/**************************************************************************
* Callback invoked when matching an opening pattern tag for a CISML file
* of a secondary motif database. It checks that the motif should be scored,
* clears out the list of sequence matches and stores the current motif.
**************************************************************************/
void motif_secondary(void *ctx, char *accession, char *name, char *db, char *lsId, double *pvalue, double *score) {
SECONDARY_LOADER_T *loader = (SECONDARY_LOADER_T*)ctx;
SECONDARY_KEY_T key;
RBNODE_T *node;
PSSM_T *pssm;
int i, seq_count;
key.db_id = loader->db_id;
key.motif_id = accession;
node = rbtree_lookup(loader->secondary_motifs, &key, FALSE, NULL);
if (node != NULL) {
loader->secondary_motif = (SECONDARY_MOTIF_T*)rbtree_value(node);
if (!(loader->secondary_motif->loaded)) {
seq_count = rbtree_size(loader->sequences);
for (i = 0; i < seq_count; ++i) loader->secondary_matches[i] = 0;
if (loader->score_threshold_or_multiplier < 0 && loader->score_threshold_or_multiplier >= -1) {
pssm = build_motif_pssm(loader->secondary_motif->motif, loader->background, loader->background, NULL, 0, PSSM_RANGE, 0, FALSE);
loader->calculated_score_threshold = pssm_best_match_score(pssm) * (-loader->score_threshold_or_multiplier);
free_pssm(pssm);
}
} else {
die("Already seen CISML data for this motif!");
}
} else {
loader->secondary_motif = NULL;
}
}
/**************************************************************************
* Reads a CISML file containing scores for the primary motif for each
* of the sequences and records the best match above the score threshold
* for each sequence.
**************************************************************************/
void load_spamo_primary(int margin, double score_threshold, ARRAY_T *background,
MOTIF_T *motif, RBTREE_T *sequences, const char *cisml) {
CISML_CALLBACKS_T callbacks;
PRIMARY_LOADER_T data;
PSSM_T *pssm;
memset(&callbacks, 0, sizeof(CISML_CALLBACKS_T));
callbacks.start_pattern = motif_primary;
callbacks.start_scanned_sequence = sequence_primary;
callbacks.start_matched_element = match_primary;
callbacks.end_scanned_sequence = sequence_end_primary;
data.motif = motif;
data.margin = margin;
data.sequences = sequences;
data.current_sequence = NULL;
data.in_motif = FALSE;
data.hits_size = 10;
data.hits = mm_malloc(sizeof(int) * data.hits_size);
data.hit_count = 0;
if (score_threshold < 0 && score_threshold >= -1) {
pssm = build_motif_pssm(motif, background, background, NULL, 0, PSSM_RANGE, 0, FALSE);
data.calculated_score_threshold = pssm_best_match_score(pssm) * (-score_threshold);
free_pssm(pssm);
} else {
data.calculated_score_threshold = score_threshold;
}
parse_cisml(&callbacks, &data, cisml);
free(data.hits);
}
/************************************************************************
* Free the memory used by an mhmm state.
************************************************************************/
static void free_state
(MHMM_STATE_T *a_state)
{
/* Don't bother with empty states. */
if (a_state == NULL)
return;
myfree(a_state->itrans_out);
free_array(a_state->trans_out);
myfree(a_state->itrans_in);
free_array(a_state->trans_in);
free_array(a_state->emit);
free_array(a_state->emit_odds);
free_pssm(a_state->pssm);
free_pssm(a_state->npssm);
}
/*************************************************************************
* Entry point for pmp_bf
*************************************************************************/
int main(int argc, char *argv[]) {
char* bg_filename = NULL;
char* motif_name = "motif"; // Use this motif name in the output.
