void show_StandardOutputOptions(StandardOutputOptions * out,AlnBlock * alb,PackAln * pal,char * divide_str,FILE * ofp)
{
assert(out);
assert(alb);
assert(pal);
assert(ofp);
assert(divide_str);
if( out->show_alb == TRUE ) {
mapped_ascii_AlnBlock(alb,Score2Bits,0,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( out->show_cumlative_alb == TRUE ) {
mapped_ascii_AlnBlock(alb,Score2Bits,1,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( out->show_cumlative_pal == TRUE ) {
show_bits_and_cumlative_PackAln(pal,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( out->show_pal == TRUE ) {
show_simple_PackAln(pal,ofp);
fprintf(ofp,"%s\n",divide_str);
}
return;
}
boolean show_output(void)
{
int i;
cDNA * cdna;
Protein * trans;
GenomicOverlapResults * gor;
AlnColumn * alt;
if( show_pretty == TRUE ) {
show_pretty_aln();
}
if( show_match_sum == TRUE ) {
show_MatchSummary_genewise_header(ofp);
show_MatchSummarySet_genewise(mss,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_pretty_gene == TRUE ) {
show_pretty_GenomicRegion(gr,0,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_supp_gene == TRUE ) {
show_pretty_GenomicRegion(gr,1,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_embl == TRUE ) {
write_Embl_FT_GenomicRegion(gr,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_diana == TRUE ) {
write_Diana_FT_GenomicRegion(gr,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_overlap == TRUE ) {
gor = Genomic_overlap(gr,embl);
show_GenomicOverlapResults(gor,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_trans == TRUE ) {
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);
}
}
fprintf(ofp,"%s\n",divide_str);
}
if( show_pep == TRUE ) {
alt = alb->start;
for(;alt != NULL;) {
trans = Protein_from_GeneWise_AlnColumn(gen->baseseq,alt,1,&alt,ct,is_random_AlnColumn_genewise);
if ( trans == NULL )
break;
write_fasta_Sequence(trans->baseseq,ofp);
free_Protein(trans);
}
fprintf(ofp,"%s\n",divide_str);
}
if( show_cdna == TRUE ) {
for(i=0;i<gr->len;i++) {
cdna = get_cDNA_from_Transcript(gr->gene[i]->transcript[0]);
write_fasta_Sequence(cdna->baseseq,ofp);
}
fprintf(ofp,"%s\n",divide_str);
}
if( show_ace == TRUE ) {
show_ace_GenomicRegion(gr,gen->baseseq->name,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_gff == TRUE ) {
show_GFF_GenomicRegion(gr,gen->baseseq->name,"GeneWise",ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_gene_plain == TRUE ) {
show_GenomicRegion(gr,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_AlnBlock == TRUE ) {
mapped_ascii_AlnBlock(alb,Score2Bits,0,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_cumlative_PackAln == TRUE ) {
show_bits_and_cumlative_PackAln(pal,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_PackAln == TRUE ) {
show_simple_PackAln(pal,ofp);
fprintf(ofp,"%s\n",divide_str);
}
return TRUE;
}
int main(int argc,char ** argv)
{
Sequence * gen;
Genomic * genomic;
CodonTable * ct = NULL;
GenomeEvidenceSet * ges = NULL;
RandomCodonScore * rcs;
FILE * ifp = NULL;
ComplexSequence * cs = NULL;
ComplexSequenceEvalSet * cses = NULL;
AlnBlock * alb;
PackAln * pal;
GenomicRegion * gr;
int i;
Protein * trans;
cDNA * cdna;
int kbyte = 10000;
int stop_codon_pen = 200;
int start_codon_pen = 30;
int new_gene = 5000;
int switch_cost = 100;
int smell = 8;
DPRunImpl * dpri = NULL;
EstEvidence * est;
boolean show_trans = TRUE;
boolean show_cdna = FALSE;
boolean show_genes = TRUE;
boolean show_alb = FALSE;
boolean show_pal = FALSE;
boolean show_gff = TRUE;
boolean show_debug = FALSE;
boolean show_geneu = TRUE;
char * divide_string = "//";
