/**
* 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);
}
/**
* Creates and stores a motifs using the motif-x
* algorithm for a given mod until no more are left.
*/
void create_motifx_motifs(SUMMARY_T* summary,
MOMO_OPTIONS_T* options,
MOD_INFO_T * mod_info,
SEQ_T** all_sequences,
int num_sequences) {
int i;
ARRAYLST_T* phospho_seqs = mod_info->seq_list;
ARRAYLST_T* bg_seqs = mod_info->bg_seq_list;
// Initialize status
MOTIFX_STATUS_T* phospho_status = init_status_array(arraylst_size(phospho_seqs));
MOTIFX_STATUS_T* bg_status = init_status_array(arraylst_size(bg_seqs));
// Initialize sequence counter. This contains the number of ACTIVE sequences in status
int* num_active = mm_malloc(sizeof(int));
int* num_bg_active = mm_malloc(sizeof(int));
*num_active = arraylst_size(phospho_seqs);
*num_bg_active = arraylst_size(bg_seqs);
// Initialize count matrices
MATRIX_T* phospho_count = NULL;
MATRIX_T* bg_count = NULL;
phospho_count = get_count_matrix(phospho_count, phospho_seqs, NULL, options, summary);
bg_count = get_count_matrix(bg_count, bg_seqs, NULL, options, summary);
// Recursively create motifs
create_motifx_motif(phospho_seqs,
bg_seqs,
&phospho_status,
&bg_status,
phospho_count,
bg_count,
num_active,
num_bg_active,
mod_info->mod_name,
mod_info,
options,
summary);
// Clean up
myfree(num_active);
myfree(num_bg_active);
myfree(phospho_status);
myfree(bg_status);
free_matrix(phospho_count);
free_matrix(bg_count);
}
/***********************************************************************
* 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;
}
void ramen_load_motifs() {
BOOLEAN_T read_file = FALSE;
MREAD_T *mread;
ARRAYLST_T* read_motifs;
int num_motifs_before_rc;
int i;
int j;
memset(&motifs, 0, sizeof(ramen_motifs_t));
read_motifs = arraylst_create();
for (i = 0; i < args.number_motif_files; i++) {
mread = mread_create(args.motif_filenames[i], OPEN_MFILE);
if (args.bg_format == FILE_BG) {
mread_set_bg_source(mread, args.bg_filename);
} else {
mread_set_background(mread, motifs.bg_freqs);
}
mread_set_pseudocount(mread, args.pseudocount);
mread_load(mread, read_motifs);
if (!(motifs.bg_freqs)) motifs.bg_freqs = mread_get_background(mread);
mread_destroy(mread);
}
// reverse complement the originals adding to the original read in list
num_motifs_before_rc = arraylst_size(read_motifs);
add_reverse_complements(read_motifs);
motifs.num = arraylst_size(read_motifs);
//Allocate array for the motifs
motif_list_to_array(read_motifs, &(motifs.motifs), &(motifs.num));
//free the list of motifs
free_motifs(read_motifs);
// check reverse complements.
assert(motifs.num / 2 == num_motifs_before_rc);
// reset motif count to before rev comp
motifs.num = num_motifs_before_rc;
//Now, we need to convert the motifs into odds matrices if we're doing that kind of scoring
for (i=0;i<2*motifs.num;i++) {
convert_to_odds_matrix(motif_at(motifs.motifs, i), motifs.bg_freqs);
}
}
/*************************************************************************
* 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;
}
/***********************************************************************
* Convert a list of motifs into an array of motifs with a count.
* This is intended to allow backwards compatibility with the older
* version.
***********************************************************************/
void motif_list_to_array(ARRAYLST_T *motif_list, MOTIF_T **motif_array, int *num) {
int count, i;
MOTIF_T *motifs;
count = arraylst_size(motif_list);
motifs = (MOTIF_T*)mm_malloc(sizeof(MOTIF_T) * count);
for (i = 0; i < count; ++i) {
copy_motif((MOTIF_T*)arraylst_get(i, motif_list), motifs+i);
}
*motif_array = motifs;
*num = count;
}
/*************************************************************************
* Output CentriMo text output
*************************************************************************/
static void output_centrimo_text(CENTRIMO_OPTIONS_T *options, int motifN,
ARRAYLST_T *stats_list) {
MOTIF_STATS_T *stats;
char *file_path;
int i, pad;
double log_motifN;
FILE *text_file;
MOTIF_T *motif;
// find the evalue conversion factor
log_motifN = log(motifN);
// Sort and write centrimo.txt
arraylst_qsort(motif_stats_compar, stats_list);
// open centrimo text file
file_path = make_path_to_file(options->output_dirname, TEXT_FILENAME);
text_file = fopen(file_path, "w");
free(file_path);
fputs("# motif \tE-value\tadj_p-value\tlog_adj_p-value\t"
"bin_width\ttotal_width\tsites_in_bin\ttotal_sites\tp_success\t"
"p-value\tmult_tests\n", text_file);
fprintf(text_file, "# Found %d motifs with E-values <= %g\n",
arraylst_size(stats_list), options->evalue_thresh);
// write centrimo text output
for (i = 0; i < arraylst_size(stats_list); i++) {
stats = arraylst_get(i, stats_list);
motif = stats->motif;
pad = 19 - strlen(get_motif_id(motif));
fprintf(text_file, "%s %-*s\t", get_motif_id(motif),
pad, get_motif_id2(motif));
print_log_value(text_file, stats->log_adj_pvalue + log_motifN, 1);
fputs("\t", text_file);
print_log_value(text_file, stats->log_adj_pvalue, 1);
fprintf(text_file, "\t%.2f\t%d\t%d\t%.0f\t%ld\t%.5f\t",
stats->log_adj_pvalue, stats->central_window+1, stats->all_window,
stats->central_sites, stats->total_sites,
stats->central_prob);
print_log_value(text_file, stats->log_pvalue, 1);
fprintf(text_file, "\t%d\n", stats->n_win_tested);
}
fclose(text_file);
}
/***********************************************************************
* Create two copies of each motif. The new IDs are preceded by "+"
* and "-", and the "-" version is the reverse complement of the "+"
* version.
