ecoprimer.c 28.4 KB
Newer Older
1 2 3 4 5 6 7 8
/*
 * ecoprimer.c
 *
 *  Created on: 7 nov. 2008
 *      Author: coissac
 */

#include "libecoprimer/ecoprimer.h"
9
#include "libecoprimer/PrimerSets.h"
10 11 12 13 14 15 16
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <stdlib.h>
#include <getopt.h>
#include <time.h>
#include <sys/time.h>
17
#include <dlfcn.h>
18 19 20
#include"libthermo/nnparams.h"
#include"libthermo/thermostats.h"

21

22
#define VERSION "0.3"
23
  /* TR: by default, statistics are made on species level*/
Eric Coissac committed
24 25 26
#define DEFAULTTAXONRANK "species"

static int cmpprintedpairs(const void* p1,const void* p2);
27
//float _Z27calculateMeltingTemperature_ (char * seq1, char * seq2);
Eric Coissac committed
28

29 30
void* lib_handle = NULL;
float (*calcMelTemp)(char*, char*);
31 32 33 34 35 36 37 38

/* ----------------------------------------------- */
/* printout help                                   */
/* ----------------------------------------------- */
#define PP fprintf(stdout,

static void PrintHelp()
{
39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
			  PP      "------------------------------------------\n");
			  PP      " ecoPrimer Version %s\n", VERSION);
			  PP      "------------------------------------------\n");
              PP      "synopsis : finding primers and measureing the quality of primers and barcode region\n");
              PP      "usage: ./ecoPrimer [options] \n");
              PP      "------------------------------------------\n");
              PP      "options:\n");
              PP      "-d    : [D]atabase : to match the expected format, the database\n");
              PP      "        has to be formated first by the ecoPCRFormat.py program located.\n");
              PP      "        in the ecoPCR/tools directory.\n");
              PP      "        ecoPCRFormat.py creates three file types :\n");
              PP      "            .sdx : contains the sequences\n");
              PP      "            .tdx : contains information concerning the taxonomy\n");
              PP      "            .rdx : contains the taxonomy rank\n\n");
              PP      "        ecoPrimer needs all the file type. As a result, you have to write the\n");
Eric Coissac committed
54
              PP      "        database radical without any extension. For example /ecoPrimerDB/fstvert\n\n");
55 56
              PP      "-e    : [E]rror : max error allowed by oligonucleotide (0 by default)\n\n");
              PP      "-h    : [H]elp - print <this> help\n\n");
57
              PP      "-i    : [I]gnore the given taxonomy id (define the counterexample taxon set).\n\n");
58 59
              PP      "-l    : minimum [L]ength : define the minimum amplication length. \n\n");
              PP      "-L    : maximum [L]ength : define the maximum amplicationlength. \n\n");
60
              PP      "-r    : [R]estricts the search to the given taxonomic id (restrict the example taxon set).\n\n");
61
              PP      "-E    : [E]xception taxid allows to indicate than some subclade of example sequences are conterexamples.\n\n");
62
              PP      "-c    : Consider that the database sequences are [c]ircular\n\n");
63
              PP      "-3 	 : Three prime strict match\n\n");
64 65 66 67 68
              PP      "-q    : Strict matching [q]uorum, percentage of the sequences in which strict primers are found. By default it is 70\n\n");
              PP      "-s    : [S]ensitivity quorum\n\n");
              PP      "-t    : required [t]axon level for results, by default the results are computed at species level\n\n");
              PP      "-x    : false positive quorum\n\n");
              PP      "-D    : set in [d]ouble strand mode\n\n");
69
              PP      "-O    : set the primer length (default 18) \n\n");
70
              PP      "-S    : Set in [s]ingle strand mode\n\n");
71 72
              PP      "-m    : Salt correction method for Tm computation (SANTALUCIA : 1 or OWCZARZY:2, default=1)\n\n");
              PP      "-a    : Salt contentration in M for Tm computation (default 0.05 M)\n\n");
73
              PP      "-U    : No multi match\n\n");
74 75 76 77
              PP      "-U    : Define the [R]eference sequence identifier (must be part of example set)\n\n");
              PP      "-A    : Print the list of all identifier of sequences present in the database\n\n");
              PP      "-f    : Remove data mining step during  strict primer identification\n\n");
              PP      "-v    : Store statistic file about memory usage during strict primer identification\n\n");
78
              PP      "-p    : Print sets of primers\n\n");
79 80 81
              PP      "\n");
              PP      "------------------------------------------\n");
              PP      "Table result description : \n");
82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102
              PP      "column  1 : serial number\n");
              PP      "column  2 : primer1\n");
              PP      "column  3 : primer2\n");
              PP      "column  4 : primer1 Tm without mismatch\n");
              PP      "column  5 : primer1 lowest Tm against exemple sequences\n");
              PP      "column  6 : primer2 Tm without mismatch\n");
              PP      "column  7 : primer2 lowest Tm against exemple sequences\n");
              PP      "column  8 : primer1 G+C count\n");
              PP      "column  9 : primer2 G+C count\n");
              PP      "column 10 : good/bad\n");
              PP      "column 11 : amplified example sequence count\n");
              PP      "column 12 : amplified counterexample sequence count\n");
              PP      "column 13 : yule\n");
              PP      "column 14 : amplified example taxa count\n");
              PP      "column 15 : amplified counterexample taxa count\n");
              PP      "column 16 : ratio of amplified example taxa versus all example taxa (Bc index)\n");
              PP      "column 17 : unambiguously identified example taxa count\n");
              PP      "column 18 : ratio of specificity unambiguously identified example taxa versus all example taxa (Bs index)\n");
              PP      "column 19 : minimum amplified length\n");
              PP      "column 20 : maximum amplified length\n");
              PP      "column 21 : average amplified length\n");
103 104
              PP      "------------------------------------------\n");
              PP		" http://www.grenoble.prabi.fr/trac/ecoPrimer/\n");
Eric Coissac committed
105
              PP      "------------------------------------------\n\n");
106 107
              PP      "\n");

