int main(int argc, char *argv[]) {
char c;
int opt_idx, node;
FILE *out_f = NULL, *msa_f, *mod_f;
char *out_root;
TreeModel *mod;
MSA *msa;
char out_fname[STR_MED_LEN];
struct option long_opts[] = {
{"refseq", 1, 0, 'r'},
{"msa-format", 1, 0, 'i'},
{"seqs", 1, 0, 's'},
{"exclude", 0, 0, 'x'},
{"no-probs", 0, 0, 'n'},
{"suff-stats", 0, 0, 'S'},
{"encode", 1, 0, 'e'},
{"keep-gaps", 0, 0, 'k'},
{"gibbs", 1, 0, 'G'},
{"help", 0, 0, 'h'},
{0, 0, 0, 0}
};
/* arguments and defaults for options */
FILE *refseq_f = NULL;
msa_format_type msa_format = UNKNOWN_FORMAT;
int suff_stats = FALSE, exclude = FALSE, keep_gaps = FALSE, do_probs = TRUE;
List *seqlist = NULL;
PbsCode *code = NULL;
int gibbs_nsamples = -1;
while ((c = (char)getopt_long(argc, argv, "r:i:s:e:knxSh", long_opts, &opt_idx)) != -1) {
switch (c) {
case 'r':
refseq_f = phast_fopen(optarg, "r");
break;
case 'i':
msa_format = msa_str_to_format(optarg);
if (msa_format == UNKNOWN_FORMAT)
die("ERROR: unrecognized alignment format.\n");
break;
case 'S':
suff_stats = TRUE;
break;
case 'e':
code = pbs_new_from_file(phast_fopen(optarg, "r"));
break;
case 's':
seqlist = get_arg_list(optarg);
break;
case 'x':
exclude = TRUE;
break;
case 'n':
do_probs = FALSE;
break;
case 'k':
keep_gaps = TRUE;
break;
case 'G':
gibbs_nsamples = get_arg_int_bounds(optarg, 1, INFTY);
break;
case 'h':
printf("%s", HELP);
exit(0);
case '?':
die("Bad argument. Try 'prequel -h'.\n");
}
}
if (optind != argc - 3)
die("Three arguments required. Try 'prequel -h'.\n");
set_seed(-1);
if (!do_probs && (suff_stats || code != NULL))
die("ERROR: --no-probs can't be used with --suff-stats or --encode.\n");
msa_f = phast_fopen(argv[optind], "r");
if (msa_format == UNKNOWN_FORMAT)
msa_format = msa_format_for_content(msa_f, 1);
fprintf(stderr, "Reading alignment from %s...\n", argv[optind]);
if (msa_format == MAF) {
msa = maf_read(msa_f, refseq_f, 1, NULL, NULL, NULL, -1, !suff_stats, NULL,
NO_STRIP, FALSE);
/* (no need to store order if suff_stats mode) */
}
else
msa = msa_new_from_file_define_format(msa_f, msa_format, NULL);
if (msa->ss == NULL) {
fprintf(stderr, "Extracting sufficient statistics...\n");
ss_from_msas(msa, 1, TRUE, NULL, NULL, NULL, -1, 0);
}
else if (msa->ss->tuple_idx == NULL && !suff_stats)
die("ERROR: ordered representation of alignment required unless --suff-stats.\n");
mod_f = phast_fopen(argv[optind+1], "r");
out_root = argv[optind+2];
mod = tm_new_from_file(mod_f, 1);
/* MH prune just like in phastcons */
int old_nnodes = mod->tree->nnodes;
List *pruned_names = lst_new_ptr(msa->nseqs);
tm_prune(mod, msa, pruned_names);
if (lst_size(pruned_names) == (old_nnodes + 1) / 2)
die("ERROR: no match for leaves of tree in alignment (leaf names must match alignment names).\n");
if (lst_size(pruned_names) > 0) {
fprintf(stderr, "WARNING: pruned away leaves of tree with no match in alignment (");
int j;
for (j = 0; j < lst_size(pruned_names); j++)
fprintf(stderr, "%s%s", ((String*)lst_get_ptr(pruned_names, j))->chars, j < lst_size(pruned_names) - 1 ? ", " : ").\n");
}
lst_free_strings(pruned_names);
tr_name_ancestors(mod->tree);
if (mod->order != 0)
die("ERROR: Only single nucleotide models are supported.\n");
if (mod->nratecats > 1)
die("ERROR: Rate variation not supported.\n");
mod->tree_posteriors = tl_new_tree_posteriors(mod, msa, TRUE, FALSE,
FALSE, FALSE, FALSE, FALSE,
FALSE);
fprintf(stderr, "Computing posterior probabilities...\n");
if (gibbs_nsamples > 0)
die("ERROR: --gibbs not implemented yet.");
/* gb_sample_ancestral_seqs(mod, msa, mod->tree_posteriors, gibbs_nsamples); */
else
tl_compute_log_likelihood(mod, msa, NULL, NULL, -1, mod->tree_posteriors);
fprintf(stderr, "Reconstructing indels by parsimony...\n");
do_indels(msa, mod);
for (node = 0; node < mod->tree->nnodes; node++) {
int i, j;
TreeNode *n = lst_get_ptr(mod->tree->nodes, node);
if (n->lchild == NULL || n->rchild == NULL) continue;
if (seqlist != NULL) {
int in_list = str_in_list_charstr(n->name, seqlist);
if ((in_list && exclude) || (!in_list && !exclude))
continue;
}
fprintf(stderr, "Writing output for ancestral node '%s'...\n",
n->name);
