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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703
|
#include "GraphOutput.h"
const string GraphOutput::graph_file_suffix = ".graph";
const string GraphOutput::nodes_file_suffix = ".nodes";
const string GraphOutput::edges_file_suffix = ".edges";
const string GraphOutput::substarters_file_suffix = ".substarters";
const string GraphOutput::starters_file_suffix = ".starters";
const string GraphOutput::xml_file_suffix = ".xgmml";
const string GraphOutput::json_nodes_file_suffix = ".json_nodes";
const string GraphOutput::json_edges_file_suffix = ".json_edges";
const string GraphOutput::json_substarters_file_suffix = ".json_substarters";
const string GraphOutput::json_starters_file_suffix = ".json_starters";
const string GraphOutput::json_file_suffix = ".json";
/************************************************************************************************************************/
/* init function initialize the files need to construct graph file or sequences file */
/* */
/************************************************************************************************************************/
void GraphOutput::init(bool erase){
//printf("create a graph erase=%s graph_format=%d first_id_nodes=%d first_id_edges=%d\n"", erase?"true":"false", graph_format, first_id_els.node, first_id_els.edge);
graph_file_name=(prefix+graph_file_suffix);
nodes_file_name=(prefix+nodes_file_suffix);
edges_file_name=(prefix+edges_file_suffix);
substarters_file_name=(prefix+substarters_file_suffix);
starters_file_name=(prefix+starters_file_suffix);
xml_file_name=(prefix+xml_file_suffix);
json_nodes_file_name=(prefix+json_nodes_file_suffix);
json_edges_file_name=(prefix+json_edges_file_suffix);
json_substarters_file_name=(prefix+json_substarters_file_suffix);
json_starters_file_name=(prefix+json_starters_file_suffix);
json_file_name=(prefix+json_file_suffix);
switch (graph_format){
case 0:// FORMAT .GRAPH
graph_file = fopen(graph_file_name.c_str(),erase?"w":"a");
fprintf(graph_file,"digraph dedebruijn {\n");
break;
case 1: // FORMAT .NODES AND .EDGES
nodes_file = fopen(nodes_file_name.c_str(),erase?"w":"a");
edges_file = fopen(edges_file_name.c_str(),erase?"w":"a");
break;
case 2 :// FORMAT .XGMML
graph_file = fopen(xml_file_name.c_str(),erase?"w":"a");
break;
case 3: // FORMAT .json
nodes_file = fopen(json_nodes_file_name.c_str(),erase?"w":"a");
edges_file = fopen(json_edges_file_name.c_str(),erase?"w":"a");
substarters_file = fopen(json_substarters_file_name.c_str(),erase?"w":"a");
starters_file = fopen(json_starters_file_name.c_str(),erase?"w":"a");
graph_file = fopen(json_file_name.c_str(),erase?"w":"a");
break;
}
}
/************************************************************************************************************************/
/* printf GraphOutput and initialize files (files are not erasing) */
/* */
/************************************************************************************************************************/
GraphOutput::GraphOutput(string prefix, int graph_format, id_els first_id_els) : prefix(prefix), graph_format(graph_format), first_id_els(first_id_els)
{ // PIERRE: need something different than 0 for the first node
printf("graph_format=%d first_id_nodes=%lu first_id_edges=%d\n", graph_format, first_id_els.node, first_id_els.edge);
init(false);
}
/************************************************************************************************************************/
/* Initialize first elements and files (files are erasing) */
/* */
/************************************************************************************************************************/
GraphOutput::GraphOutput(string prefix, int graph_format) : prefix(prefix), graph_format(graph_format)
{
first_id_els.node=0;
