| 1 |
/* BaitFisher (version 1.2.7) 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 GFF_COLLECTION_H |
| 28 |
#define GFF_COLLECTION_H |
| 29 |
|
| 30 |
#include "cstdio" |
| 31 |
#include "easystring.h" |
| 32 |
#include <vector> |
| 33 |
#include <list> |
| 34 |
#include <set> |
| 35 |
#include <map> |
| 36 |
#include "range_functions.h" |
| 37 |
#include "GFF-class.h" |
| 38 |
|
| 39 |
|
| 40 |
using namespace std; |
| 41 |
|
| 42 |
static int ____verbosity = 1; |
| 43 |
|
| 44 |
|
| 45 |
// Currently, GFF_record_list has no destructor. |
| 46 |
// This can lead to memory leaks, since this class stores |
| 47 |
// pointers to GFF_record, which will never be destructed explicitly. |
| 48 |
// TODO!!!! |
| 49 |
|
| 50 |
class GFF_record_list : public list<GFF_record*> |
| 51 |
{ |
| 52 |
public: |
| 53 |
void add(GFF_record *pf) |
| 54 |
{ |
| 55 |
// cout << "Adding: "; pf->print(cout); cout << endl; |
| 56 |
push_back(pf); |
| 57 |
} |
| 58 |
|
| 59 |
// Keep only entries with a feature value f. |
| 60 |
void filter_by_feature(easystring &f) |
| 61 |
{ |
| 62 |
list<GFF_record*>::iterator it, it_end; |
| 63 |
it = begin(); |
| 64 |
it_end = end(); |
| 65 |
|
| 66 |
while (it != it_end) |
| 67 |
{ |
| 68 |
if ((**it).getFeature() != f ) |
| 69 |
it = erase(it); |
| 70 |
else |
| 71 |
++it; |
| 72 |
} |
| 73 |
} |
| 74 |
|
| 75 |
// Find all attribute values for a given set of attribute names: |
| 76 |
set<easystring> getSetOfAttributeValues(vector<easystring> att_name_vec, bool case_sensitive = true) |
| 77 |
{ |
| 78 |
set<easystring> s; |
| 79 |
/* list<GFF_record*>::iterator it, it_end; */ |
| 80 |
|
| 81 |
/* it = begin(); */ |
| 82 |
/* it_end = end(); */ |
| 83 |
|
| 84 |
/* while (it != it_end) */ |
| 85 |
/* { */ |
| 86 |
/* s.insert((**it).getGeneName()); */ |
| 87 |
/* ++it; */ |
| 88 |
/* } */ |
| 89 |
return s; |
| 90 |
} |
| 91 |
|
| 92 |
void getListOfGeneLocations(GFF_record_list &logl) |
| 93 |
{ |
| 94 |
/* list<GeneLocation*> logl; */ |
| 95 |
/* GeneLocation *gl; */ |
| 96 |
/* set<string> s = getSetOfGeneNames(); */ |
| 97 |
/* set<string>::iterator s_it = s.begin(); */ |
| 98 |
/* set<string>::iterator s_it_end = s.end(); */ |
| 99 |
/* string geneName; */ |
| 100 |
/* CfeatureList::iterator l_it; */ |
| 101 |
/* CfeatureList::iterator l_it_end; */ |
| 102 |
/* unsigned range_start, range_end; */ |
| 103 |
/* int direction = 0; */ |
| 104 |
/* bool found; */ |
| 105 |
|
| 106 |
/* while(s_it != s_it_end) */ |
| 107 |
/* { */ |
| 108 |
/* geneName = *s_it; */ |
| 109 |
/* l_it = begin(); */ |
| 110 |
/* l_it_end = end(); */ |
| 111 |
/* found = false; */ |
| 112 |
|
| 113 |
/* // Find first occurence: */ |
| 114 |
/* while(l_it != l_it_end) */ |
| 115 |
/* { */ |
| 116 |
/* if ((**l_it).getGeneName() == geneName) */ |
| 117 |
/* { */ |
| 118 |
/* range_start = (**l_it).getStart(); */ |
| 119 |
/* range_end = (**l_it).getEnd(); */ |
| 120 |
/* direction = (**l_it).getDirection(); */ |
| 121 |
/* found = true; */ |
| 122 |
/* break; */ |
| 123 |
/* } */ |
| 124 |
/* ++l_it; */ |
| 125 |
/* } */ |
| 126 |
|
| 127 |
/* // Find other occurences: */ |
| 128 |
/* while(l_it != l_it_end) */ |
| 129 |
/* { */ |
| 130 |
/* if ((**l_it).getGeneName() == geneName) */ |
| 131 |
/* { */ |
| 132 |
/* range_union( range_start, range_end, */ |
| 133 |
/* (**l_it).getStart(), (**l_it).getEnd(), */ |
| 134 |
/* range_start, range_end); */ |
| 135 |
/* } */ |
| 136 |
/* ++l_it; */ |
| 137 |
/* } */ |
| 138 |
|
| 139 |
/* if (!found) */ |
| 140 |
/* { */ |
| 141 |
/* cerr << "Fatal error in element function getListOfGeneLocations. Gene with name " */ |
| 142 |
/* << geneName << " not found." << endl; */ |
| 143 |
/* exit(0); */ |
| 144 |
/* } */ |
| 145 |
|
| 146 |
/* gl = new GeneLocation(geneName, range_start, range_end, direction); */ |
| 147 |
/* logl.push_back(gl); */ |
| 148 |
/* ++s_it; */ |
| 149 |
/* } */ |
| 150 |
/* return logl; */ |
| 151 |
} |
| 152 |
|
| 153 |
|
| 154 |
|
| 155 |
void getVectorOfFeatures_withGivenName(const easystring &the_geneName, |
| 156 |
vector<GFF_record*> &vogffr ) |
| 157 |
{ |
| 158 |
/* CfeatureList::iterator it, it_end; */ |
| 159 |
|
| 160 |
/* vogf.clear(); */ |
| 161 |
|
| 162 |
/* it = begin(); */ |
| 163 |
/* it_end = end(); */ |
| 164 |
|
| 165 |
/* while (it != it_end) */ |
| 166 |
/* { */ |
| 167 |
/* if ( (**it).getGeneName() == the_geneName ) */ |
| 168 |
/* { */ |
| 169 |
/* vogf.push_back(*it); */ |
| 170 |
/* // list_of_features.push_back(*it); */ |
| 171 |
/* } */ |
| 172 |
/* ++it; */ |
| 173 |
/* } */ |
| 174 |
/* stable_sort(vogf.begin(), vogf.end(), lessThan_genomeFeature); */ |
| 175 |
} |
| 176 |
|
| 177 |
/* CfeatureList::iterator find_equal_feature(CgenomeFeature &gf) */ |
| 178 |
/* { */ |
| 179 |