108 109 110 111 112 113 114 115 116 117 118 119 120 121 122
}

static void ExitUsage(int stat)
{
        PP      "usage: ecoprimer [-d database] [-l value] [-L value] [-e value] [-r taxid] [-i taxid] [-R rank] [-t taxon level]\n");
        PP      "type \"ecoprimer -h\" for help\n");

        if (stat)
            exit(stat);
}

#undef  PP

void initoptions(poptions_t options)
{
123
	options->statistics=FALSE;
124
	options->filtering=TRUE;
125
	options->lmin=0;                   //< Amplifia minimal length
126
	options->lmax=1000;                   //< Amplifia maximal length
127 128 129 130
	options->error_max=3;              //**< maximum error count in fuzzy search
	options->primer_length=18;          //**< minimal length of the primers
	options->restricted_taxid=NULL;      //**< limit amplification below these taxid
	options->ignored_taxid=NULL;         //**< no amplification below these taxid
131
	options->exception_taxid=NULL;         //**< no amplification below these taxid
132
	options->prefix=NULL;
133 134
	options->reference=NULL;
	options->refseq=NULL;
135 136
	options->circular=0;
	options->doublestrand=1;
137
	options->strict_quorum=0.3;
138
	options->strict_exclude_quorum=0.1;
139
	options->sensitivity_quorum=0.3;
140
	options->false_positive_quorum=0.1;
141
	options->strict_three_prime=0;
142 143
	options->r=0;
	options->g=0;
144
	options->e=0;
145
	options->no_multi_match=FALSE;
146
	options->pnparm = NULL;
Eric Coissac committed
147
	strcpy(options->taxonrank, DEFAULTTAXONRANK);			/*taxon level for results, species by default*/
148
	options->saltmethod = SALT_METHOD_SANTALUCIA;
149
	options->salt = DEF_SALT;
150
	options->printAC=FALSE;
151
	options->print_sets_of_primers = FALSE;
152 153
}

154 155
void printapair(int32_t index,ppair_t pair, poptions_t options)
{
Eric Coissac committed
156 157 158 159 160 161 162 163 164
	bool_t asdirect1=pair->asdirect1;
	bool_t asdirect2=pair->asdirect2;
	bool_t asdirecttmp;
	word_t w1=pair->p1->word;
	word_t w2=pair->p2->word;
	word_t wtmp;
	bool_t good1=pair->p1->good;
	bool_t good2=pair->p2->good;
	bool_t goodtmp;
165 166
	bool_t strand;
	uint32_t i;
167
	float temp;
168
	CNNParams nnparams;
169