first_id_els.edge=0;
init(true);
}
/************************************************************************************************************************/
/* write graph file or sequence file */
/* */
/************************************************************************************************************************/
void GraphOutput::close()
{
switch (graph_format){
case 0:
fprintf(graph_file,"}\n");
fclose(graph_file);
break;
case 1:
fclose(nodes_file);
fclose(edges_file);
break;
case 2:
fprintf(graph_file,"</graph>\n");
fclose(graph_file);
break;
case 3:
// We need to store all nodes and then all edges in the final .json file
fclose(nodes_file);
fclose(edges_file);
fclose(substarters_file);
fclose(starters_file);
ifstream nodes(json_nodes_file_name.c_str(), ios::in);
ifstream edges(json_edges_file_name.c_str(), ios::in);
ifstream substarters(json_substarters_file_name.c_str(), ios::in);
ifstream starters(json_starters_file_name.c_str(), ios::in);
if(!edges || !nodes || !substarters | !starters){fprintf(stderr,"Cannot open file %s, %s, %s or %s, exit\n", json_edges_file_suffix.c_str(), json_nodes_file_suffix.c_str(), json_substarters_file_suffix.c_str(), json_starters_file_suffix.c_str()); exit(1);}
string line;
// long count_nodes=0;
// long count_edges=0;
// long cumul =0;
// long edges_per_extension = 0;
fprintf(graph_file,"{\n"); // overall json {
bool first=true;
while(getline(starters,line)){
if(!first) fprintf(graph_file,",\n"); // separates starters
first = false;
fprintf(graph_file,"%s\n", line.c_str());
fprintf(graph_file,"\"substarters\": [");
getline(substarters,line);
bool at_least_one_sub=false;
if(continue_starter_write(line)){ // if this substater is not empty
at_least_one_sub=true;
fprintf(graph_file,"\n%s",line.c_str());
while(getline(substarters,line)) {
if (continue_starter_write(line)){
fprintf(graph_file,",\n%s",line.c_str());
}
else break; // end of this substarter
}
}
if(!at_least_one_sub) {
fprintf(graph_file,"\n]\n"); // there was no substarter
getline(nodes,line); // we read a gost line containing startNewStarter
}
else { // there was at least one substarter
fprintf(graph_file,"\n],\n");
fprintf(graph_file,"\"extremGraphs\":[\n"); // we print this line only if we had at least one
int i =0;
//fprintf(graph_file," %s \n"line.c_str());
bool first_data_xtrem_graph=true;
while(getline(nodes,line) && continue_starter_write(line)){
if(!first_data_xtrem_graph) fprintf(graph_file,",\n"); // separates data_xtrem_graph
first_data_xtrem_graph = false;
//getline(nodes,line);
//fprintf(graph_file,",\n");
fprintf(graph_file,"{\"data\":{\"id\":\"k%d\", %s \n\"nodes\":[",i,line.c_str()); // prints data for the starter
// prints the first node (that necessarly exists)
getline(nodes,line);
fprintf(graph_file,"\n\t%s",line.c_str()); // prints the first node without comma before and
// count_nodes++;
// cumul += sequence_length(line);
//for each node of each extension
while(getline(nodes,line)){
//test if there are at the end of the array of node for this extension
if (read_continue(line)){ // prints the other nodes
fprintf(graph_file,",\n\t%s",line.c_str());
// count_nodes++;
// cumul += sequence_length(line);
}
else{ // prints the edges of nodes of this extension
fprintf(graph_file,"\n],\n"); // end of nodes
fprintf(graph_file,"\"edges\": ["); // starts of edges
getline(edges,line);
// edges_per_extension=0;
if (read_continue(line)){// test of end
fprintf(graph_file,"\n\t%s",line.c_str()); // prints the first edge without comma before
// count_edges++;
// edges_per_extension++;
}
else{ // there was NO edge
break;
//getline(edges,line);
}
// We already read one edge, lets continue (starting with a ',')
//for each edges of each extension
while(getline(edges,line)) {
if (read_continue(line)){// test of end
fprintf(graph_file,",\n\t%s",line.c_str()); // print other edges
