int main(int argc,char ** argv)
{
SequenceDB * db;
Sequence * seq;
SeqLookupInterface * sli;
SeqLookupPos * slp;
HSPScanInterface * hsi;
LinearHSPmanager * lm;
HitList * hl;
CompMat * mat;
int ret;
HSPScanInterfacePara p;
p.min_score= 30;
p.max_results = 200;
db = single_fasta_SequenceDB(argv[1]);
mat = read_Blast_file_CompMat("blosum62.bla");
sli = new_ghash_SeqLookupInterface();
for(seq = init_SequenceDB(db,&ret); seq != NULL;seq = get_next_SequenceDB(db) ) {
load_aa_flat_Sequence_SeqLookupInterface(sli,hard_link_Sequence(seq));
}
seq = read_fasta_file_Sequence(argv[2]);
assert(seq);
hsi = Wise2_new_one_off_HSPScanInterface(sli,mat,20,10);
/* hspm = simple_HSPScan_scan_query((void*)hsi->data,seq); */
lm = (*hsi->scan_query)(hsi->data,seq,&p);
hl = Wise2_HitList_from_LinearHSPmanager(lm);
Wise2_write_pseudoblast_HitList(hl,stdout);
}
boolean build_objects(void)
{
boolean ret = TRUE;
Protein * pro_temp;
Genomic * gen_temp;
FILE * ifp;
startend = threestatemodel_mode_from_string(startend_string);
if( startend == TSM_unknown ) {
warn("String %s was unable to converted into a start/end policy\n",startend_string);
ret = FALSE;
}
if( tstart_str != NULL ) {
if( is_integer_string(tstart_str,&tstart) == FALSE || tstart < 0) {
warn("Could not make %s out as target start",tstart);
ret = FALSE;
}
}
if( tend_str != NULL ) {
if( is_integer_string(tend_str,&tend) == FALSE || tend < 0) {
warn("Could not make %s out as target end",tend);
ret = FALSE;
}
}
if( is_integer_string(gap_str,&gap) == FALSE ) {
warn("Could not make %s out as gap penalty (must be integer at the moment)",gap_str);
ret = FALSE;
}
if( is_integer_string(ext_str,&ext) == FALSE ) {
warn("Could not make %s out as gap penalty (must be integer at the moment)",ext_str);
ret = FALSE;
}
if( is_embl == FALSE ) {
if( (gen = read_fasta_file_Genomic(dna_seq_file,length_of_N)) == NULL ) {
ret = FALSE;
warn("Could not read genomic sequence in %s",dna_seq_file);
gen = NULL;
}
} else {
embl = read_EMBL_GenomicRegion_file(dna_seq_file);
if( embl == NULL ) {
warn("Could not read genomic EMBL file in %s",dna_seq_file);
gen = NULL;
ret = FALSE;
} else {
gen = hard_link_Genomic(embl->genomic);
}
}
if( gen != NULL ) {
if( tstart != -1 || tend != -1 ) {
if( tstart == -1 )
tstart = 0;
if( tend == -1 )
tend = gen->baseseq->len;
gen_temp = truncate_Genomic(gen,tstart-1,tend);
if( gen_temp == NULL ){
ret = FALSE;
} else {
free_Genomic(gen);
gen = gen_temp;
}
} else {
/* no truncation required */
}
if( reverse == TRUE ) {
if( tstart > tend ) {
warn("You have already reversed the DNA by using %d - %d truncation. Re-reversing",tstart,tend);
}
gen_temp = reverse_complement_Genomic(gen);
free_Genomic(gen);
gen = gen_temp;
}
}
/*
* Can't truncate on GenomicRegion (for good reasons!).
