AlnBlock * Align_Sequences_ProteinBlockAligner(Sequence * one,Sequence * two,CompMat * comp,int bentry,int bexit,int b1exit,int b_self,int b_on,DPRunImpl * dpri)
{
ComplexSequence * cone=NULL;
ComplexSequence * ctwo=NULL;
AlnBlock * alb= NULL;
PackAln * pal=NULL;
ComplexSequenceEvalSet * evalfunc = NULL;
if( one == NULL || two == NULL || comp == NULL ) {
warn("Passed in NULL objects into Align_Sequences_ProteinSmithWaterman!");
return NULL;
}
if( one->type != SEQUENCE_PROTEIN ) {
warn("Sequence %s is not typed as protein... ignoring!\n",one->name);
}
if( two->type != SEQUENCE_PROTEIN ) {
warn("Sequence %s is not typed as protein... ignoring!\n",two->name);
}
evalfunc = default_aminoacid_ComplexSequenceEvalSet();
cone = new_ComplexSequence(one,evalfunc);
if( cone == NULL )
goto cleanup;
ctwo = new_ComplexSequence(two,evalfunc);
if( ctwo == NULL )
goto cleanup;
pal = PackAln_bestmemory_ProteinBlockAligner(cone,ctwo,comp,bentry,b1exit,b_on,b_self,bexit,NULL,dpri);
if( pal == NULL )
goto cleanup;
alb = convert_PackAln_to_AlnBlock_ProteinSW(pal);
goto cleanup;
cleanup :
if( cone != NULL )
free_ComplexSequence(cone);
if( ctwo != NULL )
free_ComplexSequence(ctwo);
if( pal != NULL )
free_PackAln(pal);
if( evalfunc != NULL )
free_ComplexSequenceEvalSet(evalfunc);
return alb;
}
cDNADB * new_cDNADB_from_single_seq(cDNA * seq)
{
ComplexSequence * cs,*cs_rev;
Sequence * temp;
ComplexSequenceEvalSet * cses;
cses = default_cDNA_ComplexSequenceEvalSet();
cs = new_ComplexSequence(seq->baseseq,cses);
temp = reverse_complement_Sequence(seq->baseseq);
cs_rev = new_ComplexSequence(temp,cses);
free_Sequence(temp);
free_ComplexSequenceEvalSet(cses);
return new_cDNADB_from_forrev_cseq(cs,cs_rev);
}
ComplexSequence * init_cDNADB(cDNADB * cdnadb,int * return_status)
{
ComplexSequence * cs;
Sequence * seq;
if( cdnadb->is_single_seq == TRUE) {
*return_status = DB_RETURN_OK;
cdnadb->done_forward = TRUE;
return hard_link_ComplexSequence(cdnadb->forw);
}
/* is a seq db */
seq = init_SequenceDB(cdnadb->sdb,return_status);
if( seq == NULL || *return_status == DB_RETURN_ERROR || *return_status == DB_RETURN_END ) {
return NULL; /** error already reported **/
}
if( force_to_dna_Sequence(seq,cdnadb->error_tol,NULL) == FALSE ) {
warn("first sequence below error level, have to fail at the moment. Ooops...");
free_Sequence(seq);
*return_status = DB_RETURN_ERROR;
return NULL;
}
cdnadb->current = seq;
cdnadb->done_forward = TRUE;
cs = new_ComplexSequence(seq,cdnadb->cses);
if( cs == NULL ) {
warn("Cannot make initial ComplexSequence. Unable to error catch this. Failing!");
*return_status = DB_RETURN_ERROR;
return NULL;
}
return cs;
}
int main(int argc,char ** argv)
{
Sequence * seq;
ComplexSequence * cs;
ComplexSequenceEvalSet * cset;
GeneStats * st;
GeneModel * gm;
GeneModelParam * gp;
FILE * ifp;
gp = std_GeneModelParam();
seq = read_fasta_file_Sequence("../../test_data/human.genomic");
ifp = openfile("gene.stat","r");
st = read_GeneStats(ifp);
/* dump_GeneStats(st,stdout); */
fflush(stdout);
gm = GeneModel_from_GeneStats(st,gp);
show_GeneModel(gm,stdout);
fflush(stdout);
cset = new_ComplexSequenceEvalSet_from_GeneModel(gm);
cs = new_ComplexSequence(seq,cset);
show_ComplexSequence(cs,stdout);
}
ComplexSequence * evaluate_ComplexSequence_Genomic(Genomic * gen,ComplexSequenceEvalSet * cses,int score_for_repeat,int score_for_cds_in_repeat)