// count_edges++;
// edges_per_extension++;
}
else{
break;
}
}
break;
}
} // end all edges
if( ! first_data_xtrem_graph) // we read at least one xtrem graph data
fprintf(graph_file,"\n]\n}}"); // END: ] edges, } data, } xtrem graph
i++;
} // end all xtrem graphs of one starter
fprintf(graph_file,"]"); // end all xtrem graphs of this starter
} // end at least one substarter
// if(edges_per_extension>0){
// fseek(graph_file, -2, SEEK_CUR);
// fprintf(graph_file,"\n]\n},\n"); // ] closes the last extremGraph
//
// }
//end of graph file en close file
fprintf(graph_file,"\n}"); // end of a starter
} // end all starters
// if(edges_per_extension>0){
// fseek(graph_file, -13, SEEK_CUR);
// fprintf(graph_file,"}}\n]\n}}\n]\n}\n}");
//
// }else{
// fseek(graph_file, -4, SEEK_CUR);
// fprintf(graph_file,"}}\n]\n}\n}");
// }
fprintf(graph_file,"\n}"); // end of the json
nodes.close(); //remove(json_nodes_file_name.c_str());
edges.close(); //remove(json_edges_file_name.c_str());
substarters.close();//remove(json_substarters_file_name.c_str());
starters.close();//remove(json_starters_file_name.c_str());
fclose(graph_file);
break;
}
}
/************************************************************************************************************************/
/* print head for a starter */
/* */
/************************************************************************************************************************/
void GraphOutput::print_starter_head(int index, char* sequence)
{
if(graph_format == 2){
/*fprintf(graph_file,"<?xml version=\"1.0\"?>\n<!DOCTYPE graph SYSTEM \"http://www.cs.rpi.edu/~puninj/XGMML/xgmml.dtd\">\n<graph directed=\"1\">\n");
fprintf(graph_file,"<graph label=\"%s\" starterID=%d sequence=%s\n", (char *)prefix.c_str(), index, sequence);
fprintf(graph_file,"xmlns:dc=\"http://purl.org/dc/elements/1.1/\" \n");
fprintf(graph_file,"xmlns:xlink=\"http://www.w3.org/1999/xlink\" \n");
fprintf(graph_file,"xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\" \n");
fprintf(graph_file,"xmlns:cy=\"http://www.cytoscape.org\" \n");
fprintf(graph_file,"xmlns=\"http://www.cs.rpi.edu/XGMML\" \n");
fprintf(graph_file,"directed=\"1\">\n");*/
}else if(graph_format == 3) // json format
fprintf(starters_file,"\"Starter_%d\":{\"id\":\"S%d\", \"sequence\":\"%s\",\n", index,index, sequence);
}
/************************************************************************************************************************/
/* test if get an other kmer */
/* */
/************************************************************************************************************************/
int GraphOutput::read_continue(string line) //test if it's the end of nodes or edges for each substarters
{
int err,match;
regex_t preg;
const char *line_c =NULL;
const char *str_regex = "endOfKmer";
line_c = line.c_str();
err = regcomp (&preg, str_regex, REG_NOSUB | REG_EXTENDED);
if (err == 0)
{
match = regexec (&preg, line_c, 0, NULL, 0);
regfree (&preg);
}
return match;
}
/************************************************************************************************************************/
/* test if get an other kmer */
/* */
/************************************************************************************************************************/
int GraphOutput::continue_starter_write(string line) //test if it's the end of nodes or edges for each substarters
{
int err,match;
regex_t preg;
const char *line_c =NULL;
const char *str_regex = "startNewStarter";
line_c = line.c_str();
err = regcomp (&preg, str_regex, REG_NOSUB | REG_EXTENDED);
if (err == 0)
{
match = regexec (&preg, line_c, 0, NULL, 0);
regfree (&preg);
}
return match;
}
/************************************************************************************************************************/