* but we want only a section of the EMBL file to be used
*
* So... swap genomic now. Positions in EMBL are still valid,
* however - some genes will loose their sequence, which will be damaging. ;)
*/
if( is_embl ) {
free_Genomic(embl->genomic);
embl->genomic = hard_link_Genomic(gen); /* pointer could be dead anyway ;) */
}
if( target_abs == TRUE ) {
if( is_embl == TRUE ) {
warn("Sorry you can't both use absolute positioning and EMBL files as I can't cope with all the coordinate remapping. You'll have to convert to fasta.");
ret = FALSE;
}
gen->baseseq->offset = 1;
gen->baseseq->end = strlen(gen->baseseq->seq);
}
if( alg_str != NULL ) {
alg = gwrap_alg_type_from_string(alg_str);
} else {
if( use_tsm == TRUE ) {
alg_str = "623L";
} else {
alg_str = "623";
}
alg = gwrap_alg_type_from_string(alg_str);
}
if( qstart_str != NULL ) {
if( is_integer_string(qstart_str,&qstart) == FALSE || qstart < 0) {
warn("Could not make %s out as query start",qstart);
ret = FALSE;
}
}
if( qend_str != NULL ) {
if( is_integer_string(qend_str,&qend) == FALSE || qend < 0) {
warn("Could not make %s out as query end",qend);
ret = FALSE;
}
}
if( use_tsm == FALSE ) {
if( startend != TSM_default && startend != TSM_global && startend != TSM_local && startend != TSM_endbiased) {
warn("Proteins can only have local/global/endbias startend policies set, not %s",startend_string);
ret = FALSE;
}
if( (pro = read_fasta_file_Protein(protein_file)) == NULL ) {
ret = FALSE;
warn("Could not read Protein sequence in %s",protein_file);
} else {
if( qstart != -1 || qend != -1 ) {
if( qstart == -1 )
qstart = 0;
if( qend == -1 )
qend = pro->baseseq->len;
pro_temp = truncate_Protein(pro,qstart-1,qend);
if( pro_temp == NULL ){
ret = FALSE;
} else {
free_Protein(pro);
pro = pro_temp;
}
}
}
} else {
/** using a HMM **/
/*tsm = read_HMMer_1_7_ascii_file(hmm_file);*/
/*tsm = Wise2_read_ThreeStateModel_from_hmmer1_file(hmm_file);*/
tsm = HMMer2_read_ThreeStateModel(hmm_file);
if( tsm == NULL ) {
warn("Could not read hmm from %s\n",hmm_file);
ret = FALSE;
} else {
display_char_in_ThreeStateModel(tsm);
if( hmm_name != NULL ) {
if( tsm->name != NULL )
ckfree(tsm->name);
tsm->name = stringalloc(hmm_name);
}
if( tsm == NULL ) {
warn("Could not read %s as a hmm",hmm_file);
}
/** have to set start/end **/
set_startend_policy_ThreeStateModel(tsm,startend,30,0.1);
}
} /* end of else tsm != NULL */
if( main_block_str != NULL ) {
if( is_integer_string(main_block_str,&main_block) == FALSE ) {
warn("Could not get maximum main_block number %s",main_block_str);
ret = FALSE;
}
}
if( is_double_string(subs_string,&subs_error) == FALSE ) {
warn("Could not convert %s to a double",subs_error);
ret = FALSE;
}
if( is_double_string(indel_string,&indel_error) == FALSE ) {
warn("Could not convert %s to a double",indel_error);
ret = FALSE;
}
if( is_double_string(allN_string,&allN) == FALSE ) {
warn("Could not convert %s to a double",allN_string);
ret = FALSE;
}
if( strcmp(cfreq_string,"model") == 0 ) {
model_codon = TRUE;
} else if ( strcmp(cfreq_string,"flat") == 0 ) {
model_codon = FALSE;
} else {
warn("Cannot interpret [%s] as a codon modelling parameter\n",cfreq_string);
ret = FALSE;
}
if( strcmp(splice_string,"model") == 0 ) {
model_splice = TRUE;
} else if ( strcmp(splice_string,"flat") == 0 ) {
model_splice = FALSE;
gmp->use_gtag_splice = TRUE;
} else {
warn("Cannot interpret [%s] as a splice modelling parameter\n",splice_string);
ret = FALSE;
}
if( strcmp(null_string,"syn") == 0 ) {
use_syn = TRUE;
} else if ( strcmp(null_string,"flat") == 0 ) {
use_syn = FALSE;
} else {
warn("Cannot interpret [%s] as a null model string\n",null_string);
ret = FALSE;
}
if( strcmp(intron_string,"model") == 0 ) {
use_tied_model = FALSE;
} else if ( strcmp(intron_string,"tied") == 0 ) {
use_tied_model = TRUE;
} else {
warn("Cannot interpret [%s] as a intron tieing switch\n",intron_string);
ret = FALSE;
}
if( (rm = default_RandomModel()) == NULL) {
warn("Could not make default random model\n");
ret = FALSE;
}
if( use_new_stats == 0 ) {
if( (gf = read_GeneFrequency21_file(gene_file)) == NULL) {
ret = FALSE;
warn("Could not read a GeneFrequency file in %s",gene_file);
}
} else {
