static double get_n_unique_multisets (
int n, /* size of multisets */
int m /* number of item types */
)
{
int i, j, k;
double **f; /* dynamic programming array */
create_2array(f, double, n+1, m+1)
/* initialize */
for (i=0; i<=n; i++) {
for (j=0; j<=m; j++) {
if (i==0 || j==1) {
f[i][j] = 1;
} else if (i==1) {
f[i][j] = j;
} else {
f[i][j] = 0;
}
}
}
/* fill in array */
for (j=2; j<=m; j++)
for (i=2; i<=n; i++)
for (k=0; k<=i; k++)
f[i][j] += f[k][j-1];
fprintf(stderr, "unique multisets (%d %d) %g\n", n, m, f[n][m]);
free_2array(f, n);
return f[n][m];
} /* get_n_unique_multisets */
SEQ_T *gendb(
FILE *out, // Output stream; return output if null.
int type, // Type of alphabet.
// 0: protein w/ambigs
// 1: dna w/ambigs
// 2: codons
// 3: dna w/o ambigs
// 4: protein w/o ambigs
char *bfile, // Name of Markov model file.
int use_order,// Order of Markov model to use.
double *f, // model; 0-order model used if bfile==NULL.
int nseqs, // Number of sequences.
int min, // Shortest sequence.
int max, // Longest sequence.
int seed // Random seed.
)
{
char *alph; // alphabet
double *def_f; // letter or codon frequencies
double *cum; // letter/codon cumulative distr.
char **letters; // letters/codons to print
int r; // number of letters/codons */
int c; // length of letter/codon strings */
int order;
// Get the letters and alphabet stuff.
letters = get_letters(type, &alph, &r, &c, &def_f);
if (f == NULL) f = def_f;
// Get the cumulative distribution(s).
cum = get_cum_distr(bfile, f, alph, r, use_order, &order);
// Print the random sequences.
SEQ_T *seq = print_random_seqs(out, seed, nseqs, min, max, letters, r, c, order, cum);
if (out) {
fflush(out);
}
myfree(cum);
free_2array(letters, r);
myfree(def_f);
return(seq);
} // gendb
double *llr_distr(
int A, /* dimension of discrete distribution */
double *dd, /* discrete distribution */
int N, /* number of samples */
int desired_range, /* desired range for scaled LLR */
double frac, /* fraction of scores to use */
double *alpha, /* scale factor for scaled LLR */
int *offset, /* prob[0] = prob(offset) */
int *range /* range for scaled LLR */
)
{
int i; /* index over alphabet */
int n; /* index over samples */
int k; /* other index */
int I; /* LLR */
double dd_sum; /* sum of dd */
int **IP; /* I'_i[n] */
int *minI=NULL; /* minimum intermediate value of I */
int *maxI=NULL; /* maximum intermediate value of I */
int Irange; /* maxI-minI+1 */
double logNfact; /* log N! */
double **logP; /* log P_i[n] */
double **logSP; /* log script_P[# samples][LLR] */
double *prob=NULL; /* final probability distribution */
double min, max, min_dd;
/* create space for IP, P, minI and maxI */
create_2array(IP, int, A, N+1);
create_2array(logP, double, A, N+1);
Resize(minI, N+1, int);
Resize(maxI, N+1, int);
/* make sure distribution sums to 1.0 and has no 0's */
for (i=dd_sum=0; i<A; i++) dd_sum += dd[i] + EPSILON;
for (i=0; i<A; i++) dd[i] = (dd[i]+EPSILON)/dd_sum;
/* compute N! */
logNfact = 0;
for (i=2; i<=N; i++) logNfact += log(i);
/* get estimates of minimum and miximum values of llr */
for (i=0, min_dd=1; i<A; i++) min_dd = MIN(min_dd, dd[i]);
max = NINT(-N * log(min_dd));
for (i=min=0; i<A; i++) min += dd[i]*N*(log(dd[i]) - log(dd[i]));
