/**
* Creates a motif for a given mod using a simple frequency matrix.
*/
void create_simple_motif(SUMMARY_T* summary,
MOMO_OPTIONS_T* options,
MOD_INFO_T * mod_info) {
int i;
int j;
const char* alph_letters = summary->alph_letters;
// Create the frequency matrix
MATRIX_T* freqs = NULL;
freqs = get_count_matrix(freqs, mod_info->seq_list, NULL, options, summary);
normalize_rows(0.0, freqs);
// Create the motif
MOTIF_INFO_T* motifinfo = mm_malloc(sizeof(MOTIF_INFO_T));
motifinfo->motif = allocate_motif(mod_info->mod_name, "", summary->alph, freqs, NULL);
motifinfo->seqs = arraylst_create();
for (i = 0; i < arraylst_size(mod_info->seq_list); ++i) {
SEQ_T* seqobject = options->eliminate_repeats ? hash_get_entry_value(arraylst_get(i, mod_info->seq_list)) : arraylst_get(i, mod_info->seq_list);
arraylst_add(get_raw_sequence(seqobject), motifinfo->seqs);
}
motifinfo->fg_size = arraylst_size(mod_info->seq_list);
arraylst_add(motifinfo, mod_info->motifinfos);
// clean up
free_matrix(freqs);
}
/***********************************************************************
* Converts a list of TRANSFAC motifs to a list MEME motif.
* If the use_accession parameter is true the TRANSFAC accession
* is used as the name of the MEME motif. Otherwise the ID is used.
* Caller is responsible for freeing the returned ARRAYLST
***********************************************************************/
ARRAYLST_T *convert_transfac_motifs_to_meme_motifs(
BOOLEAN_T use_accession,
int pseudocount,
ARRAY_T *bg,
ARRAYLST_T *tfac_motifs
) {
int num_motifs = arraylst_size(tfac_motifs);
ARRAYLST_T *meme_motifs = arraylst_create_sized(num_motifs);
int motif_index = 0;
for (motif_index = 0; motif_index < num_motifs; ++motif_index) {
TRANSFAC_MOTIF_T *tfac_motif
= (TRANSFAC_MOTIF_T *) arraylst_get(motif_index, tfac_motifs);
char *name = NULL;
if (use_accession == TRUE) {
name = get_transfac_accession(tfac_motif);
if (name == NULL) {
die("No accession string found in TRANSFAC motif.");
}
}
else {
name = get_transfac_id(tfac_motif);
if (name == NULL) {
die("No ID string found in TRANSFAC motif.");
}
}
MOTIF_T *meme_motif
= convert_transfac_motif_to_meme_motif(name, pseudocount, bg, tfac_motif);
arraylst_add(meme_motif, meme_motifs);
}
return meme_motifs;
}
/*
* Loads all the currently buffered motifs into a list.
* If the file is set then this will read all the motifs in the
* file into the list. If a list is not passed then
* it will create a new one.
* returns the list.
