/***********************************************************************
* Apply a pseudocount to the motif pspm.
***********************************************************************/
void apply_pseudocount_to_motif
(MOTIF_T* motif, ARRAY_T *background, double pseudocount)
{
int pos, letter, len, asize, sites;
double prob, count, total;
ARRAY_T *temp;
// no point in doing work when it makes no difference
if (pseudocount == 0) return;
assert(pseudocount > 0);
// motif dimensions
asize = alph_size(motif->alph, ALPH_SIZE);
len = motif->length;
// create a uniform background if none is given
temp = NULL;
if (background == NULL) {
temp = allocate_array(asize);
get_uniform_frequencies(motif->alph, temp);
background = temp;
}
// calculate the counts
sites = (motif->num_sites > 0 ? motif->num_sites : DEFAULT_SITE_COUNT);
total = sites + pseudocount;
for (pos = 0; pos < len; ++pos) {
for (letter = 0; letter < asize; ++letter) {
prob = get_matrix_cell(pos, letter, motif->freqs);
count = (prob * sites) + (pseudocount * get_array_item(letter, background));
prob = count / total;
set_matrix_cell(pos, letter, prob, motif->freqs);
}
}
if (temp) free_array(temp);
}
/*
* When the parser has been selected do some processing
*/
static void parser_selected(MREAD_T *mread) {
ALPH_T alph;
MFORMAT_T* format;
format = mread->formats;
// get the alphabet
alph = format->get_alphabet(mread->formats->data);
// get the background
if (format->get_bg(format->data, &(mread->motif_bg))) {
normalize_subarray(0, alph_size(alph, ALPH_SIZE), 0.0, mread->motif_bg);
resize_array(mread->motif_bg, alph_size(alph, ALL_SIZE));
calc_ambigs(alph, FALSE, mread->motif_bg);
} else {
mread->motif_bg = get_uniform_frequencies(alph, mread->motif_bg);
}
set_pseudo_bg(mread);
}
/*
* Sets the background for the pseudo-counts
* but requires the alphabet to do it.
*/
static void set_pseudo_bg(MREAD_T *mread) {
ALPH_T alph;
alph = mread->formats->get_alphabet(mread->formats->data);
assert(alph != INVALID_ALPH);
if (!mread->other_bg) {
// no change to other_bg
if (mread->other_bg_src == NULL ||
strcmp(mread->other_bg_src, "--nrdb--") == 0) {
mread->other_bg = get_nrdb_frequencies(alph, NULL);
} else if (strcmp(mread->other_bg_src, "--uniform--") == 0) {
mread->other_bg = get_uniform_frequencies(alph, NULL);
} else if (strcmp(mread->other_bg_src, "--motif--") == 0 ||
strcmp(mread->other_bg_src, "motif-file") == 0) {
// motif_bg is loaded elsewhere
} else {
mread->other_bg = get_file_frequencies(&(alph), mread->other_bg_src, NULL);
}
}
if (mread->other_bg) mread->pseudo_bg = mread->other_bg;
else mread->pseudo_bg = mread->motif_bg;
}
ARRAY_T* ramen_load_background() {
ALPH_T alph = DNA_ALPH;
ARRAY_T* freqs;
switch (args.bg_format) {
case UNIFORM_BG:
freqs = get_uniform_frequencies(alph, NULL);
break;
case MOTIF_BG:
//We've previously read in the freqs when we read the motif list
freqs = motifs.bg_freqs; //so we're just copying a pointer address so that we use them.
break;
case FILE_BG:
freqs = get_file_frequencies(&alph, args.bg_filename, NULL);
break;
default:
die("Illegal background option");
freqs = NULL; // make compiler happy
}
return freqs;
}