/* recalculate length for a node (more efficient than capture length in string and convert the in integer) */
/* */
/************************************************************************************************************************/
long GraphOutput::sequence_length(string line)
{
string seq_char;
int err,match,start, end;
regex_t preg;
long seq_len=0;
size_t nmatch, size;
const char *str_regex ="([A-Z]+)"; //regex capture sequences characters
const char *line_c =NULL;
line_c = line.c_str();
err = regcomp (&preg, str_regex, REG_EXTENDED);
if (err == 0)//security for error string snapshot and if regex match
{
nmatch = 0;
nmatch = preg.re_nsub;
regmatch_t *pmatch=NULL;
pmatch = (regmatch_t*) malloc (sizeof (*pmatch) * nmatch);
if (pmatch)
{
match = regexec (&preg, line_c, nmatch, pmatch, 0);
regfree (&preg);
if (match == 0)
{
char *seq_char =NULL;
start = pmatch[0].rm_so;
end = pmatch[0].rm_eo;
size = end - start;
seq_len = sizeof(line_c[start])*(size);
}
}
}
else
{
fprintf (stderr, "LOW MEMORY !\n");
exit (EXIT_FAILURE);
}
return seq_len;
}
/************************************************************************************************************************/
/* output a single substarter to a file */
/* */
/************************************************************************************************************************/
void GraphOutput::print_substarter(long index, char *ascii_node, string comment) // output a single node to a file
{
if(graph_format==2){
}else if(graph_format==3){
fprintf(substarters_file," { \"data\": { \"id\":\"s%ld\", \"sequence\":\"%s\", %s}}\n",index,ascii_node, comment.c_str());
}
}
/************************************************************************************************************************/
/* output a single substarter to a file */
/* */
/************************************************************************************************************************/
void GraphOutput::print_substarters_end() // output a single node to a file
{
if(graph_format==2){
}else if(graph_format==3){
fprintf(substarters_file,"startNewStarter\n");
}
}
/************************************************************************************************************************/
/* output a single node to a file */
/* */
/************************************************************************************************************************/
//TODO: comment with xgmml format
void GraphOutput::print_node(long index, char *ascii_node) // output a single node to a file
{
switch (graph_format){
case 0: // DOT format
fprintf(graph_file,"%ld [label=\"%s\"];\n",index,ascii_node);
break;
case 1: // kissplice format
fprintf(nodes_file,"%ld\t%s\n",index,ascii_node);
break;
case 2: // XGMML format
fprintf(graph_file,"<node id=\"%ld\" label=\"%s\">\n</node>\n",index,ascii_node);
break;
case 3: // json format
fprintf(nodes_file," { \"data\": { \"id\":\"n%ld\", \"sequence\":\"%s\"}}\n",index,ascii_node);
break;
}
}
/************************************************************************************************************************/
/* output a single substarter to a file */
/* */
/************************************************************************************************************************/
void GraphOutput::print_nodes_end() // output a single node to a file
{
if(graph_format==2){
}else if(graph_format==3){
fprintf(nodes_file,"startNewStarter\n");
}
}
/************************************************************************************************************************/
/* output a single edges to a file */
/* */
/************************************************************************************************************************/
//TODO: comment with xgmml format
void GraphOutput::print_edge(long index, long id, long id2, string label,string comment)
