/*************************************************************************
* 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
/***********************************************************************
Process command line options
***********************************************************************/
static void process_command_line(
int argc,
char* argv[],
MCAST_OPTIONS_T *options
) {
// Set default values for command line arguments
options->allow_clobber = TRUE;
options->text_only = FALSE;
options->motif_format = MEME_FORMAT;
options->bg_filename = NULL;
options->motif_filename = NULL;
options->output_dirname = "mcast_out";
options->seq_filename = NULL;
options->max_gap = "50";
options->pseudo_weight = "4.0";
options->e_thresh = "10.0";
options->p_thresh = "0.0005";
options->quiet = FALSE;
options->use_synth = FALSE;
// Define command line options.
int option_count = 12;
int option_index = 0;
cmdoption const cmdoptions[] = {
{"bgfile", REQUIRED_VALUE},
{"bgweight", REQUIRED_VALUE},
{"e-thresh", REQUIRED_VALUE},
{"max-gap", REQUIRED_VALUE},
{"o", REQUIRED_VALUE},
{"oc", REQUIRED_VALUE},
{"p-thresh", REQUIRED_VALUE},
{"synth", NO_VALUE},
{"text", NO_VALUE},
{"transfac", NO_VALUE},
{"verbosity", REQUIRED_VALUE},
{"quiet", NO_VALUE},
};
simple_setopt(argc, argv, option_count, cmdoptions);
// Define the usage message.
const char *usage =
"USAGE: mcast [options] <query> <database>\n"
"\n"
" [--bgfile <file>] File containing n-order Markov background model\n"
" [--bgweight <b>] Add b * background frequency to each count in query\n"
" (default: 4.0 )\n"
" [--e-thresh <value>] Print matches with E-values less than E\n"
" (default = 10)\n"
" [--max-gap <value>] Maximum allowed distance between adjacent hits\n"
" (default = 50)\n"
" [--o <output dir>] Name of output directory. Existing files will not be\n"
" overwritten (default=mcast_out)\n"
" [--oc <output dir>] Name of output directory. Existing files will be\n"
" overwritten.\n"
" [--p-thresh <value>] p-value threshold for motif hits\n"
" (default = 0.0005).\n"
" [--synth] Use synthetic scores for distribution\n"
" [--text] Output plain text rather than HTML.\n"
" [--transfac] Query is in TRANSFAC format (default: MEME format)\n"
" [--verbosity <value>] Verbosity of error messagess\n";
// Parse the command line.
while (1) {
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) {
simple_getopterror(&message);
die("Error in command line arguments.\n%s", usage);
}
// Assign the parsed value to the appropriate variable
if (strcmp(option_name, "bgfile") == 0) {
options->bg_filename = option_value;
} else if (strcmp(option_name, "bgweight") == 0) {
options->pseudo_weight = option_value;
} else if (strcmp(option_name, "e-thresh") == 0) {
options->e_thresh = option_value;
} else if (strcmp(option_name, "max-gap") == 0) {
options->max_gap = option_value;
}
else if (strcmp(option_name, "o") == 0){
// Set output directory with no clobber
options->output_dirname = option_value;
options->allow_clobber = FALSE;
}
else if (strcmp(option_name, "oc") == 0){
// Set output directory with clobber
options->output_dirname = option_value;
options->allow_clobber = TRUE;
} else if (strcmp(option_name, "p-thresh") == 0) {
options->p_thresh = option_value;
} else if (strcmp(option_name, "synth") == 0) {
options->use_synth = TRUE;
} else if (strcmp(option_name, "text") == 0) {
options->text_only = TRUE;
} else if (strcmp(option_name, "transfac") == 0) {
options->motif_format = TRANSFAC_FORMAT;
} else if (strcmp(option_name, "quiet") == 0) {
options->quiet = TRUE;
} else if (strcmp(option_name, "verbosity") == 0) {
verbosity = (VERBOSE_T) atoi(option_value);
}
}
// Read and verify the two required arguments.