if (suff_stats) {
if (out_f == NULL) {
sprintf(out_fname, "%s.stats", out_root);
out_f = phast_fopen(out_fname, "w+");
fprintf(out_f, "#count\t");
for (j = 0; j < mod->rate_matrix->size; j++)
fprintf(out_f, "p(%c)%c", mod->rate_matrix->states[j],
j == mod->rate_matrix->size - 1 ? '\n' : '\t');
}
for (i = 0; i < msa->ss->ntuples; i++) {
if (mod->tree_posteriors->base_probs[0][0][node][i] == -1)
continue; /* no base this node */
fprintf(out_f, "%.0f\t", msa->ss->counts[i]);
for (j = 0; j < mod->rate_matrix->size; j++) {
fprintf(out_f, "%f%c",
mod->tree_posteriors->base_probs[0][j][node][i],
j == mod->rate_matrix->size - 1 ? '\n' : '\t');
}
}
}
else if (code == NULL && do_probs) { /* ordinary sequence-by-sequence
output */
sprintf(out_fname, "%s.%s.probs", out_root, n->name);
out_f = phast_fopen(out_fname, "w+");
fprintf(out_f, "#");
for (j = 0; j < mod->rate_matrix->size; j++)
fprintf(out_f, "p(%c)%c", mod->rate_matrix->states[j],
j == mod->rate_matrix->size - 1 ? '\n' : '\t');
for (i = 0; i < msa->length; i++) {
if (mod->tree_posteriors->base_probs[0][0][node][msa->ss->tuple_idx[i]] == -1) {
/* no base */
if (keep_gaps) fprintf(out_f, "-\n");
/* otherwise do nothing */
}
else
for (j = 0; j < mod->rate_matrix->size; j++)
fprintf(out_f, "%f%c",
mod->tree_posteriors->base_probs[0][j][node][msa->ss->tuple_idx[i]],
j == mod->rate_matrix->size - 1 ? '\n' : '\t');
}
phast_fclose(out_f);
}
else if (code == NULL && !do_probs) { /* write point estimates
to FASTA file */
char *outseq = smalloc((msa->length + 1) * sizeof(char));
int len = 0;
for (i = 0; i < msa->length; i++) {
if (mod->tree_posteriors->base_probs[0][0][node][msa->ss->tuple_idx[i]] == -1) {
/* no base */
if (keep_gaps) outseq[len++] = GAP_CHAR;
/* otherwise do nothing */
}
else {
double maxprob = 0;
int maxidx = -1;
for (j = 0; j < mod->rate_matrix->size; j++) {
if (mod->tree_posteriors->base_probs[0][j][node][msa->ss->tuple_idx[i]] > maxprob) {
maxprob = mod->tree_posteriors->base_probs[0][j][node][msa->ss->tuple_idx[i]];
maxidx = j;
}
}
outseq[len++] = mod->rate_matrix->states[maxidx];
}
}
outseq[len] = '\0';
/* print in FASTA format */
sprintf(out_fname, "%s.%s.fa", out_root, n->name);
out_f = phast_fopen(out_fname, "w+");
print_seq_fasta(out_f, outseq, n->name, len);
phast_fclose(out_f);
sfree(outseq);
}
else { /* encoded sequence-by-sequence
output */
double error, tot_error = 0;
int ngaps = 0;
Vector *v;
unsigned *encoded;
/* first encode tuple by tuple */
v = vec_new(mod->rate_matrix->size);
encoded = smalloc(msa->ss->ntuples * sizeof(unsigned));
for (i = 0; i < msa->ss->ntuples; i++) {
if (mod->tree_posteriors->base_probs[0][0][node][i] == -1) {
encoded[i] = code->gap_code;
ngaps += msa->ss->counts[i];
}
else {
for (j = 0; j < mod->rate_matrix->size; j++)
vec_set(v, j, mod->tree_posteriors->base_probs[0][j][node][i]);
encoded[i] = pbs_get_index(code, v, &error);
tot_error += error * msa->ss->counts[i];
}
}
vec_free(v);
/* now write site by site */
sprintf(out_fname, "%s.%s.bin", out_root, n->name);
out_f = phast_fopen(out_fname, "w+");
for (i = 0; i < msa->length; i++) {
if (keep_gaps || encoded[msa->ss->tuple_idx[i]] != code->gap_code)
pbs_write_binary(code, encoded[msa->ss->tuple_idx[i]], out_f);
}
fprintf(stderr, "Average approximation error ('%s'): %f bits\n",
n->name, tot_error/(msa->length - ngaps));
sfree(encoded);
}
}
fprintf(stderr, "Done.\n");
return 0;
}
int main(int argc, char *argv[]) {
char c;
List *l;
int i, j, strand, bed_output = 0, backgd_nmods = -1, feat_nmods = -1,
winsize = -1, verbose = 0, max_nmods, memblocksize, old_nleaves,
refidx = 1, base_by_base = FALSE, windowWig = FALSE;
TreeModel **backgd_mods = NULL, **feat_mods = NULL;
HMM *backgd_hmm = NULL, *feat_hmm = NULL;
msa_format_type inform = UNKNOWN_FORMAT;
GFF_Set *features = NULL;
MSA *msa, *msa_compl=NULL;
double **backgd_emissions, **feat_emissions, **mem, **dummy_emissions,
*winscore_pos=NULL, *winscore_neg=NULL;
int *no_alignment=NULL;
List *pruned_names;
char *msa_fname;
FILE *infile;
int opt_idx;
struct option long_opts[] = {
{"background-mods", 1, 0, 'b'},
{"background-hmm", 1, 0, 'B'},