*
* The reverse complement is always listed directly after the original.
***********************************************************************/
void add_reverse_complements
(ARRAYLST_T* motifs)
{
int i, count;
char motif_id[MAX_MOTIF_ID_LENGTH + 1]; // Name of the current motif;
count = arraylst_size(motifs);
//double the array size
arraylst_preallocate(count*2, motifs);
arraylst_add_n(count, NULL, motifs);
//move and reverse complement the original motifs
for (i = count-1; i >= 0; --i) {
//move the motif to its new position
arraylst_swap(i, 2*i, motifs);
//get the motif and the one that will become the reverse complement
MOTIF_T *orig = arraylst_get(2*i, motifs);
if (get_motif_strand(orig) == '?') set_motif_strand('+', orig);
//copy and reverse complement the motif to the position after
MOTIF_T *rc = dup_rc_motif(orig);
arraylst_set(2*i + 1, rc, motifs);
}
assert(arraylst_size(motifs) == (2 * count));
}
/*****************************************************************************
* MEME > scanned_sites_summary > scanned_sites > scanned_site
****************************************************************************/
void mxml_scanned_site(void *ctx, char *motif_id, char strand, int position, double log10pvalue) {
CTX_T *data;
SCANNED_SEQ_T *sseq;
int *mindex;
data = (CTX_T*)ctx;
if (data->options & SCANNED_SITES) {
sseq = (SCANNED_SEQ_T*)arraylst_get(
arraylst_size(data->fscope.scanned_sites)-1, data->fscope.scanned_sites);
mindex = (int*)rbtree_get(data->motif_lookup, motif_id);
if (mindex == NULL) {
local_error(data, "Scanned site references unknown motif \"%s\".\n", motif_id);
return;
}
sseq_set(sseq, data->current_site++, (*mindex) + 1, strand, position, log10pvalue);
}
}
/**
* Remove sequences do not match a pattern from phospho and bg lists and update their respective count matrix
*/
void remove_sequences_and_update_matrix(char letter,
int pos,
ARRAYLST_T* seqs,
MOTIFX_STATUS_T** status_array,
int* num_active,
MATRIX_T* count,
SUMMARY_T* summary,
MOMO_OPTIONS_T* options) {
int i;
const char* alph_letters = summary->alph_letters;
// Look through phospho_seqs and remove sequences. Update phospho_seqs
for (i = 0; i < arraylst_size(seqs); ++i) {
char* curr_seq = get_raw_sequence((SEQ_T*) (options->eliminate_repeats ? hash_get_entry_value((HASH_TABLE_ENTRY*) arraylst_get(i, seqs)) : arraylst_get(i, seqs)));
// For anything active that does not match the pattern, turn it inactive.