if (option_index + 2 != argc) {
fprintf(stderr, "%s", usage);
exit(1);
}
options->motif_filename = argv[option_index];
options->seq_filename = argv[option_index+1];
if (options->motif_filename == NULL) {
die("No motif file given.\n%s", usage);
}
if (options->seq_filename == NULL) {
die("No sequence file given.\n%s", usage);
}
}
/*************************************************************************
* int main
*************************************************************************/
int main(int argc, char *argv[])
{
/* Data structures. */
int num_motifs; /* The number of motifs in the model. */
MOTIF_T motifs[2 * MAX_MOTIFS]; /* The motifs. */
STRING_LIST_T* motif_occurrences = NULL; /* Strings describing occurrences of
motifs */
BOOLEAN_T has_reverse_strand = FALSE; /* MEME file contained both strands */
ARRAY_T* background; /* Background probs for alphabet. */
ORDER_T* order_spacing; /* Linear HMM order and spacing. */
MATRIX_T* transp_freq = NULL; /* Matrix of inter-motif transitions freqs. */
MATRIX_T* spacer_ave = NULL; /* Matrix of average spacer lengths. */
MHMM_T * the_hmm = NULL; /* The HMM being constructed. */
/* Command line parameters. */
char * meme_filename; /* Input file containg motifs. */
char * hmm_type_str; /* HMM type. */
HMM_T hmm_type;
STRING_LIST_T* requested_motifs; /* Indices of requested motifs. */
int request_n; /* The user asked for the first n motifs. */
double e_threshold; /* E-value threshold for motif inclusion. */
double complexity_threshold; // For eliminating low-complexity motifs.
double p_threshold; /* p-value threshold for motif occurences. */
char* order_string; /* Motif order and spacing. */
int spacer_states; /* Number of states in each spacer. */
BOOLEAN_T fim; /* Represent spacers as free insertion
modules? */
BOOLEAN_T keep_unused; // Drop unused inter-motif transitions?
double trans_pseudo; /* Transition pseudocount. */
double spacer_pseudo; // Spacer (self-loop) pseudocount. */
char* description; // Descriptive text to be stored in model.
BOOLEAN_T print_header; /* Print file header? */
BOOLEAN_T print_params; /* Print parameter summary? */
BOOLEAN_T print_time; /* Print timing data (dummy: always false). */
/* Local variables. */
int i_motif;
/**********************************************
* COMMAND LINE PROCESSING
**********************************************/
// Define command line options.
cmdoption const options[] = {
{"type", OPTIONAL_VALUE},
{"description", REQUIRED_VALUE},
{"motif", REQUIRED_VALUE},
{"nmotifs", REQUIRED_VALUE},
{"ethresh", REQUIRED_VALUE},
{"lowcomp", REQUIRED_VALUE},
{"pthresh", REQUIRED_VALUE},
{"order", REQUIRED_VALUE},
{"nspacer", REQUIRED_VALUE},
{"fim", NO_VALUE},
{"keep-unused", NO_VALUE},
{"transpseudo", REQUIRED_VALUE},
{"spacerpseudo", REQUIRED_VALUE},
{"verbosity", REQUIRED_VALUE},
{"noheader", NO_VALUE},
{"noparams", NO_VALUE},
{"notime", NO_VALUE},
{"quiet", NO_VALUE},
};
int option_count = 18;
int option_index = 0;
// Define the usage message.
