void calc_entropy (
MODEL *model, /* the model */
DATASET *dataset /* the dataset */
)
{
int i, j;
double *rentropy = model->rentropy; /* IC of each column */
double ent = 0; /* entropy per column */
double rel = 0; /* relative entropy per col. */
int alength = dataset->alength; /* length of alphabet */
double *back = dataset->back; /* background model freqs */
THETA obs = model->obs; /* observed frequencies */
int w = model->w; /* width of motif */
int N = model->nsites_dis; /* number of sites */
double log_pop; /* log product of col p-value */
double max_ic = LOG(alength)/LOG(2); // maximum IC per column
//double e = (alength-1) / (2 * LOG(2) * N); // small sample correction
double ic = 0; // "corrected" IC
/* calculate the relative entropy of each column in motif */
model->llr = log_pop = 0;
for (i=0; i<w; i++) { /* position */
double llr; /* log likelihood ratio of column */
rentropy[i] = 0.0;
double H = 0; // negative entropy in this column
for (j=0; j<alength; j++) { /* alphabet letter */
double f = obs(i, j); /* motif freq */
double p = back[j]; /* background freq */
double h = f ? f * LOG2(f) : 0; // entropy of current letter
rel += p ? f * LOG2(p) : 0; /* total relative entropy */
ent += h; /* total entropy */
H += -h; // negative entropy in this column
rentropy[i] += (f && p) ? f * LOG(f/p) : 0;
} /* alphabet letter */
llr = N * rentropy[i]; /* log likelihood ratio */
RND(llr, RNDDIG, llr); /* round to RNDDIG places */
model->llr += llr; /* llr for model */
log_pop += get_llr_pv(llr, N, 1, LLR_RANGE, 1.0, alength, back);
rentropy[i] /= LOG(2);
// ic += MAX(0, (max_ic - (H + e)));
ic += max_ic - H;
} /* position in motif */
/* compute the log E-value of the motif */
model->logev = get_log_sig(-log_pop, model->mtype, w, N, N, model->invcomp,
model->pal, dataset);
model->rel = (ent - rel)/w; /* compute rel. entropy/col */
// LOGO total information content
RND(ic, RNDDIG, ic); // round to RNDDIG places
model->ic = ic;
} /* calc_entropy */
/**
* search_matrix_partition
*
* Searches the specified partition of the matrix, for the S_POINT with the
* smallest significance value.
*
* \return The S_POINT with the smallest significance value. Returns NULL if no
* S_POINT (in the partition) had a significance less than BIG.
*/
static S_POINT *search_matrix_partition (
SP_MATRIX *sp_mat, ///< The matrix containing the partition of interest
DATASET *data, ///< Sequence dataset.
MODEL *model, ///< The nascent motif model. Contains parameters needed
///< in order to calculate significance of scores
PARTITION *part ///< The coordinates of the partition within the matrix
) {
// Consider each S_POINT in the partition. Find the S_POINT with the
// smallest significance value...
double curr_best_sig = BIG;
S_POINT *curr_best_sp = NULL;
int curr_w, curr_n;
for (curr_w = part->min_w; curr_w <= part->max_w; curr_w++) {
assert (curr_w <= get_max_width(sp_mat));
for (curr_n = part->min_n; curr_n <= part->max_n; curr_n++) {
assert (curr_n <= get_max_nsites(sp_mat));
int w_idx = curr_w - get_min_width(sp_mat);
int n_idx = curr_n - get_min_nsites(sp_mat);
// Get the current S_POINT from the SP_MATRIX:
S_POINT *curr_sp = get_spoint(sp_mat, w_idx, n_idx);
// Only consider the current s_point if it has been initialised. Note
// that (spoint initialised <==> contains non-empty cons0 string):
double curr_sig = BIG; // s_point is non-significant by default.
if ((curr_sp->cons0 != NULL) && (strcmp(curr_sp->cons0, "") != 0)) {
curr_sig = get_log_sig(
curr_sp->score,
model->mtype,
curr_sp->w0,
curr_sp->wgt_nsites,
curr_sp->nsites0,
model->invcomp,
model->pal,
data
);
curr_sp->sig = curr_sig;
if (curr_sig <= curr_best_sig) {
curr_best_sig = curr_sig;
curr_best_sp = curr_sp;
}
} // Only considering s_point if initialised
} // curr_n
} // curr_w
return curr_best_sp;
} // search_matrix_partition