MOTIFX_STATUS_T status = (*status_array)[i];
if (status == ACTIVE && curr_seq[pos] != letter) {
*num_active = *num_active - 1;
(*status_array)[i] = INACTIVE;
}
}
count = get_count_matrix(count, seqs, status_array, options, summary);
}
/*************************************************************************
* 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 ama
*************************************************************************/
int main(int argc, char **argv) {
AMA_OPTIONS_T options;
ARRAYLST_T *motifs;
clock_t c0, c1; // measuring cpu_time
MOTIF_AND_PSSM_T *combo;
CISML_T *cisml;
PATTERN_T** patterns;
PATTERN_T *pattern;
FILE *fasta_file, *text_output, *cisml_output;
int i, seq_loading_num, seq_counter, unique_seqs, seq_len, scan_len, x1, x2, y1, y2;
char *seq_name, *path;
bool need_postprocessing, created;
SEQ_T *sequence;
RBTREE_T *seq_ids;
RBNODE_T *seq_node;
double *logcumback;
ALPH_T *alph;
// process the command
process_command_line(argc, argv, &options);
// load DNA motifs
motifs = load_motifs(&options);
// get the alphabet
if (arraylst_size(motifs) > 0) {
combo = (MOTIF_AND_PSSM_T*)arraylst_get(0, motifs);
alph = alph_hold(get_motif_alph(combo->motif));
} else {
alph = alph_dna();
}
// pick columns for GC operations
x1 = -1; x2 = -1; y1 = -1; y2 = -1;
if (alph_size_core(alph) == 4 && alph_size_pairs(alph) == 2) {
x1 = 0; // A
x2 = alph_complement(alph, x1); // T
y1 = (x2 == 1 ? 2 : 1); // C
y2 = alph_complement(alph, y1); // G
assert(x1 != x2 && y1 != y2 && x1 != y1 && x2 != y2 && x1 != y2 && x2 != y1);
}
// record starting time
c0 = clock();
// Create cisml data structure for recording results
cisml = allocate_cisml(PROGRAM_NAME, options.command_line, options.motif_filename, options.fasta_filename);
set_cisml_background_file(cisml, options.bg_filename);
// make a CISML pattern to hold scores for each motif
for (i = 0; i < arraylst_size(motifs); i++) {
combo = (MOTIF_AND_PSSM_T*)arraylst_get(i, motifs);
add_cisml_pattern(cisml, allocate_pattern(get_motif_id(combo->motif), ""));
}
// Open the FASTA file for reading.
fasta_file = NULL;
if (!open_file(options.fasta_filename, "r", false, "FASTA", "sequences", &fasta_file)) {
die("Couldn't open the file %s.\n", options.fasta_filename);
}
if (verbosity >= NORMAL_VERBOSE) {
if (options.last == 0) {
fprintf(stderr, "Using entire sequence\n");
} else {
fprintf(stderr, "Limiting sequence to last %d positions.\n", options.last);
}
}
//
// Read in all sequences and score with all motifs
//
seq_loading_num = 0; // keeps track on the number of sequences read in total
seq_counter = 0; // holds the index to the seq in the pattern
unique_seqs = 0; // keeps track on the number of unique sequences
need_postprocessing = false;
sequence = NULL;
logcumback = NULL;
seq_ids = rbtree_create(rbtree_strcasecmp,rbtree_strcpy,free,rbtree_intcpy,free);
while (read_one_fasta(alph, fasta_file, options.max_seq_length, &sequence)) {
++seq_loading_num;
seq_name = get_seq_name(sequence);
seq_len = get_seq_length(sequence);
scan_len = (options.last != 0 ? options.last : seq_len);
// red-black trees are only required if duplicates should be combined
if (options.combine_duplicates){
//lookup seq id and create new entry if required, return sequence index
seq_node = rbtree_lookup(seq_ids, get_seq_name(sequence), true, &created);
if (created) { // assign it a loading number
rbtree_set(seq_ids, seq_node, &unique_seqs);
seq_counter = unique_seqs;
++unique_seqs;
} else {
seq_counter = *((int*)rbnode_get(seq_node));
}
}
//
// Set up sequence-dependent background model and compute
// log cumulative probability of sequence.
// This needs the sequence in raw format.
//
if (options.sdbg_order >= 0)
logcumback = log_cumulative_background(alph, options.sdbg_order, sequence);
// Index the sequence, throwing away the raw format and ambiguous characters
index_sequence(sequence, alph, SEQ_NOAMBIG);
// Get the GC content of the sequence if binning p-values by GC
// and store it in the sequence object.
if (options.num_gc_bins > 1) {
ARRAY_T *freqs = get_sequence_freqs(sequence, alph);
set_total_gc_sequence(sequence, get_array_item(y1, freqs) + get_array_item(y2, freqs)); // f(C) + f(G)
free_array(freqs); // clean up
} else {
set_total_gc_sequence(sequence, -1); // flag ignore
}
// Scan with motifs.
for (i = 0; i < arraylst_size(motifs); i++) {
pattern = get_cisml_patterns(cisml)[i];
combo = (MOTIF_AND_PSSM_T*)arraylst_get(i, motifs);
if (verbosity >= HIGHER_VERBOSE) {
fprintf(stderr, "Scanning %s sequence with length %d "
"abbreviated to %d with motif %s with length %d.\n",
seq_name, seq_len, scan_len,
get_motif_id(combo->motif), get_motif_length(combo->motif));
}
SCANNED_SEQUENCE_T* scanned_seq = NULL;
if (!options.combine_duplicates || get_pattern_num_scanned_sequences(pattern) <= seq_counter) {
// Create a scanned_sequence record and save it in the pattern.