char usage[1000] = "";
strcat(usage, "USAGE: mhmm [options] <MEME file>\n");
strcat(usage, "\n");
strcat(usage, " Options:\n");
strcat(usage, " --type [linear|complete|star] (default=linear)\n");
strcat(usage, " --description <string> (may be repeated)\n");
strcat(usage, " --motif <motif #> (may be repeated)\n");
strcat(usage, " --nmotifs <#>\n");
strcat(usage, " --ethresh <E-value>\n");
strcat(usage, " --lowcomp <value>\n");
strcat(usage, " --pthresh <p-value>\n");
strcat(usage, " --order <string>\n");
strcat(usage, " --nspacer <spacer length> (default=1)\n");
strcat(usage, " --fim\n");
strcat(usage, " --keep-unused\n");
strcat(usage, " --transpseudo <pseudocount>\n");
strcat(usage, " --spacerpseudo <pseudocount>\n");
strcat(usage, " --verbosity 1|2|3|4|5 (default=2)\n");
strcat(usage, " --noheader\n");
strcat(usage, " --noparams\n");
strcat(usage, " --notime\n");
strcat(usage, " --quiet\n");
strcat(usage, "\n");
/* Make sure various options are set to NULL or defaults. */
meme_filename = NULL;
hmm_type_str = NULL;
hmm_type = INVALID_HMM;
requested_motifs = new_string_list();
request_n = 0;
e_threshold = 0.0;
complexity_threshold = 0.0;
p_threshold = 0.0;
order_string = NULL;
spacer_states = DEFAULT_SPACER_STATES,
fim = FALSE;
keep_unused = FALSE;
trans_pseudo = DEFAULT_TRANS_PSEUDO;
spacer_pseudo = DEFAULT_SPACER_PSEUDO;
description = NULL;
print_header = TRUE;
print_params = TRUE;
print_time = FALSE;
simple_setopt(argc, argv, option_count, options);
// Parse the command line.
while (1) {
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) {
simple_getopterror(&message);
die("Error processing command line options (%s)\n", message);
}
if (strcmp(option_name, "type") == 0) {
if (option_value != NULL) {
hmm_type_str = option_value;
}
} else if (strcmp(option_name, "description") == 0) {
description = option_value;
} else if (strcmp(option_name, "motif") == 0) {
add_string(option_value, requested_motifs);
} else if (strcmp(option_name, "nmotifs") == 0) {
request_n = atoi(option_value);
} else if (strcmp(option_name, "ethresh") == 0) {
e_threshold = atof(option_value);
} else if (strcmp(option_name, "lowcomp") == 0) {
complexity_threshold = atof(option_value);
} else if (strcmp(option_name, "pthresh") == 0) {
p_threshold = atof(option_value);
} else if (strcmp(option_name, "order") == 0) {
order_string = option_value;
} else if (strcmp(option_name, "nspacer") == 0) {
spacer_states = atoi(option_value);
} else if (strcmp(option_name, "fim") == 0) {
fim = TRUE;
} else if (strcmp(option_name, "keep-unused") == 0) {
keep_unused = TRUE;
} else if (strcmp(option_name, "transpseudo") == 0) {
trans_pseudo = atof(option_value);
} else if (strcmp(option_name, "spacerpseudo") == 0) {
spacer_pseudo = atof(option_value);
} else if (strcmp(option_name, "verbosity") == 0) {
verbosity = (VERBOSE_T)atoi(option_value);
} else if (strcmp(option_name, "noheader") == 0) {
print_header = FALSE;
} else if (strcmp(option_name, "noparams") == 0) {
print_params = FALSE;
} else if (strcmp(option_name, "notime") == 0) {
print_time = FALSE;
} else if (strcmp(option_name, "quiet") == 0) {
print_header = print_params = print_time = FALSE;
verbosity = QUIET_VERBOSE;
}
}
// Read the single required argument.
if (option_index + 1 != argc) {
fprintf(stderr, "%s", usage);
exit(1);
}
meme_filename = argv[option_index];
// Set up motif requests.
if (request_n != 0) {
if (get_num_strings(requested_motifs) != 0) {
die("Can't combine the -motif and -nmotifs options.\n");
} else {
for (i_motif = 0; i_motif < request_n; i_motif++) {
char motif_id[MAX_MOTIF_ID_LENGTH + 1];
sprintf(motif_id, "%d", i_motif + 1);
add_string(motif_id, requested_motifs);
}
}
}
/* Set the model type. */
hmm_type = convert_enum_type_str(hmm_type_str, LINEAR_HMM, HMM_STRS,
NUM_HMM_T);
/* Gotta have positive spacer length. */
if (spacer_states <= 0) {
die("Negative spacer length (%d).\n", spacer_states);
}
/* Make sure motifs weren't selected redundantly. */
// FIXME: Add tests for complexity threshold.