{"feature-mods", 1, 0, 'f'},
{"feature-hmm", 1, 0, 'F'},
{"features", 1, 0, 'g'},
{"window", 1, 0, 'w'},
{"window-wig", 1, 0, 'W'},
{"base-by-base", 0, 0, 'y'},
{"msa-format", 1, 0, 'i'},
{"refidx", 1, 0, 'r'},
{"output-bed", 0, 0, 'd'},
{"verbose", 0, 0, 'v'},
{"help", 0, 0, 'h'},
{0, 0, 0, 0}
};
while ((c = getopt_long(argc, argv, "B:b:F:f:r:g:w:W:i:ydvh", long_opts, &opt_idx)) != -1) {
switch (c) {
case 'B':
backgd_hmm = hmm_new_from_file(phast_fopen(optarg, "r"));
break;
case 'b':
l = get_arg_list(optarg);
backgd_nmods = lst_size(l);
backgd_mods = smalloc(backgd_nmods * sizeof(void*));
for (i = 0; i < backgd_nmods; i++)
backgd_mods[i] = tm_new_from_file(phast_fopen(((String*)lst_get_ptr(l, i))->chars, "r"), 1);
lst_free_strings(l);
lst_free(l);
break;
case 'F':
feat_hmm = hmm_new_from_file(phast_fopen(optarg, "r"));
break;
case 'f':
l = get_arg_list(optarg);
feat_nmods = lst_size(l);
feat_mods = smalloc(feat_nmods * sizeof(void*));
for (i = 0; i < feat_nmods; i++)
feat_mods[i] = tm_new_from_file(phast_fopen(((String*)lst_get_ptr(l, i))->chars, "r"), 1);
lst_free_strings(l);
lst_free(l);
break;
case 'g':
features = gff_read_set(phast_fopen(optarg, "r"));
break;
case 'w':
winsize = get_arg_int(optarg);
if (winsize <= 0) die("ERROR: window size must be positive.\n");
break;
case 'W':
winsize = get_arg_int(optarg);
if (winsize <= 0) die("ERROR: window size must be positive.\n");
windowWig = TRUE;
break;
case 'y':
base_by_base = TRUE;
break;
case 'i':
inform = msa_str_to_format(optarg);
if (inform == UNKNOWN_FORMAT) die("Bad argument to -i.\n");
break;
case 'r':
refidx = get_arg_int_bounds(optarg, 0, INFTY);
break;
case 'd':
bed_output = 1;
break;
case 'h':
printf("%s", HELP);
exit(0);
case 'v':
verbose = 1;
break;
case '?':
die("Bad argument. Try '%s -h'.\n", argv[0]);
}
}
set_seed(-1);
if (backgd_mods == NULL || feat_mods == NULL)
die("ERROR: -b and -f required. Try '%s -h'.\n", argv[0]);
if (backgd_nmods == 1 && backgd_hmm == NULL)
backgd_hmm = hmm_create_trivial();
else if (backgd_hmm == NULL)
die("ERROR: -B required. Try '%s -h'.\n", argv[0]);
if (feat_nmods == 1 && feat_hmm == NULL)
feat_hmm = hmm_create_trivial();
else if (feat_hmm == NULL)
die("ERROR: -F required. Try '%s -h'.\n", argv[0]);
if ((winsize == -1 && features == NULL && !base_by_base) ||
(winsize != -1 && features != NULL) ||
(winsize != -1 && base_by_base) ||
(features != NULL && base_by_base))
die("ERROR: must specify exactly one of -g, -w, and -y. Try '%s -h'.\n", argv[0]);
if (backgd_hmm->nstates != backgd_nmods)
die("ERROR: number of states must equal number of tree models for background.\n");
if (feat_hmm->nstates != feat_nmods)
die("ERROR: number of states must equal number of tree models for features.\n");
if (features != NULL && lst_size(features->features) == 0)
die("ERROR: empty features file.\n");
if (base_by_base && (backgd_nmods > 1 || feat_nmods > 1))
die("ERROR: only single phylogenetic models (not HMMs) are supported with --base-by-base.\n");
if (optind != argc - 1)
die("ERROR: too few arguments. Try '%s -h'.\n", argv[0]);
if (verbose) fprintf(stderr, "Reading alignment ...\n");
msa_fname = argv[optind];
infile = phast_fopen(msa_fname, "r");
if (inform == UNKNOWN_FORMAT)
inform = msa_format_for_content(infile, 1);
if (inform == MAF)
msa = maf_read(infile, NULL, 1, NULL, NULL,
NULL, -1, TRUE, NULL, NO_STRIP, FALSE);
else
msa = msa_new_from_file_define_format(infile, inform, NULL);
if (msa_alph_has_lowercase(msa)) msa_toupper(msa);
msa_remove_N_from_alph(msa);
/* need ordered representation of alignment */
if (msa->seqs == NULL && (msa->ss == NULL || msa->ss->tuple_idx == NULL) )
die("ERROR: ordered sufficient statistics are required.\n");
pruned_names = lst_new_ptr(msa->nseqs);
for (i = 0; i < backgd_nmods; i++) {
old_nleaves = (backgd_mods[i]->tree->nnodes + 1) / 2;
tm_prune(backgd_mods[i], msa, pruned_names);
if (lst_size(pruned_names) >= old_nleaves)
die("ERROR: no match for leaves of tree in alignment (background model #%d)\n", i+1);
else if (lst_size(pruned_names) > 0) {
fprintf(stderr, "WARNING: pruned away leaves in background model (#%d) with no match in alignment (", i+1);