*/
ARRAYLST_T* mread_load(MREAD_T *mread, ARRAYLST_T *motifs) {
MOTIF_T *motif;
if (motifs == NULL) motifs = arraylst_create();
while ((motif = mread_next_motif(mread)) != NULL) {
arraylst_add(motif, motifs);
}
return motifs;
}
/*************************************************************************
* Read a motif database
*************************************************************************/
static MOTIF_DB_T* read_motifs(int id, char* motif_source, char* bg_source,
ARRAY_T** bg, double pseudocount, RBTREE_T *selected, ALPH_T alph) {
// vars
int read_motifs;
MOTIF_DB_T* motifdb;
MREAD_T *mread;
MOTIF_T *motif;
ARRAYLST_T *motifs;
// open the motif file for reading
mread = mread_create(motif_source, OPEN_MFILE);
mread_set_pseudocount(mread, pseudocount);
// determine background to use
if (*bg != NULL) mread_set_background(mread, *bg);
else mread_set_bg_source(mread, bg_source);
// load motifs
read_motifs = 0;
if (rbtree_size(selected) > 0) {
motifs = arraylst_create();
while(mread_has_motif(mread)) {
motif = mread_next_motif(mread);
read_motifs++;
if (rbtree_find(selected, get_motif_id(motif))) {
arraylst_add(motif, motifs);
} else {
DEBUG_FMT(NORMAL_VERBOSE, "Discarding motif %s in %s.\n",
get_motif_id(motif), motif_source);
destroy_motif(motif);
}
}
} else {
motifs = mread_load(mread, NULL);
read_motifs = arraylst_size(motifs);
}
arraylst_fit(motifs);
if (read_motifs > 0) {
// check the alphabet
if (mread_get_alphabet(mread) != alph) {
die("Expected %s alphabet motifs\n", alph_name(alph));
}
// get the background
if (*bg == NULL) *bg = mread_get_background(mread);
} else {
fprintf(stderr, "Warning: Motif file %s contains no motifs.\n", motif_source);
}
// clean up motif reader
mread_destroy(mread);
// create motif db
motifdb = mm_malloc(sizeof(MOTIF_DB_T));
memset(motifdb, 0, sizeof(MOTIF_DB_T));
motifdb->id = id;
motifdb->source = strdup(motif_source);
motifdb->motifs = motifs;
return motifdb;
}
/*****************************************************************************
* MEME > scanned_sites_summary > scanned_sites
****************************************************************************/
void mxml_start_scanned_seq(void *ctx, char *seq_id, double log10pvalue, int site_count) {
CTX_T *data;
int *length;
struct seqinfo *seq;
data = (CTX_T*)ctx;
if (data->options & SCANNED_SITES) {
data->current_site = 0;
seq = (struct seqinfo *)rbtree_get(data->sequence_lookup, seq_id);
if (seq == NULL) {
local_error(data, "Scanned sites references unknown sequence \"%s\".\n", seq_id);
return;
}
arraylst_add(sseq_create(seq->name, seq->length, log10pvalue, site_count), data->fscope.scanned_sites);
}
}
ARRAYLST_T* load_motifs(AMA_OPTIONS_T *opts) {
ARRAYLST_T *motifs;
ARRAY_T *pos_bg_freqs, *rev_bg_freqs;
MREAD_T *mread;
MOTIF_T *motif, *motif_rc;
double range;
PSSM_T *pos_pssm, *neg_pssm;
int total_motifs;
ALPH_T *alph;
//
// Read the motifs and background model.
//
//this reads any meme file, xml, txt and html
mread = mread_create(opts->motif_filename, OPEN_MFILE);
mread_set_bg_source(mread, opts->bg_filename);
mread_set_pseudocount(mread, opts->pseudocount);
// sanity check, since the rest of the code relies on the motifs being complementable
alph = alph_hold(mread_get_alphabet(mread));
if (alph == NULL) die("Unable to determine alphabet from motifs");
if (opts->scan_both_strands && !alph_has_complement(alph)) {
opts->scan_both_strands = false;
}
if (opts->num_gc_bins > 1 && alph_size_core(alph) != 4 && alph_size_pairs(alph) != 2) {
fprintf(stderr, "Warning: The motif alphabet does not have exactly 2 complementary pairs so \"GC binning\" will be disabled.\n");
opts->num_gc_bins = 1;
}
pos_bg_freqs = mread_get_background(mread);
rev_bg_freqs = NULL;
if (opts->scan_both_strands) {
rev_bg_freqs = allocate_array(get_array_length(pos_bg_freqs));
copy_array(pos_bg_freqs, rev_bg_freqs);
complement_swap_freqs(alph, rev_bg_freqs, rev_bg_freqs);
}
// allocate memory for motifs
motifs = arraylst_create();
//
// Convert motif matrices into log-odds matrices.
// Scale them.
// Compute the lookup tables for the PDF of scaled log-odds scores.
