ecoprimer.c 25.6 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 "libthermo/libthermo.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
#define VERSION "0.3"
20
  /* TR: by default, statistics are made on species level*/
Eric Coissac committed
21 22 23
#define DEFAULTTAXONRANK "species"

static int cmpprintedpairs(const void* p1,const void* p2);
24
//float _Z27calculateMeltingTemperature_ (char * seq1, char * seq2);
Eric Coissac committed
25

26 27
void* lib_handle = NULL;
float (*calcMelTemp)(char*, char*);
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
void openlibman ()
{
    // Open the library.
    char* lib_name = "./libPHunterLib.dylib";
    lib_handle = dlopen(lib_name, RTLD_NOW);
    if (lib_handle) {
        fprintf(stderr, "[%s] dlopen(\"%s\", RTLD_NOW): Successful\n", __FILE__, lib_name);
    }
    else {
        fprintf(stderr, "[%s] Unable to open library: %s\n",
            __FILE__, dlerror());
        exit(EXIT_FAILURE);
    }
 
    // Get the symbol addresses.
    calcMelTemp = dlsym(lib_handle, "_Z27calculateMeltingTemperaturePcS_");
    if (calcMelTemp) {
        fprintf(stderr, "[%s] dlsym(lib_handle, \"addRating\"): Successful\n", __FILE__);
    }
    else {
        fprintf(stderr, "[%s] Unable to get symbol: %s\n",
            __FILE__, dlerror());
        exit(EXIT_FAILURE);
    }
}

void closlibman ()
{
	if (lib_handle) dlclose(lib_handle);
}
59 60 61 62 63 64 65
/* ----------------------------------------------- */
/* printout help                                   */
/* ----------------------------------------------- */
#define PP fprintf(stdout,

static void PrintHelp()
{
66 67 68 69 70 71 72 73 74 75 76 77 78 79 80
			  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
81
              PP      "        database radical without any extension. For example /ecoPrimerDB/fstvert\n\n");
82 83 84 85 86 87 88
              PP      "-e    : [E]rror : max error allowed by oligonucleotide (0 by default)\n\n");
              PP      "-h    : [H]elp - print <this> help\n\n");
              PP      "-i    : [I]gnore the given taxonomy id.\n\n");
              PP      "-l    : minimum [L]ength : define the minimum amplication length. \n\n");
              PP      "-L    : maximum [L]ength : define the maximum amplicationlength. \n\n");
              PP      "-r    : [R]estricts the search to the given taxonomic id.\n\n");
              PP      "-c    : Consider that the database sequences are [c]ircular\n\n");
Eric Coissac committed
89
//              PP      "-3 	 : Three prime strict match\n\n");
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
              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");
              PP      "-S    : Set in [s]ingle strand mode\n\n");
              PP      "-U    : No multi match\n\n");
              PP      "\n");
              PP      "------------------------------------------\n");
              PP      "Table result description : \n");
              PP      "column 1 : serial number\n");
              PP      "column 2 : primer1\n");
              PP      "column 3 : primer2\n");
              PP      "column 4 : good/bad\n");
              PP      "column 5 : in sequence count\n");
              PP      "column 6 : out sequence count\n");
              PP      "column 7 : yule\n");
              PP      "column 8 : in taxa count\n");
              PP      "column 9 : out taxa count\n");
              PP      "column 10 : coverage\n");
Eric Coissac committed
110 111 112 113 114
              PP      "column 11 : unambiguously identified taxa\n");
              PP      "column 12 : specificity\n");
              PP      "column 13 : minimum amplified length\n");
              PP      "column 14 : maximum amplified length\n");
              PP      "column 15 : average amplified length\n");
115 116
              PP      "------------------------------------------\n");
              PP		" http://www.grenoble.prabi.fr/trac/ecoPrimer/\n");
Eric Coissac committed
117
              PP      "------------------------------------------\n\n");
118 119
              PP      "\n");