strip_out_boolean_def_argument(&argc,argv,"geneutr",&show_geneu);
strip_out_boolean_def_argument(&argc,argv,"genes",&show_genes);
strip_out_boolean_def_argument(&argc,argv,"trans",&show_trans);
strip_out_boolean_def_argument(&argc,argv,"gff",&show_gff);
strip_out_boolean_def_argument(&argc,argv,"alb",&show_alb);
strip_out_boolean_def_argument(&argc,argv,"pal",&show_pal);
strip_out_boolean_def_argument(&argc,argv,"debug",&show_debug);
strip_out_boolean_def_argument(&argc,argv,"cdna",&show_cdna);
strip_out_integer_argument(&argc,argv,"stop",&stop_codon_pen);
strip_out_integer_argument(&argc,argv,"start",&start_codon_pen);
strip_out_integer_argument(&argc,argv,"gene",&new_gene);
strip_out_integer_argument(&argc,argv,"switch",&switch_cost);
strip_out_integer_argument(&argc,argv,"smell",&smell);
dpri = new_DPRunImpl_from_argv(&argc,argv);
if( dpri == NULL ) {
fatal("Unable to build DPRun implementation. Bad arguments");
}
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 3 ) {
show_help(stdout);
exit(12);
}
ct = read_CodonTable_file("codon.table");
gen = read_fasta_file_Sequence(argv[1]);
ifp = openfile(argv[2],"r");
ges = read_est_evidence(ifp,ct);
for(i=0;i<ges->len;i++) {
est = (EstEvidence *) ges->geu[i]->data;
est->in_smell = smell;
}
rcs= RandomCodonScore_alloc();
for(i=0;i<125;i++) {
if( is_stop_codon(i,ct) ) {
rcs->codon[i] = -1000000;
} else {
rcs->codon[i] = 0;
}
/* fprintf(stderr,"Got %d for %d\n",rcs->codon[i],i); */
}
cses = default_genomic_ComplexSequenceEvalSet();
cs = new_ComplexSequence(gen,cses);
pal = PackAln_bestmemory_GenomeWise9(ges,cs,-switch_cost,-new_gene,-start_codon_pen,-stop_codon_pen,rcs,NULL,dpri);
alb = convert_PackAln_to_AlnBlock_GenomeWise9(pal);
genomic = Genomic_from_Sequence(gen);
gr = new_GenomicRegion(genomic);
add_Genes_to_GenomicRegion_GeneWise(gr,1,gen->len,alb,gen->name,0,NULL);
if( show_genes ) {
show_pretty_GenomicRegion(gr,0,stdout);
fprintf(stdout,"%s\n",divide_string);
}
if( show_gff ) {
show_GFF_GenomicRegion(gr,gen->name,"genomwise",stdout);
fprintf(stdout,"%s\n",divide_string);
}
if( show_trans ) {
for(i=0;i<gr->len;i++) {
if( gr->gene[i]->ispseudo == TRUE ) {
fprintf(stdout,"#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,stdout);
}
}
fprintf(stdout,"%s\n",divide_string);
}
if( show_cdna ) {
for(i=0;i<gr->len;i++) {
cdna = get_cDNA_from_Transcript(gr->gene[i]->transcript[0]);
write_fasta_Sequence(cdna->baseseq,stdout);
}
fprintf(stdout,"%s\n",divide_string);
}
if( show_geneu ) {
show_utr_exon_genomewise(alb,stdout);
fprintf(stdout,"%s\n",divide_string);
}
if( show_alb ) {
mapped_ascii_AlnBlock(alb,id,1,stdout);
fprintf(stdout,"%s\n",divide_string);
}
if( show_debug ) {
debug_genomewise(alb,ges,ct,gen,stdout);
fprintf(stdout,"%s\n",divide_string);
}
if( show_pal ) {
show_simple_PackAln(pal,stdout);
fprintf(stdout,"%s\n",divide_string);
}
return 0;
}
boolean show_output(void)
{
int i,k;
ThreeStateModel * temptsm;
AlnBlock * alb;
PackAln * pal;
MatchSummarySet * mss;
Protein * ps;
cDNA * cdna;
double bits;
boolean fitted_res = FALSE;
AlnBlockList * alist;
AlnBlock * anchored;
SequenceSet * set;
AlnColumn * alt;
Protein * trans;
/* sort by bit score first */
sort_Hscore_by_score(hs);
if( search_mode == PC_SEARCH_S2DB ) {
if( hs->his == NULL || hs->his->total < 1000 ) {
info("Cannot fit histogram to a db smaller than 1,000");
fprintf(ofp,"[Warning: Can't fit histogram to a db smaller than 1,000]\n\n");
show_histogram = FALSE;
} else {
fitted_res = TRUE;
fit_Hscore_to_EVD(hs,20);
}
}
/* deal with initialising anchored alignment.