if ((get_num_strings(requested_motifs) != 0) && (e_threshold != 0.0)) {
die("Can't use -motif or -nmotifs with -ethresh.");
}
if ((get_num_strings(requested_motifs) != 0) && (order_string != NULL)) {
die("Can't use -motif or -nmotifs with -order.");
}
if ((order_string != NULL) && (e_threshold != 0.0)) {
die("Can't use -ethresh and -order.");
}
/* Prevent trying to build a complete or star model with ordering. */
if (order_string != NULL) {
if (hmm_type == COMPLETE_HMM)
die("Can't specify motif order with a completely connected model.");
else if (hmm_type == STAR_HMM)
die("Can't specify motif order with a star model.");
}
// Parse the order string.
order_spacing = create_order(order_string);
/**********************************************
* READING THE MOTIFS
**********************************************/
BOOLEAN_T read_file = FALSE;
double pseudocount = 0;
read_meme_file(
meme_filename,
"motif-file", // Take bg freq. from motif file.
pseudocount,
REQUIRE_PSPM,
&num_motifs,
motifs,
&motif_occurrences,
&has_reverse_strand,
&background
);
process_raw_motifs_for_model(
&num_motifs,
motifs,
motif_occurrences,
requested_motifs,
has_reverse_strand,
keep_unused,
p_threshold,
e_threshold,
complexity_threshold,
&order_spacing,
&transp_freq,
&spacer_ave,
trans_pseudo,
spacer_pseudo
);
/**********************************************
* BUILDING THE HMM
**********************************************/
/* Build the motif-based HMM. */
if (hmm_type == LINEAR_HMM) {
if (order_spacing != NULL) {
reorder_motifs(order_spacing, &num_motifs, motifs);
}
else {
die("No order specified for the motifs.\n"
"For the linear model the motif file must contain motif occurence\n"
"data or the motif order must be specified using "
"the --order option.");
}
build_linear_hmm(
background,
order_spacing,
spacer_states,
motifs,
num_motifs,
fim,
&the_hmm
);
} else if (hmm_type == COMPLETE_HMM) {
build_complete_hmm(
background,
spacer_states,
motifs,
num_motifs,
transp_freq,
spacer_ave,
fim,
&the_hmm
);
} else if (hmm_type == STAR_HMM) {
build_star_hmm(
background,
spacer_states,
motifs,
num_motifs,
fim,
&the_hmm
);
}
// Add some global information.
copy_string(&(the_hmm->motif_file), meme_filename);
/**********************************************
* WRITING THE HMM
**********************************************/
/* Print the header. */
if (print_header)
write_header(
program,
"",
description,
meme_filename,
NULL,
NULL,
stdout
);
/* Write the HMM. */
write_mhmm(verbosity, the_hmm, stdout);
/* Print the program parameters. */
if (print_params) {
printf("Program parameters for mhmm\n");
printf(" MEME file: %s\n", meme_filename);
printf(" Motifs:");
write_string_list(" ", requested_motifs, stdout);
printf("\n");
printf(" Model topology: %s\n",
convert_enum_type(hmm_type, HMM_STRS, NUM_HMM_T));
printf(" States per spacer: %d\n", spacer_states);
printf(" Spacers are free-insertion modules: %s\n",
boolean_to_string(fim));
printf("\n");
}
free_array(background);
free_string_list(requested_motifs);
free_order(order_spacing);
free_matrix(transp_freq);
free_matrix(spacer_ave);
for (i_motif = 0; i_motif < num_motifs; i_motif++)
free_motif(&(motifs[i_motif]));
free_mhmm(the_hmm);
return(0);
}
int main
(int argc,
char * argv[])
{
const int P_LEFT = -1;
const int P_ONETAILED = 0;
const int P_RIGHT = 1;
const int P_TWOTAILED = 2;
const int P_ALL = 3;
// Default parameter settings.