170
	//nparam_InitParams(&nnparams, DEF_CONC_PRIMERS,DEF_CONC_SEQUENCES,DEF_SALT,SALT_METHOD_SANTALUCIA);
171 172

	char *c;
173 174
	char p1[32];
	char p2[32];
Eric Coissac committed
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196

	if (!asdirect1)
		w1=ecoComplementWord(w1,options->primer_length);

	if (!asdirect2)
		w2=ecoComplementWord(w2,options->primer_length);


	if (w2 < w1)
	{
		wtmp=w1;
		w1=w2;
		w2=wtmp;

		asdirecttmp=asdirect1;
		asdirect1=asdirect2;
		asdirect2=asdirecttmp;

		goodtmp=good1;
		good1=good2;
		good2=goodtmp;
	}
Eric Coissac committed
197

198
	//print serial number
199 200
	printf("%6d\t",index);

201 202 203 204 205
	c = ecoUnhashWord(w1,options->primer_length);
	strcpy (p1, c);
	c = ecoUnhashWord(w2,options->primer_length);
	strcpy (p2, c);

206
	//print primer1
207
	printf("%s\t", p1);
208

209
	//print primer2
210
	printf("%s", p2);
211

212
	//print primer1 melting temperature
213
	printf ("\t%3.1f", pair->p1temp);
214

215
	//print minimum melting temperature of approximate versions of primer1
216 217
	printf ("\t%3.1f", pair->p1mintemp);

218
	//print primer2 melting temperature
219 220
	printf ("\t%3.1f", pair->p2temp);

221
	//print minimum melting temperature of approximate versions of primer2
222 223
	printf ("\t%3.1f", pair->p2mintemp);

224 225
	//print gc contents of primer1
	printf ("\t%d",nparam_CountGCContent(p1));
226

227 228
	//print gc contents of primer2
	printf ("\t%d",nparam_CountGCContent(p2));
229

230
	//print good/bad pair indicator
Eric Coissac committed
231
	printf("\t%c%c", "bG"[(int)good1],"bG"[(int)good2]);
232

233
	//print inexample count
234
	printf("\t%d", pair->inexample);
235

236
	//print out example count
237
	printf("\t%d", pair->outexample);
238

239
	//print yule
240 241
	printf("\t%4.3f", pair->yule);

242
	//print in taxa count
243
	printf("\t%d", pair->intaxa);
244

245
	//print out taxa count
246
	printf("\t%d", pair->outtaxa);
247

248
	//print coverage
Eric Coissac committed
249
	printf("\t%4.3f", (float)pair->bc);
250

251
	//print well identified taxa count
Eric Coissac committed
252
	printf("\t%d", pair->intaxa - pair->notwellidentifiedtaxa);
253

254
	//print specificity
Eric Coissac committed
255
	printf("\t%4.3f", pair->bs);
256

257
	//print min amplifia lenght
258
	printf("\t%d", pair->mind);
259

260
	//print max amplifia lenght
261
	printf("\t%d", pair->maxd);
262

263
	//print average amplifia lenght
264
	printf("\t%3.2f", (float)pair->sumd/pair->amplifiacount);
265

266
	//print amplifia information about reference sequence if specified
267 268 269
	if (options->refseq && pair->refsequence >=0)
	{
		printf("\t%s:",options->reference);
270
		strand = pair->pcr.amplifias[pair->refsequence].strand;
271

272
		if (strand)
273 274 275 276 277 278 279 280 281 282 283 284
			printf("join(");
		else
			printf("complement(");

		printf("%d..%d,%d..%d",pair->pcr.amplifias[pair->refsequence].begin - options->primer_length + 1,
				                 pair->pcr.amplifias[pair->refsequence].begin,
							  	 pair->pcr.amplifias[pair->refsequence].end + 2,
							  	 pair->pcr.amplifias[pair->refsequence].end + options->primer_length + 1
							  	 );
		printf(")");
		printf("\t");

285 286 287 288 289 290 291 292
		for (c=pair->pcr.amplifias[pair->refsequence].amplifia,
		     i=pair->pcr.amplifias[pair->refsequence].begin;
			 i<=pair->pcr.amplifias[pair->refsequence].end;
			 i++,
			 c+=(strand)? 1:-1)
			printf("%c","acgt"[(strand)? (*c):(~*c)&3]);