if( (gs = GeneStats_from_GeneModelParam(gmp)) == NULL ){
ret=FALSE;
warn("Could not read gene statistics in %s",new_gene_file);
}
} /* end of else using new gene stats */
if( (mat = read_Blast_file_CompMat(matrix_file)) == NULL) {
if( use_tsm == TRUE ) {
info("I could not read the Comparison matrix file in %s; however, you are using a HMM so it is not needed. Please set the WISECONFIGDIR or WISEPERSONALDIR variable correctly to prevent this message.",matrix_file);
} else {
warn("Could not read Comparison matrix file in %s",matrix_file);
ret = FALSE;
}
}
if( (ct = read_CodonTable_file(codon_file)) == NULL) {
ret = FALSE;
warn("Could not read codon table file in %s",codon_file);
}
if( (ofp = openfile(output_file,"W")) == NULL) {
warn("Could not open %s as an output file",output_file);
ret = FALSE;
}
rmd = RandomModelDNA_std();
return ret;
}
boolean build_objects(void)
{
boolean ret = TRUE;
Protein * pro_temp;
SequenceDB * psdb;
startend = threestatemodel_mode_from_string(startend_string);
if( startend == TSM_unknown ) {
warn("String %s was unable to converted into a start/end policy\n",startend_string);
ret = FALSE;
}
if( use_single_dna == TRUE ) {
cdna = read_fasta_file_cDNA(dna_seq_file);
if( cdna == NULL ) {
warn("Could not open single dna sequence in %s",dna_seq_file);
ret = FALSE;
}
} else {
sdb = single_fasta_SequenceDB(dna_seq_file);
if( sdb == NULL ) {
warn("Could not build a sequence database on %s",dna_seq_file);
ret = FALSE;
}
}
rm = default_RandomModel();
if( (mat = read_Blast_file_CompMat(matrix_file)) == NULL) {
if( use_tsm == TRUE ) {
info("I could not read the Comparison matrix file in %s; however, you are using a HMM so it is not needed. Please set the WISECONFIGDIR or WISEPERSONALDIR variable correctly to prevent this message.",matrix_file);
} else {
warn("Could not read Comparison matrix file in %s",matrix_file);
ret = FALSE;
}
}
if( is_integer_string(gap_str,&gap) == FALSE ) {
warn("Could not get gap string number %s",gap_str);
ret = FALSE;
}
if( is_integer_string(ext_str,&ext) == FALSE ) {
warn("Could not get ext string number %s",ext_str);
ret = FALSE;
}
if( qstart_str != NULL ) {
if( is_integer_string(qstart_str,&qstart) == FALSE || qstart < 0) {
warn("Could not make %s out as query start",qstart);
ret = FALSE;
}
}
if( qend_str != NULL ) {
if( is_integer_string(qend_str,&qend) == FALSE || qend < 0) {
warn("Could not make %s out as query end",qend);
ret = FALSE;
}
}
if( aln_number_str != NULL ) {
if( is_integer_string(aln_number_str,&aln_number) == FALSE || aln_number < 0) {
warn("Weird aln number string %s...\n",aln_number_str);
ret = FALSE;
}
}
if( report_str != NULL ) {
if( is_integer_string(report_str,&report_stagger) == FALSE ) {
warn("Weird report stagger asked for %s",report_str);
ret = FALSE;
}
}
if( use_pfam1 == TRUE ) {
tsmdb = new_PfamHmmer1DB_ThreeStateDB(protein_file);
if( set_search_type_ThreeStateDB(tsmdb,startend_string) == FALSE) {
warn("Unable to set global/local switch on threestatedb");
ret = FALSE;
}
} else if ( use_pfam2 == TRUE ) {
tsmdb = HMMer2_ThreeStateDB(protein_file);
if( set_search_type_ThreeStateDB(tsmdb,startend_string) == FALSE) {
warn("Unable to set global/local switch on threestatedb");
ret = FALSE;
}
} else if ( use_tsm == TRUE) {
/** using a HMM **/
tsm = HMMer2_read_ThreeStateModel(protein_file);
if( tsm == NULL ) {
warn("Could not read hmm from %s\n",protein_file);
ret = FALSE;
} else {
display_char_in_ThreeStateModel(tsm);
if( hmm_name != NULL ) {
if( tsm->name != NULL )
ckfree(tsm->name);
tsm->name = stringalloc(hmm_name);
} else {
if( tsm->name == NULL ) {
tsm->name = stringalloc(protein_file);
}
}
/** have to set start/end **/
set_startend_policy_ThreeStateModel(tsm,startend,15,0.2);
tsmdb = new_single_ThreeStateDB(tsm,rm);
if( tsmdb == NULL ) {
warn("Could not build a threestatemodel database from a single tsm. Weird!");
ret = FALSE;
}
} /* end of else tsm != NULL */
} /* end of else is tsm */
else if( use_single_pro ) {
if( startend != TSM_default && startend != TSM_global && startend != TSM_local ) {
warn("Proteins can only have local/global startend policies set, not %s",startend_string);
ret = FALSE;
}