/* CfeatureList::iterator it = begin(); */ |
| 180 |
/* CfeatureList::iterator it_end = end(); */ |
| 181 |
|
| 182 |
/* it = lower_bound(it, it_end, &gf, lessThan_genomeFeature); */ |
| 183 |
/* it_end = upper_bound(it, it_end, &gf, lessThan_genomeFeature); */ |
| 184 |
|
| 185 |
/* while (it != it_end) */ |
| 186 |
/* { */ |
| 187 |
/* if ( **it == gf ) */ |
| 188 |
/* return it; */ |
| 189 |
/* ++it; */ |
| 190 |
/* } */ |
| 191 |
/* return end(); */ |
| 192 |
/* } */ |
| 193 |
|
| 194 |
void print(ostream &os, int flag = 0) |
| 195 |
{ |
| 196 |
list<GFF_record*>::iterator it, it_end; |
| 197 |
|
| 198 |
it = begin(); |
| 199 |
it_end = end(); |
| 200 |
|
| 201 |
while (it != it_end) |
| 202 |
{ |
| 203 |
(**it).print(os, flag); |
| 204 |
os << endl; |
| 205 |
++it; |
| 206 |
} |
| 207 |
} |
| 208 |
|
| 209 |
unsigned print_sequences(FILE *of, easystring &format, CSequence_Mol &seq, int char_per_line, |
| 210 |
bool ref_comp_if_neg_direction = true) |
| 211 |
{ |
| 212 |
GFF_record_list::iterator it, it_end; |
| 213 |
easystring seq_name = seq.getName(); |
| 214 |
unsigned count = 0; |
| 215 |
|
| 216 |
it = begin(); |
| 217 |
it_end = end(); |
| 218 |
|
| 219 |
while (it != it_end) |
| 220 |
{ |
| 221 |
// if (it->getSeqid == seq_name) // This is also checked in the print_sequence member function of the GFF_record. |
| 222 |
{ |
| 223 |
if ( (**it).print_sequence(of, format, seq, char_per_line, ref_comp_if_neg_direction) ) |
| 224 |
++count; |
| 225 |
} |
| 226 |
++it; |
| 227 |
} |
| 228 |
return count; |
| 229 |
} |
| 230 |
|
| 231 |
}; // End class GFF_record_list : public list<GFF_record*> |
| 232 |
|
| 233 |
|
| 234 |
|
| 235 |
|
| 236 |
|
| 237 |
|
| 238 |
|
| 239 |
class GFF_collection |
| 240 |
{ |
| 241 |
map<easystring, int> sequences; // counts the GFF-records associated to sequences |
| 242 |
map<easystring, int> features; // counts the GFF-records associated to features |
| 243 |
unsigned total_number; |
| 244 |
unsigned max_seq_name_length; |
| 245 |
|
| 246 |
// Type reminder: class GFF_record_list : public list<GFF_record*> |
| 247 |
|
| 248 |
GFF_record_list gff_record_list; // not inherited since then we can lose control |
| 249 |
// over features added to the list. |
| 250 |
|
| 251 |
public: |
| 252 |
GFF_collection(int v=0):total_number(0), max_seq_name_length(0) |
| 253 |
{} |
| 254 |
|
| 255 |
void reset() |
| 256 |
{ |
| 257 |
sequences.clear(); |
| 258 |
features.clear(); |
| 259 |
gff_record_list.clear(); |
| 260 |
|
| 261 |
total_number = 0; |
| 262 |
max_seq_name_length = 0; |
| 263 |
} |
| 264 |
|
| 265 |
|
| 266 |
void add(GFF_record* a) |
| 267 |
{ |
| 268 |
map<easystring, int>::iterator it; |
| 269 |
|
| 270 |
easystring sid = a->getSeqid(); |
| 271 |
easystring fea = a->getFeature(); |
| 272 |
|
| 273 |
++total_number; |
| 274 |
if ( max_seq_name_length < sid.length() ) |
| 275 |
max_seq_name_length = sid.length(); |
| 276 |
|
| 277 |
// Search for sequnece name in map |
| 278 |
it = sequences.find(sid); |
| 279 |
if (it != sequences.end() ) |
| 280 |
{ |
| 281 |
++(it->second); // Count the feature for this list |
| 282 |
} |
| 283 |
else // Add seq to map and set counter to 1 |
| 284 |
{ |
| 285 |
sequences[sid] = 1; |
| 286 |
} |
| 287 |
|
| 288 |
// Search for feature name in map |
| 289 |
it = features.find(fea); |
| 290 |
if (it != features.end() ) |
| 291 |
{ |
| 292 |
++(it->second); // Count the feature for this list |
| 293 |
} |
| 294 |
else // Add seq to map and set counter to 1 |
| 295 |
{ |
| 296 |
features[fea] = 1; |
| 297 |
} |
| 298 |
|
| 299 |
gff_record_list.add(a); |
| 300 |
} |
| 301 |
|
| 302 |
unsigned size() |
| 303 |
{ |
| 304 |
return gff_record_list.size(); |
| 305 |
} |
| 306 |
|
| 307 |
|
| 308 |
void add(GFF_collection &col) |
| 309 |
{ |
| 310 |
GFF_record_list::iterator it, it_end; |
| 311 |
|
| 312 |
it = col.gff_record_list.begin(); |
| 313 |
it_end = col.gff_record_list.end(); |
| 314 |
|
| 315 |
while (it != it_end) |
| 316 |
{ |
| 317 |
add(*it); |
| 318 |
++it; |
| 319 |
} |
| 320 |
|
| 321 |
} |
| 322 |
|
| 323 |
static void set_verbosity(int v) |
| 324 |
{ |
| 325 |
____verbosity = v; |
| 326 |
} |
| 327 |
|
| 328 |
|
| 329 |
const GFF_record_list& getGFFrecordList() |
| 330 |
{ |
| 331 |
return gff_record_list; |
| 332 |
} |
| 333 |
|
| 334 |
unsigned getNumGFFrecords() |
| 335 |
{ |
| 336 |
return total_number; |
| 337 |
} |
| 338 |
|
| 339 |
unsigned getMaxSeqidLength() |
| 340 |
{ |
| 341 |
return max_seq_name_length; |
| 342 |
} |
| 343 |
|
| 344 |
void print(ostream &os, int flag = 0) |
| 345 |
{ |
| 346 |
gff_record_list.print(os, flag); |
| 347 |
} |
| 348 |
|
| 349 |
void sort() |
| 350 |
{ |
| 351 |
gff_record_list.sort(position_lessThan_GFF_record_pointer); |
| 352 |
} |
| 353 |
|
| 354 |
