int main(int argc,char ** argv)
{
int start;
int end;
Sequence * in;
int i;
in = read_fasta_file_Sequence(argv[1]);
start = atoi(argv[2]);
end = atoi(argv[3]);
for(i = start;i<= end;i++) {
fprintf(stdout,"%d %c [%c]\n",i,in->seq[i-1],char_complement_base(in->seq[i-1]));
}
}
int main(int argc,char ** argv)
{
DnaMatchPara * para;
HitListOutputImpl * hitoutput;
HitList * hitlist;
Sequence * reference;
Sequence * swap;
Sequence * trans;
SequenceSet * amplimers;
int show_hitlist = 0;
int show_swapped = 1;
hitoutput = new_HitListOutputImpl_from_argv(&argc,argv);
para = new_DnaMatchPara_from_argv(&argc,argv);
strip_out_boolean_def_argument(&argc,argv,"hitlist",&show_hitlist);
strip_out_boolean_def_argument(&argc,argv,"swapped",&show_hitlist);
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 3 ) {
show_help(stdout);
exit(12);
}
reference = read_fasta_file_Sequence(argv[1]);
amplimers = read_fasta_SequenceSet_file(argv[2]);
hitlist = HitList_from_Sequence_SequenceSet_DNA(reference,amplimers,para);
if( show_hitlist ) {
show_HitList_HitListOutputImpl(hitoutput,hitlist,stdout);
}
swap = swapped_Sequence(reference,hitlist);
trans = translate_swapped(swap);
if( show_swapped ) {
write_fasta_Sequence(swap,stdout);
write_fasta_Sequence(trans,stdout);
}
}
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);
}
int main(int argc,char ** argv)
{
SignalMap * map;
int i;
FILE * sm;
Sequence * seq;
SignalSeq * ss;
FILE * sseqf;
PackAln * pal;
AlnBlock * alb;
DPRunImpl * dpri;
srandomdev();
sm = openfile(argv[1],"r");
dpri = new_DPRunImpl_from_argv(&argc,argv);
map = read_SignalMap(sm);
seq = read_fasta_file_Sequence(argv[2]);
sseqf = openfile(argv[3],"r");
ss = read_SignalSeq(sseqf);
assert(map != NULL);
assert(seq != NULL);
assert(ss != NULL);
pal = PackAln_bestmemory_SimpleSignalMat(ss,seq,map,-10,-2,NULL,dpri);
alb = convert_PackAln_to_AlnBlock_SimpleSignalMat(pal);
show_alignment_with_fit_SimpleSignalMat(alb,ss,seq,map,stdout);
}
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);
}
int main(int argc,char **argv)
{
int i;
AlignGeneModelParam * agmp;
GeneStats * gs;
GeneModelParam * gmp = NULL;
CompProb * comp_prob;
DnaProbMatrix * dm;
CodonTable * ct;
RandomModel * rm;
Sequence * test;
ct = read_CodonTable_file("codon.table");
rm = default_RandomModel();
comp_prob = read_Blast_file_CompProb("wag85");
gmp = new_GeneModelParam_from_argv(&argc,argv);
dm = DnaProbMatrix_from_match(0.8,NMaskType_VARIABLE);
if((gs=GeneStats_from_GeneModelParam(gmp)) == NULL ) {
fatal("Could not build gene stats");
}
agmp = std_AlignGeneModelParam(comp_prob,dm,ct,gs);
test = read_fasta_file_Sequence(argv[1]);
assert(test);
for(i=0;i<test->len;i++) {
fprintf(stdout,"%c ss5 %.6f ss3 %.6f\n",test->seq[i],prob_SpliceSiteProb(agmp->ss5,test,i),prob_SpliceSiteProb(agmp->ss3,test,i));
}
}
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 type = ALIGN_NORMAL;
DPRunImpl * dpri = NULL;
HitList * hl;
HitListOutputImpl * hloi;
Sequence * query;
Sequence * target;
Sequence * target_rev;
PairwiseShortDna * two;
LocalCisHitSet * set;
LocalCisHitSet * greedy_set;
LocalCisHitScore * lchs;
LocalCisHitSetPara * setpara;
MotifMatrixPara * mmp;
MotifMatrixScore * mms;
TransFactorMatchSet * tfms_query = NULL;
TransFactorMatchSet * tfms_target = NULL;
TransFactorMatchSet * tfms_target_rev = NULL;
int qstart = -1;
int qend = -1;