{
int i,j;
ComplexSequence * out;
if( cses == NULL || cses->type != SEQUENCE_GENOMIC ) {
warn("ComplexSequenceEvalSet is not valid for genomic!");
return NULL;
}
assert(gen);
assert(gen->baseseq);
assert(gen->baseseq->seq);
out = new_ComplexSequence(gen->baseseq,cses);
if( out == NULL ) {
return NULL;
}
for(i=0;i<gen->len;i++) {
for(j=gen->repeat[i]->start;j<gen->repeat[i]->end;j++) {
if( j >= gen->baseseq->len ) {
warn("Overran sequence - j position %d, sequence length %d on repeat %d",j,gen->baseseq->len,i);
break;
}
CSEQ_GENOMIC_REPEAT(out,j) = score_for_repeat;
CSEQ_GENOMIC_CDSPOT(out,j) = score_for_cds_in_repeat;
}
}
/*
for(i=0;i<gen->baseseq->len;i++)
fprintf(stderr,"At position %6d %d\n",CSEQ_GENOMIC_CDSPOT(out,j));
*/
return out;
}
ComplexSequence * reload_cDNADB(ComplexSequence * last,cDNADB * cdnadb,int * return_status)
{
ComplexSequence * cs;
Sequence * seq,*temp;
/** free Complex Sequence **/
if ( last != NULL ) {
free_ComplexSequence(last);
}
if( cdnadb->forward_only == TRUE) {
temp = reload_SequenceDB(NULL,cdnadb->sdb,return_status);
if ( *return_status != DB_RETURN_OK ) {
return NULL;
}
cs = new_ComplexSequence(temp,cdnadb->cses);
return cs;
}
if( cdnadb->is_single_seq == TRUE ) {
if( cdnadb->done_forward == TRUE ) {
*return_status = DB_RETURN_OK;
cdnadb->done_forward = FALSE;
return hard_link_ComplexSequence(cdnadb->rev);
} else {
*return_status = DB_RETURN_END;
return NULL;
}
}
/** standard database **/
if( cdnadb->done_forward == TRUE ) {
if( cdnadb->current == NULL ) {
warn("A bad internal cDNA db error - unable to find current sequence in db reload");
*return_status = DB_RETURN_ERROR;
return NULL;
}
temp = reverse_complement_Sequence(cdnadb->current);
if( temp == NULL ) {
warn("A bad internal cDNA db error - unable to reverse complements current");
*return_status = DB_RETURN_ERROR;
return NULL;
}
cs = new_ComplexSequence(temp,cdnadb->cses);
if( cs == NULL ) {
warn("A bad internal cDNA db error - unable to make complex sequence in db reload");
*return_status = DB_RETURN_ERROR;
return NULL;
}
free_Sequence(temp);
cdnadb->done_forward = FALSE;
return cs;
}
/* otherwise we have to get a new sequence */
seq = reload_SequenceDB(NULL,cdnadb->sdb,return_status);
if( seq == NULL || *return_status == DB_RETURN_ERROR || *return_status == DB_RETURN_END ) {
return NULL; /** error already reported **/
}
uppercase_Sequence(seq);
if( force_to_dna_Sequence(seq,cdnadb->error_tol,NULL) == FALSE ) {
if( cdnadb->error_handling == CDNADB_READ_THROUGH ) {
warn("Unable to map %s sequence to a cDNA sequence, but ignoring that for the moment...",seq->name);
free_Sequence(seq);
return reload_cDNADB(NULL,cdnadb,return_status);
} else {
warn("Unable to map %s sequence to a cDNA sequence. Failing",seq->name);
*return_status = DB_RETURN_ERROR;
return NULL;
}
}
cs = new_ComplexSequence(seq,cdnadb->cses);
if( cs == NULL ) {
if( cdnadb->error_handling == CDNADB_READ_THROUGH ) {
warn("Unable to map %s sequence to a cDNA sequence, but ignoring that for the moment...",seq->name);
free_Sequence(seq);
return reload_cDNADB(NULL,cdnadb,return_status);
} else {
warn("Unable to map %s sequence to a cDNA sequence. Failing",seq->name);
*return_status = DB_RETURN_ERROR;
return NULL;
}
}
cdnadb->current = free_Sequence(cdnadb->current);