for (j = 0; j < lst_size(pruned_names); j++)
fprintf(stderr, "%s%s", ((String*)lst_get_ptr(pruned_names, j))->chars,
j < lst_size(pruned_names) - 1 ? ", " : ").\n");
}
lst_free_strings(pruned_names);
}
for (i = 0; i < feat_nmods; i++) {
old_nleaves = (feat_mods[i]->tree->nnodes + 1) / 2;
tm_prune(feat_mods[i], msa, pruned_names);
if (lst_size(pruned_names) >= old_nleaves)
die("ERROR: no match for leaves of tree in alignment (features model #%d)\n", i+1);
else if (lst_size(pruned_names) > 0) {
fprintf(stderr, "WARNING: pruned away leaves in features model (#%d) with no match in alignment (", i+1);
for (j = 0; j < lst_size(pruned_names); j++)
fprintf(stderr, "%s%s", ((String*)lst_get_ptr(pruned_names, j))->chars,
j < lst_size(pruned_names) - 1 ? ", " : ").\n");
}
lst_free_strings(pruned_names);
}
lst_free(pruned_names);
/* first have to subtract offset from features, if necessary */
if (msa->idx_offset != 0 && features != NULL) {
for (i = 0; i < lst_size(features->features); i++) {
GFF_Feature *f = lst_get_ptr(features->features, i);
f->start -= msa->idx_offset;
f->end -= msa->idx_offset;
}
}
/* convert to coord frame of alignment */
if (features != NULL && refidx != 0) {
if (verbose) fprintf(stderr, "Mapping coordinates ...\n");
msa_map_gff_coords(msa, features, refidx, 0, 0);
if (lst_size(features->features) == 0)
die("ERROR: no features within coordinate range of alignment.\n");
}
/* Make a reverse complemented copy of the alignment. The two
strands will be processed separately, to avoid problems with
overlapping features, etc. */
if (!base_by_base) { /* skip in base by base case */
if (verbose) fprintf(stderr, "Creating reverse complemented alignment ...\n");
msa_compl = msa_create_copy(msa, 0);
/* temporary workaround: make sure reverse complement not based on
sufficient stats */
if (msa_compl->seqs == NULL) ss_to_msa(msa_compl);
if (msa_compl->ss != NULL) {
ss_free(msa_compl->ss);
msa_compl->ss = NULL;
}
msa_reverse_compl(msa_compl);
}
/* allocate memory for computing scores */
backgd_emissions = smalloc(backgd_nmods * sizeof(void*));
for (i = 0; i < backgd_nmods; i++)
backgd_emissions[i] = smalloc(msa->length * sizeof(double));
feat_emissions = smalloc(feat_nmods * sizeof(void*));
for (i = 0; i < feat_nmods; i++)
feat_emissions[i] = smalloc(msa->length * sizeof(double));
max_nmods = max(backgd_nmods, feat_nmods);
dummy_emissions = smalloc(max_nmods * sizeof(void*));
mem = smalloc(max_nmods * sizeof(void*));
/* memory for forward algorithm -- each block must be as large as
the largest feature */
if (features != NULL) {
for (i = 0, memblocksize = -1; i < lst_size(features->features); i++) {
GFF_Feature *f = lst_get_ptr(features->features, i);
if (f->end - f->start + 1 > memblocksize)
memblocksize = f->end - f->start + 1;
}
}
else memblocksize = winsize; /* -1 if base-by-base mode */
if (memblocksize > 0)
for (i = 0; i < max_nmods; i++)
mem[i] = smalloc(memblocksize * sizeof(double));
if (winsize != -1) {
winscore_pos = smalloc(msa->length * sizeof(double));
winscore_neg = smalloc(msa->length * sizeof(double));
no_alignment = smalloc(msa->length * sizeof(int));
for (i = 0; i < msa->length; i++) {
winscore_pos[i] = winscore_neg[i] = NEGINFTY;
if (refidx == 0)
no_alignment[i] = FALSE;
else
no_alignment[i] = msa_missing_col(msa, refidx, i);
}
}
/* the rest will be repeated for each strand */
for (strand = 1; strand <= 2; strand++) {
MSA *thismsa = strand == 1 ? msa : msa_compl;
double *winscore = strand == 1 ? winscore_pos : winscore_neg;
if (base_by_base && strand == 2) break; /* don't do second pass in
base_by_base case */
if (verbose) fprintf(stderr, "Processing %c strand ...\n",
strand == 1 ? '+' : '-');
/* set up dummy categories array, so that emissions are only
computed where needed */
thismsa->categories = smalloc(thismsa->length * sizeof(int));
thismsa->ncats = 1;
if (winsize != -1) {
if (strand == 1)
for (i = 0; i < thismsa->length; i++)
thismsa->categories[i] = no_alignment[i] ? 0 : 1;
else
for (i = 0; i < thismsa->length; i++)
thismsa->categories[i] = no_alignment[thismsa->length - i - 1] ? 0 : 1;
}