scanned_seq = allocate_scanned_sequence(seq_name, seq_name, pattern);
set_scanned_sequence_length(scanned_seq, scan_len);
} else {
// get existing sequence record
scanned_seq = get_pattern_scanned_sequences(pattern)[seq_counter];
set_scanned_sequence_length(scanned_seq, max(scan_len, get_scanned_sequence_length(scanned_seq)));
}
// check if scanned component of sequence has sufficient length for the motif
if (scan_len < get_motif_length(combo->motif)) {
// set score to zero and p-value to 1 if not set yet
if(!has_scanned_sequence_score(scanned_seq)){
set_scanned_sequence_score(scanned_seq, 0.0);
}
if(options.pvalues && !has_scanned_sequence_pvalue(scanned_seq)){
set_scanned_sequence_pvalue(scanned_seq, 1.0);
}
add_scanned_sequence_scanned_position(scanned_seq);
if (get_scanned_sequence_num_scanned_positions(scanned_seq) > 0L) {
need_postprocessing = true;
}
if (verbosity >= HIGH_VERBOSE) {
fprintf(stderr, "%s too short for motif %s. Score set to 0.\n",
seq_name, get_motif_id(combo->motif));
}
} else {
// scan the sequence using average/maximum motif affinity
ama_sequence_scan(alph, sequence, logcumback, combo->pssm_pair,
options.scoring, options.pvalues, options.last, scanned_seq,
&need_postprocessing);
}
} // All motifs scanned
free_seq(sequence);
if (options.sdbg_order >= 0) myfree(logcumback);
} // read sequences
fclose(fasta_file);
if (verbosity >= HIGH_VERBOSE) fprintf(stderr, "(%d) sequences read in.\n", seq_loading_num);
if (verbosity >= NORMAL_VERBOSE) fprintf(stderr, "Finished \n");
// if any sequence identifier was multiple times in the sequence set then
// postprocess of the data is required
if (need_postprocessing || options.normalize_scores) {
post_process(cisml, motifs, options.normalize_scores);
}
// output results
if (options.output_format == DIRECTORY_FORMAT) {
if (create_output_directory(options.out_dir, options.clobber, verbosity > QUIET_VERBOSE)) {
// only warn in higher verbose modes
fprintf(stderr, "failed to create output directory `%s' or already exists\n", options.out_dir);
exit(1);
}
path = make_path_to_file(options.out_dir, text_filename);
//FIXME check for errors: MEME doesn't either and we at least know we have a good directory
text_output = fopen(path, "w");
free(path);
path = make_path_to_file(options.out_dir, cisml_filename);
//FIXME check for errors
cisml_output = fopen(path, "w");
free(path);
print_cisml(cisml_output, cisml, true, NULL, false);
print_score(cisml, text_output);
fclose(cisml_output);
fclose(text_output);
} else if (options.output_format == GFF_FORMAT) {
print_score(cisml, stdout);
} else if (options.output_format == CISML_FORMAT) {
print_cisml(stdout, cisml, true, NULL, false);
} else {
die("Output format invalid!\n");
}
//
// Clean up.
//
rbtree_destroy(seq_ids);
arraylst_destroy(motif_and_pssm_destroy, motifs);
free_cisml(cisml);
rbtree_destroy(options.selected_motifs);
alph_release(alph);
// measure time
if (verbosity >= NORMAL_VERBOSE) { // starting time
c1 = clock();
fprintf(stderr, "cycles (CPU); %ld cycles\n", (long) c1);
fprintf(stderr, "elapsed CPU time: %f seconds\n", (float) (c1-c0) / CLOCKS_PER_SEC);
}
return 0;
}
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;
}
void generate_ceq_logos(char *meme_path, char *output_dir) {
int i, dir_len, prefix_len, path_len;
ARRAY_T *background;
BOOLEAN_T has_reverse_strand;
char *path, *alphabet;
double logo_height, logo_width;
ARRAYLST_T *motifs;
MOTIF_T *motif;
motifs = arraylst_create();
logo_height = LOGOHEIGHT;
//make the path
dir_len = strlen(output_dir);
prefix_len = strlen(LOGO_PREFIX);
path_len = dir_len + 1 + prefix_len + MAX_MOTIF_ID_LENGTH + 1;
path = malloc(sizeof(char)*path_len);
strncpy(path, output_dir, path_len);
if (path[dir_len-1] != '/') {
path[dir_len] = '/';
path[++dir_len] = '\0';
}
strncpy(path+dir_len, LOGO_PREFIX, path_len - dir_len);
// Read all motifs into an array.
read_meme_file2(meme_path,
NULL, // bg file name
DEFAULT_PSEUDOCOUNTS,
REQUIRE_PSPM,
motifs,
NULL,//motif occurrences
&has_reverse_strand,
&background);
// global alphabet is set by read_meme_file
alphabet = get_alphabet(FALSE);
if (create_output_directory(output_dir, TRUE, (verbosity >= NORMAL_VERBOSE))) {
// Failed to create output directory.