if( (pro = read_fasta_file_Protein(protein_file)) == NULL ) {
ret = FALSE;
warn("Could not read Protein sequence in %s",protein_file);
} else {
if( qstart != -1 || qend != -1 ) {
if( qstart == -1 )
qstart = 0;
if( qend == -1 )
qend = pro->baseseq->len;
pro_temp = truncate_Protein(pro,qstart-1,qend);
if( pro_temp == NULL ){
ret = FALSE;
} else {
free_Protein(pro);
pro = pro_temp;
}
}
if( startend == TSM_global)
tsm = global_ThreeStateModel_from_half_bit_Sequence(pro,mat,rm,-gap,-ext);
else
tsm = ThreeStateModel_from_half_bit_Sequence(pro,mat,rm,-gap,-ext);
if( tsm == NULL ) {
warn("Could not build ThreeStateModel from a single protein sequence...");
ret = FALSE;
} else {
tsmdb = new_single_ThreeStateDB(tsm,rm);
if( tsmdb == NULL ) {
warn("Could not build a threestatemodel database from a single tsm. Weird!");
ret = FALSE;
}
} /* end of could build a TSM */
} /* else is a real protein */
} /* end of else is single protein */
else if (use_db_pro == TRUE ) {
psdb = single_fasta_SequenceDB(protein_file);
tsmdb = new_proteindb_ThreeStateDB(psdb,mat,-gap,-ext);
free_SequenceDB(psdb);
}
else {
warn("No protein input file! Yikes!");
}
/***
if( use_tsm == FALSE ) {
} else {
****/
if( main_block_str != NULL ) {
if( is_integer_string(main_block_str,&main_block) == FALSE ) {
warn("Could not get maximum main_block number %s",main_block_str);
ret = FALSE;
}
}
if( evalue_search_str != NULL && is_double_string(evalue_search_str,&evalue_search_cutoff) == FALSE ) {
warn("Could not convert %s to a double",evalue_search_str);
ret = FALSE;
}
if( is_double_string(search_cutoff_str,&search_cutoff) == FALSE ) {
warn("Could not convert %s to a double",search_cutoff_str);
ret = FALSE;
}
if( is_double_string(subs_string,&subs_error) == FALSE ) {
warn("Could not convert %s to a double",subs_error);
ret = FALSE;
}
if( is_double_string(indel_string,&indel_error) == FALSE ) {
warn("Could not convert %s to a double",indel_error);
ret = FALSE;
}
if( is_double_string(allN_string,&allN) == FALSE ) {
warn("Could not convert %s to a double",allN_string);
ret = FALSE;
}
if( strcmp(null_string,"syn") == 0 ) {
use_syn = TRUE;
} else if ( strcmp(null_string,"flat") == 0 ) {
use_syn = FALSE;
} else {
warn("Cannot interpret [%s] as a null model string\n",null_string);
ret = FALSE;
}
if( alg_str != NULL ) {
alg = alg_estwrap_from_string(alg_str);
} else {
alg_str = "312";
alg = alg_estwrap_from_string(alg_str);
}
if( aln_alg_str != NULL ) {
aln_alg = alg_estwrap_from_string(aln_alg_str);
} else {
/* if it is a protein, don't loop */
if( use_single_pro == TRUE || use_db_pro == TRUE )
aln_alg_str = "333";
else
aln_alg_str = "333L";
aln_alg = alg_estwrap_from_string(aln_alg_str);
}
if( (rm = default_RandomModel()) == NULL) {
warn("Could not make default random model\n");
ret = FALSE;
}
if( (ct = read_CodonTable_file(codon_file)) == NULL) {
ret = FALSE;
warn("Could not read codon table file in %s",codon_file);
}
if( (ofp = openfile(output_file,"W")) == NULL) {
warn("Could not open %s as an output file",output_file);
ret = FALSE;
}
rmd = RandomModelDNA_std();
cps = flat_cDNAParser(indel_error);
cm = flat_CodonMapper(ct);
sprinkle_errors_over_CodonMapper(cm,subs_error);
return ret;
}
HSPScanInterface * new_HSPScanInterface_from_ScanWiseHSPImpl(ScanWiseHSPImpl * i,ProteinIndexConstructor * pic,SeqLookupLoadPara * slp)
{
HSPScanInterface * out;
SeqLookupInterface * sli;
SequenceDB * db;
Sequence * seq;
CompMat * mat;
int ret;
int c;
mat = read_Blast_file_CompMat(i->matrix_file);
if( i->use_corba == FALSE && i->use_mysql == FALSE && i->use_wiseserver == FALSE && i->use_compress == FALSE && i->use_multiscan == FALSE) {
if( i->direct_sequence == NULL ) {
fatal("If no server based sequence, must have direct sequence");
} else {
db = single_fasta_SequenceDB(i->direct_sequence);
sli = new_SeqLookupInterface_from_ProteinIndexConstructor(pic);
load_SequenceDB_SeqLookupLoadPara(slp,db,sli);
free_SequenceDB(db);
out = new_one_off_HSPScanInterface(sli,mat,15,40);
}
} else if( i->use_corba == TRUE ) {
#ifdef SCAN_CORBA
if( i->ior_file == NULL ) {
fatal("Corba specified, but no ior file given");
}
out = new_corba_HSPScan(sorb,i->ior_file,mat);
#else