STRING_LIST_T* selected_motifs = NULL;
double fg_rate = 1.0;
double bg_rate = 1.0;
double purine_pyrimidine = 1.0; // r
double transition_transversion = 0.5; // R
double pseudocount = 0.1;
GAP_SUPPORT_T gap_support = SKIP_GAPS;
MODEL_TYPE_T model_type = F81_MODEL;
BOOLEAN_T use_halpern_bruno = FALSE;
char* ustar_label = NULL; // TLB; create uniform star tree
int i;
program_name = "pmp_bf";
/**********************************************
* COMMAND LINE PROCESSING
**********************************************/
// Define command line options. (FIXME: Repeated code)
// FIXME: Note that if you add or remove options you
// must change n_options.
int n_options = 12;
cmdoption const pmp_options[] = {
{"hb", NO_VALUE},
{"ustar", REQUIRED_VALUE},
{"model", REQUIRED_VALUE},
{"pur-pyr", REQUIRED_VALUE},
{"transition-transversion", REQUIRED_VALUE},
{"bg", REQUIRED_VALUE},
{"fg", REQUIRED_VALUE},
{"motif", REQUIRED_VALUE},
{"motif-name", REQUIRED_VALUE},
{"bgfile", REQUIRED_VALUE},
{"pseudocount", REQUIRED_VALUE},
{"verbosity", REQUIRED_VALUE}
};
int option_index = 0;
// Define the usage message.
char usage[1000] = "";
strcat(usage, "USAGE: pmp [options] <tree file> <MEME file>\n");
strcat(usage, "\n");
strcat(usage, " Options:\n");
// Evolutionary model parameters.
strcat(usage, " --hb\n");
strcat(usage, " --model single|average|jc|k2|f81|f84|hky|tn");
strcat(usage, " (default=f81)\n");
strcat(usage, " --pur-pyr <float> (default=1.0)\n");
strcat(usage, " --transition-transversion <float> (default=0.5)\n");
strcat(usage, " --bg <float> (default=1.0)\n");
strcat(usage, " --fg <float> (default=1.0)\n");
// Motif parameters.
strcat(usage, " --motif <id> (default=all)\n");
strcat(usage, " --motif-name <string> (default from motif file)\n");
// Miscellaneous parameters
strcat(usage, " --bgfile <background> (default from motif file)\n");
strcat(usage, " --pseudocount <float> (default=0.1)\n");
strcat(usage, " --ustar <label>\n"); // TLB; create uniform star tree
strcat(usage, " --verbosity [1|2|3|4] (default 2)\n");
strcat(usage, "\n Prints the FP and FN rate at each of 10000 score values.\n");
strcat(usage, "\n Output format: [<motif_id> score <score> FPR <fpr> TPR <tpr>]+\n");
// Parse the command line.
if (simple_setopt(argc, argv, n_options, pmp_options) != NO_ERROR) {
die("Error processing command line options: option name too long.\n");
}
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);
die("Error processing command line options (%s)\n", message);
}
if (strcmp(option_name, "model") == 0) {
if (strcmp(option_value, "jc") == 0) {
model_type = JC_MODEL;
} else if (strcmp(option_value, "k2") == 0) {
model_type = K2_MODEL;
} else if (strcmp(option_value, "f81") == 0) {
model_type = F81_MODEL;
} else if (strcmp(option_value, "f84") == 0) {
model_type = F84_MODEL;
} else if (strcmp(option_value, "hky") == 0) {
model_type = HKY_MODEL;
} else if (strcmp(option_value, "tn") == 0) {
model_type = TAMURA_NEI_MODEL;
} else if (strcmp(option_value, "single") == 0) {
model_type = SINGLE_MODEL;
} else if (strcmp(option_value, "average") == 0) {
model_type = AVERAGE_MODEL;
} else {
die("Unknown model: %s\n", option_value);
}
} else if (strcmp(option_name, "hb") == 0){
use_halpern_bruno = TRUE;
} else if (strcmp(option_name, "ustar") == 0){ // TLB; create uniform star tree
ustar_label = option_value;
} else if (strcmp(option_name, "pur-pyr") == 0){
purine_pyrimidine = atof(option_value);
} else if (strcmp(option_name, "transition-transversion") == 0){
transition_transversion = atof(option_value);
} else if (strcmp(option_name, "bg") == 0){
bg_rate = atof(option_value);
} else if (strcmp(option_name, "fg") == 0){
fg_rate = atof(option_value);
} else if (strcmp(option_name, "motif") == 0){
if (selected_motifs == NULL) {
selected_motifs = new_string_list();
}
add_string(option_value, selected_motifs);
} else if (strcmp(option_name, "motif-name") == 0){
motif_name = option_value;
} else if (strcmp(option_name, "bgfile") == 0){
bg_filename = option_value;
} else if (strcmp(option_name, "pseudocount") == 0){
pseudocount = atof(option_value);
} else if (strcmp(option_name, "verbosity") == 0){
verbosity = atoi(option_value);
}
}
// Must have tree and motif file names
if (argc != option_index + 2) {
fprintf(stderr, "%s", usage);
exit(EXIT_FAILURE);
}
/**********************************************
* Read the phylogenetic tree.