exit(1);
}
for(i = 0; i < arraylst_size(motifs); i++) {
motif = (MOTIF_T*)arraylst_get(i, motifs);
logo_width = get_motif_length(motif);
if (logo_width > MAXLOGOWIDTH) logo_width = MAXLOGOWIDTH;
copy_and_sanatise_name(path+(dir_len+prefix_len), get_motif_id(motif), path_len - (dir_len + prefix_len));
CL_create2(
motif, // motif
"", // no title
NULL, // no second motif
"", // no x-axis label
FALSE, // no error bars
FALSE, // ssc
logo_height, // logo height (cm)
logo_width, // logo width (cm)
alphabet, // alphabet
0, // no offset to second motif
path, // output file path
"MEME (no SSC)" // program name
);
}
free_motifs(motifs);
free_array(background); // not used
free(path);
}
/**
* 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);
}
/*************************************************************************
* 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;
}
/*************************************************************************
* Entry point for ama
*************************************************************************/
int main(int argc, char *argv[]) {
int max_seq_length = MAX_SEQ;
STRING_LIST_T* selected_motifs = NULL;
double pseudocount = 0.01;
int output_format = CISML_FORMAT;
program_name = "ama";
int scoring = AVG_ODDS;
BOOLEAN_T pvalues = FALSE;
BOOLEAN_T normalize_scores = FALSE;
BOOLEAN_T combine_duplicates = FALSE;
int num_gc_bins = 1;
int sdbg_order = -1; // don't use sequence background
BOOLEAN_T scan_both_strands = TRUE;
ARRAY_T* pos_bg_freqs = NULL;
ARRAY_T* rev_bg_freqs = NULL;
clock_t c0, c1; /* measuring cpu_time */
CISML_T *cisml;
char * out_dir = NULL;
BOOLEAN_T clobber = FALSE;
int i;
int last = 0;
ALPH_T alph = INVALID_ALPH;
/**********************************************
* COMMAND LINE PROCESSING
**********************************************/
const int num_options = 16;
cmdoption const motif_scan_options[] = {
{ "max-seq-length", REQUIRED_VALUE },
{ "motif", REQUIRED_VALUE },
{ "motif-pseudo", REQUIRED_VALUE },
{ "rma", NO_VALUE },
{ "pvalues", NO_VALUE },
{ "sdbg", REQUIRED_VALUE },
{ "norc", NO_VALUE },
{ "cs", NO_VALUE },
{ "o-format", REQUIRED_VALUE },
{ "o", REQUIRED_VALUE },
{ "oc", REQUIRED_VALUE },
{ "scoring", REQUIRED_VALUE },
{ "verbosity", REQUIRED_VALUE },
{ "gcbins", REQUIRED_VALUE },
{ "last", REQUIRED_VALUE },
{ "version", NO_VALUE }
};
int option_index = 0;
// Define the usage message.
char usage[] = "USAGE: ama [options] <motif file> <sequence file> [<background file>]\n"
"\n"
" Options:\n"
" --sdbg <order>\t\t\tUse Markov background model of\n"
" \t\t\t\t\torder <order> derived from the sequence\n"
" \t\t\t\t\tto compute its likelihood ratios.\n"
" \t\t\t\t\tOverrides --pvalues, --gcbins and --rma;\n"
" \t\t\t\t\t<background file> is required unless\n"
" \t\t\t\t\t--sdbg is given.\n"
" --motif <id>\t\t\tUse only the motif identified by <id>.\n"
" \t\t\t\t\tThis option may be repeated.\n"
" --motif-pseudo <float>\t\tThe value <float> times the background\n"
" \t\t\t\t\tfrequency is added to the count of each\n"
" \t\t\t\t\tletter when creating the likelihood \n"
" \t\t\t\t\tratio matrix (default: %g).\n"
" --norc\t\t\t\tDisables the scanning of the reverse\n"
" \t\t\t\t\tcomplement strand.\n"
" --scoring [avg-odds|max-odds]\tIndicates whether the average or \n"
" \t\t\t\t\tthe maximum odds should be calculated\n"
" \t\t\t\t\t(default: avg-odds)\n"
" --rma\t\t\t\tScale motif scores to the range 0-1.\n"
" \t\t\t\t\t(Relative Motif Affinity).\n"
" \t\t\t\t\tMotif scores are scaled by the maximum\n"
" \t\t\t\t\tscore achievable by that PWM. (default:\n"
" \t\t\t\t\tmotif scores are not normalized)\n"
" --pvalues\t\t\t\tPrint p-value of avg-odds score in cisml\n"
" \t\t\t\t\toutput. Ignored for max-odds scoring.\n"
" \t\t\t\t\t(default: p-values are not printed)\n"
" --gcbins <bins>\t\t\tCompensate p-values for GC content of\n"
" \t\t\t\t\teach sequence using given number of \n"
" \t\t\t\t\tGC range bins. Recommended bins: 41.\n"
" \t\t\t\t\t(default: p-values are based on\n"
" \t\t\t\t\tfrequencies in background file)\n"
" --cs\t\t\t\tEnable combining sequences with same\n"
" \t\t\t\t\tidentifier by taking the average score\n"
" \t\t\t\t\tand the Sidac corrected p-value.\n"
" --o-format [gff|cisml]\t\tOutput file format (default: cisml)\n"
" \t\t\t\t\tignored if --o or --oc option used\n"
" --o <directory>\t\t\tOutput all available formats to\n"
" \t\t\t\t\t<directory>; give up if <directory>\n"
" \t\t\t\t\texists\n"
" --oc <directory>\t\t\tOutput all available formats to\n"
" \t\t\t\t\t<directory>; if <directory> exists\n"
" \t\t\t\t\toverwrite contents\n"
" --verbosity [1|2|3|4]\t\tControls amount of screen output\n"
" \t\t\t\t\t(default: %d)\n"
" --max-seq-length <int>\t\tSet the maximum length allowed for \n"
" \t\t\t\t\tinput sequences. (default: %d)\n"
" --last <int>\t\t\tUse only scores of (up to) last <n>\n"
" \t\t\t\t\tsequence positions to compute AMA.\n"
" --version \t\t\tPrint version and exit.\n"
"\n";
// Parse the command line.