void get_List_of_gff_records_of_a_sequence(const easystring &seq, |
| 355 |
GFF_record_list &list_of_records) |
| 356 |
{ |
| 357 |
GFF_record_list::iterator it, it_end; |
| 358 |
|
| 359 |
it = gff_record_list.begin(); |
| 360 |
it_end = gff_record_list.end(); |
| 361 |
|
| 362 |
while (it != it_end) |
| 363 |
{ |
| 364 |
if ( (**it).getSeqid() == seq ) |
| 365 |
{ |
| 366 |
list_of_records.push_back(*it); |
| 367 |
} |
| 368 |
++it; |
| 369 |
} |
| 370 |
} |
| 371 |
|
| 372 |
|
| 373 |
// Worries: Perfomrance. |
| 374 |
// Note: attribute_key must be lower case, since we only do a lower case comparison. |
| 375 |
void get_List_of_gff_records_for_attribute(const easystring &attribute_key, |
| 376 |
const easystring &attribute_value, |
| 377 |
GFF_record_list &list_of_records) |
| 378 |
{ |
| 379 |
GFF_record_list::iterator it, it_end; |
| 380 |
|
| 381 |
it = gff_record_list.begin(); |
| 382 |
it_end = gff_record_list.end(); |
| 383 |
|
| 384 |
list_of_records.clear(); |
| 385 |
|
| 386 |
while (it != it_end) |
| 387 |
{ |
| 388 |
easystring val = (**it).getValueOfAttribute(attribute_key, true); |
| 389 |
|
| 390 |
if ( val == attribute_value ) |
| 391 |
{ |
| 392 |
list_of_records.push_back(*it); |
| 393 |
} |
| 394 |
++it; |
| 395 |
} |
| 396 |
} |
| 397 |
|
| 398 |
|
| 399 |
vector<easystring> getVectorOfSeqid() |
| 400 |
{ |
| 401 |
vector<easystring> v; |
| 402 |
map<easystring, int>::iterator it, it_end; |
| 403 |
|
| 404 |
it = sequences.begin(); |
| 405 |
it_end = sequences.end(); |
| 406 |
while (it != it_end) |
| 407 |
{ |
| 408 |
v.push_back( it->first ); |
| 409 |
++it; |
| 410 |
} |
| 411 |
return v; |
| 412 |
} |
| 413 |
|
| 414 |
void get_min_max_number_of_features_for_Seqid(int &mi, int &ma) |
| 415 |
{ |
| 416 |
mi = ma = 0; // Only used when collection is empty |
| 417 |
map<easystring, int>::iterator it, it_end; |
| 418 |
|
| 419 |
it = sequences.begin(); |
| 420 |
it_end = sequences.end(); |
| 421 |
|
| 422 |
if (it != it_end) |
| 423 |
mi = ma = it->second; |
| 424 |
while (it != it_end) |
| 425 |
{ |
| 426 |
if (it->second > ma) |
| 427 |
ma = it->second; |
| 428 |
if (it->second < mi) |
| 429 |
mi = it->second; |
| 430 |
++it; |
| 431 |
} |
| 432 |
} |
| 433 |
|
| 434 |
|
| 435 |
void addSeqidsToSet(set<easystring> &s) |
| 436 |
{ |
| 437 |
map<easystring, int>::iterator it, it_end; |
| 438 |
|
| 439 |
it = sequences.begin(); |
| 440 |
it_end = sequences.end(); |
| 441 |
|
| 442 |
while (it != it_end) |
| 443 |
{ |
| 444 |
s.insert( it->first ); |
| 445 |
++it; |
| 446 |
} |
| 447 |
} |
| 448 |
|
| 449 |
|
| 450 |
void readGFFfile(easystring filename, |
| 451 |
unsigned &good_lines, |
| 452 |
unsigned &bad_lines, |
| 453 |
bool &file_error ) |
| 454 |
{ |
| 455 |
ifstream is(filename.c_str() ); |
| 456 |
easystring line; |
| 457 |
GFF_record *gffr; |
| 458 |
bool match_OK; |
| 459 |
|
| 460 |
file_error = false; |
| 461 |
good_lines = 0; |
| 462 |
bad_lines = 0; |
| 463 |
|
| 464 |
if ( is.fail() ) |
| 465 |
{ |
| 466 |
file_error = true; |
| 467 |
return; |
| 468 |
} |
| 469 |
|
| 470 |
getline(is, line); |
| 471 |
while (is) |
| 472 |
{ |
| 473 |
line.removeSpacesBack(); |
| 474 |
if (line[0] == '#' || line.empty() ) |
| 475 |
{ |
| 476 |
getline(is, line); |
| 477 |
continue; |
| 478 |
} |
| 479 |
|
| 480 |
gffr = new GFF_record(line); |
| 481 |
match_OK = gffr->good(); |
| 482 |
|
| 483 |
if (match_OK) |
| 484 |
{ |
| 485 |
add(gffr); |
| 486 |
++good_lines; |
| 487 |
} |
| 488 |
else |
| 489 |
{ |
| 490 |
++bad_lines; |
| 491 |
std::cerr << endl << "Problematic line: " << line << endl; |
| 492 |
std::cerr << "Reason for error: " << gffr->getErrorReason() << endl; |
| 493 |
delete gffr; |
| 494 |
} |
| 495 |
getline(is, line); |
| 496 |
} |
| 497 |
is.close(); |
| 498 |
|
| 499 |
// gff_record_list.sort(lessThan_genomeFeature); |
| 500 |
} |
| 501 |
|
| 502 |
void print_sequences_all_features(FILE *of, easystring &format, CFile *seq_file, int char_per_line, |
| 503 |
bool ref_comp_if_neg_direction, |
| 504 |
unsigned &count_seq, unsigned &count_printed_features) |
| 505 |
{ |
| 506 |
// Variables to read sequence file: |
| 507 |
CSequence_Mol seq(CSequence_Mol::dna); |
| 508 |
|
| 509 |
count_seq=0; |
| 510 |
count_printed_features=0; |
| 511 |
|
| 512 |
//std::ios::sync_with_stdio(false); |
| 513 |
|
| 514 |
// For each sequence: analyse the features |
| 515 |
while (!seq_file->eof()) |
| 516 |
{ |
| 517 |
seq.readRawFastaSequence(*seq_file); |
| 518 |
++count_seq; |
| 519 |
|
| 520 |
// cerr << count_seq << " " << seq.getName() << endl; |
| 521 |
|
| 522 |
count_printed_features += gff_record_list.print_sequences(of, format, seq, char_per_line, ref_comp_if_neg_direction); |
| 523 |
} |
| 524 |
} |
| 525 |
|
| 526 |
|
| 527 |
