Exemplo n.º 1
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;
}
Exemplo n.º 2
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);
    }
  } 
 
}