* Could be done for either single HMMs or single proteins,
* but we will only do it for HMMs at the moment
*/
if( make_anchored_aln == TRUE ) {
if( tsm == NULL ) {
warn("Attempting to make an achored alignment without a HMM. impossible!");
make_anchored_aln = FALSE;
} else {
anchored = single_unit_AlnBlock(tsm->len,"MATCH_STATE");
set = SequenceSet_alloc_std();
}
}
/* dofus catcher */
if( aln_alg != alg ) {
fprintf(ofp,"\n#\n#WARNING!\n#\n# Your alignment algorithm is different from your search algorithm.\n# This is probably quite sensible but will lead to differing scores.\n# Use the search score as an indicator of the significance of the match\n# Read the docs for more information\n#\n");
}
fprintf(ofp,"\n\n#High Score list\n");
fprintf(ofp,"#Protein ID DNA Str ID Bits Evalue\n");
fprintf(ofp,"--------------------------------------------------------------------------\n");
for(i=0;i<hs->len;i++) {
bits = Score2Bits(hs->ds[i]->score);
if( bits < search_cutoff ) {
break;
}
if( fitted_res == TRUE && evalue_search_str != NULL ) {
if( hs->ds[i]->evalue > evalue_search_cutoff )
break;
}
if( fitted_res == TRUE)
fprintf(ofp,"Protein %-20sDNA [%c] %-24s %.2f %.2g\n",hs->ds[i]->query->name,hs->ds[i]->target->is_reversed == TRUE ? '-' : '+',hs->ds[i]->target->name,bits,hs->ds[i]->evalue);
else
fprintf(ofp,"Protein %-20sDNA [%c] %-24s %.2f\n",hs->ds[i]->query->name,hs->ds[i]->target->is_reversed == TRUE ? '-' : '+',hs->ds[i]->target->name,bits);
}
if( search_mode == PC_SEARCH_S2DB && show_histogram == TRUE ) {
fprintf(ofp,"\n\n#Histogram\n");
fprintf(ofp,"-----------------------------------------------------------------------\n");
PrintASCIIHistogram(hs->his,ofp);
}
fprintf(ofp,"\n\n#Alignments\n");
fprintf(ofp,"-----------------------------------------------------------------------\n");
for(i=0;i<hs->len;i++) {
bits = Score2Bits(hs->ds[i]->score);
if( bits < search_cutoff ) {
break;
}
if( i >= aln_number ) {
break;
}
if( fitted_res == TRUE && evalue_search_str != NULL ) {
if( hs->ds[i]->evalue > evalue_search_cutoff )
break;
}
fprintf(ofp,"\n\n>Results for %s vs %s (%s) [%d]\n",hs->ds[i]->query->name,hs->ds[i]->target->name,hs->ds[i]->target->is_reversed == TRUE ? "reverse" : "forward",i+1 );
cdna = get_cDNA_from_cDNADB(cdb,hs->ds[i]->target);
temptsm = indexed_ThreeStateModel_ThreeStateDB(tsmdb,hs->ds[i]->query);
alb = AlnBlock_from_TSM_estwise_wrap(temptsm,cdna,cps,cm,ct,rmd,aln_alg,use_syn,allN,flat_insert,dpri,&pal);
if( alb == NULL ) {
warn("Got a NULL alignment. Exiting now due to presumed problems");
fprintf(ofp,"\n\n*Got a NULL alignment. Exiting now due to presumed problems*\n\n");