//
range = 300; // 100 is not very good; 1000 is great but too slow
neg_pssm = NULL;
total_motifs = 0;
while (mread_has_motif(mread)) {
motif = mread_next_motif(mread);
total_motifs++;
if (rbtree_size(opts->selected_motifs) == 0 || rbtree_find(opts->selected_motifs, get_motif_id(motif)) != NULL) {
if (verbosity >= HIGH_VERBOSE) {
fprintf(stderr, "Using motif %s of width %d.\n", get_motif_id(motif), get_motif_length(motif));
}
pos_pssm =
build_motif_pssm(
motif,
pos_bg_freqs,
pos_bg_freqs,
NULL, // Priors not used
0.0L, // alpha not used
range,
opts->num_gc_bins,
true
);
//
// Note: If scanning both strands, we complement the motif frequencies
// but not the background frequencies so the motif looks the same.
// However, the given frequencies are used in computing the p-values
// since they represent the frequencies on the negative strands.
// (If we instead were to complement the input sequence, keeping the
// the motif fixed, we would need to use the complemented frequencies
// in computing the p-values. Is that any clearer?)
//
if (opts->scan_both_strands) {
motif_rc = dup_rc_motif(motif);
neg_pssm =
build_motif_pssm(
motif_rc,
rev_bg_freqs,
pos_bg_freqs,
NULL, // Priors not used
0.0L, // alpha not used
range,
opts->num_gc_bins,
true
);
destroy_motif(motif_rc);
}
arraylst_add(motif_and_pssm_create(motif, pos_pssm, neg_pssm), motifs);
} else {
if (verbosity >= HIGH_VERBOSE) fprintf(stderr, "Skipping motif %s.\n",
get_motif_id(motif));
destroy_motif(motif);
}
}
mread_destroy(mread);
free_array(pos_bg_freqs);
free_array(rev_bg_freqs);
alph_release(alph);
if (verbosity >= NORMAL_VERBOSE) {
fprintf(stderr, "Loaded %d/%d motifs from %s.\n",
arraylst_size(motifs), total_motifs, opts->motif_filename);
}
return motifs;
}
/**
* Recursive function. Creates and stores a motif using the motif-x
* algorithm until no more are left.
*/
void create_motifx_motif(ARRAYLST_T* phospho_seqs,
ARRAYLST_T* bg_seqs,
MOTIFX_STATUS_T** phospho_status,
MOTIFX_STATUS_T** bg_status,
MATRIX_T* phospho_count,
MATRIX_T* bg_count,
int* num_active,
int* num_bg_active,
char* modname,
MOD_INFO_T* mod_info,
MOMO_OPTIONS_T* options,
SUMMARY_T* summary) {
int i;
int j;
const char* alph_letters = summary->alph_letters;
// Initialize pattern, sequence count, bg sequence count, and overall score for this motif.
char* pattern = mm_malloc(options->width + 1);
for (i = 0; i < options->width; ++i) {
pattern[i] = 'X';
}
pattern[options->width] = '\0';
int* num_active_copy = mm_malloc(sizeof(int));
*num_active_copy = *num_active;
int* num_bg_active_copy = mm_malloc(sizeof(int));
*num_bg_active_copy = *num_bg_active;
double* motif_score = mm_malloc(sizeof(double));
*motif_score = 0;
// Set the pattern, num active copy, num bg active copy, motif score, and get a count of the sequences
MATRIX_T* result_count_matrix = add_to_pattern(pattern, phospho_seqs, bg_seqs, phospho_status, bg_status, num_active_copy, num_bg_active_copy, phospho_count, bg_count, motif_score, summary, options);
// If any of the characters are not X, then we have found a pattern
BOOLEAN_T found_pattern = FALSE;
for (i = 0; i < options->width; ++i) {
if (pattern[i] != 'X') {
found_pattern = TRUE;
}
}
// If there is a pattern, store the pattern and call create_motifx_motif again.
