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;
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 * 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);
}
}
}