return FALSE;
}
if( use_single_pro == FALSE)
mss = MatchSummarySet_from_AlnBlock_genewise(alb,temptsm->name,1,cdna->baseseq);
else
mss = MatchSummarySet_from_AlnBlock_genewise(alb,pro->baseseq->name,pro->baseseq->offset,cdna->baseseq);
if( show_pretty == TRUE ) {
fprintf(ofp,"\n%s output\nScore %4.2f bits over entire alignment.\nThis will be different from per-alignment scores. See manual for details\nFor computer parsable output, try %s -help or read the manual\n",program_name,Score2Bits(pal->score),program_name);
if( use_syn == FALSE ) {
fprintf(ofp,"Scores as bits over a flat simple random model\n\n");
} else {
fprintf(ofp,"Scores as bits over a synchronous coding model\n\n");
}
ps = pseudo_Protein_from_ThreeStateModel(temptsm);
protcdna_ascii_display(alb,ps->baseseq->seq,ps->baseseq->name,ps->baseseq->offset,cdna,ct,15,main_block,TRUE,ofp);
free_Protein(ps);
fprintf(ofp,"%s\n",divide_str);
}
if( show_match_sum == TRUE ) {
show_MatchSummary_genewise_header(ofp);
show_MatchSummarySet_genewise(mss,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_pep == TRUE ) {
alt = alb->start;
for(;alt != NULL;) {
trans = Protein_from_GeneWise_AlnColumn(cdna->baseseq,alt,1,&alt,ct,is_random_AlnColumn_genewise);
if ( trans == NULL )
break;
write_fasta_Sequence(trans->baseseq,ofp);
free_Protein(trans);
}
fprintf(ofp,"%s\n",divide_str);
}
if( show_AlnBlock == TRUE ) {
mapped_ascii_AlnBlock(alb,Score2Bits,0,ofp);
fprintf(ofp,"%s\n",divide_str);
}
if( show_PackAln == TRUE ) {
show_simple_PackAln(pal,ofp);
fprintf(ofp,"%s\n",divide_str);
}
/*
* This goes at the end because it destroys the alb structure
*/
if( make_anchored_aln == TRUE ) {
/* attach sequence to als in alb, so we have it for later use */
alb->seq[1]->data = (void *) cdna->baseseq;
/* add to SequenceSet so we can destroy the memory */
add_SequenceSet(set,hard_link_Sequence(cdna->baseseq));
alist = split_AlnBlock(alb,is_random_AlnColumn_genewise);
for(k=0;k<alist->len;k++) {
/* actually produce the anchored alignment */
/*mapped_ascii_AlnBlock(alist->alb[k],Score2Bits,stderr);*/
add_to_anchored_AlnBlock(anchored,alist->alb[k]);
/* dump_ascii_AlnBlock(anchored,stderr);*/
}
}
alb = free_AlnBlock(alb);
pal = free_PackAln(pal);
mss = free_MatchSummarySet(mss);
cdna = free_cDNA(cdna);
temptsm = free_ThreeStateModel(temptsm);
}
if( do_complete_analysis == TRUE ) {
fprintf(ofp,"\n\n#Complete Analysis\n");
fprintf(ofp,"-------------------------------------------------------------\n\n");
/* ok - end of loop over relevant hits. If we have an
* anchored alignment, print it out!