{
switch (graph_format){
case 0: // DOT format
fprintf(graph_file,"%ld -> %ld [label=\"%s\"];\n",id,id2,label.c_str());
break;
case 1: // kissplice format
fprintf(edges_file,"%ld\t%ld\t%s\n",id,id2,label.c_str());
break;
case 2: // XGMML format
fprintf(graph_file,"<edge source=\"%ld\" target=\"%ld\" label=\"%s\">\n</edge>\n",id,id2,label.c_str());
break;
case 3: // json format
fprintf(edges_file,"{ \"data\":{ \"id\": \"e%ld\", \"source\": \"n%ld\",\"target\": \"n%ld\",\"direction\": \"%s\"%s}}\n",index, id,id2,label.c_str(), comment.c_str());
break;
}
}
/************************************************************************************************************************/
/* output a single substarter to a file */
/* */
/************************************************************************************************************************/
void GraphOutput::print_edges_end() // output a single node to a file
{
if(graph_format==2){
}else if(graph_format==3){
fprintf(edges_file,"startNewStarter\n");
}
}
/************************************************************************************************************************/
/* load nodes extremities */
/* */
/************************************************************************************************************************/
void GraphOutput::load_nodes_extremities(string linear_seqs_name)
{
kmer_links.clear(); // PIERRE: reset previous stored kmer links
Bank *Nodes = new Bank((char *)linear_seqs_name.c_str());
long nb_nodes = first_id_els.node; //PIERRE;
char * rseq;
int readlen;
sizeKmer--; // nodes extremities overlap by (k-1)-mers, so let's extract (k-1)-mers
while (Nodes->get_next_seq(&rseq,&readlen))
{
kmer_type left_kmer, right_kmer, left_kmer_fw, left_kmer_rc, right_kmer_fw, right_kmer_rc;
left_kmer = extractKmerFromRead(rseq,0,&left_kmer_fw,&left_kmer_rc, false);
right_kmer = extractKmerFromRead(rseq,readlen-sizeKmer,&right_kmer_fw,&right_kmer_rc, false);
Strand left_strand = (left_kmer == left_kmer_fw)?FW:RC;
Strand right_strand = (right_kmer == right_kmer_fw)?FW:RC;
kmer_links[left_kmer].insert(node_strand(nb_nodes, left_strand, LEFT));
kmer_links[right_kmer].insert(node_strand(nb_nodes, right_strand, RIGHT));
nb_nodes++;
}
Nodes->close();
delete Nodes;
sizeKmer++; // make sure to restore k
}
/************************************************************************************************************************/
/* make string for nodes data (length, depth, direction) */
/* */
/************************************************************************************************************************/
//TODO: debug mode
//TODO: XGMML data node
string GraphOutput::data_regex(char* header)
{
//bool debug = verb>=2 ? 1 : 0;
char data[200];
int err,match,start, end;
regex_t preg;
size_t nmatch, size;
const char *str_regex ="len__([0-9]+)__depth__([0-9]+)__direction__(LEFT|RIGHT)"; //regex capture sequences characters
const char *str_request = header;
err = regcomp (&preg, str_regex, REG_EXTENDED);
if (err == 0)//security for error string snapshot and if regex match
{
nmatch = 0;
nmatch = preg.re_nsub;
regmatch_t *pmatch=NULL;
pmatch = (regmatch_t*) malloc (sizeof (*pmatch) * nmatch);
if (pmatch)
{
match = regexec (&preg, str_request, nmatch, pmatch, 0);
regfree (&preg);
if (match == 0)
{
int start_len = pmatch[1].rm_so;
int end_len = pmatch[1].rm_eo;
int start_depth = pmatch[2].rm_so;
int end_depth = pmatch[2].rm_eo;
size_t size_len = end_len - start_len;
size_t size_depth =end_depth - start_depth;
char * len = (char*) malloc (sizeof (*len) * (size_len + 1));
char * depth = (char*) malloc (sizeof (*depth) * (size_depth + 1));
if (len && depth)
{
strncpy (len, &str_request[start_len], size_len);
strncpy (depth, &str_request[start_depth], size_depth);