else if (features != NULL) {
for (i = 0; i < thismsa->length; i++) thismsa->categories[i] = 0;
for (i = 0; i < lst_size(features->features); i++) {
GFF_Feature *f = lst_get_ptr(features->features, i);
if (f->start <= 0 || f->end <= 0) {
fprintf(stderr, "WARNING: feature out of range ('");
gff_print_feat(stderr, f);
fprintf(stderr, "')\n");
continue;
}
if (strand == 1 && f->strand != '-')
for (j = f->start - 1; j < f->end; j++)
thismsa->categories[j] = 1;
else if (strand == 2 && f->strand == '-')
for (j = thismsa->length - f->end;
j < thismsa->length - f->start + 1; j++)
thismsa->categories[j] = 1;
}
}
else { /* base-by-base scores */
for (i = 0; i < thismsa->length; i++) thismsa->categories[i] = 1;
}
if (thismsa->ss != NULL) ss_update_categories(thismsa);
/* compute emissions */
for (i = 0; i < backgd_nmods; i++) {
if (verbose)
fprintf(stderr, "Computing emissions for background model #%d ...\n", i+1);
tl_compute_log_likelihood(backgd_mods[i], thismsa,
backgd_emissions[i], NULL, 1, NULL);
}
for (i = 0; i < feat_nmods; i++) {
if (verbose)
fprintf(stderr, "Computing emissions for features model #%d ...\n", i+1);
tl_compute_log_likelihood(feat_mods[i], thismsa,
feat_emissions[i], NULL, 1, NULL);
}
/* now compute scores */
if (winsize != -1) { /* windows case */
int winstart;
if (verbose) fprintf(stderr, "Computing scores ...\n");
for (winstart = 0; winstart <= thismsa->length - winsize; winstart++) {
int centeridx = winstart + winsize/2;
if (strand == 2) centeridx = thismsa->length - centeridx - 1;
if (no_alignment[centeridx]) continue;
for (j = 0; j < feat_nmods; j++)
dummy_emissions[j] = &(feat_emissions[j][winstart]);
winscore[centeridx] = hmm_forward(feat_hmm, dummy_emissions,
winsize, mem);
if (winscore[centeridx] <= NEGINFTY) {
winscore[centeridx] = NEGINFTY;
continue;
}
for (j = 0; j < backgd_nmods; j++)
dummy_emissions[j] = &(backgd_emissions[j][winstart]);
winscore[centeridx] -= hmm_forward(backgd_hmm, dummy_emissions,
winsize, mem);
if (winscore[centeridx] < NEGINFTY) winscore[centeridx] = NEGINFTY;
}
}
else if (features != NULL) { /* features case */
if (verbose) fprintf(stderr, "Computing scores ...\n");
for (i = 0; i < lst_size(features->features); i++) {
GFF_Feature *f = lst_get_ptr(features->features, i);
int s, e;
if ((strand == 1 && f->strand == '-') ||
(strand == 2 && f->strand != '-') ||
f->start <= 0 || f->end <= 0 || f->end - f->start < 0)
continue;
/* effective coords */
if (f->strand == '-') {
s = thismsa->length - f->end + 1;
e = thismsa->length - f->start + 1;
}
else {
s = f->start;
e = f->end;
}
f->score_is_null = 0;
for (j = 0; j < feat_nmods; j++)
dummy_emissions[j] = &(feat_emissions[j][s-1]);
f->score = hmm_forward(feat_hmm, dummy_emissions, e - s + 1, mem);
if (f->score <= NEGINFTY) {
f->score = NEGINFTY;
continue;
}
for (j = 0; j < backgd_nmods; j++)
dummy_emissions[j] = &(backgd_emissions[j][s-1]);
f->score -= hmm_forward(backgd_hmm, dummy_emissions, e - s + 1, mem);
if (f->score < NEGINFTY) f->score = NEGINFTY;
}
}
}
if (verbose) fprintf(stderr, "Generating output ...\n");
if (winsize != -1 && windowWig == FALSE) { /* standard windows output */
for (i = 0, j = 0; i < msa->length; i++) {
if (no_alignment[i] == FALSE)
printf("%d\t%.3f\t%.3f\n", j + msa->idx_offset + 1, winscore_pos[i],
winscore_neg[i]);
if (ss_get_char_pos(msa, i, 0, 0) != GAP_CHAR) j++;
}
}
else if (windowWig == TRUE) { /* windows with wig output */
int last = NEGINFTY;
for (i = 0, j = 0; i < msa->length; i++) {
if (refidx == 0 || msa_get_char(msa, refidx-1, i) != GAP_CHAR) {
if (no_alignment[i] == FALSE && winscore_pos[i] > NEGINFTY) {
if (j > last + 1)
printf("fixedStep chrom=%s start=%d step=1\n",
refidx > 0 ? msa->names[refidx-1] : "alignment",
j + msa->idx_offset + 1);
printf("%.3f\n", winscore_pos[i]);
last = j;
}
j++;
}
}
}
else if (features != NULL) { /* features output */
/* return to coord frame of reference seq (also, replace offset) */
if (refidx != 0)
msa_map_gff_coords(msa, features, 0, refidx, msa->idx_offset);
else if (msa->idx_offset != 0) {
for (i = 0; i < lst_size(features->features); i++) {
GFF_Feature *f = lst_get_ptr(features->features, i);