if (found_pattern) {
// fill out the rest of the pattern (e.g. if you have pattern ..ASAAA, and realize the actual pattern is A.ASAAA
for (i = 0; i < options->width; i++) {
for (j = 0; j < strlen(alph_letters); j++) {
if ((int) get_matrix_cell_defcheck(i, j, result_count_matrix) == *num_active_copy) {
pattern[i] = alph_letters[j];
}
}
}
// create the pattern name
char* pattern_name = mm_malloc(strlen(pattern) + strlen(modname) + 3);
pattern_name[0] = '\0';
strncat(pattern_name, pattern, strlen(pattern)/2);
strncat(pattern_name, "_", 1);
strncat(pattern_name, modname, strlen(modname));
strncat(pattern_name, "_", 1);
strncat(pattern_name, pattern + strlen(pattern)/2 + 1, strlen(pattern)/2);
// convert this count matrix into frequencies
normalize_rows(0.0, result_count_matrix);
// Store this motif
MOTIF_INFO_T* motifinfo = mm_malloc(sizeof(MOTIF_INFO_T));
MOTIF_T* motif = allocate_motif(pattern_name, "", summary->alph, result_count_matrix, NULL);
set_motif_nsites(motif, *num_active_copy);
motifinfo->motif = motif;
motifinfo->seqs = arraylst_create();
motifinfo->score = *motif_score;
motifinfo->fg_match = *num_active_copy;
motifinfo->fg_size = *num_active;
motifinfo->bg_match = *num_bg_active_copy;
motifinfo->bg_size = *num_bg_active;
for (i = 0; i < arraylst_size(phospho_seqs); ++i) {
MOTIFX_STATUS_T status = (*phospho_status)[i];
if (status == ACTIVE) {
SEQ_T* active_sequence = (options->eliminate_repeats) ? hash_get_entry_value(arraylst_get(i, phospho_seqs)) : arraylst_get(i, phospho_seqs);
arraylst_add(get_raw_sequence(active_sequence), motifinfo->seqs);
}
}
arraylst_add(motifinfo, mod_info->motifinfos);
// delete the sequences from this motif. turn inactive into active.
delete_sequences(phospho_status, arraylst_size(phospho_seqs));
delete_sequences(bg_status, arraylst_size(bg_seqs));
// update the count of number of actives
*num_active = *num_active - *num_active_copy;
*num_bg_active = *num_bg_active - *num_bg_active_copy;
// recalculate phospho count and bg count.
phospho_count = get_count_matrix(phospho_count, phospho_seqs, phospho_status, options, summary);
bg_count = get_count_matrix(bg_count, bg_seqs, bg_status, options, summary);
// free up space
myfree(pattern);
myfree(num_active_copy);
myfree(num_bg_active_copy);
myfree(motif_score);
myfree(pattern_name);
// try to create another motif.
create_motifx_motif(phospho_seqs,
bg_seqs,
phospho_status,
bg_status,
phospho_count,
bg_count,
num_active,
num_bg_active,
modname,
mod_info,
options,
summary);
}
// free up space
myfree(pattern);
myfree(num_active_copy);
myfree(num_bg_active_copy);
myfree(motif_score);
}
/***********************************************************************
* Read TRANSFAC motifs from a TRANSFAC file.
* Returns an arraylist of pointers to TRANSFAC_MOTIF_T
***********************************************************************/
ARRAYLST_T *read_motifs_from_transfac_file (
const char* transfac_filename // Name of TRANSFAC file or '-' for stdin IN
) {
// Create dynamic storage for motifs
ARRAYLST_T *motif_list = arraylst_create();
// Open the TRANFAC file for reading.
FILE *transfac_file = NULL;
if (open_file(
transfac_filename,
"r",
TRUE, // Allow '-' for stdin
"transfac file",
"",
&transfac_file
) == FALSE) {
exit(1);
}
// Read and parse the TRANFAC file.
int num_bases = 4;
char *line = NULL;
while ((line = getline2(transfac_file)) != NULL) {
// Split the line into an initial tag and everything else.
char *this_accession = split(line, ' ');
char *tag = line;
// Have we reached a new matrix?
if (strcmp(tag, "AC") == 0) {
trim(this_accession);
char *this_id = NULL;
char *this_name = NULL;
char *this_descr = NULL;
char *this_species = NULL;
char this_consensus[MAX_CONSENSUS_LENGTH];
STRING_LIST_T *species_list = new_string_list();
// Old versions of TRANSFAC use pee-zero; new use pee-oh.