void getVectorOfFeatures(vector<easystring> &the_features) |
| 528 |
{ |
| 529 |
map<easystring, int>::iterator it, it_end; |
| 530 |
it = features.begin(); |
| 531 |
it_end = features.end(); |
| 532 |
|
| 533 |
the_features.clear(); |
| 534 |
|
| 535 |
while (it != it_end) |
| 536 |
{ |
| 537 |
the_features.push_back(it->first); |
| 538 |
++it; |
| 539 |
} |
| 540 |
} |
| 541 |
|
| 542 |
|
| 543 |
void getRangeList(CRangeList &rl, const easystring &seq) |
| 544 |
{ |
| 545 |
GFF_record_list::iterator it, it_end; |
| 546 |
it = gff_record_list.begin(); |
| 547 |
it_end = gff_record_list.end(); |
| 548 |
|
| 549 |
rl.clear(); |
| 550 |
|
| 551 |
while (it != it_end) |
| 552 |
{ |
| 553 |
if ( (**it).getSeqid() == seq ) |
| 554 |
{ |
| 555 |
// Remember: Ranges should be 0 based and the end should be the point after the last element in the range. |
| 556 |
// Coordinates in the gff file are 1 based. |
| 557 |
rl.add( (**it).getStart(), |
| 558 |
(**it).getEnd()+1); // the range class expects |
| 559 |
} |
| 560 |
++it; |
| 561 |
} |
| 562 |
} |
| 563 |
|
| 564 |
|
| 565 |
void getConsolidatedRangeListOfGFFCollection_for_Sequence(CRangeList &crl, easystring &seq) |
| 566 |
{ |
| 567 |
CRangeList rl; |
| 568 |
getRangeList(rl, seq); |
| 569 |
rl.get_consolidated_range_list(crl); |
| 570 |
} |
| 571 |
|
| 572 |
|
| 573 |
unsigned get_coverage_loop(std::ostream &os_error) |
| 574 |
{ |
| 575 |
map<easystring, int>::iterator it, it_end; |
| 576 |
|
| 577 |
it = sequences.begin(); |
| 578 |
it_end = sequences.end(); |
| 579 |
|
| 580 |
unsigned all_len=0; |
| 581 |
unsigned n; |
| 582 |
|
| 583 |
while (it != it_end) |
| 584 |
{ |
| 585 |
// Do something with it->first: |
| 586 |
|
| 587 |
os_error << "Analysing sequence coverage:" << it->first << endl; |
| 588 |
CRangeList rl1; |
| 589 |
|
| 590 |
getRangeList(rl1, it->first); |
| 591 |
os_error << "Elements: " << rl1.size() << endl; |
| 592 |
rl1.sort(); |
| 593 |
n = rl1.coverage_len_loop(); |
| 594 |
os_error << "Contribution: " << n << endl; |
| 595 |
all_len += n; |
| 596 |
++it; |
| 597 |
} |
| 598 |
return all_len; |
| 599 |
} |
| 600 |
|
| 601 |
|
| 602 |
unsigned get_coverage(std::ostream &os_error) |
| 603 |
{ |
| 604 |
map<easystring, int>::iterator it, it_end; |
| 605 |
|
| 606 |
it = sequences.begin(); |
| 607 |
it_end = sequences.end(); |
| 608 |
|
| 609 |
unsigned all_len=0; |
| 610 |
unsigned n; |
| 611 |
|
| 612 |
while (it != it_end) |
| 613 |
{ |
| 614 |
// Do something with it->first: |
| 615 |
|
| 616 |
// os_error << "Analysing sequence coverage:" << it->first << endl; |
| 617 |
CRangeList rl1; |
| 618 |
getRangeList(rl1, it->first); |
| 619 |
// os_error << "Elements: " << rl1.size() << endl; |
| 620 |
n = rl1.coverage_len(); |
| 621 |
// os_error << "Contribution: " << n << endl; |
| 622 |
all_len += n; |
| 623 |
++it; |
| 624 |
} |
| 625 |
return all_len; |
| 626 |
} |
| 627 |
|
| 628 |
|
| 629 |
|
| 630 |
friend void get_coverage_info_loop(GFF_collection &gff1, GFF_collection &gff2, |
| 631 |
unsigned &len_gff1, unsigned &len_gff2, |
| 632 |
unsigned &len_union, unsigned &len_intersection, |
| 633 |
unsigned &only_gff1, unsigned &only_gff2) |
| 634 |
{ |
| 635 |
set<easystring> s; |
| 636 |
|
| 637 |
gff1.addSeqidsToSet(s); |
| 638 |
gff2.addSeqidsToSet(s); |
| 639 |
|
| 640 |
Crange limit(0, -1u); |
| 641 |
bool err1, err2; |
| 642 |
CRangeList rl1; |
| 643 |
CRangeList rl2; |
| 644 |
|
| 645 |
unsigned len_gff1_this_seq; |
| 646 |
unsigned len_gff2_this_seq; |
| 647 |
unsigned len_union_this_seq; |
| 648 |
unsigned len_intersection_this_seq; |
| 649 |
unsigned limit_len_dummy; |
| 650 |
|
| 651 |
len_gff1 = 0; |
| 652 |
len_gff2 = 0; |
| 653 |
len_union = 0; |
| 654 |
len_intersection = 0; |
| 655 |
only_gff1 = 0; |
| 656 |
only_gff2 = 0; |
| 657 |
|
| 658 |
set<easystring>::iterator it, it_end; |
| 659 |
map<easystring, int>::iterator it_find; |
| 660 |
|
| 661 |
it = s.begin(); |
| 662 |
it_end = s.end(); |
| 663 |
|
| 664 |
while (it != it_end) |
| 665 |
{ |
| 666 |
err1 = false; |
| 667 |
err2 = false; |
| 668 |
|
| 669 |
it_find = gff1.sequences.find(*it); |
| 670 |
if (it_find == gff1.sequences.end() ) |
| 671 |
{ |
| 672 |
if (____verbosity > 1) |
| 673 |
{ |
| 674 |
cerr << "Note: Sequence " << *it |
| 675 |
<< " is present in gff file 2 but not in file 1." << endl; |
| 676 |
} |
| 677 |
err1 = true; |
| 678 |
} |
| 679 |
it_find = gff2.sequences.find(*it); |
| 680 |
if (it_find == gff2.sequences.end() ) |
| 681 |
{ |
| 682 |
if (____verbosity > 1) |
| 683 |
{ |
| 684 |
cerr << "Note: Sequence " << *it |
| 685 |
<< " is present in gff file 1 but not in file 2." << endl; |
| 686 |
} |
| 687 |
err2 = true; |
| 688 |
} |
| 689 |
|
| 690 |
if (!(err1 || err2)) |
| 691 |
{ |
| 692 |
if (____verbosity > 0) |
