no gaps, Ns in range? |
| 311 |
// In principle we have already conducted this check in check_full_coverage_and_required_taxa_in_range. |
| 312 |
// This information is not shared a global scope, so it is not available any more. |
| 313 |
valid_sequences[i] = !seq->range_contains_gaps_or_Ns(pos_start, pos_end); |
| 314 |
if (valid_sequences[i]) |
| 315 |
{ |
| 316 |
// std::cerr << i << ", "; |
| 317 |
++ number_of_valid_sequences; |
| 318 |
} |
| 319 |
} |
| 320 |
// std::cerr << std::endl; |
| 321 |
|
| 322 |
// DEBUG code: Check output of back translation |
| 323 |
if (global_VERBOSITY > 100) |
| 324 |
{ |
| 325 |
std::cout << "#1 MSA:" << std::endl; |
| 326 |
print_msa_backrecoded(std::cout); |
| 327 |
} |
| 328 |
|
| 329 |
// Valid distances among sequences are in the range 0..1. |
| 330 |
// With a larger value we indicate a problem, e.g. Ns or gaps in the sequences. |
| 331 |
// In order not to cluster sequences that contain Ns or gaps, we |
| 332 |
// set the dist_threshold to a maximum value of 10. |
| 333 |
// Distances with a value >10 will not be clustered. |
| 334 |
// A good value for distances of sequences that contain gaps or Ns is 100. |
| 335 |
if (dist_threshold > 1) |
| 336 |
dist_threshold = 10; |
| 337 |
} |
| 338 |
|
| 339 |
void print_msa_backrecoded(std::ostream &os) |
| 340 |
{ |
| 341 |
unsigned i, N=seqs->GetTaxaNum(); |
| 342 |
|
| 343 |
os << "Exon-locus MSA:" << pos_start+1 << " " << pos_end << std::endl; |
| 344 |
for (i=0; i < N; ++i) |
| 345 |
{ |
| 346 |
faststring tmp( msa[i]+pos_start, msa[i]+pos_end); |
| 347 |
back_recode_range(tmp.begin(), tmp.end()); |
| 348 |
os.width(4); |
| 349 |
if (valid_sequences[i]) |
| 350 |
{ |
| 351 |
// std::cerr.setf(ios::right); |
| 352 |
os << i << "+ " << tmp << std::endl; |
| 353 |
} |
| 354 |
else |
| 355 |
{ |
| 356 |
os << i << "- " << tmp << std::endl; |
| 357 |
} |
| 358 |
} |
| 359 |
} |
| 360 |
|
| 361 |
|
| 362 |
void print_msa_backrecoded_all(std::ostream &os, int flag = 0) |
| 363 |
{ |
| 364 |
print_msa_backrecoded(os); |
| 365 |
|
| 366 |
std::list<Csequence_cluster_and_center_sequence>::iterator it, it_end; |
| 367 |
it = list_of_clusters.begin(); |
| 368 |
it_end = list_of_clusters.end(); |
| 369 |
while (it != it_end) |
| 370 |
{ |
| 371 |
it->print_msa_backrecoded(os, flag); |
| 372 |
++it; |
| 373 |
} |
| 374 |
} |
| 375 |
|
| 376 |
|
| 377 |
~Csequence_loci_cluster_collection() |
| 378 |
{ |
| 379 |
} |
| 380 |
|
| 381 |
// Implemented in Csequence_cluster_and_center_sequence.cpp |
| 382 |
void cluster_locus(faststring &, const faststring &); |
| 383 |
|
| 384 |
// Implemented in Csequence_cluster_and_center_sequence.cpp |
| 385 |
|
| 386 |
void compute_center_for_all_clusters(char); |
| 387 |
|
| 388 |
void print(std::ostream &os) |
| 389 |
{ |
| 390 |
std::list<Csequence_cluster_and_center_sequence>::iterator it, it_end; |
| 391 |
|
| 392 |
os << "Collection of clusters and their center sequences: " |
| 393 |
<< pos_start+1 << " " << pos_end |
| 394 |
<< " dist_threshold " << dist_threshold |
| 395 |
<< std::endl; |
| 396 |
|
| 397 |
it = list_of_clusters.begin(); |
| 398 |
it_end = list_of_clusters.end(); |
| 399 |
|
| 400 |