verbosity = NORMAL_VERBOSE;
int requested_p_value = P_ALL;
const int num_options = 2;
cmdoption const options[] = {
{ "verbosity", REQUIRED_VALUE },
{ "p-value", REQUIRED_VALUE }
};
// Define the usage message.
char usage[400] = "";
strcat(usage, "USAGE: ranksum_test [options] <n> <p> <r>\n");
strcat(usage, "\n");
strcat(usage, " <n> number of samples \n");
strcat(usage, " <p> number of positives\n");
strcat(usage, " <r> ranksum of positives (may be a real number)\n");
strcat(usage, "\n");
strcat(usage, " Options:\n");
strcat(usage, " --p-value -1|0|1|2|3 (-1=left, 0=one-tailed,1=right,\n"
" 2=two-tailed, 3=all (default))\n");
strcat(usage, " --verbosity 1|2|3|4 (default = 2)\n");
strcat(usage, "\n");
// Parse the command line.
int option_index = 0;
char* option_name = NULL;
char* option_value = NULL;
const char * message = NULL;
char line[MAX_LINE]; // Buffer for reading.
simple_setopt(argc, argv, num_options, options);
while(1) {
// Read the next option, and break if we're done.
int c = simple_getopt(&option_name, &option_value, &option_index);
if (c == 0) {
break;
} else if (c < 0) {
simple_getopterror(&message);
die("Error processing command line options (%s)\n", message);
}
if (strcmp(option_name, "p-value") == 0) {
requested_p_value = atoi(option_value);
if (requested_p_value < -1 || requested_p_value > 3)
die("Error requested p-value parameter unknown (%d)\n", requested_p_value);
}
else if (strcmp(option_name, "verbosity") == 0) {
verbosity = atoi(option_value);
}
}
// Read the single required argument.
if (option_index + 3 != argc) {
fprintf(stderr, "%s", usage);
exit(1);
}
int n = atoi(argv[option_index]);option_index++;
int p = atoi(argv[option_index]);option_index++;
double r = atof(argv[option_index]);option_index++;
RSR_T* mww = ranksum_from_stats(n,p,r);
// Print to stdout.
if (requested_p_value == P_RIGHT){
printf("%g\n",RSR_get_p_right(mww));
} else if (requested_p_value == P_LEFT){
printf("%g\n",RSR_get_p_left(mww));
} else if (requested_p_value == P_ONETAILED){
printf("%g\n",RSR_get_p_onetailed(mww));
} else if (requested_p_value == P_TWOTAILED){
printf("%g\n",RSR_get_p_twotailed(mww));
} else {
printf("p-left\t%g\tp-right\t%g\tone-tailed\t%g\ttwo-tailed\t%g\tU-value\t%g\n",
RSR_get_p_left(mww),
RSR_get_p_right(mww),
RSR_get_p_onetailed(mww),
RSR_get_p_twotailed(mww),
RSR_get_u(mww));
}
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
int main(int argc, char **argv) {
// Defaults for command line options.
char* bfile = NULL; // Background file.
int seed = 0; // For random numbers.
int min = LOWEST; // Minimum sequence length.
int max = HIGHEST; // Maximum sequence length.
int use_order = -1; // Use order defined in bfile.
int type = 0; // (See usage statement.)
BOOLEAN_T dummy = FALSE; // Don't print dummy sequence.
// Define command line options.
const int num_options = 7;
cmdoption const options[] = {
{"bfile", REQUIRED_VALUE},
{"seed", REQUIRED_VALUE},
{"minseq", REQUIRED_VALUE},
{"maxseq", REQUIRED_VALUE},
{"order", REQUIRED_VALUE},
{"type", REQUIRED_VALUE},
{"dummy", NO_VALUE}
};
int option_index = 0;
simple_setopt(argc, argv, num_options, options);
// Define the usage message.