fatal("Asking for CORBA, but scanwisep was not compiled with SCAN_CORBA defined.");
#endif
} else if ( i->use_mysql == TRUE ) {
#ifdef SCAN_MYSQL
out = new_HSPScanInterface_MysqlProteinIndex(i->host,i->dbname,i->username,i->password,mat,i->step);
#else
fatal("Asking for mysql, but scanwisep was not compiled with SCAN_MYSQL defined");
#endif
} else if ( i->use_wiseserver == TRUE ) {
#ifdef SCAN_WISESERVER
out = new_wise_transfer_HSPScanInterface(i->host,i->port);
#else
fatal("Asking for wiseserver, but scanwisep was not compiled with SCAN_WISESERVER defined");
#endif
} else if ( i->use_compress == TRUE ) {
#ifdef SCAN_COMPRESS
sli = new_direct_CompressedProteinLookup();
db = single_fasta_SequenceDB(i->direct_sequence);
load_SequenceDB_SeqLookupLoadPara(slp,db,sli);
free_SequenceDB(db);
out = new_one_off_HSPScanInterface(sli,mat,15,40);
#else
fatal("Asking for compressed, but scanwisep was not compiled with SCAN_COMPRESS defined");
#endif
} else if( i->use_multiscan == TRUE ) {
if( i->multiscan_file == NULL ) {
fatal("Must provide a file for a multiple server scan");
}
out = new_multiclient_HSPScanInterface(i->multiscan_file);
}
assert(out != NULL);
free_CompMat(mat); /* hard linked internally */
return out;
}
int main(int argc,char ** argv)
{
DPRunImpl * dpri = NULL;
ScanWiseHSPImpl * scani = NULL;
HSP2HitListImpl * hsp2hiti = NULL;
HitListOutputImpl * hloi = NULL;
ProteinIndexConstructor * pic = NULL;
HSPScanInterface * hsi;
HSPScanInterfacePara * para;
SearchStatInterface * ssi;
SearchStatInterface * ssl;
SeqLookupLoadPara * slp;
HSPset2HitPairPara * hsp2hit;
CompMat * mat;
SequenceDB * db;
Sequence * seq;
int ret;
int i;
int effective_db_size = 300000;
int kk;
int count = 0;
LinearHSPmanager * lm;
HitList * hl;
boolean use_mott = 1;
boolean trunc_best_hsp = 0;
boolean verbose = 0;
static struct rusage use;
struct timeval t0, t1;
gettimeofday(&t0, NULL);
dpri = new_DPRunImpl_from_argv(&argc,argv);
dpri->memory = DPIM_Explicit;
scani = new_ScanWiseHSPImpl_from_argv(&argc,argv);
hsp2hiti = new_HSP2HitListImpl_from_argv(&argc,argv);
hloi = new_HitListOutputImpl_from_argv(&argc,argv);
slp = new_SeqLookupLoadPara_from_argv(&argc,argv);
pic = new_ProteinIndexConstructor_from_argv(&argc,argv);
hsp2hit = new_HSPset2HitPairPara_from_argv(&argc,argv);
para = new_HSPScanInterfacePara_from_argv(&argc,argv);
verbose = strip_out_boolean_argument(&argc,argv,"verbose") ;
strip_out_boolean_def_argument(&argc,argv,"mott",&use_mott);
strip_out_boolean_def_argument(&argc,argv,"besthsp",&trunc_best_hsp);
strip_out_integer_argument(&argc,argv,"dbsize",&effective_db_size);
#ifdef SCAN_CORBA
sorb = get_Wise2Corba_Singleton(&argc,argv,"orbit-local-orb");
#endif
if( dpri == NULL ) {
fatal("Unable to build DPRun implementation. Bad arguments");
}
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 2 ) {
show_help(stdout);
exit(12);
}
/* ugly, but we don't want to bounce matrices around the network... */
mat = read_Blast_file_CompMat("BLOSUM62.bla");
erroroff(REPORT);
hsi = new_HSPScanInterface_from_ScanWiseHSPImpl(scani,pic,slp);
ssi = new_Mott_SearchStatInterface();
ssl = new_lookup_SearchStatInterface(40,2.3);
if( verbose ) {
info("contacted database");
}
db = single_fasta_SequenceDB(argv[1]);
if( db == NULL ) {
fatal("Could not open sequence db...\n");
}
for(seq = init_SequenceDB(db,&ret); seq != NULL;seq = get_next_SequenceDB(db) ) {
count++;
for(i=0;i<seq->len;i++) {
if( !isalpha(seq->seq[i]) ) {
fatal("Sequence position %d [%c] is not valid",i,seq->seq[i]);
}
seq->seq[i] = toupper(seq->seq[i]);
}
info("Processing %s",seq->name);
getrusage(RUSAGE_SELF,&use);
/* info("Before query %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
lm = (*hsi->scan_query)(hsi->data,seq,para);
fprintf(stderr,"Got linear manager is %d entries\n",lm->len);
if( lm->mat == NULL ) {
lm->mat = hard_link_CompMat(mat);
}
getrusage(RUSAGE_SELF,&use);
/*
info("After query %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
sort_LinearHSPmanager(lm,compare_HSPset_score);
if( trunc_best_hsp == 1 ) {
for(kk=1;kk<lm->len;kk++) {
free_HSPset(lm->set[kk]);
lm->set[kk] = NULL;
}
lm->len = 1;
}
getrusage(RUSAGE_SELF,&use);
/*
info("After sort %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