| 693 |
{ |
| 694 |
cerr << "Analysing sequence " << *it << endl; |
| 695 |
} |
| 696 |
|
| 697 |
gff1.getRangeList(rl1, *it); |
| 698 |
gff2.getRangeList(rl2, *it); |
| 699 |
|
| 700 |
Crange b1 = rl1.bounds(); |
| 701 |
Crange b2 = rl2.bounds(); |
| 702 |
|
| 703 |
Crange limit = range_span(b1, b2); |
| 704 |
|
| 705 |
rl1.sort(); |
| 706 |
rl2.sort(); |
| 707 |
coverage_values_loop(limit, rl1, rl2, limit_len_dummy, |
| 708 |
len_gff1_this_seq, |
| 709 |
len_gff2_this_seq, |
| 710 |
len_union_this_seq, |
| 711 |
len_intersection_this_seq); |
| 712 |
|
| 713 |
// cerr << len_gff1_this_seq << endl; |
| 714 |
// cerr << len_gff2_this_seq << endl; |
| 715 |
// cerr << len_union_this_seq << endl; |
| 716 |
// cerr << len_intersection_this_seq << endl; |
| 717 |
|
| 718 |
len_gff1 += len_gff1_this_seq; |
| 719 |
len_gff2 += len_gff2_this_seq; |
| 720 |
len_union += len_union_this_seq; |
| 721 |
len_intersection += len_intersection_this_seq; |
| 722 |
} |
| 723 |
else // we still want to update the individual lengths as well as the union length: |
| 724 |
{ |
| 725 |
if (!err1) |
| 726 |
{ |
| 727 |
gff1.getRangeList(rl1, *it); |
| 728 |
rl1.sort(); |
| 729 |
unsigned n = rl1.coverage_len_loop(); |
| 730 |
len_gff1 += n; |
| 731 |
len_union += n; |
| 732 |
++only_gff1; |
| 733 |
} |
| 734 |
if (!err2) |
| 735 |
{ |
| 736 |
gff2.getRangeList(rl2, *it); |
| 737 |
rl2.sort(); |
| 738 |
unsigned n = rl2.coverage_len_loop(); |
| 739 |
len_gff2 += n; |
| 740 |
len_union += n; |
| 741 |
++only_gff2; |
| 742 |
} |
| 743 |
} |
| 744 |
++it; |
| 745 |
} |
| 746 |
} |
| 747 |
|
| 748 |
|
| 749 |
friend void get_coverage_info(GFF_collection &gff1, GFF_collection &gff2, |
| 750 |
unsigned &len_gff1, unsigned &len_gff2, |
| 751 |
unsigned &len_union, unsigned &len_intersection, |
| 752 |
unsigned &only_gff1, unsigned &only_gff2) |
| 753 |
{ |
| 754 |
set<easystring> s; |
| 755 |
|
| 756 |
gff1.addSeqidsToSet(s); |
| 757 |
gff2.addSeqidsToSet(s); |
| 758 |
|
| 759 |
Crange limit(0, -1u); |
| 760 |
bool err1, err2; |
| 761 |
CRangeList rl1; |
| 762 |
CRangeList rl2; |
| 763 |
|
| 764 |
unsigned len_gff1_this_seq; |
| 765 |
unsigned len_gff2_this_seq; |
| 766 |
unsigned len_union_this_seq; |
| 767 |
unsigned len_intersection_this_seq; |
| 768 |
unsigned limit_len_dummy; |
| 769 |
|
| 770 |
len_gff1 = 0; |
| 771 |
len_gff2 = 0; |
| 772 |
len_union = 0; |
| 773 |
len_intersection = 0; |
| 774 |
only_gff1 = 0; |
| 775 |
only_gff2 = 0; |
| 776 |
|
| 777 |
set<easystring>::iterator it, it_end; |
| 778 |
map<easystring, int>::iterator it_find; |
| 779 |
|
| 780 |
it = s.begin(); |
| 781 |
it_end = s.end(); |
| 782 |
|
| 783 |
while (it != it_end) |
| 784 |
{ |
| 785 |
err1 = false; |
| 786 |
err2 = false; |
| 787 |
it_find = gff1.sequences.find(*it); |
| 788 |
if (it_find == gff1.sequences.end() ) |
| 789 |
{ |
| 790 |
if (____verbosity > 1) |
| 791 |
{ |
| 792 |
cerr << "Note: Sequence " << *it |
| 793 |
<< " is present in gff file 1 but not in file 2." << endl; |
| 794 |
} |
| 795 |
err1 = true; |
| 796 |
} |
| 797 |
it_find = gff2.sequences.find(*it); |
| 798 |
if (it_find == gff2.sequences.end() ) |
| 799 |
{ |
| 800 |
if (____verbosity > 1) |
| 801 |
{ |
| 802 |
cerr << "Note: Sequence " << *it |
| 803 |
<< " is present in gff file 2 but not in file 1." << endl; |
| 804 |
} |
| 805 |
err2 = true; |
| 806 |
} |
| 807 |
|
| 808 |
if (!( err1 || err2 )) |
| 809 |
{ |
| 810 |
if (____verbosity > 0) |
| 811 |
{ |
| 812 |
cerr << "Analysing sequence " << *it << endl; |
| 813 |
} |
| 814 |
|
| 815 |
gff1.getRangeList(rl1, *it); |
| 816 |
gff2.getRangeList(rl2, *it); |
| 817 |
|
| 818 |
Crange b1 = rl1.bounds(); |
| 819 |
Crange b2 = rl2.bounds(); |
| 820 |
|
| 821 |
Crange limit = range_span(b1, b2); |
| 822 |
|
| 823 |
rl1.sort(); |
| 824 |
rl2.sort(); |
| 825 |
coverage_values_loop(limit, rl1, rl2, limit_len_dummy, |
| 826 |
len_gff1_this_seq, |
| 827 |
len_gff2_this_seq, |
| 828 |
len_union_this_seq, |
| 829 |
len_intersection_this_seq); |
| 830 |
|
| 831 |
// cerr << len_gff1_this_seq << endl; |
| 832 |
// cerr << len_gff2_this_seq << endl; |
| 833 |
// cerr << len_union_this_seq << endl; |
| 834 |
// cerr << len_intersection_this_seq << endl; |
| 835 |
|
| 836 |
len_gff1 += len_gff1_this_seq; |
| 837 |
len_gff2 += len_gff2_this_seq; |
| 838 |
len_union += len_union_this_seq; |
| 839 |
len_intersection += len_intersection_this_seq; |
| 840 |
} |
| 841 |
else // we still want to update the individual lengths as well as the union length: |
| 842 |
{ |
| 843 |
if (!err1) |
| 844 |
{ |
| 845 |
gff1.getRangeList(rl1, *it); |
| 846 |
unsigned n = rl1.coverage_len(); |
| 847 |
len_gff1 += n; |
| 848 |
len_union += n; |
| 849 |
++only_gff1; |
| 850 |
} |
| 851 |
if (!err2) |
| 852 |
{ |
| 853 |