120 121 122 123 124 125 126 127 128 129 130 131 132 133 134
}

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)
{
135
	options->statistics=FALSE;
136
	options->filtering=TRUE;
137
	options->lmin=0;                   //< Amplifia minimal length
138
	options->lmax=1000;                   //< Amplifia maximal length
139 140 141 142 143
	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
	options->prefix=NULL;
144 145
	options->reference=NULL;
	options->refseq=NULL;
146 147 148 149 150 151
	options->circular=0;
	options->doublestrand=1;
	options->strict_quorum=0.7;
	options->strict_exclude_quorum=0.1;
	options->sensitivity_quorum=0.9;
	options->false_positive_quorum=0.1;
152
	options->strict_three_prime=0;
153 154 155
	options->r=0;
	options->g=0;
	options->no_multi_match=FALSE;
Eric Coissac committed
156
	strcpy(options->taxonrank, DEFAULTTAXONRANK);			/*taxon level for results, species by default*/
157 158 159 160 161 162 163 164 165 166 167 168 169 170
}

void printcurrenttime ()
{
    time_t     now;
    struct tm  *ts;
    char       buf[80];

    /* Get the current time */
    now = time(NULL);

    /* Format and print the time, "ddd yyyy-mm-dd hh:mm:ss zzz" */
    ts = localtime(&now);
    strftime(buf, sizeof(buf), "%a %Y-%m-%d %H:%M:%S %Z", ts);
171
    fprintf(stderr,"#%d#, %s\n",(int)now, buf);
172 173 174 175 176 177 178 179 180 181 182 183 184 185
 }

void printcurrenttimeinmilli()
{
     struct timeval tv;
     struct timezone tz;
     struct tm *tm;
     gettimeofday(&tv, &tz);
     tm=localtime(&tv.tv_sec);
     fprintf(stderr, " %d:%02d:%02d %d %d \n", tm->tm_hour, tm->tm_min,
              tm->tm_sec, tv.tv_usec, tv.tv_usec/1000);
}

/*TR: Added*/
186 187 188

void printapair(int32_t index,ppair_t pair, poptions_t options)
{
Eric Coissac committed
189 190 191 192 193 194 195 196 197
	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;
198 199
	bool_t strand;
	uint32_t i;
200
	float temp;
201 202

	char *c;
203 204
	char p1[32];
	char p2[32];
Eric Coissac committed
205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226

	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
227

228 229
	printf("%6d\t",index);

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
	c = ecoUnhashWord(w1,options->primer_length);
	strcpy (p1, c);
	c = ecoUnhashWord(w2,options->primer_length);
	strcpy (p2, c);

	printf("%s\t", p1);
	printf("%s", p2);
	
	/*For thermo: first word should be 5'-3'*/
	/*if (!asdirect1)
	{
		wtmp = ecoComplementWord(w1,options->primer_length);
		c = ecoUnhashWord(wtmp,options->primer_length);
		strcpy (p1, c);
	}*/
	/*For thermo: first word should be 5'-3'*/
	/*if (asdirect2)
	{
		wtmp = ecoComplementWord(w2,options->primer_length);
		c = ecoUnhashWord(wtmp,options->primer_length);
		strcpy (p2, c);
	}*/

	/*temp = calculateMeltingTemperature (p1, p2);*/
	//float temp = calculateMeltingTemperature ("CTGTTTACCAAAAACATC", "GGTCTGAACTCAGATCAC");

	temp = calculateMeltingTemperatureBasic(p1);
	printf ("\t%4.3f", temp);
	
	temp = calculateMeltingTemperatureBasic(p2);
	printf ("\t%4.3f", temp);
	
	printf ("\t%d",countGCContent(p1));
	
	printf ("\t%d",countGCContent(p2));
265

Eric Coissac committed
266
	printf("\t%c%c", "bG"[(int)good1],"bG"[(int)good2]);
267 268 269 270 271 272 273 274


	printf("\t%d", pair->inexample);
	printf("\t%d", pair->outexample);
	printf("\t%4.3f", pair->yule);

	printf("\t%d", pair->intaxa);
	printf("\t%d", pair->outtaxa);
Eric Coissac committed
275
	printf("\t%4.3f", (float)pair->bc);
276

Eric Coissac committed
277
	printf("\t%d", pair->intaxa - pair->notwellidentifiedtaxa);
278

Eric Coissac committed
279
	printf("\t%4.3f", pair->bs);
280 281 282 283


	printf("\t%d", pair->mind);
	printf("\t%d", pair->maxd);
284 285 286 287 288
	printf("\t%3.2f", (float)pair->sumd/pair->inexample);

	if (options->refseq && pair->refsequence >=0)
	{
		printf("\t%s:",options->reference);
289
		strand = pair->pcr.amplifias[pair->refsequence].strand;
290