hl = HitList_from_HSP_HSP2HitListImpl(hsp2hiti,lm,dpri,hsp2hit);
getrusage(RUSAGE_SELF,&use);
/*
info("After conversion %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
free_LinearHSPmanager(lm);
if( use_mott == 1 ) {
apply_SearchStat_to_HitList(hl,ssi,effective_db_size);
} else {
for(kk=0;kk<hl->len;kk++) {
hl->pair[kk]->bit_score = hl->pair[kk]->raw_score / 2.0;
}
}
sort_HitList_by_score(hl);
show_HitList_HitListOutputImpl(hloi,hl,stdout);
getrusage(RUSAGE_SELF,&use);
/*
info("After output %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
free_HitList(hl);
free_Sequence(seq);
}
free_DPRunImpl(dpri);
free_HSPScanInterface(hsi);
gettimeofday(&t1, NULL);
fprintf(stderr, "[client stats] queries, time (s): %d %f\n",
count,
(t1.tv_sec - t0.tv_sec) +
(t1.tv_usec - t0.tv_usec) * 1e-6);
return 0;
}
int main(int argc,char ** argv)
{
Sequence * query;
Sequence * target;
CompMat * comp;
char * comp_file;
int gap = (12);
int ext = (2);
int a = 120;
int b = 10;
int c = 3;
ComplexSequence * query_cs;
ComplexSequence * target_cs;
ComplexSequenceEvalSet * evalfunc;
boolean show_label_output = FALSE;
boolean show_fancy_output = FALSE;
boolean use_abc = FALSE;
PackAln * pal;
AlnBlock * alb;
DPRunImpl * dpri = NULL;
/*
* Process command line options
* -h or -help gives us help
* -g for gap value (an int) - rely on commandline error processing
* -e for ext value (an int) - rely on commandline error processing
* -m for matrix (a char)
* -l - label output
* -f - fancy output
*
*
* Use calls to commandline.h functions
*
*/
if( strip_out_boolean_argument(&argc,argv,"h") == TRUE || strip_out_boolean_argument(&argc,argv,"-help") == TRUE) {
show_help(stdout);
exit(1);
}
dpri = new_DPRunImpl_from_argv(&argc,argv);
if( dpri == NULL ) {
fatal("Unable to build DPRun implementation. Bad arguments");
}
show_label_output = strip_out_boolean_argument(&argc,argv,"l");
show_fancy_output = strip_out_boolean_argument(&argc,argv,"f");
/** if all FALSE, set fancy to TRUE **/
if( show_label_output == FALSE )
show_fancy_output = TRUE;
(void) strip_out_integer_argument(&argc,argv,"g",&gap);
(void) strip_out_integer_argument(&argc,argv,"e",&ext);
(void) strip_out_integer_argument(&argc,argv,"a",&a);
(void) strip_out_integer_argument(&argc,argv,"b",&b);
(void) strip_out_integer_argument(&argc,argv,"c",&c);
use_abc = strip_out_boolean_argument(&argc,argv,"abc");
comp_file = strip_out_assigned_argument(&argc,argv,"m");
if( comp_file == NULL)
comp_file = "blosum62.bla";
if( argc != 3 ) {
warn("Must have two arguments for sequence 1 and sequence 2 %d",argc);
show_help(stdout);
exit(1);
}
/*
* Read in two sequences
*/
if( (query=read_fasta_file_Sequence(argv[1])) == NULL ) {
fatal("Unable to read the sequence in file %s",argv[1]);
}
if( (target=read_fasta_file_Sequence(argv[2])) == NULL ) {
fatal("Unable to read the sequence in file %s",argv[2]);
}
/*
* Open a blosum matrix. This will be opened from WISECONFIGDIR
* or WISEPERSONALDIR if it is not present in the current directory.
*/
comp = read_Blast_file_CompMat(comp_file);
if( comp == NULL ) {
fatal("unable to read file %s",comp_file);
}
/* if abc - factor up matrix! */
if( use_abc == TRUE ) {
factor_CompMat(comp,10);
}
/*
* Make an alignment. I don't care about the implementation:
* hand it over to sw_wrap function to do it
*
*/
if( use_abc ) {
evalfunc = default_aminoacid_ComplexSequenceEvalSet();
query_cs = new_ComplexSequence(query,evalfunc);
if( query_cs == NULL )
fatal("Cannot build cs objects!");
target_cs = new_ComplexSequence(target,evalfunc);
if( target_cs == NULL )
fatal("Cannot build cs objects!");
pal = PackAln_bestmemory_abc(query_cs,target_cs,comp,-a,-b,-c,NULL,dpri);
alb = convert_PackAln_to_AlnBlock_abc(pal);
free_ComplexSequence(query_cs);
free_ComplexSequence(target_cs);
} else {
alb = Align_Sequences_ProteinSmithWaterman(query,target,comp,-gap,-ext,dpri);
}
/*
* show output. If multiple outputs, divide using //
*/
if( show_label_output == TRUE ) {
show_flat_AlnBlock(alb,stdout);
puts("//\n");
}
if( show_fancy_output == TRUE ) {
write_pretty_seq_align(alb,query,target,15,50,stdout);
puts("//\n");
}
/*
* Destroy the memory.