*/
if( make_anchored_aln == TRUE ) {
/*dump_ascii_AlnBlock(anchored,stderr);*/
write_mul_estwise_AlnBlock(anchored,ct,ofp);
fprintf(ofp,"%s\n",divide_str);
}
}
return TRUE;
}
int main (int argc,char ** argv)
{
MappedCloneSet * trusted;
MappedCloneSet * weak;
MappedCloneMatch * match;
FILE * in;
int kbyte = 10000;
PackAln * pal;
AlnBlock * alb;
int spread = 30;
boolean show_alb = 0;
boolean show_pal = 0;
boolean show_zip = 1;
boolean show_path = 0;
char * alg_string = "local";
char * temp;
char * divide_string = "//";
strip_out_boolean_def_argument(&argc,argv,"alb",&show_alb);
strip_out_boolean_def_argument(&argc,argv,"pal",&show_pal);
strip_out_boolean_def_argument(&argc,argv,"zip",&show_zip);
strip_out_boolean_def_argument(&argc,argv,"path",&show_path);
strip_out_integer_argument(&argc,argv,"wgap",&query_gap_start);
strip_out_integer_argument(&argc,argv,"wext",&query_gap_extend);
strip_out_integer_argument(&argc,argv,"wswitch",&query_switch_cost);
strip_out_integer_argument(&argc,argv,"tgap",&target_gap_start);
strip_out_integer_argument(&argc,argv,"text",&target_gap_extend);
strip_out_integer_argument(&argc,argv,"match",&match_score);
strip_out_integer_argument(&argc,argv,"mismatch",&mismatch_score);
temp =strip_out_assigned_argument(&argc,argv,"alg");
if( temp != NULL ) {
alg_string = temp;
}
strip_out_integer_argument(&argc,argv,"spread",&spread);
strip_out_integer_argument(&argc,argv,"kbyte",&kbyte);
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 3 ) {
show_help(stdout);
exit(12);
}
in = fopen(argv[1],"r");
if( in == NULL ) {
fatal("Unable to open %s",argv[1]);
}
trusted = read_MappedCloneSet(in);
/* fprintf(stderr,"first start %d\n",trusted->clone[0]->start);*/
in = fopen(argv[2],"r");
if( in == NULL ) {
fatal("Unable to open %s",argv[2]);
}
change_max_BaseMatrix_kbytes(kbyte);
weak = read_MappedCloneSet(in);
synchronise_MappedCloneSets(trusted,weak);
/* fprintf(stderr,"score for 2,2 is %d\n",MappedCloneSet_match(weak,trusted,2,2,0,10,-5)); */
match = new_MappedCloneMatch(weak,trusted,match_score,mismatch_score);
fprintf(stderr,"Match matrix calculated\n");
if( strcmp(alg_string,"global") == 0 ) {
pal = PackAln_bestmemory_CloneWise(weak,trusted,match,-query_gap_start,-query_gap_extend,-target_gap_start,-target_gap_extend,spread,-query_switch_cost,NULL);
alb = convert_PackAln_to_AlnBlock_CloneWise(pal);
} else if ( strcmp(alg_string,"local") == 0 ) {
pal = PackAln_bestmemory_LocalCloneWise(weak,trusted,match,-query_gap_start,-query_gap_extend,-target_gap_start,-target_gap_extend,spread,-query_switch_cost,NULL);
alb = convert_PackAln_to_AlnBlock_LocalCloneWise(pal);
} else {
/* keep gcc happy */
pal = NULL;
alb = NULL;
fatal("Not a proper algorithm string %s",alg_string);
}
if( show_path ) {
extended_path(alb,weak,trusted,stdout);
fprintf(stdout,"%s\n",divide_string);
}
if( show_zip ) {
debug_zip(alb,weak,trusted,stdout);
fprintf(stdout,"%s\n",divide_string);
}
if( show_alb ) {
mapped_ascii_AlnBlock(alb,id,1,stdout);
fprintf(stdout,"%s\n",divide_string);
}
if( show_pal ) {
show_simple_PackAln(pal,stdout);
fprintf(stdout,"%s\n",divide_string);
}
return 0;
}
int main(int argc,char ** argv)
{
int i;
DPRunImpl * dpri = NULL;
GeneModelParam * gmp = NULL;
GeneModel * gm = NULL;
FILE * ifp;
SeqAlign * al;
PairBaseSeq * pbs;
ComplexSequenceEval * splice5;
ComplexSequenceEval * splice3;
ComplexSequence * cseq;
CompMat * score_mat;
CompProb * comp_prob;
RandomModel * rm;
PairBaseCodonModelScore * codon_score;
PairBaseModelScore* nonc_score;
PairBaseCodonModelScore * start;