cdnadb->current = seq;
cdnadb->done_forward= TRUE;
return cs;
}
AlnBlock * Align_Sequences_ProteinSmithWaterman(Sequence * one,Sequence * two,CompMat * comp,int gap,int ext,DPRunImpl * dpri)
{
AlnBlock * out = NULL;
ComplexSequenceEvalSet * evalfunc = NULL;
ComplexSequence * query_cs = NULL;
ComplexSequence * target_cs = NULL;
PackAln * pal = NULL;
if( one == NULL || two == NULL || comp == NULL ) {
warn("Passed in NULL objects into Align_Sequences_ProteinSmithWaterman!");
return NULL;
}
if( one->type != SEQUENCE_PROTEIN ) {
warn("Sequence %s is not typed as protein... ignoring!\n",one->name);
}
if( two->type != SEQUENCE_PROTEIN ) {
warn("Sequence %s is not typed as protein... ignoring!\n",two->name);
}
if( gap > 0 || ext > 0 ) {
warn("Gap penalties %d,%d only make sense if they are negative",gap,ext);
return NULL;
}
evalfunc = default_aminoacid_ComplexSequenceEvalSet();
query_cs = new_ComplexSequence(one,evalfunc);
if( query_cs == NULL )
goto cleanup;
target_cs = new_ComplexSequence(two,evalfunc);
if( target_cs == NULL )
goto cleanup;
pal = PackAln_bestmemory_ProteinSW(query_cs,target_cs,comp,gap,ext,NULL,dpri);
if( pal == NULL )
goto cleanup;
out = convert_PackAln_to_AlnBlock_ProteinSW(pal);
goto cleanup;
cleanup :
if( query_cs != NULL )
free_ComplexSequence(query_cs);
if( target_cs != NULL )
free_ComplexSequence(target_cs);
if( pal != NULL )
free_PackAln(pal);
if( evalfunc != NULL )
free_ComplexSequenceEvalSet(evalfunc);
return out;
}
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)
{
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)
{
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)
{
int i;
SequenceSet * in;
Sequence * trans;
ThreeStateDB * tsd;
DPRunImpl * dpri;
CodonTable * ct;
int return_status;
ThreeStateModel * tsm;
ThreeStateScore * tss;
Protein * hmmp;
ComplexSequence * cs;
ComplexSequenceEvalSet * cses;
PackAln * pal;
AlnBlock * alb;
int show_align = 0;
int show_alb = 0;
int show_verbose = 1;
int show_trans = 0;
ct = read_CodonTable_file("codon.table");
cses = default_aminoacid_ComplexSequenceEvalSet();
dpri = new_DPRunImpl_from_argv(&argc,argv);
strip_out_boolean_def_argument(&argc,argv,"pretty",&show_align);
strip_out_boolean_def_argument(&argc,argv,"alb",&show_alb);
strip_out_boolean_def_argument(&argc,argv,"trans",&show_trans);
if( argc != 3 ) {
show_help(stdout);
exit(63);
}
in = read_fasta_SequenceSet_file(argv[1]);
tsd = HMMer2_ThreeStateDB(argv[2]);
assert(in);
assert(tsd);
assert(in->len == 2);
trans = translate_Sequence(in->set[0],ct);
if( show_trans ) {
write_fasta_Sequence(trans,stdout);
}
cs = new_ComplexSequence(trans,cses);
open_ThreeStateDB(tsd);
while( (tsm = read_TSM_ThreeStateDB(tsd,&return_status)) != NULL ) {
fold_RandomModel_into_ThreeStateModel(tsm,tsm->rm);
set_startend_policy_ThreeStateModel(tsm,TSM_local,10,1.0);
tss = ThreeStateScore_from_ThreeStateModel(tsm);
hmmp = pseudo_Protein_from_ThreeStateModel(tsm);
pal = PackAln_bestmemory_ThreeStateLoop(tss,cs,NULL,dpri);
alb = convert_PackAln_to_AlnBlock_ThreeStateLoop(pal);
if( show_alb ) {
show_flat_AlnBlock(alb,stdout);
}
if( show_align ) {
write_pretty_seq_align(alb,hmmp->baseseq,trans,15,50,stdout);
}
if( show_verbose ) {
show_verbose_evo(alb,tsm,in->set[0],in->set[1],ct,stdout);
}
}
}
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;
}