*/
free_Sequence(query);
free_Sequence(target);
free_CompMat(comp);
free_AlnBlock(alb);
return 0;
}
int main(int argc,char ** argv)
{
Sequence * cdna;
Sequence * gen;
Sequence * active_gen;
Sequence * active_cdna;
int i;
int dstart = -1;
int dend = -1;
int cstart = -1;
int cend = -1;
CodonTable * ct = NULL;
CodonMatrixScore * cm = NULL;
RandomCodon * rndcodon = NULL;
RandomCodonScore * rndcodonscore = NULL;
DnaMatrix * dm = NULL;
DPRunImpl * dpri = NULL;
GeneModel * gm;
GeneModelParam * gmp;
GeneStats * gs;
GeneParser21 * gp21;
GeneParser21Score * gp21s;
GeneParser4Score * gp;
ComplexSequenceEvalSet * cdna_cses;
ComplexSequenceEvalSet * gen_cses;
ComplexSequence * cs_cdna;
ComplexSequence * cs_gen;
Genomic * gent;
GenomicRegion * gr;
CompMat * cmat;
CompProb * cprob;
char * matfile = "blosum62.bla";
Protein * trans;
PackAln * pal;
AlnBlock * alb;
FILE * ofp = stdout;
dpri = new_DPRunImpl_from_argv(&argc,argv);
gmp = new_GeneModelParam_from_argv(&argc,argv);
strip_out_integer_argument(&argc,argv,"u",&dstart);
strip_out_integer_argument(&argc,argv,"v",&dend);
strip_out_integer_argument(&argc,argv,"s",&cstart);
strip_out_integer_argument(&argc,argv,"t",&cend);
strip_out_standard_options(&argc,argv,show_help,show_version);
ct = read_CodonTable_file(codon_file);
cmat = read_Blast_file_CompMat(matfile);
cprob = CompProb_from_halfbit(cmat);
cm = naive_CodonMatrixScore_from_prob(ct,cprob);
gm = GeneModel_from_GeneModelParam(gmp);
cdna = read_fasta_file_Sequence(argv[1]);
gen = read_fasta_file_Sequence(argv[2]);
if( dstart != -1 || dend != -1 ) {
if( dstart == -1 ) {
dstart = 1;
}
if( dend == -1 ) {
dend = gen->len;
}
active_gen = magic_trunc_Sequence(gen,dstart,dend);
} else {
active_gen = hard_link_Sequence(gen);
}
if( cstart != -1 || cend != -1 ) {
if( cstart == -1 ) {
cstart = 1;
}
if( cend == -1 ) {
cend = gen->len;
}
active_cdna = magic_trunc_Sequence(gen,cstart,cend);
} else {
active_cdna = hard_link_Sequence(gen);
}
rndcodon = RandomCodon_from_raw_CodonFrequency(gm->codon,ct);
fold_in_RandomModelDNA_into_RandomCodon(rndcodon,gm->rnd);
rndcodonscore = RandomCodonScore_from_RandomCodon(rndcodon);
assert(active_cdna);
assert(active_gen);
cdna_cses = default_cDNA_ComplexSequenceEvalSet();
gen_cses = new_ComplexSequenceEvalSet_from_GeneModel(gm);
cs_cdna = new_ComplexSequence(active_cdna,cdna_cses);
cs_gen = new_ComplexSequence(active_gen,gen_cses);
gp21 = std_GeneParser21();
GeneParser21_fold_in_RandomModelDNA(gp21,gm->rnd);
gp21s = GeneParser21Score_from_GeneParser21(gp21);
gp = GeneParser4Score_from_GeneParser21Score(gp21s);
dm = identity_DnaMatrix(Probability2Score(halfbit2Probability(1)),Probability2Score(halfbit2Probability(-1)));
assert(cs_cdna);
assert(cs_gen);
assert(gp);
assert(rndcodonscore);
assert(dm);
assert(dpri);
/* show_CodonMatrixScore(cm,ct,ofp);*/
pal = PackAln_bestmemory_CdnaWise10(cs_cdna,cs_gen,gp,cm,rndcodonscore,dm,
Probability2Score(halfbit2Probability(-12)),
Probability2Score(halfbit2Probability(-2)),
Probability2Score(halfbit2Probability(-5)),
Probability2Score(halfbit2Probability(0)),
NULL,
dpri);
alb = convert_PackAln_to_AlnBlock_CdnaWise10(pal);
gent = Genomic_from_Sequence(gen);
assert(gent);
gr = new_GenomicRegion(gent);
assert(gr);
add_Genes_to_GenomicRegion_GeneWise(gr,active_gen->offset,active_gen->end,alb,cdna->name,0,NULL);
mapped_ascii_AlnBlock(alb,Score2Bits,0,ofp);
show_pretty_GenomicRegion(gr,0,ofp);
for(i=0;i<gr->len;i++) {
if( gr->gene[i]->ispseudo == TRUE ) {
fprintf(ofp,"#Gene %d is a pseudo gene - no translation possible\n",i);
} else {
trans = get_Protein_from_Translation(gr->gene[i]->transcript[0]->translation[0],ct);
write_fasta_Sequence(trans->baseseq,ofp);
}
}
}
