extern void init_llr_pv_tables(
int min, /* minimum number of sites */
int max, /* maximum number of sites */
int alength, /* alphabet length */
double *back, /* background frequencies */
BOOLEAN pal /* sites are palindromes */
)
{
int nsites; /* number of sites */
/* set effective number of sites to double if pal */
if (pal) { min *= 2; max *= 2; }
if (!NO_STATUS)
fprintf(stderr,
"Initializing the motif probability tables for %d to %d sites...\n",
min, max);
/* make sure the distr table gets initialized on all nodes */
(void) get_llr_pv(0, 1, 1, LLR_RANGE, 1.0, alength, back);
for (nsites=min; nsites<=max; nsites += pal ? 2 : 1) { /* nsites */
/* allocate space for table */
(void) get_llr_pv(0, nsites, 0, LLR_RANGE, 1.0, alength, back);
if (!load_balance_llr(nsites, pal)) {
continue; /* for parallel */
}
/* create table */
if (!NO_STATUS) { fprintf(stderr, "nsites = %d\r", nsites); }
(void) get_llr_pv(0, nsites, 1, LLR_RANGE, 1.0, alength, back);
} /* nsites */
broadcast_llr(min, max, pal); /* for parallel; collect the tables */
#ifdef DEBUG
/* print results */
int n;
for (n=min; n<=max; n++) {
int I;
int w = 1;
printf("# N I llr 1-cdf\n");
for (I=0; I<=distrs[n].range[w]; I++) { /* LLR */
double m2, e2;
if (distrs[n].cdf[w][I] == LOGZERO) {
m2 = e2 = 0;
} else {
exp10_logx(distrs[n].cdf[w][I]/log(10.0), m2, e2, 1);
}
printf("%3d %3d %5.1f %3.1fe%+05.0f\n",
n, I, (distrs[n].offset[w]+I)/distrs[n].alpha, m2, e2);
} /* LLR */
}
#endif
if (!NO_STATUS)fprintf(stderr, "\nDone initializing\n");
} /* init_llr_pv_tables */
extern void em(
MODEL *model, /* the model */
DATASET *dataset, /* the dataset */
PRIORS *priors, /* the priors */
int maxiter, /* maximum number of iterations */
double distance /* stopping criterion */
)
{
int alength = dataset->alength;
THETA theta_save;
int iter; /* iteration number */
double (*E_STEP)(MODEL *, DATASET *); /* expectation step function */
double (*E_STEP0)(MODEL *, DATASET *); /* expectation step function */
/* maximization step function */
void (*M_STEP)(MODEL *, DATASET *, PRIORS *, int);
int nc = model->c; /* number of components of model */
int max_w = model->w[nc-1]; /* width of last component */
BOOLEAN converged = FALSE; /* EM has converged */
/* create a place to save old value of theta */
create_2array(theta_save, double, max_w, alength);
/* set up the correct type of EM to run */
M_STEP = m_step;
E_STEP = e_step;
E_STEP0 = e_step;
switch (model->mtype) {
case Oops:
E_STEP = e_step;
break;
case Zoops:
E_STEP = zoops_e_step;
break;
case Tcm:
E_STEP = tcm_e_step;
break;
default:
fprintf(stderr,"Unknown model type in em()! \n");
exit(1);
break;
}
/* use like_e_step to set z matrix on iteration 0 if motifs were given */
if (dataset->nmotifs > 0) {E_STEP0 = E_STEP; E_STEP = like_e_step;}
/* get the probability that a site starting at position x_ij would
NOT overlap a previously found motif; used in E_STEP.
*/
get_not_o(dataset, model->w[1], FALSE);
/* Perform EM for number of iterations or until no improvement */
for (iter=0; iter < maxiter; iter++) {
int w = model->w[nc-1]; /* width of model */
THETA theta = model->theta[nc-1]; /* final theta of last component */
if (iter > 0 && dataset->nmotifs > 0) E_STEP = E_STEP0;
if (PRINTALL) ajFmtPrintF(outf,"\niter %d\n", iter);
#ifdef PARALLEL
/* If we're running in parallel, only print from one node. */
if (mpMyID() == 0)
#endif
if ((!NO_STATUS) && ((iter % 10) == 0))
fprintf(stderr, "\rem: w=%4d, iter=%4d ", w, iter);
/* fix this later: save current contents of theta */
copy_theta(theta, theta_save, w, alength);
/* expectation step */
model->ll = E_STEP(model, dataset);
/* maximization step */
M_STEP(model, dataset, priors, iter);
/* print status if requested */
if (PRINT_LL) {
double m1, e1;
double nsites = model->lambda[1] * ps(dataset, model->w[1]);
calc_like(model, dataset);
exp10_logx(model->sig, m1, e1);
ajFmtPrintF(outf,"iter=%d w=%d ll=%8.2f e_ll=%8.2f nsites=%6.1f sig=%5.3fe%+04.0f",
iter, model->w[1], model->ll, model->e_ll, nsites, m1, e1);
}
if (PRINTALL) {
int c;
for (c=0; c<nc; c++) {
ajFmtPrintF(outf,"component %2d: lambda= %8.6f\n", c,
model->lambda[c]);
print_theta(2, model->theta[c], model->w[c], "", dataset, NULL);
print_theta(2, model->obs[c], model->w[c], "", dataset, NULL);
}
}
if (PRINT_Z) print_zij(dataset, model);
/* see if EM has converged */
converged = check_convergence(theta_save, theta, w, distance, alength,
iter, maxiter);
if (converged) {iter++; break;} /* done */
}
/* save the number of iterations (counting from zero)*/
model->iter += iter;
/* get the consensus of each component of the model */
{
THETA theta = model->theta[1];
int w = model->w[1];
char *cons = model->cons;
cons = get_consensus(theta, w, dataset, 1, MINCONS);
}
/* calculate the expected likelihood of the model */
calc_like(model, dataset);
free_2array(theta_save, max_w);
}