293
	}
294 295
	else
		printf("\t\t");
296 297

	printf("\n");
298 299 300

}

Eric Coissac committed
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319
static int cmpprintedpairs(const void* p1,const void* p2)
{
	float s1,s2;
	ppair_t pair1,pair2;

	pair1=*((ppair_t*)p1);
	pair2=*((ppair_t*)p2);

	s1 = pair1->yule * pair1->bs;
	s2 = pair2->yule * pair2->bs;

//	fprintf(stderr,"s1 : %4.3f  %4.3f   %4.3f\n",pair1->yule , pair1->bs,s1);
//	fprintf(stderr,"s2 : %4.3f  %4.3f   %4.3f\n\n",pair2->yule , pair2->bs,s2);

	if (s1 > s2) return -1;
	if (s1 < s2) return 1;
	return 0;
}

320
uint32_t filterandsortpairs(ppair_t* sortedpairs,uint32_t count, poptions_t options, pecodnadb_t seqdb)
321 322 323 324 325 326 327 328 329 330 331 332 333 334
{
	uint32_t i,j;
	float q,qfp;

	for (i=0,j=0;i < count;i++)
	{
		if (options->insamples)
			q = (float)sortedpairs[i]->inexample/options->insamples;
		else q=1.0;

		if (options->outsamples)
			qfp = (float)sortedpairs[i]->outexample/options->outsamples;
		else qfp=0.0;

335
		sortedpairs[i]->wellIdentifiedSeqs = NULL; //TR 05/09/10 - wellIdentified needed for primer sets
336 337
		sortedpairs[i]->quorumin = q;
		sortedpairs[i]->quorumout = qfp;
Eric Coissac committed
338
		sortedpairs[i]->yule = q - qfp;
339 340 341 342 343
		sortedpairs[j]=sortedpairs[i];

		if (q > options->sensitivity_quorum &&
			qfp < options->false_positive_quorum)
		{
344 345
			//TR 05/09/10 - wellIdentified needed for primer sets
			sortedpairs[j]->wellIdentifiedSeqs = ECOMALLOC(options->dbsize * sizeof(int),"Cannot allocate well_identified_array");
346
			(void)taxonomycoverage(sortedpairs[j],options);
347
			taxonomyspecificity(sortedpairs[j], seqdb, options->dbsize);
348 349
			j++;
		}
Eric Coissac committed
350

351
	}
Eric Coissac committed
352
	qsort(sortedpairs,j,sizeof(ppair_t),cmpprintedpairs);
353 354 355
	return j;
}

Eric Coissac committed
356

357
void printpairs (ppairtree_t pairs, poptions_t options,ecotaxonomy_t *taxonomy, pecodnadb_t seqdb)
358 359 360 361 362
{
   ppair_t* sortedpairs;
   ppair_t* index;
   ppairlist_t pl;
   size_t i,j;
Eric Coissac committed
363
   size_t count;
Eric Coissac committed
364 365
   char *taxon[]={"taxon","taxa"};
   ecotx_t    *current_taxon;
366
   pairset pair_sets;
Eric Coissac committed
367 368

   //printf("Index\tPrimer1\tPrimer2\tGB\tInexampleCount\tOutexampleCount\tYule\tIntaxaCount\tOuttaxaCount\tCoverage\tSpecificity\tMinAmplifiedLength\tMaxAmplifiedLength\tAvgAmplifiedLength\n");
369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385

   fprintf(stderr,"Total pair count : %d\n",pairs->count);

   sortedpairs = ECOMALLOC(pairs->count*sizeof(ppair_t),"Cannot Allocate ordered pairs");
   index=sortedpairs;
   pl=pairs->first;
   j=0;
   while(pl->next)
   {
	   for (i=0;i<pl->paircount;i++,j++)
		   sortedpairs[j]=pl->pairs+i;
	   pl=pl->next;
   }

   for (i=0;i<pl->paircount;i++,j++)
	   sortedpairs[j]=pl->pairs+i;

386
   count=filterandsortpairs(sortedpairs,pairs->count,options, seqdb);
387
   getThermoProperties(sortedpairs, count, options);
388