while (strcmp(tag, "PO") != 0 && strcmp(tag, "P0") != 0) {
line = getline2(transfac_file);
if (line == NULL) {
die ("Can't find PO line for TRANSFAC matrix %s.\n", this_accession);
}
char *data = split(line, ' ');
if (data != NULL) {
trim(data);
}
tag = line;
// Store the id line.
if (strcmp(tag, "ID") == 0) {
this_id = strdup(data);
}
// Store the species line.
else if (strcmp(tag, "BF") == 0) {
add_string(data, species_list);
}
// Store the name line.
else if (strcmp(tag, "NA") == 0) {
this_name = strdup(data);
}
// Store the description line.
else if (strcmp(tag, "DE") == 0) {
this_descr = strdup(data);
}
}
// Check how many positions in the motif
// Mark current position in file
fpos_t file_position;
errno = 0;
int status = fgetpos(transfac_file, &file_position);
if (status) {
die("Error reading file %s: %s", transfac_filename, strerror(errno));
}
int num_motif_positions = 0;
while (TRUE) {
// Read till we reach the end of the counts or the end of the motif
line = getline2(transfac_file);
if (line == NULL) {
break;
}
char *data = split(line, ' ');
if (data != NULL) {
trim(data);
}
tag = line;
// Read till we reach the end of the counts or the end of the motif
if ((strcmp(tag, "XX\n") == 0) || (strcmp(tag, "//\n") == 0)) {
break;
}
++num_motif_positions;
}
// Rewind file
errno = 0;
status = fsetpos(transfac_file, &file_position);
if (status) {
die("Error reading file %s: %s", transfac_filename, strerror(errno));
}
// Read the motif counts.
int num_seqs = 0;
this_consensus[0] = 0;
MATRIX_T *motif_counts = allocate_matrix(num_motif_positions, 4);
int position = 0;
while (TRUE) {
line = getline2(transfac_file);
if (line == NULL) {
break;
}
char *data = split(line, ' ');
if (data != NULL) {
trim(data);
}
tag = line;
// Look for the end of the motif.
if ((strcmp(tag, "XX\n") == 0) || (strcmp(tag, "//\n") == 0)) {
break;
}
position = atoi(tag);
if (position > num_motif_positions) {
die(
"Error reading motif counts at position %d of motif %s in file %s",
position, this_accession, transfac_filename
);
}
// Store the contents of this row.
int count[4];
char consensus;
sscanf(
data,
"%d %d %d %d %c",
&(count[0]),
&(count[1]),
&(count[2]),
&(count[3]),
&consensus
);
int i_base;
for (i_base = 0; i_base < num_bases; i_base++) {
set_matrix_cell(position - 1, i_base, count[i_base], motif_counts);
}
this_consensus[position - 1] = consensus;
}
this_consensus[position] = 0;
TRANSFAC_MOTIF_T *motif = new_transfac_motif(
this_accession,
this_id,
this_name,
this_descr,
this_consensus,
species_list,
motif_counts
);
arraylst_add(motif, motif_list);
}
}
fclose(transfac_file);
return motif_list;
}
/*************************************************************************
* Entry point for centrimo
*************************************************************************/
int main(int argc, char *argv[]) {
CENTRIMO_OPTIONS_T options;
SEQ_SITES_T seq_sites;
SITE_COUNTS_T counts;
int seqN, motifN, seqlen, db_i, motif_i, i;
double log_pvalue_thresh;
SEQ_T** sequences = NULL;
ARRAY_T* bg_freqs = NULL;
ARRAYLST_T *stats_list;
MOTIF_DB_T **dbs, *db;
MREAD_T *mread;
MOTIF_STATS_T *stats;
MOTIF_T *motif, *rev_motif;
PSSM_T *pos_pssm, *rev_pssm;
char *sites_path, *desc;
FILE *sites_file;
HTMLWR_T *html;
JSONWR_T *json;
// COMMAND LINE PROCESSING
process_command_line(argc, argv, &options);
// load the sequences
read_sequences(options.alphabet, options.seq_source, &sequences, &seqN);
seqlen = (seqN ? get_seq_length(sequences[0]) : 0);
// calculate a sequence background (unless other background is given)
if (!options.bg_source) {
bg_freqs = calc_bg_from_fastas(options.alphabet, seqN, sequences);
}
// load the motifs
motifN = 0;
dbs = mm_malloc(sizeof(MOTIF_DB_T*) * arraylst_size(options.motif_sources));
for (i = 0; i < arraylst_size(options.motif_sources); i++) {
char* db_source;
db_source = (char*)arraylst_get(i, options.motif_sources);
dbs[i] = read_motifs(i, db_source, options.bg_source, &bg_freqs,
options.pseudocount, options.selected_motifs, options.alphabet);
motifN += arraylst_size(dbs[i]->motifs);
}
log_pvalue_thresh = log(options.evalue_thresh) - log(motifN);
// Setup some things for double strand scanning
if (options.scan_both_strands == TRUE) {
// Set up hash tables for computing reverse complement
setup_hash_alph(DNAB);
setalph(0);
// Correct background by averaging on freq. for both strands.