gff2.getRangeList(rl2, *it); |
| 854 |
unsigned n = rl2.coverage_len(); |
| 855 |
len_gff2 += n; |
| 856 |
len_union += n; |
| 857 |
++only_gff2; |
| 858 |
} |
| 859 |
} |
| 860 |
++it; |
| 861 |
} // while |
| 862 |
} // END friend void get_coverage_info |
| 863 |
|
| 864 |
|
| 865 |
// Main purpose: Find in1in2not3not4 = (1^2)\(3 U 4) |
| 866 |
friend void get_coverage_info_in1in2not3no4_loop |
| 867 |
(GFF_collection &gff1, GFF_collection &gff2, |
| 868 |
GFF_collection &gff3, GFF_collection &gff4, |
| 869 |
unsigned &len_gff1, unsigned &len_gff2, |
| 870 |
unsigned &len_gff3, unsigned &len_gff4, |
| 871 |
unsigned &in1not3not4, unsigned &in2not3not4, |
| 872 |
unsigned &in1in2not3not4, unsigned &in3in4not1not2 |
| 873 |
) |
| 874 |
{ |
| 875 |
len_gff1 = 0; |
| 876 |
len_gff2 = 0; |
| 877 |
len_gff3 = 0; |
| 878 |
len_gff4 = 0; |
| 879 |
in1not3not4 = 0; |
| 880 |
in2not3not4 = 0; |
| 881 |
in1in2not3not4 = 0; |
| 882 |
in3in4not1not2 = 0; |
| 883 |
|
| 884 |
set<easystring> s; |
| 885 |
|
| 886 |
gff1.addSeqidsToSet(s); |
| 887 |
gff2.addSeqidsToSet(s); |
| 888 |
gff3.addSeqidsToSet(s); |
| 889 |
gff4.addSeqidsToSet(s); |
| 890 |
|
| 891 |
// bool noseq1, noseq2, noseq3, noseq4; |
| 892 |
CRangeList rl1; |
| 893 |
CRangeList rl2; |
| 894 |
CRangeList rl3; |
| 895 |
CRangeList rl4; |
| 896 |
|
| 897 |
unsigned len_gff1_this_seq; |
| 898 |
unsigned len_gff2_this_seq; |
| 899 |
unsigned len_gff3_this_seq; |
| 900 |
unsigned len_gff4_this_seq; |
| 901 |
unsigned in1not3not4_this_seq; |
| 902 |
unsigned in2not3not4_this_seq; |
| 903 |
unsigned in1in2not3not4_this_seq; |
| 904 |
unsigned in3in4not1not2_this_seq; |
| 905 |
|
| 906 |
set<easystring>::iterator it, it_end; |
| 907 |
map<easystring, int>::iterator it_find; |
| 908 |
|
| 909 |
it = s.begin(); |
| 910 |
it_end = s.end(); |
| 911 |
|
| 912 |
while (it != it_end) |
| 913 |
{ |
| 914 |
if (____verbosity > 0) |
| 915 |
{ |
| 916 |
cerr << "Analysing sequence: " << *it << endl; |
| 917 |
} |
| 918 |
/* noseq1 = false; */ |
| 919 |
/* noseq2 = false; */ |
| 920 |
/* noseq3 = false; */ |
| 921 |
/* noseq4 = false; */ |
| 922 |
|
| 923 |
it_find = gff1.sequences.find(*it); |
| 924 |
if (it_find == gff1.sequences.end() ) |
| 925 |
{ |
| 926 |
if (____verbosity > 1) |
| 927 |
{ |
| 928 |
cerr << "Note: Sequence " << *it |
| 929 |
<< " is not present in gff file 1." << endl; |
| 930 |
} |
| 931 |
// noseq1 = true; |
| 932 |
rl1 = CRangeList(); |
| 933 |
} |
| 934 |
else |
| 935 |
{ |
| 936 |
gff1.getRangeList(rl1, *it); |
| 937 |
} |
| 938 |
|
| 939 |
it_find = gff2.sequences.find(*it); |
| 940 |
if (it_find == gff2.sequences.end() ) |
| 941 |
{ |
| 942 |
if (____verbosity > 1) |
| 943 |
{ |
| 944 |
cerr << "Note: Sequence " << *it |
| 945 |
<< " is not present in gff file 2." << endl; |
| 946 |
} |
| 947 |
// noseq2 = true; |
| 948 |
rl2 = CRangeList(); |
| 949 |
} |
| 950 |
else |
| 951 |
{ |
| 952 |
gff2.getRangeList(rl2, *it); |
| 953 |
} |
| 954 |
|
| 955 |
it_find = gff3.sequences.find(*it); |
| 956 |
if (it_find == gff3.sequences.end() ) |
| 957 |
{ |
| 958 |
if (____verbosity > 1) |
| 959 |
{ |
| 960 |
cerr << "Note: Sequence " << *it |
| 961 |
<< " is not present in gff file 3." << endl; |
| 962 |
} |
| 963 |
// noseq3 = true; |
| 964 |
rl3 = CRangeList(); |
| 965 |
} |
| 966 |
else |
| 967 |
{ |
| 968 |
gff3.getRangeList(rl3, *it); |
| 969 |
} |
| 970 |
|
| 971 |
it_find = gff4.sequences.find(*it); |
| 972 |
if (it_find == gff4.sequences.end() ) |
| 973 |
{ |
| 974 |
if (____verbosity > 1) |
| 975 |
{ |
| 976 |
cerr << "Note: Sequence " << *it |
| 977 |
<< " is not present in gff file 4." << endl; |
| 978 |
} |
| 979 |
// noseq4 = true; |
| 980 |
rl4 = CRangeList(); |
| 981 |
} |
| 982 |
else |
| 983 |
{ |
| 984 |
gff4.getRangeList(rl4, *it); |
| 985 |
} |
| 986 |
|
| 987 |
|
| 988 |
|
| 989 |
Crange b1 = rl1.bounds(); |
| 990 |
Crange b2 = rl2.bounds(); |
| 991 |
Crange b3 = rl2.bounds(); |
| 992 |
Crange b4 = rl2.bounds(); |
| 993 |
|
| 994 |
Crange limit = range_span(b1, b2); |
| 995 |
limit = range_span(limit, b3); |
| 996 |
limit = range_span(limit, b4); |
| 997 |
|
| 998 |
rl1.sort(); |
| 999 |
rl2.sort(); |
| 1000 |
rl3.sort(); |
| 1001 |
rl4.sort(); |
| 1002 |
|
| 1003 |
coverage_values_loop(limit, |
| 1004 |
rl1, rl2, rl3, rl4, |
| 1005 |
len_gff1_this_seq, |
| 1006 |
len_gff2_this_seq, |
| 1007 |
len_gff3_this_seq, |
| 1008 |
len_gff4_this_seq, |
| 1009 |
in1not3not4_this_seq, |
| 1010 |
in2not3not4_this_seq, |
| 1011 |
in1in2not3not4_this_seq, |
| 1012 |
in3in4not1not2_this_seq |
| 1013 |
); |
| 1014 |
|
| 1015 |
/* cerr << "len1: " << len_gff1_this_seq << endl; */ |
| 1016 |
/* cerr << "len2: " << len_gff2_this_seq << endl; */ |
| 1017 |
/* cerr << "len3: " << len_gff3_this_seq << endl; */ |
| 1018 |