f->start += msa->idx_offset;
f->end += msa->idx_offset;
}
}
if (bed_output)
gff_print_bed(stdout, features, FALSE);
else
gff_print_set(stdout, features);
}
else { /* base-by-base scores */
/* in this case, we can just output the difference between the emissions */
printf("fixedStep chrom=%s start=%d step=1\n",
refidx > 0 ? msa->names[refidx-1] : "alignment",
msa->idx_offset + 1);
for (i = 0, j = 0; i < msa->length; i++) {
if (refidx == 0 || msa_get_char(msa, refidx-1, i) != GAP_CHAR) {
printf("%.3f\n", feat_emissions[0][i] - backgd_emissions[0][i]);
j++;
}
}
}
if (verbose) fprintf(stderr, "\nDone.\n");
return 0;
}
int main(int argc, char *argv[]) {
List *pruned_names = lst_new_ptr(5);
TreeModel *source_mod;
MSA *msa = NULL, *out_msa;
IndelHistory *ih;
char *read_hist_fname = NULL;
char c;
int opt_idx, old_nnodes, i;
msa_format_type msa_format = UNKNOWN_FORMAT;
int output_alignment = FALSE, ia_names = FALSE;
struct option long_opts[] = {
{"msa-format", 1, 0, 'i'},
{"output-alignment", 0, 0, 'A'},
{"read-history", 1, 0, 'H'},
{"ia-names", 0, 0, 'I'},
{"help", 0, 0, 'h'},
{0, 0, 0, 0}
};
while ((c = getopt_long(argc, argv, "i:H:AIh", long_opts, &opt_idx)) != -1) {
switch (c) {
case 'i':
msa_format = msa_str_to_format(optarg);
if (msa_format == -1)
die("ERROR: unrecognized alignment format.\n");
break;
case 'A':
output_alignment = TRUE;
break;
case 'H':
read_hist_fname = optarg;
break;
case 'I':
ia_names = TRUE;
break;
case 'h':
printf("%s", HELP);
exit(0);
case '?':
die("Bad argument. Try 'indelHistory -h'.\n");
}
}
set_seed(-1);
if (read_hist_fname != NULL) {
fprintf(stderr, "Reading indel history from %s...\n", read_hist_fname);
ih = ih_new_from_file(phast_fopen(read_hist_fname, "r"));
}
else {
FILE *mfile;
if (optind != argc - 2)
die("Two arguments required. Try 'indelHistory -h'.\n");
fprintf(stderr, "Reading alignment from %s...\n", argv[optind]);
mfile = phast_fopen(argv[optind], "r");
if (msa_format == UNKNOWN_FORMAT)
msa_format = msa_format_for_content(mfile, 1);
msa = msa_new_from_file_define_format(mfile, msa_format, "ACGTNB^.-");
phast_fclose(mfile);
if (msa->seqs == NULL && (msa->ss == NULL || msa->ss->tuple_idx == NULL))
die("ERROR: ordered representation of alignment required.\n");
fprintf(stderr, "Reading tree from %s...\n", argv[optind+1]);
source_mod = tm_new_from_file(phast_fopen(argv[optind+1], "r"), 1);
/* prune tree, if necessary */
old_nnodes = source_mod->tree->nnodes;
tm_prune(source_mod, msa, pruned_names);
if (lst_size(pruned_names) == (old_nnodes + 1) / 2)
die("ERROR: no match for leaves of tree in alignment (leaf names must match alignment names).\n");
if (lst_size(pruned_names) > 0) {
fprintf(stderr, "WARNING: pruned away leaves of tree with no match in alignment (");
for (i = 0; i < lst_size(pruned_names); i++)
fprintf(stderr, "%s%s", ((String*)lst_get_ptr(pruned_names, i))->chars,
i < lst_size(pruned_names) - 1 ? ", " : ").\n");
}
lst_free(pruned_names);
tr_name_ancestors(source_mod->tree);
if (msa->nseqs > (source_mod->tree->nnodes + 1) / 2) { /* assume ancestral
seqs specified
in this case */
if (ia_names) {
fprintf(stderr, "Converting sequence names...\n");
ih_convert_ia_names(msa, source_mod->tree);
}
fprintf(stderr, "Extracting indel history from alignment...\n");
ih = ih_extract_from_alignment(msa, source_mod->tree);
}
else { /* infer by parsimony */
if (msa->ss == NULL) {
fprintf(stderr, "Extracting sufficient statistics...\n");
ss_from_msas(msa, 1, TRUE, NULL, NULL, NULL, -1, 0);
}
fprintf(stderr, "Inferring indel history by parsimony...\n");
ih = ih_reconstruct(msa, source_mod->tree);
}
}
if (output_alignment) {
out_msa = ih_as_alignment(ih, msa);
msa_print(stdout, out_msa, FASTA, FALSE);
}
else
ih_print(ih, stdout,
read_hist_fname != NULL ? read_hist_fname : argv[optind],
"indelHistory");
fprintf(stderr, "Done.\n");
return 0;
}
int main(int argc, char *argv[]) {
char c;
char *msa_fname = NULL;
int opt_idx, i, old_nnodes;
MSA *msa;
List *pruned_names = lst_new_ptr(5), *tmpl;
BDPhyloHmm *bdphmm;
GFF_Set *predictions;
int found = FALSE;
List *ignore_types = lst_new_ptr(1);