char usage[1000] = "";
strcpy(usage, "USAGE: gendb [options] <numseqs>\n");
strcat(usage, "\n");
strcat(usage, " Options:\n");
strcat(usage, " --bfile <file>\n");
strcat(usage, " --seed <int> (default=0)\n");
strcat(usage, " --minseq <int> (default=50)\n");
strcat(usage, " --maxseq <int> (default=2000)\n");
strcat(usage, " --order <int> use Markov model of given order\n");
strcat(usage, " --type 0|1|2|3|4\n");
strcat(usage, " 0=protein (default)\n");
strcat(usage, " 1=dna with ambiguous characters\n");
strcat(usage, " 2=codons\n");
strcat(usage, " 3=dna w/o ambiguous characters\n");
strcat(usage, " 4=protein w/o ambiguous characters\n");
strcat(usage, " --dummy\n");
// Parse the command line.
while (1) {
int c = 0;
char* option_name = NULL;
char* option_value = NULL;
const char* message = "";
// 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) {
die("Error processing command line options (%s)\n", message);
}
if (strcmp(option_name, "bfile") == 0) {
bfile = option_value;
} else if (strcmp(option_name, "seed") == 0) {
seed = atoi(option_value);
} else if (strcmp(option_name, "minseq") == 0) {
min = (int)atof(option_value);
} else if (strcmp(option_name, "maxseq") == 0) {
max = (int)atof(option_value);
} else if (strcmp(option_name, "order") == 0) {
use_order = atoi(option_value);
} else if (strcmp(option_name, "type") == 0) {
type = atoi(option_value);
} else if (strcmp(option_name, "dummy") == 0) {
dummy = TRUE;
}
}
if (option_index + 1 != argc) {
fprintf(stderr, "%s", usage);
exit(EXIT_FAILURE);
}
int nseqs = atoi(argv[option_index]);
fprintf(stderr, "Generating %d sequences.\n", nseqs);
// Print dummy sequence if asked to.
if (dummy) {
printf(">SEQ_0 n= %d s= %d l= %d seed= %d\n", nseqs, min, max, seed);
}
gendb(
stdout,
type,
bfile,
use_order,
NULL, // 0-order model. -- WSN 8/13/03
nseqs,
min,
max,
seed
);
exit(0);
} // main
void ramen_getopt(int argc, char *argv[]) {
const int num_options = 12;
cmdoption const motif_scan_options[] = {
{"bgfile", REQUIRED_VALUE},
{"bgformat", REQUIRED_VALUE},
{"repeats", REQUIRED_VALUE},
{"pseudocount", REQUIRED_VALUE},
{"pvalue-cutoff", REQUIRED_VALUE},
{"verbose", REQUIRED_VALUE},
{"linreg-dumpdir", REQUIRED_VALUE},
{"linreg-switchxy", REQUIRED_VALUE},
{"log-fscores", REQUIRED_VALUE},
{"log-pwmscores", REQUIRED_VALUE},
{"normalise-motifs", REQUIRED_VALUE},
{"help", NO_VALUE},
};
int option_index = 0;
char* option_name = NULL;
char* option_value = NULL;
const char * message = NULL;
BOOLEAN_T bad_options = FALSE;
int i;
if (simple_setopt(argc, argv, num_options, motif_scan_options) != NO_ERROR) {
die("Error processing command line options: option name too long.\n");
}
/*
* Now parse the command line options
*/
//simple_getopt will return 0 when there are no more options to parse
while(simple_getopt(&option_name, &option_value, &option_index) > 0) {
if (strcmp(option_name, "bgfile") == 0) {
args.bg_filename = option_value;
} else if (strcmp(option_name, "bgformat") == 0) {
if (atoi(option_value)==MOTIF_BG) {
args.bg_format = MOTIF_BG;
} else if (atoi(option_value)==FILE_BG) {
args.bg_format = FILE_BG;
} else if (atoi(option_value)==UNIFORM_BG) {
args.bg_format = UNIFORM_BG;
} else {
ramen_usage();
ramen_terminate(1);
}