int tstart = -1;
int tend = -1;
int i;
char * temp;
DnaMatrix * dm;
DnaProbMatrix * dmp;
TransFactorBuildPara * tfbp;
TransFactorMatchPara * tfmp;
TransFactorSet * tfs;
char * motif_library = NULL;
int use_laurence = FALSE;
int use_ben = FALSE;
dmp = DnaProbMatrix_from_match(0.75,NMaskType_BANNED);
assert(dmp);
flat_null_DnaProbMatrix(dmp);
dm = DnaMatrix_from_DnaProbMatrix(dmp);
dpri = new_DPRunImpl_from_argv(&argc,argv);
hloi = new_HitListOutputImpl_from_argv(&argc,argv);
setpara = new_LocalCisHitSetPara_from_argv(&argc,argv);
mmp = new_MotifMatrixPara_from_argv(&argc,argv);
tfbp = new_TransFactorBuildPara_from_argv(&argc,argv);
tfmp = new_TransFactorMatchPara_from_argv(&argc,argv);
strip_out_integer_argument(&argc,argv,"s",&qstart);
strip_out_integer_argument(&argc,argv,"t",&qend);
strip_out_integer_argument(&argc,argv,"u",&tstart);
strip_out_integer_argument(&argc,argv,"v",&tend);
temp = strip_out_assigned_argument(&argc,argv,"motiflib");
if( temp != NULL ) {
motif_library = stringalloc(temp);
}
use_laurence = strip_out_boolean_argument(&argc,argv,"lr");
use_ben = strip_out_boolean_argument(&argc,argv,"ben");
temp = strip_out_assigned_argument(&argc,argv,"align");
if( temp != NULL ) {
if( strcmp(temp,"motif") == 0 ) {
type = ALIGN_MOTIF;
} else if ( strcmp(temp,"normal") == 0 ) {
type = ALIGN_NORMAL;
} else {
fatal("cannot recognise string %s as align type",temp);
}
}
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 3 ) {
show_help(stdout);
exit(12);
}
lchs = standard_LocalCisHitScore(NMaskType_VARIABLE);
query = read_fasta_file_Sequence(argv[1]);
target = read_fasta_file_Sequence(argv[2]);
for(i=0;i<query->len;i++) {
query->seq[i] = toupper(query->seq[i]);
}
assert(query != NULL);
assert(target != NULL);
target_rev = reverse_complement_Sequence(target);
mms = MotifMatrixScore_from_MotifMatrixPara(mmp);
if( type == ALIGN_MOTIF ) {
if( motif_library == NULL ) {
fatal("Wanted to align with motif but not motif library. Must use -motiflib");
}
if( use_laurence == TRUE ) {
tfs = read_laurence_TransFactorSet_file(motif_library);
} else if( use_ben == TRUE ) {
tfs = read_ben_IUPAC_TransFactorSet_file(motif_library);
} else {
tfs = read_TransFactorSet_file(motif_library);
}
build_TransFactorSet(tfs,tfbp);
tfms_query = calculate_TransFactorMatchSet(query,tfs,tfmp);
sort_by_start_TransFactorMatchSet(tfms_query);
tfms_target = calculate_TransFactorMatchSet(target,tfs,tfmp);
sort_by_start_TransFactorMatchSet(tfms_target);
tfms_target_rev = calculate_TransFactorMatchSet(target_rev,tfs,tfmp);
sort_by_start_TransFactorMatchSet(tfms_target);
fprintf(stdout,"Motif Set: %d in query and %d in target\n",tfms_query->len,tfms_target->len);
}
if( qstart == -1 ) {
qstart = 0;
}
if( qend == -1 ) {
qend = query->len;
}
if( tstart == -1 ) {
tstart = 0;
}
if( tend == -1 ) {
tend = target->len;
}
two = query_to_reverse_target(query,target,dm,qstart,qend,tstart,tend);
set = make_LocalCisHitSet(query,target,target_rev,two->forward,two->reverse,setpara,lchs,tfms_query,tfms_target,tfms_target_rev,mms,type == ALIGN_MOTIF ? 1 : 0,dpri);
greedy_set = greedy_weed_LocalCisHitSet(set,setpara);
hl = HitList_from_LocalCisHitSet(greedy_set);
show_HitList_HitListOutputImpl(hloi,hl,stdout);
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)
{
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;
}