len[size_len] = '\0';
depth[size_depth] = '\0';
sprintf (data, "\"length\":%s, \"depth\":%s", len, depth);
//printf ("Extension data info: length=%s, depth=%s, direction=%s \n", len, depth, direction);
}
}
}
}
else
{
fprintf (stderr, "LOW MEMORY !\n");
exit (EXIT_FAILURE);
}
return string(data);
}
/************************************************************************************************************************/
/* construct node file and edge file for graph file */
/* */
/************************************************************************************************************************/
id_els GraphOutput::construct_graph(string linear_seqs_name, const string direction) // PIERRE: i need to know the last nb_nodes
{
Bank *Nodes = new Bank((char *)linear_seqs_name.c_str());
id_els nb_els = first_id_els; //Alexan: stucture for print id elements in graph output
char * rseq;
int readlen;
char *header;
int hlen;
bool end = true;
Nodes->rewind_all();
//nb_els.node = first_id_els.node;
//nb_els.edge = first_id_els.edge;
string kmerSequence = linear_seqs_name;
kmerSequence.erase(0, 13);
strtok( (char*) kmerSequence.c_str(), "_");
// char* direction =strtok( NULL, "_");
fprintf(nodes_file, "\"sequence\":\"%s\", \"direction\":\"%s\", \"firstNodeId\":\"n%d\",\n ", kmerSequence.c_str(),direction.c_str(),nb_els.node);
sizeKmer--; // nodes extremities overlap by (k-1)-mers, so let's extract (k-1)-mers
// for each node, output all the out-edges (in-edges will correspond to out-edges of neighbors)
/* int nb_seq =0;
string s;
while (getline(file, s))
nb_seq++;*/
//for(int i=0; i<nb_seq-1; i++){
while(Nodes->get_next_seq(&rseq,&header,&readlen,&hlen)){
end = false;
kmer_type left_kmer, right_kmer, left_kmer_fw, left_kmer_rc, right_kmer_fw, right_kmer_rc;
set<node_strand>::iterator it;
left_kmer = extractKmerFromRead(rseq,0,&left_kmer_fw,&left_kmer_rc, false);
right_kmer = extractKmerFromRead(rseq,readlen-sizeKmer,&right_kmer_fw,&right_kmer_rc, false);
Strand left_strand = (left_kmer == left_kmer_fw)?FW:RC;
Strand right_strand = (right_kmer == right_kmer_fw)?FW:RC;
// left edges (are revcomp extensions)
//int nb_left_edges = 0;
for (it = kmer_links[left_kmer].begin(); it != kmer_links[left_kmer].end(); it++)
{
long cur_node = it->node;
Strand cur_strand = it->strand;
LeftOrRight cur_left_or_right = it->left_or_right;
if (cur_node == nb_els.node) // prevent self loops on same kmer
if (readlen == sizeKmer)
continue;
string label = "R";
if (cur_left_or_right == LEFT)
{
if (cur_strand != left_strand)
label+=(string)"F";
else
continue;
}
else
{
if (cur_strand == left_strand)
label+=(string)"R";
else
continue;
}
print_edge(nb_els.edge, nb_els.node,cur_node,label,"");
//nb_left_edges++;
nb_els.edge++;
}
// right edges
//int nb_right_edges = 0;
for (it = kmer_links[right_kmer].begin(); it != kmer_links[right_kmer].end(); it++)
{
long cur_node = it->node;
Strand cur_strand = it->strand;
LeftOrRight cur_left_or_right = it->left_or_right;
if (cur_node == nb_els.node) // prevent self loops on same kmer
if (readlen == sizeKmer)
continue;
string label = "F";
if (cur_left_or_right == LEFT)
{
if (cur_strand == right_strand)
label+=(string)"F";
else
continue;
}
else
{
if (cur_strand != right_strand)
label+=(string)"R";
else
continue;
}
print_edge(nb_els.edge, nb_els.node,cur_node,label,"");
//nb_right_edges++;
nb_els.edge++; //ALEXAN
}
//nb_els.edge += nb_left_edges + nb_right_edges;
//nodes
//printf("%s\n",linear_seqs_name.c_str());
// string data = data_regex(header);
// string dataEnd ("endOfJson");
// if(dataEnd.compare(data) != 0){
print_node(nb_els.node, rseq);
nb_els.node++;
// }
end = true ;
}
if(end){
fprintf(edges_file, "endOfKmer\n");
fprintf(nodes_file, "endOfKmer\n");
};
sizeKmer++; // make sure to restore k
Nodes->close();
delete Nodes;
return nb_els; // PIERRE
}
|