/* cerr << "len4: " << len_gff4_this_seq << endl; */ |
| 1019 |
|
| 1020 |
/* cerr << "in1n34: " << in1not3not4_this_seq << endl; */ |
| 1021 |
/* cerr << "in2n34: " << in2not3not4_this_seq << endl; */ |
| 1022 |
/* cerr << "in12n34: " << in1in2not3not4_this_seq << endl; */ |
| 1023 |
/* cerr << "in34n12: " << in3in4not1not2_this_seq << endl; */ |
| 1024 |
|
| 1025 |
len_gff1 += len_gff1_this_seq; |
| 1026 |
len_gff2 += len_gff2_this_seq; |
| 1027 |
len_gff3 += len_gff3_this_seq; |
| 1028 |
len_gff4 += len_gff4_this_seq; |
| 1029 |
|
| 1030 |
/* cerr << "int-res: len1: " << len_gff1 << endl; */ |
| 1031 |
/* cerr << "int-res: len2: " << len_gff2 << endl; */ |
| 1032 |
/* cerr << "int-res: len3: " << len_gff3 << endl; */ |
| 1033 |
/* cerr << "int-res: len4: " << len_gff4 << endl; */ |
| 1034 |
|
| 1035 |
|
| 1036 |
in1not3not4 += in1not3not4_this_seq; |
| 1037 |
in2not3not4 += in2not3not4_this_seq; |
| 1038 |
in1in2not3not4 += in1in2not3not4_this_seq; |
| 1039 |
in3in4not1not2 += in3in4not1not2_this_seq; |
| 1040 |
|
| 1041 |
++it; |
| 1042 |
} |
| 1043 |
} // END friend void get_coverage_info_in1in2not3no4_loop |
| 1044 |
|
| 1045 |
|
| 1046 |
void set_to_complement_in_universe(GFF_collection &universe, GFF_collection &gff, |
| 1047 |
easystring creator, easystring feature) |
| 1048 |
{ |
| 1049 |
int mi, ma; |
| 1050 |
universe.get_min_max_number_of_features_for_Seqid(mi, ma); |
| 1051 |
|
| 1052 |
if (mi != 1 || ma != 1) |
| 1053 |
{ |
| 1054 |
std::cerr << "Error in set_to_complement_in_inverse: In the universe collection each sequence id can only occurr once." |
| 1055 |
<< std::endl; |
| 1056 |
return; |
| 1057 |
} |
| 1058 |
|
| 1059 |
vector<easystring> vec_seqIds = universe.getVectorOfSeqid(); |
| 1060 |
|
| 1061 |
unsigned i, N=vec_seqIds.size(); |
| 1062 |
CRangeList rl1, rl2, rl2res; |
| 1063 |
Crange limit; |
| 1064 |
GFF_record *p; |
| 1065 |
easystring name; |
| 1066 |
|
| 1067 |
for (i=0; i<N; ++i) |
| 1068 |
{ |
| 1069 |
std::cerr << "Compute complement in " << vec_seqIds[i] << endl; |
| 1070 |
universe.getRangeList(rl1, vec_seqIds[i]); |
| 1071 |
gff.getRangeList(rl2, vec_seqIds[i]); |
| 1072 |
limit = *(rl1.begin()); |
| 1073 |
|
| 1074 |
rl2res.set_to_complement_of(rl2, limit); |
| 1075 |
|
| 1076 |
// std::cerr << "SIZE: " << rl2res.size() << endl; |
| 1077 |
|
| 1078 |
CRangeList::CRangeList_iterator_const rl_it, rl_it_end; |
| 1079 |
|
| 1080 |
rl_it = rl2res.begin(); |
| 1081 |
rl_it_end = rl2res.end(); |
| 1082 |
|
| 1083 |
easystring n100 = "."; |
| 1084 |
|
| 1085 |
while (rl_it != rl_it_end) |
| 1086 |
{ |
| 1087 |
// Remember the conventions here: |
| 1088 |
// The ranges in rl2res are non inclusive for the end of the range. |
| 1089 |
// But GFF_records store ranges such that the end coordinate is |
| 1090 |
// the last coordinate in the range. So we have to subract 1. |
| 1091 |
name = easystring("name=") + vec_seqIds[i] + "_" + easystring(rl_it->begin()) + "_" + easystring(rl_it->end()-1); |
| 1092 |
p = new GFF_record(vec_seqIds[i], creator, feature, |
| 1093 |
rl_it->begin(), rl_it->end()-1, n100, '.', '.', name); |
| 1094 |
add(p); |
| 1095 |
|
| 1096 |
// p->print(cout); |
| 1097 |
// std::cout << endl; |
| 1098 |
|
| 1099 |
// delete p; |
| 1100 |
|
| 1101 |
++rl_it; |
| 1102 |
} |
| 1103 |
|
| 1104 |
} |
| 1105 |
} |
| 1106 |
|
| 1107 |
|
| 1108 |
void set_to_union_of(GFF_collection &gff1, GFF_collection &gff2, |
| 1109 |
easystring creator, easystring feature) |
| 1110 |
{ |
| 1111 |
// Determine set of all Seqids: |
| 1112 |
set<easystring> s; |
| 1113 |
|
| 1114 |
gff1.addSeqidsToSet(s); |
| 1115 |
gff2.addSeqidsToSet(s); |
| 1116 |
|
| 1117 |
set<easystring>::iterator it, it_end; |
| 1118 |
map<easystring, int>::iterator it_find; |
| 1119 |
|
| 1120 |
it = s.begin(); |
| 1121 |
it_end = s.end(); |
| 1122 |
|
| 1123 |
// bool present1, present2; |
| 1124 |
|
| 1125 |
CRangeList rl1; |
| 1126 |
CRangeList rl2; |
| 1127 |
CRangeList rlres; |
| 1128 |
|
| 1129 |
easystring name; |
| 1130 |
|
| 1131 |
// For all Seqids |
| 1132 |
while (it != it_end) |
| 1133 |
{ |
| 1134 |
/* present1 = false; */ |
| 1135 |
/* present2 = false; */ |
| 1136 |
rl1.clear(); |
| 1137 |
rl2.clear(); |
| 1138 |
rlres.clear(); |
| 1139 |
|
| 1140 |
it_find = gff1.sequences.find(*it); |
| 1141 |
if (it_find == gff1.sequences.end() ) |
| 1142 |
{ |
| 1143 |
if (____verbosity > 1) |
| 1144 |
{ |
| 1145 |
cerr << "Note: Sequence " << *it |
| 1146 |
<< " is present in gff file 2 but not in file 1." << endl; |
| 1147 |
} |
| 1148 |
} |
| 1149 |
else |
| 1150 |
{ |
| 1151 |
// present1 = true; |
| 1152 |
gff1.getRangeList(rl1, *it); |
| 1153 |
} |
| 1154 |
|
| 1155 |
it_find = gff2.sequences.find(*it); |
| 1156 |
if (it_find == gff2.sequences.end() ) |
| 1157 |
{ |
| 1158 |