Eric Coissac committed
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
   fprintf(stderr,"Total good pair count : %u\n",(uint32_t)count);

	printf("#\n");
	printf("# ecoPrimer version %s\n",VERSION);
	printf("# Rank level optimisation : %s\n", options->taxonrank);
	printf("# max error count by oligonucleotide : %d\n",options->error_max);
	printf("#\n");

	if (options->r)
	{
		printf("# Restricted to %s:\n",taxon[(options->r>1) ? 1:0]);
		for(i=0;i<(uint32_t)options->r;i++)
		{
			current_taxon=eco_findtaxonbytaxid(taxonomy,options->restricted_taxid[i]);
			printf("#     %d : %s (%s)\n", current_taxon->taxid,
										   current_taxon->name,
										   taxonomy->ranks->label[current_taxon->rank]
										 );
		}
		printf("#\n");
	}
	if (options->g)
	{
		printf("# Ignore  %s:\n",taxon[(options->g>1) ? 1:0]);
		for(i=0;i<(uint32_t)options->r;i++)
		{
			current_taxon=eco_findtaxonbytaxid(taxonomy,options->ignored_taxid[i]);
			printf("#     %d : %s (%s)\n", current_taxon->taxid,
										   current_taxon->name,
										   taxonomy->ranks->label[current_taxon->rank]
										 );
		}
		printf("#\n");
	}
	printf("# strict primer quorum  : %3.2f\n",options->strict_quorum);
	printf("# example quorum        : %3.2f\n",options->sensitivity_quorum);
	if (options->g + options->r)
		printf("# counterexample quorum : %3.2f\n",options->false_positive_quorum);

	printf("#\n");
	printf("# database : %s\n",options->prefix);
    printf("# Database is constituted of %5d examples        corresponding to %5d %s\n",options->insamples,
    		options->intaxa,options->taxonrank);
    printf("#                        and %5d counterexamples corresponding to %5d %s\n",options->outsamples,
    		options->outtaxa,options->taxonrank);
	printf("#\n");

	if (options->lmin && options->lmax)
		printf("# amplifiat length between [%d,%d] bp\n",options->lmin,options->lmax);
	else if (options->lmin)
		printf("# amplifiat length larger than %d bp\n",options->lmin);
	else if (options->lmax)
		printf("# amplifiat length smaller than %d bp\n",options->lmax);
	if (options->circular)
		printf("# DB sequences are considered as circular\n");
	else
		printf("# DB sequences are considered as linear\n");
	printf("#\n");

448 449
   for (i=0;i < count;i++)
	   printapair(i,sortedpairs[i],options);
450 451 452 453 454 455
   
   if (options->print_sets_of_primers == TRUE)
   {
	   pair_sets = build_primers_set (sortedpairs, count, seqdb, options);
	   some_other_set_possibilities (&pair_sets, sortedpairs, count, seqdb, options);
   }
456 457 458
}


459 460
/*updateseqparams: This function counts the insample and outsample sequences
 *  and with each sequences adds a tag of the taxon to which the sequence beongs*/
461 462

void updateseqparams (pecodnadb_t seqdb, uint32_t seqdbsize, ecotaxonomy_t *taxonomy,
463 464 465 466 467 468 469
		poptions_t options, int32_t *insamples, int32_t *outsamples)
{
	uint32_t i;
	int32_t taxid;
	ecotx_t  *tmptaxon;

    for (i=0;i<seqdbsize;i++)
470
    {
471
    	seqdb[i]->isexample=isExampleTaxon(taxonomy,seqdb[i]->taxid,options);
472 473 474 475 476 477
    	if (seqdb[i]->isexample)
    		(*insamples)++;
    	else
    		(*outsamples)++;

    	taxid = taxonomy->taxons->taxon[seqdb[i]->taxid].taxid;
478
		tmptaxon = eco_findtaxonbytaxid(taxonomy, taxid);
479 480 481 482 483 484 485 486 487 488 489 490 491 492
		if (tmptaxon)
			tmptaxon = eco_findtaxonatrank(tmptaxon, options->taxonrankidx);
		if (tmptaxon)
			seqdb[i]->ranktaxonid = tmptaxon->taxid;
    }
}

void setresulttaxonrank (ecotaxonomy_t *taxonomy, poptions_t options)
{
	int32_t i;

