/*************************************************************************
* 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;
}
/*************************************************************************
* 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
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;
}
/*************************************************************************
* 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