struct option long_opts[] = {
{"refseq", 1, 0, 'M'},
{"msa-format", 1, 0, 'i'},
{"refidx", 1, 0, 'r'},
{"rho", 1, 0, 'R'},
{"phi", 1, 0, 'p'},
{"transitions", 1, 0, 't'},
{"expected-length", 1, 0, 'E'},
{"target-coverage", 1, 0, 'C'},
{"seqname", 1, 0, 'N'},
{"idpref", 1, 0, 'P'},
{"indel-model", 1, 0, 'I'},
{"indel-history", 1, 0, 'H'},
{"help", 0, 0, 'h'},
{0, 0, 0, 0}
};
/* arguments and defaults for options */
FILE *refseq_f = NULL, *msa_f = NULL;
msa_format_type msa_format = UNKNOWN_FORMAT;
TreeModel *source_mod;
double rho = DEFAULT_RHO, mu = DEFAULT_MU, nu = DEFAULT_NU,
phi = DEFAULT_PHI, gamma = -1, omega = -1,
alpha_c = -1, beta_c = -1, tau_c = -1,
alpha_n = -1, beta_n = -1, tau_n = -1;
int set_transitions = FALSE, refidx = 1, estim_phi = TRUE,
estim_gamma = TRUE, estim_omega = TRUE;
char *seqname = NULL, *idpref = NULL;
IndelHistory *ih = NULL;
while ((c = getopt_long(argc, argv, "R:t:p:E:C:r:M:i:N:P:I:H:h", long_opts, &opt_idx)) != -1) {
switch (c) {
case 'R':
rho = get_arg_dbl_bounds(optarg, 0, 1);
break;
case 't':
if (optarg[0] != '~') estim_gamma = estim_omega = FALSE;
else optarg = &optarg[1];
set_transitions = TRUE;
tmpl = get_arg_list_dbl(optarg);
if (lst_size(tmpl) != 2)
die("ERROR: bad argument to --transitions.\n");
mu = lst_get_dbl(tmpl, 0);
nu = lst_get_dbl(tmpl, 1);
if (mu <= 0 || mu >= 1 || nu <= 0 || nu >= 1)
die("ERROR: bad argument to --transitions.\n");
lst_free(tmpl);
break;
case 'p':
if (optarg[0] != '~') estim_phi = FALSE;
else optarg = &optarg[1];
phi = get_arg_dbl_bounds(optarg, 0, 1);
break;
case 'E':
if (optarg[0] != '~') estim_omega = FALSE;
else optarg = &optarg[1];
omega = get_arg_dbl_bounds(optarg, 1, INFTY);
mu = 1/omega;
break;
case 'C':
if (optarg[0] != '~') estim_gamma = FALSE;
else optarg = &optarg[1];
gamma = get_arg_dbl_bounds(optarg, 0, 1);
break;
case 'r':
refidx = get_arg_int_bounds(optarg, 0, INFTY);
break;
case 'M':
refseq_f = phast_fopen(optarg, "r");
break;
case 'i':
msa_format = msa_str_to_format(optarg);
if (msa_format == UNKNOWN_FORMAT)
die("ERROR: unrecognized alignment format.\n");
break;
case 'N':
seqname = optarg;
break;
case 'P':
idpref = optarg;
break;
case 'I':
tmpl = get_arg_list_dbl(optarg);
if (lst_size(tmpl) != 3 && lst_size(tmpl) != 6)
die("ERROR: bad argument to --indel-model.\n");
alpha_n = lst_get_dbl(tmpl, 0);
beta_n = lst_get_dbl(tmpl, 1);
tau_n = lst_get_dbl(tmpl, 2);
if (lst_size(tmpl) == 6) {
alpha_c = lst_get_dbl(tmpl, 3);
beta_c = lst_get_dbl(tmpl, 4);
tau_c = lst_get_dbl(tmpl, 5);
}
else {
alpha_c = alpha_n; beta_c = beta_n; tau_c = tau_n;
}
if (alpha_c <= 0 || alpha_c >= 1 || beta_c <= 0 || beta_c >= 1 ||
tau_c <= 0 || tau_c >= 1 || alpha_n <= 0 || alpha_n >= 1 ||
beta_n <= 0 || beta_n >= 1 || tau_n <= 0 || tau_n >= 1)
die("ERROR: bad argument to --indel-model.\n");
break;
case 'H':
fprintf(stderr, "Reading indel history from %s...\n", optarg);
ih = ih_new_from_file(phast_fopen(optarg, "r"));
break;
case 'h':
printf("%s", HELP);
exit(0);
case '?':
die("Bad argument. Try 'dless -h'.\n");
}
}
if (optind != argc - 1)
die("Missing alignment file or model file. Try 'dless -h'.\n");
if (set_transitions && (gamma != -1 || omega != -1))
die("ERROR: --transitions and --target-coverage/--expected-length cannot be used together.\n");
if ((gamma != -1 && omega == -1) || (gamma == -1 && omega != -1))
die("ERROR: --target-coverage and --expecteed-length must be used together.\n");
set_seed(-1);
if (gamma != -1)
nu = gamma/(1-gamma) * mu;
fprintf(stderr, "Reading tree model from %s...\n", argv[optind]);
source_mod = tm_new_from_file(phast_fopen(argv[optind], "r"), 1);
if (source_mod->nratecats > 1)
die("ERROR: rate variation not currently supported.\n");
if (source_mod->order > 0)
die("ERROR: only single nucleotide models are currently supported.\n");
if (!tm_is_reversible(source_mod))
phast_warning("WARNING: p-value computation assumes reversibility and your model is non-reversible.\n");
/* read alignment */
msa_f = phast_fopen(argv[optind], "r");
fprintf(stderr, "Reading alignment from %s...\n", argv[optind]);
if (msa_format == UNKNOWN_FORMAT)
msa_format = msa_format_for_content(msa_f, 1);