    /*set taxon rank for which result is to be given*/
    for (i = 0; i < taxonomy->ranks->count; i++)
    {
493
    	if (strcmp(taxonomy->ranks->label[i], options->taxonrank) == 0)
494 495 496 497 498 499 500 501 502 503 504 505 506 507
    	{
    		options->taxonrankidx = i;
    		break;
    	}
    }

    if (i == taxonomy->ranks->count)
    {
    	fprintf(stderr,"\nUnknown taxon level: '%s'\n", options->taxonrank);
    	exit(0);
    }
}
/* to get db stats, totals of species, genus etc....*/

508 509 510 511 512
static void printAC(pecodnadb_t seqdb,uint32_t seqdbsize)
{
	uint32_t i;

	for (i=0; i< seqdbsize;i++)
513
		printf("%15s (%8d bp ): %s\n",seqdb[i]->AC,seqdb[i]->SQ_length,seqdb[i]->DE);
514
}
515

516 517 518 519 520 521 522 523 524 525 526 527 528
int main(int argc, char **argv)
{
	pecodnadb_t   seqdb; /* of type ecoseq_t */
	uint32_t        seqdbsize=0;
	ecotaxonomy_t *taxonomy;

	options_t     options;
	int           carg;
	int32_t       errflag=0;

	int32_t       insamples=0;
	int32_t       outsamples=0;
	uint32_t        i;
529 530

	pwordcount_t    words;
531
//	pwordcount_t    words2;
532 533 534
	pprimercount_t  primers;
	ppairtree_t		pairs;

535 536
	int32_t		  rankdbstats = 0;

537
	CNNParams nnparams;
538

539 540
	initoptions(&options);

541
    while ((carg = getopt(argc, argv, "hAfvcUDSpE:d:l:L:e:i:r:R:q:3:s:x:t:O:m:a:")) != -1) {
542 543

     switch (carg) {
544 545 546 547 548 549
								 /* ---------------------------- */
		 case 'v':               /* set in single strand mode    */
								 /* ---------------------------- */
			options.statistics=TRUE;
			break;

550 551 552 553
			 /* ---------------------------- */
		 case 'f':               /* set in single strand mode    */
			 /* ---------------------------- */
			 options.filtering=FALSE;
554 555 556 557 558 559
			 break;

			 /* ---------------------------- */
		 case 'A':               /* set in single strand mode    */
			 /* ---------------------------- */
			 options.printAC=TRUE;
560 561
			 break;

562 563 564 565 566 567 568 569 570 571 572
                                /* -------------------- */
        case 'd':               /* database name        */
                                /* -------------------- */
        	options.prefix = ECOMALLOC(strlen(optarg)+1,
                              "Error on prefix allocation");
           strcpy(options.prefix,optarg);
           break;

                                /* -------------------- */
        case 'h':               /* help                 */
                                /* -------------------- */
573 574 575
        	PrintHelp();
        	 exit(0);
        	 break;
576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594

                                /* ------------------------- */
        case 'l':               /* min amplification lenght  */
                                /* ------------------------- */
           sscanf(optarg,"%d",&(options.lmin));
           break;

                                /* -------------------------- */
        case 'L':               /* max amplification lenght   */
                                /* -------------------------- */
          sscanf(optarg,"%d",&(options.lmax));
          break;

                                /* -------------------- */
        case 'e':               /* error max            */
                                /* -------------------- */
          sscanf(optarg,"%d",&(options.error_max));
          break;

595 596 597 598 599 600

								/* ------------------------ */
		case '3':               /* three prime strict match */
                                /* ------------------------ */
			sscanf(optarg,"%d",&(options.strict_three_prime));
			break;
601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619

                                /* -------------------- */
        case 'q':               /* strict matching quorum           */
                                /* -------------------- */
          sscanf(optarg,"%f",&(options.strict_quorum));
          break;

								/* -------------------- */
        case 's':               /* strict matching quorum      */
								/* -------------------- */
        	sscanf(optarg,"%f",&(options.sensitivity_quorum));
        	break;

        						/* -------------------- */
        case 't':               /* required taxon level for results           */
        						/* -------------------- */
        	strncpy(options.taxonrank, optarg, 19);
        	options.taxonrank[19] = 0;
            break;
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
        						/* -------------------- */
        case 'x':               /* strict matching quorum           */
								/* -------------------- */
        	sscanf(optarg,"%f",&(options.false_positive_quorum));
        	break;