**********************************************/
char* tree_filename = NULL;
TREE_T* tree = NULL;
tree_filename = argv[option_index];
option_index++;
tree = read_tree_from_file(tree_filename);
// get the species names
STRING_LIST_T* alignment_species = make_leaf_list(tree);
char *root_label = get_label(tree); // in case target in center
if (strlen(root_label)>0) add_string(root_label, alignment_species);
//write_string_list(" ", alignment_species, stderr);
// TLB; Convert the tree to a uniform star tree with
// the target sequence at its center.
if (ustar_label != NULL) {
tree = convert_to_uniform_star_tree(tree, ustar_label);
if (tree == NULL)
die("Tree or alignment missing target %s\n", ustar_label);
if (verbosity >= NORMAL_VERBOSE) {
fprintf(stderr,
"Target %s placed at center of uniform (d=%.3f) star tree:\n",
ustar_label, get_total_length(tree) / get_num_children(tree)
);
write_tree(tree, stderr);
}
}
/**********************************************
* Read the motifs.
**********************************************/
char* meme_filename = argv[option_index];
option_index++;
int num_motifs = 0;
MREAD_T *mread;
ALPH_T alph;
ARRAYLST_T *motifs;
ARRAY_T *bg_freqs;
mread = mread_create(meme_filename, OPEN_MFILE);
mread_set_bg_source(mread, bg_filename);
mread_set_pseudocount(mread, pseudocount);
// read motifs
motifs = mread_load(mread, NULL);
alph = mread_get_alphabet(mread);
bg_freqs = mread_get_background(mread);
// check
if (arraylst_size(motifs) == 0) die("No motifs in %s.", meme_filename);
// TLB; need to resize bg_freqs array to ALPH_SIZE items
// or copy array breaks in HB mode. This throws away
// the freqs for the ambiguous characters;
int asize = alph_size(alph, ALPH_SIZE);
resize_array(bg_freqs, asize);
/**************************************************************
* Compute probability distributions for each of the selected motifs.
**************************************************************/
int motif_index;
for (motif_index = 0; motif_index < arraylst_size(motifs); motif_index++) {
MOTIF_T* motif = (MOTIF_T*)arraylst_get(motif_index, motifs);
char* motif_id = get_motif_id(motif);
char* bare_motif_id = motif_id;
// We may have specified on the command line that
// only certain motifs were to be used.
if (selected_motifs != NULL) {
if (*bare_motif_id == '+' || *bare_motif_id == '-') {
// The selected motif id won't included a strand indicator.
bare_motif_id++;
}
if (have_string(bare_motif_id, selected_motifs) == FALSE) {
continue;
}
}
if (verbosity >= NORMAL_VERBOSE) {
fprintf(
stderr,
"Using motif %s of width %d.\n",
motif_id, get_motif_length(motif)
);
}
// Build an array of evolutionary models for each position in the motif.