if (simple_setopt(argc, argv, num_options, motif_scan_options) != NO_ERROR) {
die("Error processing command line options: option name too long.\n");
}
BOOLEAN_T setoutputformat = FALSE;
BOOLEAN_T setoutputdirectory = FALSE;
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);
} else if (strcmp(option_name, "max-seq-length") == 0) {
max_seq_length = atoi(option_value);
} else if (strcmp(option_name, "norc") == 0) {
scan_both_strands = FALSE;
} else if (strcmp(option_name, "cs") == 0) {
combine_duplicates = TRUE;
} 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-pseudo") == 0) {
pseudocount = atof(option_value);
} else if (strcmp(option_name, "o-format") == 0) {
if (setoutputdirectory) {
if (verbosity >= NORMAL_VERBOSE)
fprintf(stderr, "output directory specified, ignoring --o-format\n");
} else {
setoutputformat = TRUE;
if (strcmp(option_value, "gff") == 0)
output_format = GFF_FORMAT;
else if (strcmp(option_value, "cisml") == 0)
output_format = CISML_FORMAT;
else {
if (verbosity >= NORMAL_VERBOSE)
fprintf(stderr, "Output format not known. Using standard instead (cisML).\n");
output_format = CISML_FORMAT;
}
}
} else if (strcmp(option_name, "o") == 0 || strcmp(option_name, "oc") == 0) {
setoutputdirectory = TRUE;
if (setoutputformat) {
if (verbosity >= NORMAL_VERBOSE)
fprintf(stderr, "output directory specified, ignoring --o-format\n");
}
clobber = strcmp(option_name, "oc") == 0;
out_dir = (char*) malloc (sizeof(char)*(strlen(option_value)+1));
strcpy(out_dir, option_value);
output_format = DIRECTORY_FORMAT;
} else if (strcmp(option_name, "verbosity") == 0) {
verbosity = atoi(option_value);
} else if (strcmp(option_name, "scoring") == 0) {
if (strcmp(option_value, "max-odds") == 0)
scoring = MAX_ODDS;
else if (strcmp(option_value, "avg-odds") == 0)
scoring = AVG_ODDS;
else if (strcmp(option_value, "sum-odds") == 0)
scoring = SUM_ODDS;
else
die("Specified scoring scheme not known.\n", message);
} else if (strcmp(option_name, "pvalues") == 0) {
pvalues = TRUE;
} else if (strcmp(option_name, "rma") == 0) {
normalize_scores = TRUE;
fprintf(stderr, "Normalizing motif scores using RMA method.\n");
} else if (strcmp(option_name, "gcbins") == 0) {
num_gc_bins = atoi(option_value);
pvalues = TRUE;
if (num_gc_bins <= 1) die("Number of bins in --gcbins must be greater than 1.\n", message);
} else if (strcmp(option_name, "sdbg") == 0) {
sdbg_order = atoi(option_value); // >=0 means use sequence bkg
}
else if (strcmp(option_name, "last") == 0) {
int i = 0;
if (option_value[0] == '-') ++i;
while (option_value[i] != '\0') {
if (!isdigit(option_value[i])) {
die("Specified parameter 'last' contains non-numeric characters.\n");
}
++i;
}
last = atoi(option_value);
if (errno != 0) {
die("Specified parameter 'last' could not be parsed as a number as:\n%s\n",strerror(errno));
}
if (last < 0) {
die("Specified parameter 'last' had negative value (%d) when only postive or zero values are allowed \n", last);
}
}
else if (strcmp(option_name, "version") == 0) {
fprintf(stdout, VERSION "\n");
exit(EXIT_SUCCESS);
}
}
// --sdbg overrides --pvalues and --gcbins and --rma
int req_args = 3;
if (sdbg_order >= 0) {
pvalues = FALSE;
normalize_scores = FALSE;
num_gc_bins = 1;
req_args = 2;
}
// Check all required arguments given
if (sdbg_order >= 0 && argc > option_index + req_args) {
die("<background file> cannot be given together with --sdbg.\n");
} else if (argc != option_index + req_args) {
fprintf(stderr, usage, pseudocount, verbosity, max_seq_length);
exit(EXIT_FAILURE);
}
// Get required arguments.
char* motif_filename = argv[option_index];
option_index++;
char* fasta_filename = argv[option_index];
option_index++;
char* bg_filename;
if (req_args == 3) { // required unless --sdbg given
bg_filename = argv[option_index];
option_index++;
} else {
bg_filename = "--uniform--"; // So PSSMs will use uniform background;
// we can multiply them out later.