min = NINT(min);
/*printf("min = %f max = %f\n", min, max);*/
/* set alpha to achieve the desired range */
*alpha = desired_range/((max-min));
/* *alpha = NINT(((int)desired_range)/((max-min)));
if (*alpha < 1) *alpha = 1;*/
/*fprintf(stderr, "range %d max %f min %f alpha = %f\n",desired_range, max, min, *alpha);*/
/* compute I', P, minI and maxI */
for (n=0; n<=N; n++) minI[n] = maxI[n] = 0;
for (i=0; i<A; i++) { /* index over alphabet */
double logdd = LOG(dd[i]); /* log(dd[i]) */
IP[i][0] = 0; /* I'_i(0) */
logP[i][0] = 0; /* log P_i(0) */
for (n=1; n<=N; n++) { /* index over samples */
IP[i][n] = NINT(*alpha*n*log(n/(N*dd[i]))); /* I'_i(n) */
logP[i][n] = logP[i][n-1] + logdd - log(n); /* log P_i(n) */
for (k=1; k<=n; k++) { /* index over samples of new */
minI[n] = MIN(minI[n], minI[n-k] + IP[i][k]);
maxI[n] = MAX(maxI[n], maxI[n-k] + IP[i][k]);
}
}
}
/* get overall minI and maxI */
for (n=1; n<=N; n++) {
/*printf("minI[%d] %d maxI[%d] %d\n", n, minI[n], n, maxI[n]);*/
minI[0] = MIN(minI[0], minI[n]); /* min for intermediates */
maxI[0] = MAX(maxI[0], maxI[n]); /* max for intermediates */
minI[n] = LOGZEROI;
maxI[n] = 0;
}
Irange = maxI[0] - minI[0] + 2;
*offset = minI[0] - 1; /* I offset: I=-1 is array 0 */
/*printf("minI %d maxI %d Irange %d\n", minI[0], maxI[0], Irange);*/
minI[0] = LOGZEROI;
maxI[0] = 0;
/* create script_P arrays with enough space for intermediate calculations */
create_2array(logSP, double, N+1, Irange+1);
/* clear intermediate probability array */
for (n=0; n<=N; n++) for(I=0; I<Irange; I++) logSP[n][I] = LOGZERO;
/* init probability array for first letter in alphabet */
for (n=0; n<=N; n++) {
I = IP[0][n] - *offset; /* offset I */
logSP[n][I] = logNfact + logP[0][n]; /* init */
minI[n] = maxI[n] = I;
}
/* compute probabilities recursively */
for (i=1; i<A; i++) { /* index over (rest of) alphabet */
for (n=N; n>=0; n--) { /* index over samples */
for (k=1; k<=n; k++) { /* index over samples of new letter */
int min = minI[n-k];
int max = MAX(min, maxI[n-k] - (1-frac)*(maxI[n-k]-minI[n-k]+1));
/*printf("min %d maxI %d max %d\n", min, maxI[n-k], max);*/
for (I=min; I<=max; I++) { /* index over I */
if (logSP[n-k][I] > LOGZERO) {
/*printf("i %d old: %d %d new: %d %d\n", i, n-k, I, n,I+IP[i][k]);*/
logSP[n][I+IP[i][k]] =
LOGL_SUM(logSP[n][I+IP[i][k]], logP[i][k] + logSP[n-k][I]);
}
}
/* get current minimum and maximum I in intermediate arrays */
minI[n] = MIN(minI[n], minI[n-k]+IP[i][k]);
maxI[n] = MAX(maxI[n], maxI[n-k]+IP[i][k]);
}
if (n==N && i==A-1) break; /* all done */
}
}
/* compute range */
/*printf("minI[N] %d maxI[N] %d\n", minI[N], maxI[N]);*/
*range = maxI[N] - minI[N];
/* move to probability array with prob(offset) in position 0 */
*offset += minI[N]; /* prob[0] = prob(offset) */
Resize(prob, *range+2, double);
for (I=minI[N]; I<=maxI[N]; I++) prob[I-minI[N]] = logSP[N][I];
/*fprintf(stderr, "N= %d range= %d offset= %d alpha= %f\n", N, *range,
*offset, *alpha);*/
/* free up space */
free_2array(IP, A);
free_2array(logP, A);
free_2array(logSP, N+1);
myfree(minI);
myfree(maxI);
return prob;
} /* llr_distr */
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);
}