} else if (strcmp(option_name, "pvalue-cutoff") == 0) {
args.pvalue_cutoff = atof(option_value);
} else if (strcmp(option_name, "repeats") == 0) {
args.repeats = atof(option_value);
} else if (strcmp(option_name, "pseudocount") == 0) {
args.pseudocount = atof(option_value);
} else if (strcmp(option_name, "verbose") == 0) {
args.verbose = atoi(option_value);
verbosity = args.verbose;
if (args.verbose <= INVALID_VERBOSE || args.verbose > DUMP_VERBOSE) {
ramen_usage();
ramen_terminate(1);
}
} else if (strcmp(option_name, "log-fscores") == 0) {
if (strcmp(option_value,"on")==0) {
args.log_fscores = TRUE;
} else if (strcmp(option_value,"off")==0){
args.log_fscores = FALSE;
} else {
ramen_usage();
ramen_terminate(1);
}
} else if (strcmp(option_name, "log-pwmscores") == 0) {
if (strcmp(option_value,"on")==0) {
args.log_pwmscores = TRUE;
} else if (strcmp(option_value,"off")==0){
args.log_pwmscores = FALSE;
} else {
ramen_usage();
ramen_terminate(1);
}
} else if (strcmp(option_name, "normalise-motifs") == 0) {
if (strcmp(option_value,"on")==0) {
args.linreg_normalise = TRUE;
} else if (strcmp(option_value,"off")==0){
args.linreg_normalise = FALSE;
} else {
ramen_usage();
ramen_terminate(1);
}
} else if (strcmp(option_name, "linreg-dumpdir") == 0) {
args.linreg_dump_dir = option_value;
} else if (strcmp(option_name, "linreg-switchxy") == 0) {
if (strcmp(option_value,"on")==0) {
args.linreg_switchxy = TRUE;
} else if (strcmp(option_value,"off")==0){
args.linreg_switchxy = FALSE;
} else {
ramen_usage();
ramen_terminate(1);
}
} else if (strcmp(option_name, "help") == 0) {
printf("%s",ramen_get_usage()); //not to stderr
ramen_terminate(0);
} else {
printf("Error: %s is not a recognised switch.\n", option_name);
ramen_usage();
ramen_terminate(1);
}
option_index++;
}
args.sequence_filename = argv[option_index];
args.motif_filenames = &argv[option_index+1]; // FIXME: must now iterate until argc getting all motif DB filenames
args.number_motif_files = argc-option_index-1;
/* Now validate the options.
*
* Illegal combinations are:
* - sequence bg and no sequence
* - no motif
* - no sequences
* - each file exists.
*/
if (args.motif_filenames == NULL) {
fprintf(stderr, "Error: Motif file not specified.\n");
bad_options = TRUE;
} else {
int i;
for (i = 0; i < args.number_motif_files; i++) {
if (!file_exists(args.motif_filenames[i])) {
fprintf(stderr, "Error: Specified motif '%s' file does not exist.\n", args.motif_filenames[i]);
bad_options = TRUE;
}
}
}
if (args.sequence_filename == NULL) {
fprintf(stderr, "Error: Sequence file not specified.\n");
bad_options = TRUE;
} else if (!file_exists(args.sequence_filename)) {
fprintf(stderr, "Error: Specified sequence file does not exist.\n");
bad_options = TRUE;
}
if (args.bg_format == MOTIF_BG) { //bgfile is the same as the motif file.
//TODO: make more robust
args.bg_filename = argv[option_index];
args.bg_filename = NULL;
}
if (bad_options) {
ramen_usage();
ramen_terminate(1);
}
}
/***********************************************************************
Process command line options
***********************************************************************/
static void process_command_line(
int argc,
char* argv[],
CENTRIMO_OPTIONS_T *options
) {
// Define command line options.