while (it != it_end) |
| 401 |
{ |
| 402 |
it->print(os); |
| 403 |
++it; |
| 404 |
} |
| 405 |
} |
| 406 |
|
| 407 |
void get_numbers_of_valid_sequences_number_of_clusters(unsigned short &valid_sequences, unsigned short &number_of_clusters) |
| 408 |
{ |
| 409 |
valid_sequences = number_of_valid_sequences; |
| 410 |
number_of_clusters = list_of_clusters.size(); |
| 411 |
} |
| 412 |
|
| 413 |
unsigned append_center_sequences(std::vector<faststring> &v, std::vector<double> &vCG, std::vector<double> &vMaxDist) |
| 414 |
{ |
| 415 |
unsigned count = 0; |
| 416 |
std::list<Csequence_cluster_and_center_sequence>::iterator it, it_end; |
| 417 |
|
| 418 |
it = list_of_clusters.begin(); |
| 419 |
it_end = list_of_clusters.end(); |
| 420 |
|
| 421 |
while (it != it_end) |
| 422 |
{ |
| 423 |
v.push_back( it->get_center_sequence() ); |
| 424 |
vCG.push_back(it->get_CG() ); |
| 425 |
|
| 426 |
// std::cerr << "Getting max_dist_bait_to_msa: " << it->get_max_dist_bait_to_msa() << std::endl; |
| 427 |
|
| 428 |
vMaxDist.push_back(it->get_max_dist_bait_to_msa() ); |
| 429 |
++it; |
| 430 |
++count; |
| 431 |
} |
| 432 |
return count; |
| 433 |
} |
| 434 |
|
| 435 |
|
| 436 |
}; |
| 437 |
|
| 438 |
|
| 439 |
|
| 440 |
class CBait_region_information |
| 441 |
{ |
| 442 |
faststring gene_name; |
| 443 |
short exon_number; |
| 444 |
short number_of_exons; |
| 445 |
unsigned start_pos; |
| 446 |
// unsigned short bait_length; |
| 447 |
// unsigned short offset; |
| 448 |
unsigned short number_of_baits_in_region; |
| 449 |
|
| 450 |
std::vector<Csequence_loci_cluster_collection *> loci_this_bait_region; |
| 451 |
|
| 452 |
// The total_number_of_valid_bait_windows_over_all_sequences_this_bait_region is effectively, |
| 453 |
// the size of the evidence, or the number of sequences the baits are based on, after adding all contributions in a bait region. |
| 454 |
unsigned short total_number_of_valid_bait_windows_over_all_sequences_this_bait_region; |
| 455 |
unsigned short total_number_of_clusters_this_region; |
| 456 |
|
| 457 |
|
| 458 |
public: |
| 459 |
CBait_region_information(faststring &P_gene_name, short P_exon_number, short P_number_of_exons, unsigned P_start_pos, // unsigned short P_bait_length, unsigned short P_offset, |
| 460 |
unsigned short P_number_of_baits_in_region): |
| 461 |
gene_name(P_gene_name), exon_number(P_exon_number), number_of_exons(P_number_of_exons), |
| 462 |
start_pos(P_start_pos), //bait_length(P_bait_length), offset(P_offset), |
| 463 |
number_of_baits_in_region(P_number_of_baits_in_region), |
| 464 |
total_number_of_valid_bait_windows_over_all_sequences_this_bait_region(0), |
| 465 |
total_number_of_clusters_this_region(0) |
| 466 |
{} |
| 467 |
|
| 468 |
void add_info__cluster_locus(Csequence_loci_cluster_collection *p, |
| 469 |
unsigned short add_to_number_of_sequences, |
| 470 |
unsigned short add_to_number_of_baits) |
| 471 |
{ |
| 472 |
loci_this_bait_region.push_back(p); |
| 473 |
total_number_of_valid_bait_windows_over_all_sequences_this_bait_region += add_to_number_of_sequences; |
| 474 |
total_number_of_clusters_this_region += add_to_number_of_baits; |
| 475 |
} |
| 476 |
|
| 477 |
|
| 478 |