EVOMODEL_T** models = make_motif_models(
motif,
bg_freqs,
model_type,
fg_rate,
bg_rate,
purine_pyrimidine,
transition_transversion,
use_halpern_bruno
);
// Get the frequencies under the background model (row 0)
// and position-dependent scores (rows 1..w)
// for each possible alignment column.
MATRIX_T* pssm_matrix = build_alignment_pssm_matrix(
alph,
alignment_species,
get_motif_length(motif) + 1,
models,
tree,
gap_support
);
ARRAY_T* alignment_col_freqs = allocate_array(get_num_cols(pssm_matrix));
copy_array(get_matrix_row(0, pssm_matrix), alignment_col_freqs);
remove_matrix_row(0, pssm_matrix); // throw away first row
//print_col_frequencies(alph, alignment_col_freqs);
//
// Get the position-dependent null model alignment column frequencies
//
int w = get_motif_length(motif);
int ncols = get_num_cols(pssm_matrix);
MATRIX_T* pos_dep_bkg = allocate_matrix(w, ncols);
for (i=0; i<w; i++) {
// get the evo model corresponding to this column of the motif
// and store it as the first evolutionary model.
myfree(models[0]);
// Use motif PSFM for equilibrium freqs. for model.
ARRAY_T* site_specific_freqs = allocate_array(asize);
int j = 0;
for(j = 0; j < asize; j++) {
double value = get_matrix_cell(i, j, get_motif_freqs(motif));
set_array_item(j, value, site_specific_freqs);
}
if (use_halpern_bruno == FALSE) {
models[0] = make_model(
model_type,
fg_rate,
transition_transversion,
purine_pyrimidine,
site_specific_freqs,
NULL
);
} else {
models[0] = make_model(
model_type,
fg_rate,
transition_transversion,
purine_pyrimidine,
bg_freqs,
site_specific_freqs
);
}
// get the alignment column frequencies using this model
MATRIX_T* tmp_pssm_matrix = build_alignment_pssm_matrix(
alph,
alignment_species,
2, // only interested in freqs under bkg
models,
tree,
gap_support
);
// assemble the position-dependent background alignment column freqs.
set_matrix_row(i, get_matrix_row(0, tmp_pssm_matrix), pos_dep_bkg);
// chuck the pssm (not his real name)
free_matrix(tmp_pssm_matrix);
}
//
// Compute and print the score distribution under the background model
// and under the (position-dependent) motif model.
//
int range = 10000; // 10^4 gives same result as 10^5, but 10^3 differs
// under background model
PSSM_T* pssm = build_matrix_pssm(alph, pssm_matrix, alignment_col_freqs, range);
// under position-dependent background (motif) model
PSSM_T* pssm_pos_dep = build_matrix_pssm(alph, pssm_matrix, alignment_col_freqs, range);
get_pv_lookup_pos_dep(
pssm_pos_dep,
pos_dep_bkg,
NULL // no priors used
);
// print FP and FN distributions
int num_items = get_pssm_pv_length(pssm_pos_dep);
for (i=0; i<num_items; i++) {
double pvf = get_pssm_pv(i, pssm);
double pvt = get_pssm_pv(i, pssm_pos_dep);
double fpr = pvf;
double fnr = 1 - pvt;
if (fpr >= 0.99999 || fnr == 0) continue;
printf("%s score %d FPR %.3g FNR %.3g\n", motif_id, i, fpr, fnr);
}
// free stuff
free_pssm(pssm);
free_pssm(pssm_pos_dep);
if (models != NULL) {
int model_index;
int num_models = get_motif_length(motif) + 1;
for (model_index = 0; model_index < num_models; model_index++) {
free_model(models[model_index]);
}
myfree(models);
}
} // motif
arraylst_destroy(destroy_motif, motifs);
/**********************************************
* Clean up.
**********************************************/
// TLB may have encountered a memory corruption bug here
// CEG has not been able to reproduce it. valgrind says all is well.
free_array(bg_freqs);
free_tree(TRUE, tree);
free_string_list(selected_motifs);
return(0);
} // main
/*************************************************************************
* 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;
}