int main(int argc,char ** argv)
{
Sequence * query;
Sequence * target;
ComplexSequence * query_cs;
ComplexSequence * target_cs;
ComplexSequenceEvalSet * evalfunc;
CompMat * comp;
char * comp_file;
int gap = (12);
int ext = (2);
boolean show_raw_output = FALSE;
boolean show_label_output = FALSE;
boolean show_fancy_output = FALSE;
boolean has_outputted = FALSE;
PackAln * pal;
AlnBlock * alb;
/*
* Process command line options
* -h or -help gives us help
* -g for gap value (an int) - rely on commandline error processing
* -e for ext value (an int) - rely on commandline error processing
* -m for matrix (a char)
* -r - raw matrix output
* -l - label output
* -f - fancy output
*
*
* Use calls to commandline.h functions
*
*/
if( strip_out_boolean_argument(&argc,argv,"h") == TRUE || strip_out_boolean_argument(&argc,argv,"-help") == TRUE) {
show_help(stdout);
exit(1);
}
show_raw_output = strip_out_boolean_argument(&argc,argv,"r");
show_label_output = strip_out_boolean_argument(&argc,argv,"l");
show_fancy_output = strip_out_boolean_argument(&argc,argv,"f");
/** if all FALSE, set fancy to TRUE **/
if( show_raw_output == FALSE && show_label_output == FALSE )
show_fancy_output = TRUE;
(void) strip_out_integer_argument(&argc,argv,"g",&gap);
(void) strip_out_integer_argument(&argc,argv,"e",&ext);
comp_file = strip_out_assigned_argument(&argc,argv,"m");
if( comp_file == NULL)
comp_file = "blosum62.bla";
if( argc != 3 ) {
warn("Must have two arguments for sequence 1 and sequence 2 %d",argc);
show_help(stdout);
exit(1);
}
/*
* Read in two sequences
*/
if( (query=read_fasta_file_Sequence(argv[1])) == NULL ) {
fatal("Unable to read the sequence in file %s",argv[1]);
}
if( (target=read_fasta_file_Sequence(argv[2])) == NULL ) {
fatal("Unable to read the sequence in file %s",argv[2]);
}
/*
* Open a blosum matrix. This will be opened from WISECONFIGDIR
* or WISEPERSONALDIR if it is not present in the current directory.
*/
comp = read_Blast_file_CompMat(comp_file);
if( comp == NULL ) {
fatal("unable to read file %s",comp_file);
}
/*
* Convert sequences to ComplexSequences:
* To do this we need an protein ComplexSequenceEvalSet
*
*/
evalfunc = default_aminoacid_ComplexSequenceEvalSet();
query_cs = new_ComplexSequence(query,evalfunc);
if( query_cs == NULL ) {
fatal("Unable to make a protein complex sequence from %s",query->name);
}
target_cs = new_ComplexSequence(target,evalfunc);
if( target_cs == NULL ) {
fatal("Unable to make a protein complex sequence from %s",target->name);
}
/*
* Make an alignment. I don't care about the implementation:
* If the sequences are small enough then it should use explicit memory.
* Long sequences should use divide and conquor methods.
*
* Calling PackAln_bestmemory_ProteinSW is the answer
* This function decides on the best method considering the
* memory and changes accordingly. It frees the matrix memory
* at the end as well.
*
*/
pal = PackAln_bestmemory_ProteinSW(query_cs,target_cs,comp,-gap,-ext,NULL);
if( pal == NULL ) {
fatal("Unable to make an alignment from %s and %s",query->name,target->name);
}
/*
* ok, make other alignment forms, and be ready to show
*/
alb = convert_PackAln_to_AlnBlock_ProteinSW(pal);
/*
* show output. If multiple outputs, divide using //
*/
if( show_raw_output == TRUE ) {
show_simple_PackAln(pal,stdout);
puts("//\n");
}
if( show_label_output == TRUE ) {
show_flat_AlnBlock(alb,stdout);
}
if( show_fancy_output == TRUE ) {
write_pretty_seq_align(alb,query,target,15,50,stdout);
puts("//\n");
}
/*
* Destroy the memory.
*/
free_Sequence(query);
free_Sequence(target);
free_CompMat(comp);
free_ComplexSequence(query_cs);
free_ComplexSequence(target_cs);
free_PackAln(pal);
free_AlnBlock(alb);
return 0;
}