if (____verbosity > 1) |
| 1159 |
{ |
| 1160 |
cerr << "Note: Sequence " << *it |
| 1161 |
<< " is present in gff file 1 but not in file 2." << endl; |
| 1162 |
} |
| 1163 |
} |
| 1164 |
else |
| 1165 |
{ |
| 1166 |
// present2 = true; |
| 1167 |
gff2.getRangeList(rl2, *it); |
| 1168 |
} |
| 1169 |
|
| 1170 |
rlres.set_to_range_list_union(rl1, rl2); |
| 1171 |
|
| 1172 |
easystring n100 = "."; |
| 1173 |
easystring seq_name = *it; |
| 1174 |
GFF_record *p; |
| 1175 |
|
| 1176 |
CRangeList::CRangeList_iterator_const rl_it, rl_it_end; |
| 1177 |
rl_it = rlres.begin(); |
| 1178 |
rl_it_end = rlres.end(); |
| 1179 |
|
| 1180 |
while (rl_it != rl_it_end) |
| 1181 |
{ |
| 1182 |
// Remember the conventions here: |
| 1183 |
// The ranges in rlres are non inclusive for the end of the range. |
| 1184 |
// But GFF_records store ranges such that the end coordinate is |
| 1185 |
// the last coordinate in the range. So we have to subract 1. |
| 1186 |
name = easystring("name=") + seq_name + "_" + easystring(rl_it->begin()) + "_" + easystring(rl_it->end()-1); |
| 1187 |
p = new GFF_record(seq_name, creator, feature, |
| 1188 |
rl_it->begin(), rl_it->end()-1, n100, '.', '.', name); |
| 1189 |
add(p); |
| 1190 |
// p->print(cout); |
| 1191 |
// std::cout << endl; |
| 1192 |
// delete p; |
| 1193 |
++rl_it; |
| 1194 |
} // while (rl_it != rl_it_end) |
| 1195 |
++it; |
| 1196 |
} // while (it != it_end) |
| 1197 |
|
| 1198 |
} |
| 1199 |
|
| 1200 |
void set_to_intersection_of(GFF_collection &gff1, GFF_collection &gff2, |
| 1201 |
easystring creator, easystring feature) |
| 1202 |
{ |
| 1203 |
// Determine set of all Seqids: |
| 1204 |
set<easystring> s; |
| 1205 |
|
| 1206 |
gff1.addSeqidsToSet(s); |
| 1207 |
gff2.addSeqidsToSet(s); |
| 1208 |
|
| 1209 |
set<easystring>::iterator it, it_end; |
| 1210 |
map<easystring, int>::iterator it_find; |
| 1211 |
|
| 1212 |
it = s.begin(); |
| 1213 |
it_end = s.end(); |
| 1214 |
|
| 1215 |
// bool present1, present2; |
| 1216 |
|
| 1217 |
CRangeList rl1; |
| 1218 |
CRangeList rl2; |
| 1219 |
CRangeList rlres; |
| 1220 |
|
| 1221 |
easystring name; |
| 1222 |
|
| 1223 |
// For all Seqids |
| 1224 |
while (it != it_end) |
| 1225 |
{ |
| 1226 |
// present1 = false; |
| 1227 |
// present2 = false; |
| 1228 |
rl1.clear(); |
| 1229 |
rl2.clear(); |
| 1230 |
rlres.clear(); |
| 1231 |
|
| 1232 |
it_find = gff1.sequences.find(*it); |
| 1233 |
if (it_find == gff1.sequences.end() ) |
| 1234 |
{ |
| 1235 |
if (____verbosity > 1) |
| 1236 |
{ |
| 1237 |
cerr << "Note: Sequence " << *it |
| 1238 |
<< " is present in gff file 2 but not in file 1." << endl; |
| 1239 |
} |
| 1240 |
} |
| 1241 |
else |
| 1242 |
{ |
| 1243 |
// present1 = true; |
| 1244 |
gff1.getRangeList(rl1, *it); |
| 1245 |
} |
| 1246 |
|
| 1247 |
it_find = gff2.sequences.find(*it); |
| 1248 |
if (it_find == gff2.sequences.end() ) |
| 1249 |
{ |
| 1250 |
if (____verbosity > 1) |
| 1251 |
{ |
| 1252 |
cerr << "Note: Sequence " << *it |
| 1253 |
<< " is present in gff file 1 but not in file 2." << endl; |
| 1254 |
} |
| 1255 |
} |
| 1256 |
else |
| 1257 |
{ |
| 1258 |
// present2 = true; |
| 1259 |
gff2.getRangeList(rl2, *it); |
| 1260 |
} |
| 1261 |
|
| 1262 |
rlres.set_to_range_list_intersection(rl1, rl2); |
| 1263 |
|
| 1264 |
// std::cerr << "rl1" << endl; |
| 1265 |
// rl1. print_bracketed_list(std::cerr); |
| 1266 |
// std::cerr << "rl2" << endl; |
| 1267 |
// rl2. print_bracketed_list(std::cerr); |
| 1268 |
// std::cerr << "rlres" << endl; |
| 1269 |
// rlres. print_bracketed_list(std::cerr); |
| 1270 |
|
| 1271 |
easystring n100 = "."; |
| 1272 |
easystring seq_name = *it; |
| 1273 |
GFF_record *p; |
| 1274 |
|
| 1275 |
CRangeList::CRangeList_iterator_const rl_it, rl_it_end; |
| 1276 |
rl_it = rlres.begin(); |
| 1277 |
rl_it_end = rlres.end(); |
| 1278 |
|
| 1279 |
while (rl_it != rl_it_end) |
| 1280 |
{ |
| 1281 |
// Remember the conventions here: |
| 1282 |
// The ranges in rlres are non inclusive for the end of the range. |
| 1283 |
// But GFF_records store ranges such that the end coordinate is |
| 1284 |
// the last coordinate in the range. So we have to subract 1. |
| 1285 |
name = easystring("name=") + seq_name + "_" + easystring(rl_it->begin()) + "_" + easystring(rl_it->end()-1); |
| 1286 |
p = new GFF_record(seq_name, creator, feature, |
| 1287 |
rl_it->begin(), rl_it->end()-1, n100, '.', '.', name); |
| 1288 |
add(p); |
| 1289 |
// p->print(cout); |
| 1290 |
// std::cout << endl; |
| 1291 |
// delete p; |
| 1292 |
++rl_it; |
| 1293 |
} // while (rl_it != rl_it_end) |
| 1294 |
++it; |
| 1295 |
} // while (it != it_end) |
| 1296 |
|
| 1297 |
} |
| 1298 |
|
| 1299 |
|
| 1300 |
|
| 1301 |
|
| 1302 |
|
| 1303 |
}; // End class GFF_collection |
| 1304 |
|
| 1305 |
|
| 1306 |
|
| 1307 |
#endif |