							    /* ---------------------------- */
		case 'D':               /* set in double strand mode    */
							    /* ---------------------------- */
			options.doublestrand=1;
			break;

								/* ---------------------------- */
		case 'S':               /* set in single strand mode    */
								/* ---------------------------- */
			options.doublestrand=0;
			break;

			                    /* ---------------------------- */
        case 'U':               /* set in single strand mode    */
			                    /* ---------------------------- */
            options.no_multi_match=TRUE;
            break;

         						/* ------------------------------------------ */
        case 'r':               /* stores the restricting search taxonomic id */
        						/* ------------------------------------------ */
          options.restricted_taxid = ECOREALLOC(options.restricted_taxid,sizeof(int32_t)*(options.r+1),
          									"Error on restricted_taxid reallocation");
          sscanf(optarg,"%d",&(options.restricted_taxid[options.r]));
          options.r++;
652 653
          break;

654 655 656 657 658 659 660 661 662
								/* ------------------------------------------ */
        case 'E':               /* stores the restricting search taxonomic id */
								/* ------------------------------------------ */
        	options.exception_taxid = ECOREALLOC(options.exception_taxid,sizeof(int32_t)*(options.e+1),
						            "Error on exception_taxid reallocation");
			sscanf(optarg,"%d",&(options.exception_taxid[options.e]));
			options.e++;
			break;

663 664 665 666 667 668
								/* -------------------- */
        case 'R':               /* reference sequence   */
                                /* -------------------- */
          options.reference = ECOMALLOC(strlen(optarg)+1,
                                     "Error on prefix allocation");
          strcpy(options.reference,optarg);
669 670 671 672 673 674 675 676 677 678 679
          break;

         						/* --------------------------------- */
        case 'i':               /* stores the taxonomic id to ignore */
        						/* --------------------------------- */
          options.ignored_taxid = ECOREALLOC(options.ignored_taxid,sizeof(int32_t)*(options.g+1),
          									"Error on excluded_taxid reallocation");
          sscanf(optarg,"%d",&(options.ignored_taxid[options.g]));
          options.g++;
          break;

Eric Coissac committed
680 681 682 683 684 685
			                    /* --------------------------------- */
        case 'O':               /* set primer size                   */
        						/* --------------------------------- */
			sscanf(optarg,"%d",&(options.primer_length));
			break;

686 687 688 689 690 691 692 693 694 695 696 697 698
								/* --------------------------------- */
        case 'm':               /* set salt method                   */
								/* --------------------------------- */
        	sscanf(optarg,"%d",&(options.saltmethod));
        	break;

        						/* --------------------------------- */
        case 'a':               /* set salt 	                     */
								/* --------------------------------- */
        	sscanf(optarg,"%f",&(options.salt));
        	break;

        						/* -------------------- */
699 700 701 702 703
        case 'c':               /* sequences are circular */
        						/* --------------------------------- */
		  options.circular = 1;
          break;

704 705 706 707 708 709
								/* -------------------- */
        case 'p':               /* print sets of primers */
								/* --------------------------------- */
        	options.print_sets_of_primers = TRUE;
        break;

710 711 712 713 714 715
        case '?':               /* bad option           */
                                /* -------------------- */
            errflag++;
   		}

	}
716
    options.pnparm = &nnparams;
717 718
    if (options.saltmethod != 2) //if not SALT_METHOD_OWCZARZY
    	options.saltmethod = SALT_METHOD_SANTALUCIA; //then force SALT_METHOD_SANTALUCIA
719 720


721 722
    if (options.salt < 0.01 || options.salt > 0.3) //if salt value out of literature values
    	options.salt = DEF_SALT; //set to default
723

724 725
	nparam_InitParams(&nnparams, DEF_CONC_PRIMERS,DEF_CONC_SEQUENCES,options.salt,options.saltmethod);

726 727 728
    fprintf(stderr,"Reading taxonomy database ...");
    taxonomy = read_taxonomy(options.prefix,0);
    fprintf(stderr,"Ok\n");
729

730
    setresulttaxonrank(taxonomy, &options); /*TR: set rank level for statistics*/
731

732 733
    fprintf(stderr,"Reading sequence database ...\n");

