boolean build_alignment(void)
{
GeneParameter21 * gpara;
GeneModel * gm;
if( pal_file != NULL ) {
pal = read_simple_PackAln_file(pal_file);
}
if( use_new_stats == 0 ) {
gpara = GeneParameter21_wrap(gf,subs_error,indel_error,rmd,model_codon,model_splice,use_tied_model,ct,rnd_loop,cds_loop,rnd_to_model,link_loop,link_to_model);
} else {
gm = GeneModel_from_GeneStats(gs,gmp);
gpara= GeneParameter21_from_GeneModel(gm,ct,rnd_loop,cds_loop,rnd_to_model,link_loop,link_to_model,subs_error,indel_error);
}
if( gpara == NULL ) {
warn("Sorry - could not build gene parameters. Must be a bug of some sort");
return FALSE;
}
/* phased based proteins use a different source */
if( alg == GWWRAP_623P ) {
alb = AlnBlock_from_phased_protein_wrap(pro,tsm,gen,gpara->cm,rm,mat,ppp,gpara,dpri,&pal);
} else {
if( use_tsm == FALSE) {
alb = AlnBlock_from_protein_genewise_wrap(pro,gen,mat,-gap,-ext,gpara,rmd,rmd,alg,use_syn,rm,allN,startend,dpri,&pal,gwrp);
} else {
alb = AlnBlock_from_TSM_genewise_wrap(tsm,gen,gpara,rmd,rmd,use_syn,alg,allN,flat_insert,dpri,&pal,NULL);
}
}
free_GeneParameter21(gpara);
if( alb == NULL )
return FALSE;
gr = new_GenomicRegion(gen);
add_Genes_to_GenomicRegion_GeneWise(gr,gen->baseseq->offset,gen->baseseq->end,alb,use_tsm == TRUE ? tsm->name : pro->baseseq->name,pseudo,NULL);
if( use_tsm == TRUE)
mss = MatchSummarySet_from_AlnBlock_genewise(alb,tsm->name,1,gen->baseseq);
else
mss = MatchSummarySet_from_AlnBlock_genewise(alb,pro->baseseq->name,pro->baseseq->offset,gen->baseseq);
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;
}
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)
{
int i;
DPRunImpl * dpri = NULL;
GeneModelParam * gmp = NULL;
GeneModel * gm = NULL;
Sequence * seq;
RandomCodon * rc;
RandomModelDNA * rmd;
RandomCodonScore * rcs;
ComplexSequenceEval * splice5;
ComplexSequenceEval * splice3;
ComplexSequenceEvalSet * cses;
ComplexSequence * cseq;
SyExonScore * exonscore;
PackAln * pal;
AlnBlock * alb;
Genomic * genomic;
GenomicRegion * gr;
Protein * trans;
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);
ct= read_CodonTable_file("codon.table");
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");
}
seq = read_fasta_file_Sequence(argv[1]);
assert(seq);
cses = new_ComplexSequenceEvalSet_from_GeneModel(gm);
cseq = new_ComplexSequence(seq,cses);
rc = flat_RandomCodon(ct);
rmd = RandomModelDNA_std();
fold_in_RandomModelDNA_into_RandomCodon(rc,rmd);
rcs = RandomCodonScore_from_RandomCodon(rc);
exonscore = SyExonScore_flat_model(200,250,0.1,0.1);
/*
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);
*/
/*
show_RandomCodonScore(rcs,stdout);
for(i=3;i<seq->len;i++) {
fprintf(stdout,"seq %d is %c with score %d\n",i,aminoacid_from_seq(ct,seq->seq+i-2),rcs->codon[CSEQ_GENOMIC_CODON(cseq,i)]);
}
exit(0);
*/
pal = PackAln_bestmemory_StatWise10(exonscore,cseq,rcs,Probability2Score(1.0/10.0),Probability2Score(1.0/10.0),NULL,dpri);
alb = convert_PackAln_to_AlnBlock_StatWise10(pal);
mapped_ascii_AlnBlock(alb,id,1,stdout);
genomic = Genomic_from_Sequence(seq);
gr = new_GenomicRegion(genomic);
add_Genes_to_GenomicRegion_GeneWise(gr,1,seq->len,alb,"bollocks",0,NULL);
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);
}
}
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);
}
}
}