average_freq_with_complement(options.alphabet, bg_freqs);
normalize_subarray(0, alph_size(options.alphabet, ALPH_SIZE), 0.0, bg_freqs);
calc_ambigs(options.alphabet, FALSE, bg_freqs);
}
// Create output directory
if (create_output_directory(options.output_dirname, options.allow_clobber,
(verbosity >= NORMAL_VERBOSE))) {
die("Couldn't create output directory %s.\n", options.output_dirname);
}
// open output files
sites_path = make_path_to_file(options.output_dirname, SITES_FILENAME);
sites_file = fopen(sites_path, "w");
free(sites_path);
// setup html monolith writer
json = NULL;
if ((html = htmlwr_create(get_meme_etc_dir(), TEMPLATE_FILENAME))) {
htmlwr_set_dest_name(html, options.output_dirname, HTML_FILENAME);
htmlwr_replace(html, "centrimo_data.js", "data");
json = htmlwr_output(html);
if (json == NULL) die("Template does not contain data section.\n");
} else {
DEBUG_MSG(QUIET_VERBOSE, "Failed to open html template file.\n");
}
if (json) {
// output some top level variables
jsonwr_str_prop(json, "version", VERSION);
jsonwr_str_prop(json, "revision", REVISION);
jsonwr_str_prop(json, "release", ARCHIVE_DATE);
jsonwr_str_array_prop(json, "cmd", argv, argc);
jsonwr_property(json, "options");
jsonwr_start_object_value(json);
jsonwr_dbl_prop(json, "motif-pseudo", options.pseudocount);
jsonwr_dbl_prop(json, "score", options.score_thresh);
jsonwr_dbl_prop(json, "ethresh", options.evalue_thresh);
jsonwr_lng_prop(json, "maxbin", options.max_window+1);
jsonwr_bool_prop(json, "norc", !options.scan_both_strands);
jsonwr_bool_prop(json, "noflip", options.no_flip);
jsonwr_end_object_value(json);
// output the description
desc = prepare_description(&options);
if (desc) {
jsonwr_str_prop(json, "job_description", desc);
free(desc);
}
// output size metrics
jsonwr_lng_prop(json, "seqlen", seqlen);
jsonwr_lng_prop(json, "tested", motifN);
// output the fasta db
jsonwr_property(json, "sequence_db");
jsonwr_start_object_value(json);
jsonwr_str_prop(json, "source", options.seq_source);
jsonwr_lng_prop(json, "count", seqN);
jsonwr_end_object_value(json);
// output the motif dbs
jsonwr_property(json, "motif_dbs");
jsonwr_start_array_value(json);
for (db_i = 0; db_i < arraylst_size(options.motif_sources); db_i++) {
db = dbs[db_i];
jsonwr_start_object_value(json);
jsonwr_str_prop(json, "source", db->source);
jsonwr_lng_prop(json, "count", arraylst_size(db->motifs));
jsonwr_end_object_value(json);
}
jsonwr_end_array_value(json);
// start the motif array
jsonwr_property(json, "motifs");
jsonwr_start_array_value(json);
}
/**************************************************************
* Tally the positions of the best sites for each of the
* selected motifs.