PairBaseCodonModelScore * stop;
SyExonScore * exonscore;
PackAln * pal;
AlnBlock * alb;
Genomic * genomic;
GenomicRegion * gr;
GenomicRegion * gr2;
Protein * trans;
StandardOutputOptions * std_opt;
ShowGenomicRegionOptions * sgro;
char * dump_packaln = NULL;
char * read_packaln = NULL;
FILE * packifp = NULL;
boolean show_trans = 1;
boolean show_gene_raw = 0;
ct = read_CodonTable_file(codon_table);
/*
score_mat = read_Blast_file_CompMat("blosum62.bla");
comp_prob = CompProb_from_halfbit(score_mat);
*/
rm = default_RandomModel();
comp_prob = read_Blast_file_CompProb("wag85");
fold_column_RandomModel_CompProb(comp_prob,rm);
dpri = new_DPRunImpl_from_argv(&argc,argv);
if( dpri == NULL ) {
fatal("Unable to build DPRun implementation. Bad arguments");
}
gmp = new_GeneModelParam_from_argv(&argc,argv);
std_opt = new_StandardOutputOptions_from_argv(&argc,argv);
sgro = new_ShowGenomicRegionOptions_from_argv(&argc,argv);
dump_packaln = strip_out_assigned_argument(&argc,argv,"dump");
read_packaln = strip_out_assigned_argument(&argc,argv,"recover");
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 2 ) {
show_help(stdout);
exit(12);
}
if((gm=GeneModel_from_GeneModelParam(gmp)) == NULL ) {
fatal("Could not build gene model");
}
codon_score = make_PairBaseCodonModelScore(comp_prob);
nonc_score = make_PairBaseModelScore();
splice5 = ComplexSequenceEval_from_pwmDNAScore_splice(gm->splice5score);
splice3 = ComplexSequenceEval_from_pwmDNAScore_splice(gm->splice3score);
if((ifp = openfile(argv[1],"r")) == NULL ) {
fatal("Could not open file %s",argv[1]);
}
al = read_fasta_SeqAlign(ifp);
assert(al);
assert(al->len == 2);
assert(al->seq[0]->len > 0);
assert(al->seq[1]->len > 0);
/* write_fasta_SeqAlign(al,stdout);*/
pbs = new_PairBaseSeq_SeqAlign(al);
if( read_packaln == NULL ) {
cseq = ComplexSequence_from_PairBaseSeq(pbs,splice5,splice3);
}
start = make_start_PairBaseCodonModelScore(ct);
stop = make_stop_PairBaseCodonModelScore(ct);
/* show_PairBaseCodonModelScore(stop,ct,stdout); */
/*
for(i=0;i<pbs->anchor->len;i++) {
printf("%3d %c For %-6d %-6d %c Rev %-6d %-6d\n",i,pbs->anchor->seq[i],
CSEQ_PAIR_5SS(cseq,i),CSEQ_PAIR_3SS(cseq,i),
char_complement_base(pbs->anchor->seq[i]),
CSEQ_REV_PAIR_5SS(cseq,i),CSEQ_REV_PAIR_3SS(cseq,i));
}
*/
/* show_ComplexSequence(cseq,stdout);
*/
exonscore = SyExonScore_flat_model(100,150,0.1,1.0);
/*
for(i=0;i<cseq->length;i++) {
fprintf(stdout,"%d PairSeq is %d score %d\n",i,CSEQ_PAIR_PAIRBASE(cseq,i),nonc_score->base[CSEQ_PAIR_PAIRBASE(cseq,i)]);
}
exit(0);
*/
if( read_packaln != NULL ) {
packifp = openfile(read_packaln,"r");
if( packifp == NULL ) {
fatal("File %s is unopenable - ignoring dump command",dump_packaln);
} else {
pal = read_simple_PackAln(packifp);
}
} else {
pal = PackAln_bestmemory_SyWise20(exonscore,cseq,codon_score,nonc_score,start,stop,Probability2Score(1.0/100.0),Probability2Score(1.0/10000.0),Probability2Score(1.0/10.0),NULL,dpri);
}
alb = convert_PackAln_to_AlnBlock_SyWise20(pal);
if( dump_packaln != NULL ) {
packifp = openfile(dump_packaln,"w");
if( packifp == NULL ) {
warn("File %s is unopenable - ignoring dump command",dump_packaln);
} else {
show_simple_PackAln(pal,packifp);
}
}
show_score_sequence(alb,pbs,nonc_score,stdout);
/*
show_StandardOutputOptions(std_opt,alb,pal,"//",stdout);
*/
genomic = Genomic_from_Sequence(al->seq[0]);
gr = new_GenomicRegion(genomic);
gr2 = new_GenomicRegion(genomic);
add_Genes_to_GenomicRegion_new(gr,alb);
show_GenomicRegionOptions(sgro,gr,ct,"//",stdout);
return 0;
}
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;
}