291
		if (strand)
292 293 294 295 296 297 298 299 300 301 302 303
			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");

304 305 306 307 308 309 310 311
		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]);


312
	}
313 314
	else
		printf("\t\t");
315 316

	printf("\n");
317 318 319

}

Eric Coissac committed
320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338
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;
}

339 340 341 342 343 344 345 346 347 348 349 350 351 352 353
uint32_t filterandsortpairs(ppair_t* sortedpairs,uint32_t count, poptions_t options)
{
	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;

Eric Coissac committed
354

355 356
		sortedpairs[i]->quorumin = q;
		sortedpairs[i]->quorumout = qfp;
Eric Coissac committed
357
		sortedpairs[i]->yule = q - qfp;
358 359 360 361 362 363 364 365 366 367 368


		sortedpairs[j]=sortedpairs[i];



		if (q > options->sensitivity_quorum &&
			qfp < options->false_positive_quorum)
		{
			(void)taxonomycoverage(sortedpairs[j],options);
			taxonomyspecificity(sortedpairs[j]);
Eric Coissac committed
369 370
//			fprintf(stderr,"%4.3f  %4.3f   %4.3f\n",sortedpairs[j]->yule , sortedpairs[j]->bs,sortedpairs[j]->bc);

371 372
			j++;
		}
Eric Coissac committed
373

374 375
	}

Eric Coissac committed
376 377 378

	qsort(sortedpairs,j,sizeof(ppair_t),cmpprintedpairs);

379 380 381
	return j;
}

Eric Coissac committed
382

Eric Coissac committed
383
void printpairs (ppairtree_t pairs, poptions_t options,ecotaxonomy_t *taxonomy)
384 385 386 387 388
{
   ppair_t* sortedpairs;
   ppair_t* index;
   ppairlist_t pl;
   size_t i,j;
Eric Coissac committed
389
   size_t count;
Eric Coissac committed
390 391 392
   char *taxon[]={"taxon","taxa"};
   ecotx_t    *current_taxon;

Eric Coissac committed
393 394

   //printf("Index\tPrimer1\tPrimer2\tGB\tInexampleCount\tOutexampleCount\tYule\tIntaxaCount\tOuttaxaCount\tCoverage\tSpecificity\tMinAmplifiedLength\tMaxAmplifiedLength\tAvgAmplifiedLength\n");
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413

   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;

   count=filterandsortpairs(sortedpairs,pairs->count,options);

Eric Coissac committed
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
   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");

473 474
   for (i=0;i < count;i++)
	   printapair(i,sortedpairs[i],options);
475
   
476 477 478 479 480

}



481 482
/*updateseqparams: This function counts the insample and outsample sequences
 *  and with each sequences adds a tag of the taxon to which the sequence beongs*/
483 484

void updateseqparams (pecodnadb_t seqdb, uint32_t seqdbsize, ecotaxonomy_t *taxonomy,
485 486 487 488 489 490 491
		poptions_t options, int32_t *insamples, int32_t *outsamples)
{
	uint32_t i;
	int32_t taxid;
	ecotx_t  *tmptaxon;

    for (i=0;i<seqdbsize;i++)
492
    {
493 494 495 496 497 498 499
    	seqdb[i]->isexample=isGoodTaxon(taxonomy,seqdb[i]->taxid,options);
    	if (seqdb[i]->isexample)
    		(*insamples)++;
    	else
    		(*outsamples)++;

    	taxid = taxonomy->taxons->taxon[seqdb[i]->taxid].taxid;
500
		tmptaxon = eco_findtaxonbytaxid(taxonomy, taxid);
501 502 503 504 505 506 507 508 509 510 511 512 513 514
		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++)
    {
515
    	if (strcmp(taxonomy->ranks->label[i], options->taxonrank) == 0)
516 517 518 519 520 521 522 523 524 525 526 527 528 529
    	{
    		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....*/

530

531 532 533 534 535 536 537 538 539 540 541 542 543
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;
544 545

	pwordcount_t    words;
546
//	pwordcount_t    words2;
547 548 549
	pprimercount_t  primers;
	ppairtree_t		pairs;