}
// measure time
c0 = clock();
// Set up hash tables for computing reverse complement if doing --sdbg
if (sdbg_order >= 0) setup_hash_alph(DNAB);
// Create cisml data structure for recording results
cisml = allocate_cisml(program_name, motif_filename, fasta_filename);
set_cisml_background_file(cisml, bg_filename);
/**********************************************
* Read the motifs and background model.
**********************************************/
int num_motifs = 0;
MREAD_T *mread;
ARRAYLST_T *motifs;
PSSM_PAIR_T** pssm_pairs; // note pssm_pairs is an array of pointers
//this reads any meme file, xml, txt and html
mread = mread_create(motif_filename, OPEN_MFILE);
mread_set_bg_source(mread, bg_filename);
mread_set_pseudocount(mread, pseudocount);
motifs = mread_load(mread, NULL);
alph = mread_get_alphabet(mread);
pos_bg_freqs = mread_get_background(mread);
mread_destroy(mread);
num_motifs = arraylst_size(motifs);
// allocate memory for PSSM pairs
pssm_pairs = (PSSM_PAIR_T**)mm_malloc(sizeof(PSSM_PAIR_T*) * num_motifs);
if (verbosity >= NORMAL_VERBOSE)
fprintf(stderr, "Number of motifs in file %d.\n", num_motifs);
// make a CISML pattern to hold scores for each motif
PATTERN_T** patterns = NULL;
Resize(patterns, num_motifs, PATTERN_T*);
int motif_index;
for (motif_index = 0; motif_index < num_motifs; motif_index++) {
MOTIF_T* motif = (MOTIF_T*)arraylst_get(motif_index, motifs);
patterns[motif_index] = allocate_pattern(get_motif_id(motif), "");
add_cisml_pattern(cisml, patterns[motif_index]);
}
// make reverse complement motifs and background frequencies.
if (scan_both_strands == TRUE) {
add_reverse_complements(motifs);
assert(arraylst_size(motifs) == (2 * num_motifs));
rev_bg_freqs = allocate_array(get_array_length(pos_bg_freqs));
complement_dna_freqs(pos_bg_freqs, rev_bg_freqs);
}
/**************************************************************
* Convert motif matrices into log-odds matrices.
* Scale them.
* Compute the lookup tables for the PDF of scaled log-odds scores.
**************************************************************/
int ns = scan_both_strands ? 2 : 1; // number of strands
for (motif_index = 0; motif_index < num_motifs; motif_index++) {
MOTIF_T *motif, *motif_rc;
motif = (MOTIF_T*)arraylst_get(motif_index*ns, motifs);
if (scan_both_strands)
motif_rc = (MOTIF_T*)arraylst_get(motif_index*ns + 1, motifs);
else
motif_rc = NULL;
/*
* 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?)
*/
double range = 300; // 100 is not very good; 1000 is great but too slow
PSSM_T* pos_pssm =
build_motif_pssm(
motif,
pos_bg_freqs,
pos_bg_freqs,
NULL, // Priors not used
0.0L, // alpha not used
range,
num_gc_bins,
TRUE
);
PSSM_T* neg_pssm = (scan_both_strands ?
build_motif_pssm(
motif_rc,
rev_bg_freqs,
pos_bg_freqs,
NULL, // Priors not used
0.0L, // alpha not used
range,
num_gc_bins,
TRUE
)
: NULL
);
pssm_pairs[motif_index] = create_pssm_pair(pos_pssm, neg_pssm);
}
// Open the FASTA file for reading.