734
    seqdb = readdnadb(options.prefix,taxonomy,&seqdbsize, &options);
735

736 737 738 739 740
	if (options.printAC)
	{
		printAC(seqdb,seqdbsize);
		exit(0);
	}
741 742 743 744 745 746 747 748 749
    if (options.reference)
    	for (i=0; i < seqdbsize;i++)
    		if (strcmp(seqdb[i]->AC,options.reference)==0)
    		{
    			options.refseq=seqdb[i];
    			options.refseqid=i;
    			fprintf(stderr,"Reference sequence %s identified\n",options.reference);
    		}

750 751
    fprintf(stderr,"Ok\n");
    fprintf(stderr,"Sequence read : %d\n",(int32_t)seqdbsize);
752

753
    updateseqparams(seqdb, seqdbsize, taxonomy, &options, &insamples , &outsamples);
754 755 756
    options.dbsize=seqdbsize;
    options.insamples=insamples;
    options.outsamples=outsamples;
757 758 759

    rankdbstats = getrankdbstats(seqdb, seqdbsize, taxonomy, &options);

760 761 762 763
    fprintf(stderr,"Database is constituted of %5d examples        corresponding to %5d %s\n",insamples,
    		options.intaxa,options.taxonrank);
    fprintf(stderr,"                       and %5d counterexamples corresponding to %5d %s\n",outsamples,
    		options.outtaxa,options.taxonrank);
764 765 766 767 768 769
    fprintf(stderr,"Total distinct %s count %d\n",options.taxonrank, rankdbstats);

    fprintf(stderr,"\nIndexing words in sequences\n");

    words = lookforStrictPrimer(seqdb,seqdbsize,insamples,&options);
    fprintf(stderr,"\n  Strict primer count : %d\n",words->size);
770

771 772 773 774 775 776 777 778 779 780 781
//    options.filtering=FALSE;
//    words2= lookforStrictPrimer(seqdb,seqdbsize,insamples,&options);
//    fprintf(stderr,"\n  Strict primer count : %d\n",words2->size);
//
//    fprintf(stderr,"\n\n  Primer sample : \n");
//    for (i=0; i<words->size; i++)
//    	fprintf(stderr,"  + Primer : %s   sequence count : %d\n",ecoUnhashWord(words->words[i],options.primer_length),words->strictcount[i]);
//    fprintf(stderr,"\n\n  Primer sample : \n");
//    for (i=0; i<words2->size; i++)
//    	fprintf(stderr,"  + Primer : %s   sequence count : %d\n",ecoUnhashWord(words2->words[i],options.primer_length),words2->strictcount[i]);

782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817
    if (options.no_multi_match)
    {
    	(void)filterMultiStrictPrimer(words);
    	fprintf(stderr,"\n  Strict primer with single match count : %d\n",words->size);
    }


    fprintf(stderr,"\n\n  Primer sample : \n");
    for (i=0; i<MINI(10,words->size); i++)
    	fprintf(stderr,"  + Primer : %s   sequence count : %d\n",ecoUnhashWord(words->words[i],options.primer_length),words->strictcount[i]);


    fprintf(stderr,"\nEncoding sequences for fuzzy pattern matching...\n");
    for (i=0;i<seqdbsize;i++)
    {
    	encodeSequence(seqdb[i]);
    	fprintf(stderr,"  Encoded sequences %5d/%5d          \r",(int32_t)i+1,(int32_t)seqdbsize);
    }

    ECOFREE(words->strictcount,"Free strict primer count table");

    primers = lookforAproxPrimer(seqdb,seqdbsize,insamples,words,&options);

    ECOFREE(words->words,"Free strict primer table");
    ECOFREE(words,"Free strict primer structure");
    fprintf(stderr,"\n\n  Approximate repeats :%d \n", primers->size);

    fprintf(stderr,"\n\n  Primer sample : \n");
    for (i=0; i<MINI(10,primers->size); i++)
    	fprintf(stderr,"  + Primer : %s   example sequence count : %5d counterexample sequence count : %5d  status : %s\n",ecoUnhashWord(primers->primers[i].word,options.primer_length),
                       primers->primers[i].inexample,
                       primers->primers[i].outexample,
                       primers->primers[i].good ? "good":"bad");

    fprintf(stderr,"\n");

818 819 820 821
   
    	pairs = buildPrimerPairs(seqdb, seqdbsize, primers, &options);
    	printpairs (pairs, &options,taxonomy, seqdb);
    
822 823
    return 0;
}