if (msa_format == MAF) {
msa = maf_read(msa_f, refseq_f, 1, NULL, NULL, NULL, -1, TRUE, NULL,
NO_STRIP, FALSE);
}
else
msa = msa_new_from_file_define_format(msa_f, msa_format, NULL);
if (msa_alph_has_lowercase(msa)) msa_toupper(msa);
msa_remove_N_from_alph(msa);
if (msa->ss == NULL) {
fprintf(stderr, "Extracting sufficient statistics...\n");
ss_from_msas(msa, 1, TRUE, NULL, NULL, NULL, -1, 0);
}
else if (msa->ss->tuple_idx == NULL)
die("ERROR: ordered representation of alignment required unless --suff-stats.\n");
/* prune tree, if necessary */
old_nnodes = source_mod->tree->nnodes;
tm_prune(source_mod, msa, pruned_names);
if (lst_size(pruned_names) == (old_nnodes + 1) / 2)
die("ERROR: no match for leaves of tree in alignment (leaf names must match alignment names).\n");
if (lst_size(pruned_names) > 0) {
fprintf(stderr, "WARNING: pruned away leaves of tree with no match in alignment (");
for (i = 0; i < lst_size(pruned_names); i++)
fprintf(stderr, "%s%s", ((String*)lst_get_ptr(pruned_names, i))->chars,
i < lst_size(pruned_names) - 1 ? ", " : ").\n");
}
/* this has to be done after pruning tree */
tr_name_ancestors(source_mod->tree);
/* also make sure match for reference sequence in tree */
if (refidx > 0) {
for (i = 0, found = FALSE; !found && i < source_mod->tree->nnodes; i++) {
TreeNode *n = lst_get_ptr(source_mod->tree->nodes, i);
if (!strcmp(n->name, msa->names[refidx-1]))
found = TRUE;
}
if (!found) die("ERROR: no match for reference sequence in tree.\n");
}
/* checks for indel model */
if (alpha_c > 0) {
if (ih == NULL) {
fprintf(stderr, "Reconstructing indel history by parsimony...\n");
ih = ih_reconstruct(msa, source_mod->tree);
}
else {
if (ih->ncols != msa->length)
die("ERROR: indel history doesn't seem to match alignment.\n");
if (ih->tree->nnodes != source_mod->tree->nnodes)
die("ERROR: indel history doesn't seem to match tree model.\n");
}
}
bdphmm = bd_new(source_mod, rho, mu, nu, phi, alpha_c, beta_c, tau_c,
alpha_n, beta_n, tau_n, estim_gamma, estim_omega,
estim_phi);
/* compute emissions */
phmm_compute_emissions(bdphmm->phmm, msa, FALSE);
/* add emissions for indel model, if necessary */
if (alpha_c > 0) {
fprintf(stderr, "Adjusting emissions for indels...\n");
bd_add_indel_emissions(bdphmm, ih);
}
/* postprocess for missing data (requires special handling) */
fprintf(stderr, "Adjusting emissions for missing data...\n");
bd_handle_missing_data(bdphmm, msa);
if (estim_gamma || estim_omega || estim_phi) {
fprintf(stderr, "Estimating free parameters...\n");
bd_estimate_transitions(bdphmm, msa);
}
/* set seqname and idpref, if necessary */
if (seqname == NULL || idpref == NULL) {
/* derive default from file name root */
String *tmp = str_new_charstr(msa_fname);
if (!str_equals_charstr(tmp, "-")) {
str_remove_path(tmp);
str_root(tmp, '.');
if (idpref == NULL) idpref = copy_charstr(tmp->chars);
str_root(tmp, '.'); /* apply one more time for double suffix */
if (seqname == NULL) seqname = tmp->chars;
}
else if (seqname == NULL) seqname = "refseq";
}
/* obtain predictions */
fprintf(stderr, "Running Viterbi algorithm...\n");
predictions = phmm_predict_viterbi(bdphmm->phmm, seqname, NULL, idpref, NULL);
lst_push_ptr(ignore_types, str_new_charstr("nonconserved"));
gff_filter_by_type(predictions, ignore_types, TRUE, NULL);
/* score predictions */
fprintf(stderr, "Scoring predictions...\n");
bd_score_predictions(bdphmm, predictions);
/* can free emissions now */
for (i = 0; i < bdphmm->phmm->hmm->nstates; i++)
sfree(bdphmm->phmm->emissions[i]);
sfree(bdphmm->phmm->emissions);
bdphmm->phmm->emissions = NULL;
/* convert GFF to coord frame of reference sequence and adjust
coords by idx_offset, if necessary */
if (refidx != 0 || msa->idx_offset != 0)
msa_map_gff_coords(msa, predictions, 0, refidx, msa->idx_offset);
if (refidx != 0)
gff_flatten(predictions);
/* necessary because coord conversion might create overlapping
features (can happen in deletions in reference sequence) */
/* now output predictions */
fprintf(stderr, "Writing GFF to stdout...\n");
gff_print_set(stdout, predictions);
fprintf(stderr, "Done.\n");
return 0;
}