FILE* fasta_file = NULL;
if (open_file(fasta_filename, "r", FALSE, "FASTA", "sequences", &fasta_file) == 0) {
die("Couldn't open the file %s.\n", fasta_filename);
}
if (verbosity >= NORMAL_VERBOSE) {
if (last == 0) {
fprintf(stderr, "Using entire sequence\n");
} else {
fprintf(stderr, "Limiting sequence to last %d positions.\n", last);
}
}
/**************************************************************
* Read in all sequences and score with all motifs
**************************************************************/
int seq_loading_num = 0; // keeps track on the number of sequences read in total
int seq_counter = 0; // holds the index to the seq in the pattern
int unique_seqs = 0; // keeps track on the number of unique sequences
BOOLEAN_T need_postprocessing = FALSE;
SEQ_T* sequence = NULL;
RBTREE_T* seq_ids = rbtree_create(rbtree_strcasecmp,NULL,free,rbtree_intcpy,free);
RBNODE_T* seq_node;
BOOLEAN_T created;
while (read_one_fasta(alph, fasta_file, max_seq_length, &sequence)) {
++seq_loading_num;
created = FALSE;
char* seq_name = get_seq_name(sequence);
int seq_len = get_seq_length(sequence);
int scan_len;
if (last != 0) {
scan_len = last;
} else {
scan_len = seq_len;
}
// red-black trees are only required if duplicates should be combined
if (combine_duplicates){
//lookup seq id and create new entry if required, return sequence index
char *tmp_id = mm_malloc(strlen(seq_name)+1); // required copy for rb-tree
strncpy(tmp_id,seq_name,strlen(seq_name)+1);
seq_node = rbtree_lookup(seq_ids, tmp_id, TRUE, &created);
if (created) {// assign it a loading number
rbtree_set(seq_ids, seq_node, &unique_seqs);
seq_counter = unique_seqs;
++unique_seqs;
} else {
seq_counter = *((int*)rbnode_get(seq_node));
}
}
//
// Set up sequence-dependent background model and compute
// log cumulative probability of sequence.
//
double *logcumback = NULL; // array of log cumulative probs.
if (sdbg_order >= 0) {
Resize(logcumback, seq_len+1, double);
char* raw_seq = get_raw_sequence(sequence);
BOOLEAN rc = FALSE;
double *a_cp = get_markov_from_sequence(raw_seq, alph_string(alph), rc, sdbg_order, 0);
log_cum_back(raw_seq, a_cp, sdbg_order, logcumback);
myfree(a_cp);
}
// Get the GC content of the sequence if binning p-values by GC
// and store it in the sequence object.
if (num_gc_bins > 1) {
ARRAY_T *freqs = get_sequence_freqs(sequence, alph);
set_total_gc_sequence(sequence,
get_array_item(1,freqs) + get_array_item(2,freqs)); // f(C) + f(G)
free_array(freqs); // clean up
} else {
set_total_gc_sequence(sequence, -1); // flag ignore
}
/**************************************************************
* Process all motifs.
**************************************************************/
int ns = scan_both_strands ? 2 : 1;
for (motif_index = 0; motif_index < num_motifs; motif_index++) {
PATTERN_T *pattern = patterns[motif_index];
MOTIF_T* motif = (MOTIF_T*)arraylst_get(ns*motif_index, motifs);
char* motif_id = (scan_both_strands ? get_motif_st_id(motif) : get_motif_id(motif));
if (verbosity >= HIGH_VERBOSE) {
fprintf(stderr, "Using motif %s of width %d.\n", motif_id, get_motif_length(motif));
}
if ((selected_motifs == NULL) || (have_string(get_motif_id(motif), selected_motifs) == TRUE)) {
if (verbosity >= HIGHER_VERBOSE) {
fprintf(stderr, "Scanning %s sequence with length %d "
"abbreviated to %d with motif %s with length %d.\n",
seq_name, seq_len, scan_len, motif_id, get_motif_length(motif));
}
SCANNED_SEQUENCE_T* scanned_seq = NULL;
if (!combine_duplicates || get_pattern_num_scanned_sequences(pattern) <= seq_counter){
// Create a scanned_sequence record and save it in the pattern.
scanned_seq = allocate_scanned_sequence(seq_name, seq_name, pattern);
set_scanned_sequence_length(scanned_seq, scan_len);
} else {
// get existing sequence record
scanned_seq = get_pattern_scanned_sequences(pattern)[seq_counter];
set_scanned_sequence_length(scanned_seq, max(scan_len, get_scanned_sequence_length(scanned_seq)));
}
// check if scanned component of sequence has sufficient length for the motif
if (scan_len < get_motif_length(motif)) {
// set score to zero and p-value to 1 if not set yet
if(!has_scanned_sequence_score(scanned_seq)){
set_scanned_sequence_score(scanned_seq, 0.0);
}
if(pvalues && !has_scanned_sequence_pvalue(scanned_seq)){
set_scanned_sequence_pvalue(scanned_seq, 1.0);
}
add_scanned_sequence_scanned_position(scanned_seq);
if (get_scanned_sequence_num_scanned_positions(scanned_seq) > 0L) need_postprocessing = TRUE;
if (verbosity >= HIGH_VERBOSE) fprintf(stderr, "%s too short for motif %s. Score set to 0!\n", seq_name, motif_id);
} else {
// scan the sequence using average/maximum motif affinity
ama_sequence_scan(alph, sequence, logcumback, pssm_pairs[motif_index], scoring,
pvalues, last, scanned_seq, &need_postprocessing);
}
} else {
if (verbosity >= HIGH_VERBOSE) fprintf(stderr, "Skipping motif %s.\n", motif_id);
}
} // All motifs parsed
free_seq(sequence);
if (sdbg_order >= 0) myfree(logcumback);
} // read sequences