**************************************************************/
// prepare the sequence sites
memset(&seq_sites, 0, sizeof(SEQ_SITES_T));
// prepare the site counts
counts.allocated = ((2 * seqlen) - 1);
counts.sites = mm_malloc(sizeof(double) * counts.allocated);
// prepare the motifs stats list
stats_list = arraylst_create();
// prepare the other vars
motif = NULL; pos_pssm = NULL; rev_motif = NULL; rev_pssm = NULL;
for (db_i = 0; db_i < arraylst_size(options.motif_sources); db_i++) {
db = dbs[db_i];
for (motif_i = 0; motif_i < arraylst_size(db->motifs); motif_i++) {
motif = (MOTIF_T *) arraylst_get(motif_i, db->motifs);
DEBUG_FMT(NORMAL_VERBOSE, "Using motif %s of width %d.\n",
get_motif_id(motif), get_motif_length(motif));
// reset the counts
for (i = 0; i < counts.allocated; i++) counts.sites[i] = 0;
counts.total_sites = 0;
// create the pssm
pos_pssm = make_pssm(bg_freqs, motif);
// If required, do the same for the reverse complement motif.
if (options.scan_both_strands) {
rev_motif = dup_rc_motif(motif);
rev_pssm = make_pssm(bg_freqs, rev_motif);
}
// scan the sequences
for (i = 0; i < seqN; i++)
score_sequence(&options, sequences[i], pos_pssm, rev_pssm,
&seq_sites, &counts);
// DEBUG check that the sum of the sites is close to the site count
double sum_check = 0, sum_diff;
for (i = 0; i < counts.allocated; i++) sum_check += counts.sites[i];
sum_diff = counts.total_sites - sum_check;
if (sum_diff < 0) sum_diff = -sum_diff;
if (sum_diff > 0.1) {
fprintf(stderr, "Warning: site counts don't sum to accurate value! "
"%g != %ld", sum_check, counts.total_sites);
}
// output the plain text site counts
output_site_counts(sites_file, seqlen, db, motif, &counts);
// compute the best central window
stats = compute_stats(options.max_window, seqlen, db, motif, &counts);
// check if it passes the threshold
if (json && stats->log_adj_pvalue <= log_pvalue_thresh) {
output_motif_json(json, stats, &counts);
arraylst_add(stats, stats_list);
} else {
free(stats);
}
// Free memory associated with this motif.
free_pssm(pos_pssm);
free_pssm(rev_pssm);
destroy_motif(rev_motif);
}
}
if (json) jsonwr_end_array_value(json);
// finish writing sites
fclose(sites_file);
// finish writing html file
if (html) {
if (htmlwr_output(html) != NULL) {
die("Found another JSON replacement!\n");
}
htmlwr_destroy(html);
}
// write text file
output_centrimo_text(&options, motifN, stats_list);
// Clean up.
for (i = 0; i < seqN; ++i) {
free_seq(sequences[i]);
}
free(sequences);
for (i = 0; i < arraylst_size(options.motif_sources); i++) {
free_db(dbs[i]);
}
free(dbs);
free_array(bg_freqs);
free(counts.sites);
free(seq_sites.sites);
arraylst_destroy(free, stats_list);
cleanup_options(&options);
return 0;
}
/***********************************************************************
Process command line options
***********************************************************************/
static void process_command_line(
int argc,
char* argv[],
CENTRIMO_OPTIONS_T *options
) {
// Define command line options.