const int num_options = 12;
cmdoption const centrimo_options[] = {
{"bgfile", REQUIRED_VALUE},
{"o", REQUIRED_VALUE},
{"oc", REQUIRED_VALUE},
{"score", REQUIRED_VALUE},
{"motif-pseudo", REQUIRED_VALUE},
{"ethresh", REQUIRED_VALUE},
{"maxbin", REQUIRED_VALUE},
{"norc", NO_VALUE},
{"noflip", NO_VALUE},
{"desc", REQUIRED_VALUE},
{"dfile", REQUIRED_VALUE},
{"verbosity", REQUIRED_VALUE}
};
int option_index = 0;
/* Make sure various options are set to NULL or defaults. */
options->alphabet = DNA_ALPH;
options->allow_clobber = TRUE;
options->scan_both_strands = TRUE;
options->no_flip = FALSE;
options->description = NULL;
options->desc_file = NULL;
options->bg_source = NULL;
options->output_dirname = "centrimo_out";
options->seq_source = NULL;
options->motif_sources = arraylst_create();
options->score_thresh = DEFAULT_SCORE_THRESH;
options->pseudocount = DEFAULT_PSEUDOCOUNT;
options->evalue_thresh = DEFAULT_EVALUE_THRESH;
options->max_window = DEFAULT_MAX_WINDOW;
// no need to copy, as string is declared in argv array
options->selected_motifs = rbtree_create(rbtree_strcmp, NULL, NULL, NULL, NULL);
verbosity = NORMAL_VERBOSE;
simple_setopt(argc, argv, num_options, centrimo_options);
// Parse the command line.
while (TRUE) {
int c = 0;
char* option_name = NULL;
char* option_value = NULL;
const char * message = NULL;
// Read the next option, and break if we're done.
c = simple_getopt(&option_name, &option_value, &option_index);
if (c == 0) {
break;
}
else if (c < 0) {
(void) simple_getopterror(&message);
fprintf(stderr, "Error processing command line options (%s)\n", message);
fprintf(stderr, CENTRIMO_USAGE, DEFAULT_PSEUDOCOUNT, DEFAULT_SCORE_THRESH,
DEFAULT_EVALUE_THRESH, NORMAL_VERBOSE);
exit(EXIT_FAILURE);
}
if (strcmp(option_name, "bgfile") == 0){
options->bg_source = option_value;
}
else if (strcmp(option_name, "ethresh") == 0){
options->evalue_thresh = atof(option_value);
}
else if (strcmp(option_name, "maxbin") == 0){
// max_window is one less than the number of places a motif can align
// within the central window
options->max_window = atoi(option_value) - 1;
}
else if (strcmp(option_name, "motif") == 0){
rbtree_put(options->selected_motifs, option_value, NULL);
}
else if (strcmp(option_name, "motif-pseudo") == 0){
options->pseudocount = atof(option_value);
}
else if (strcmp(option_name, "norc") == 0){
options->scan_both_strands = FALSE;
}
else if (strcmp(option_name, "noflip") == 0){
options->no_flip = TRUE;
}
else if (strcmp(option_name, "o") == 0){
// Set output directory with no clobber
options->output_dirname = option_value;
options->allow_clobber = FALSE;
}
else if (strcmp(option_name, "oc") == 0){
// Set output directory with clobber
options->output_dirname = option_value;
options->allow_clobber = TRUE;
}
else if (strcmp(option_name, "score") == 0){
options->score_thresh = atof(option_value);
}
else if (strcmp(option_name, "desc") == 0) {
options->description = option_value;
}
else if (strcmp(option_name, "dfile") == 0) {
options->desc_file = option_value;
}
else if (strcmp(option_name, "verbosity") == 0){
verbosity = atoi(option_value);
}
}
// Must have sequence and motif file names
if (argc < option_index + 2) {
fprintf(stderr, "Sequences and motifs are both required\n");
fprintf(stderr, CENTRIMO_USAGE, DEFAULT_PSEUDOCOUNT, DEFAULT_SCORE_THRESH,
DEFAULT_EVALUE_THRESH, NORMAL_VERBOSE);
exit(EXIT_FAILURE);
}
// Record the input file names
options->seq_source = argv[option_index++];
for (;option_index < argc; option_index++)
arraylst_add(argv[option_index], options->motif_sources);
// Set up path values for needed stylesheets and output files.
}