550 551 552 553
	int32_t		  rankdbstats = 0;

	//printcurrenttime();
	//return 0;
554 555 556 557 558 559
	//openlibman ();
	//float temp = calculateMeltingTemperature ("GGTCTGAACTCAGATCAC", "CTGTTTACCAAAAACATC");
	//float temp = calculateMeltingTemperatureBasic ("CTGTTTACCAAAAACATC");
	//printf ("temp = %f\n", temp);
	//return 0;
	
560 561
	initoptions(&options);

562
    while ((carg = getopt(argc, argv, "hfvcUDSd:l:L:e:i:r:R:q:3:s:x:t:O:")) != -1) {
563 564

     switch (carg) {
565 566 567 568 569 570
								 /* ---------------------------- */
		 case 'v':               /* set in single strand mode    */
								 /* ---------------------------- */
			options.statistics=TRUE;
			break;

571 572 573 574 575 576
			 /* ---------------------------- */
		 case 'f':               /* set in single strand mode    */
			 /* ---------------------------- */
			 options.filtering=FALSE;
			 break;

577 578 579 580 581 582 583 584 585 586 587
                                /* -------------------- */
        case 'd':               /* database name        */
                                /* -------------------- */
        	options.prefix = ECOMALLOC(strlen(optarg)+1,
                              "Error on prefix allocation");
           strcpy(options.prefix,optarg);
           break;

                                /* -------------------- */
        case 'h':               /* help                 */
                                /* -------------------- */
588 589 590
        	PrintHelp();
        	 exit(0);
        	 break;
591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609

                                /* ------------------------- */
        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;

Eric Coissac committed
610 611 612 613 614 615
//
//								/* ------------------------ */
//		case '3':               /* three prime strict match */
//                                /* ------------------------ */
//			sscanf(optarg,"%d",&(options.strict_three_prime));
//			break;
616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634

                                /* -------------------- */
        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;
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
        						/* -------------------- */
        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++;
667 668 669 670 671 672 673 674
          break;

								/* -------------------- */
        case 'R':               /* reference sequence   */
                                /* -------------------- */
          options.reference = ECOMALLOC(strlen(optarg)+1,
                                     "Error on prefix allocation");
          strcpy(options.reference,optarg);
675 676 677 678 679 680 681 682 683 684 685
          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
686 687 688 689 690 691
			                    /* --------------------------------- */
        case 'O':               /* set primer size                   */
        						/* --------------------------------- */
			sscanf(optarg,"%d",&(options.primer_length));
			break;

692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
                                /* -------------------- */
        case 'c':               /* sequences are circular */
        						/* --------------------------------- */
		  options.circular = 1;
          break;

        case '?':               /* bad option           */
                                /* -------------------- */
            errflag++;
   		}

	}

    fprintf(stderr,"Reading taxonomy database ...");
    taxonomy = read_taxonomy(options.prefix,0);
    fprintf(stderr,"Ok\n");
708

709
    setresulttaxonrank(taxonomy, &options); /*TR: set rank level for statistics*/
710

711 712 713 714
    fprintf(stderr,"Reading sequence database ...\n");

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

715 716 717 718 719 720 721 722 723
    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);
    		}

724 725
    fprintf(stderr,"Ok\n");
    fprintf(stderr,"Sequence read : %d\n",(int32_t)seqdbsize);
726

727
    updateseqparams(seqdb, seqdbsize, taxonomy, &options, &insamples , &outsamples);
728 729 730
    options.dbsize=seqdbsize;
    options.insamples=insamples;
    options.outsamples=outsamples;
731 732 733

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

734 735 736 737
    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);
738 739 740 741 742 743 744
    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);

745 746 747 748 749 750 751 752 753 754 755
//    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]);

756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793
    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");

    /*TR: Added*/
    pairs = buildPrimerPairs(seqdb, seqdbsize, primers, &options);
Eric Coissac committed
794

795
	//fprintf(stderr,"buildPrimerPairs finished\n");
796 797
  //  setoktaxforspecificity (&pairs);

Eric Coissac committed
798
     printpairs (pairs, &options,taxonomy);
799
    // closlibman ();
800 801 802


    //ECOFREE(pairs.pairs,"Free pairs table");
803 804 805

    return 0;
}