const int num_options = 12;
cmdoption const centrimo_options[] = {
{"bgfile", REQUIRED_VALUE},
{"o", REQUIRED_VALUE},
{"oc", REQUIRED_VALUE},
{"score", REQUIRED_VALUE},
{"motif-pseudo", REQUIRED_VALUE},
{"ethresh", REQUIRED_VALUE},
{"maxbin", REQUIRED_VALUE},
{"norc", NO_VALUE},
{"noflip", NO_VALUE},
{"desc", REQUIRED_VALUE},
{"dfile", REQUIRED_VALUE},
{"verbosity", REQUIRED_VALUE}
};
int option_index = 0;
/* Make sure various options are set to NULL or defaults. */
options->alphabet = DNA_ALPH;
options->allow_clobber = TRUE;
options->scan_both_strands = TRUE;
options->no_flip = FALSE;
options->description = NULL;
options->desc_file = NULL;
options->bg_source = NULL;
options->output_dirname = "centrimo_out";
options->seq_source = NULL;
options->motif_sources = arraylst_create();
options->score_thresh = DEFAULT_SCORE_THRESH;
options->pseudocount = DEFAULT_PSEUDOCOUNT;
options->evalue_thresh = DEFAULT_EVALUE_THRESH;
options->max_window = DEFAULT_MAX_WINDOW;
// no need to copy, as string is declared in argv array
options->selected_motifs = rbtree_create(rbtree_strcmp, NULL, NULL, NULL, NULL);
verbosity = NORMAL_VERBOSE;
simple_setopt(argc, argv, num_options, centrimo_options);
// Parse the command line.
while (TRUE) {
int c = 0;
char* option_name = NULL;
char* option_value = NULL;
const char * message = NULL;
// Read the next option, and break if we're done.
c = simple_getopt(&option_name, &option_value, &option_index);
if (c == 0) {
break;
}
else if (c < 0) {
(void) simple_getopterror(&message);
fprintf(stderr, "Error processing command line options (%s)\n", message);
fprintf(stderr, CENTRIMO_USAGE, DEFAULT_PSEUDOCOUNT, DEFAULT_SCORE_THRESH,
DEFAULT_EVALUE_THRESH, NORMAL_VERBOSE);
exit(EXIT_FAILURE);
}
if (strcmp(option_name, "bgfile") == 0){
options->bg_source = option_value;
}
else if (strcmp(option_name, "ethresh") == 0){
options->evalue_thresh = atof(option_value);
}
else if (strcmp(option_name, "maxbin") == 0){
// max_window is one less than the number of places a motif can align
// within the central window
options->max_window = atoi(option_value) - 1;
}
else if (strcmp(option_name, "motif") == 0){
rbtree_put(options->selected_motifs, option_value, NULL);
}
else if (strcmp(option_name, "motif-pseudo") == 0){
options->pseudocount = atof(option_value);
}
else if (strcmp(option_name, "norc") == 0){
options->scan_both_strands = FALSE;
}
else if (strcmp(option_name, "noflip") == 0){
options->no_flip = TRUE;
}
else if (strcmp(option_name, "o") == 0){
// Set output directory with no clobber
options->output_dirname = option_value;
options->allow_clobber = FALSE;
}
else if (strcmp(option_name, "oc") == 0){
// Set output directory with clobber
options->output_dirname = option_value;
options->allow_clobber = TRUE;
}
else if (strcmp(option_name, "score") == 0){
options->score_thresh = atof(option_value);
}
else if (strcmp(option_name, "desc") == 0) {
options->description = option_value;
}
else if (strcmp(option_name, "dfile") == 0) {
options->desc_file = option_value;
}
else if (strcmp(option_name, "verbosity") == 0){
verbosity = atoi(option_value);
}
}
// Must have sequence and motif file names
if (argc < option_index + 2) {
fprintf(stderr, "Sequences and motifs are both required\n");
fprintf(stderr, CENTRIMO_USAGE, DEFAULT_PSEUDOCOUNT, DEFAULT_SCORE_THRESH,
DEFAULT_EVALUE_THRESH, NORMAL_VERBOSE);
exit(EXIT_FAILURE);
}
// Record the input file names
options->seq_source = argv[option_index++];
for (;option_index < argc; option_index++)
arraylst_add(argv[option_index], options->motif_sources);
// Set up path values for needed stylesheets and output files.
}