void get_vector_of_bait_sequences(std::vector<faststring> &v, std::vector<unsigned> &bait_counts, std::vector<double> &vCG, std::vector<double> &vMaxDist) |
| 479 |
{ |
| 480 |
v.clear(); |
| 481 |
vCG.clear(); |
| 482 |
vMaxDist.clear(); |
| 483 |
|
| 484 |
if (total_number_of_clusters_this_region != 0) |
| 485 |
{ |
| 486 |
v.reserve(total_number_of_clusters_this_region); |
| 487 |
vCG.reserve(total_number_of_clusters_this_region); |
| 488 |
vMaxDist.reserve(total_number_of_clusters_this_region); |
| 489 |
} |
| 490 |
else |
| 491 |
{ |
| 492 |
v.reserve(10*number_of_baits_in_region); |
| 493 |
vCG.reserve(10*number_of_baits_in_region); |
| 494 |
vMaxDist.reserve(10*number_of_baits_in_region); |
| 495 |
} |
| 496 |
|
| 497 |
int i, N=loci_this_bait_region.size(); |
| 498 |
unsigned count; |
| 499 |
for (i=0; i<N; ++i) |
| 500 |
{ |
| 501 |
count = loci_this_bait_region[i]->append_center_sequences(v, vCG, vMaxDist); |
| 502 |
bait_counts.push_back(count); |
| 503 |
} |
| 504 |
} |
| 505 |
|
| 506 |
|
| 507 |
void print_baits_result(std::ostream &os, const faststring &filename) |
| 508 |
{ |
| 509 |
std::vector<faststring> v; |
| 510 |
std::vector<double> vCG; |
| 511 |
std::vector<double> vMaxDist; |
| 512 |
std::vector<unsigned> bait_counts; |
| 513 |
|
| 514 |
get_vector_of_bait_sequences(v, bait_counts, vCG, vMaxDist); |
| 515 |
|
| 516 |
os.setf(std::ios::fixed); |
| 517 |
os.precision(3); |
| 518 |
|
| 519 |
os << filename << "\t" |
| 520 |
<< gene_name << "\t" |
| 521 |
<< exon_number << "\t" |
| 522 |
<< number_of_exons << "\t" |
| 523 |
<< start_pos+1 << "\t" |
| 524 |
<< total_number_of_valid_bait_windows_over_all_sequences_this_bait_region << "\t" |
| 525 |
<< total_number_of_clusters_this_region |
| 526 |
<< "\t"; |
| 527 |
|
| 528 |
// print_container(os, bait_counts, "(",",",")\t"); |
| 529 |
|
| 530 |
unsigned i, N; |
| 531 |
N = v.size(); |
| 532 |
|
| 533 |
if (v.size() != vCG.size()) |
| 534 |
{ |
| 535 |
std::cerr << "Internal error: v and vCG have different sizes. Sizes are " << v.size() << " and " << vCG.size() << std::endl; |
| 536 |
exit(-1); |
| 537 |
} |
| 538 |
|
| 539 |
if (N == 0) |
| 540 |
{ |
| 541 |
std::cerr << "ERROR: NUMBER OF BAITS IS 0 for this locus. NEEDS TO BE VERIFIED." << std::endl; |
| 542 |
exit(-11); |
| 543 |
} |
| 544 |
|
| 545 |
int index_bait_counts=0; |
| 546 |
unsigned bait_sum=0; |
| 547 |
|
| 548 |
bait_sum += bait_counts[index_bait_counts]; |
| 549 |
++index_bait_counts; |
| 550 |
|
| 551 |
for (i=0; i<N-1; ++i) |
| 552 |
{ |
| 553 |
if (i == (bait_sum-1) ) |
| 554 |
{ |
| 555 |
os << index_bait_counts << " " << v[i] << " " << vCG[i] << " " << vMaxDist[i] << ","; |
| 556 |
|
| 557 |
bait_sum += bait_counts[index_bait_counts]; |
| 558 |
++index_bait_counts; |
| 559 |
} |
| 560 |
else |
| 561 |
{ |
| 562 |
os << index_bait_counts << " " << v[i] << " " << vCG[i] << " " << vMaxDist[i] << ","; |
| 563 |
} |
| 564 |
} |
| 565 |
os << index_bait_counts << " " << v[i] << " " << vCG[i] << " " << vMaxDist[i] << std::endl << std::flush; |
| 566 |
} // END void print_baits_result(std::ostream &os, const faststring &filename) |
| 567 |
}; // END class CBait_region_information |
| 568 |
|
| 569 |
|
| 570 |
#endif |