static int gt_seed_extend_runner(GT_UNUSED int argc,
GT_UNUSED const char **argv,
GT_UNUSED int parsed_args,
void *tool_arguments,
GtError *err)
{
GtSeedExtendArguments *arguments = tool_arguments;
GtEncseqLoader *encseq_loader = NULL;
GtEncseq *aencseq = NULL, *bencseq = NULL;
GtGreedyextendmatchinfo *grextinfo = NULL;
GtXdropmatchinfo *xdropinfo = NULL;
GtQuerymatchoutoptions *querymatchoutopt = NULL;
GtTimer *seedextendtimer = NULL;
GtExtendCharAccess cam = GT_EXTEND_CHAR_ACCESS_ANY;
GtUword errorpercentage = 0UL;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments != NULL);
gt_assert(arguments->se_minidentity >= GT_EXTEND_MIN_IDENTITY_PERCENTAGE &&
arguments->se_minidentity <= 100UL);
/* Calculate error percentage from minidentity */
errorpercentage = 100UL - arguments->se_minidentity;
/* Measure whole running time */
if (arguments->benchmark || arguments->verbose) {
gt_showtime_enable();
}
if (gt_showtime_enabled())
{
seedextendtimer = gt_timer_new();
gt_timer_start(seedextendtimer);
}
/* Load encseq A */
encseq_loader = gt_encseq_loader_new();
gt_encseq_loader_enable_autosupport(encseq_loader);
aencseq = gt_encseq_loader_load(encseq_loader,
gt_str_get(arguments->dbs_indexname),
err);
if (aencseq == NULL)
had_err = -1;
/* If there is a 2nd read set: Load encseq B */
if (!had_err) {
if (strcmp(gt_str_get(arguments->dbs_queryname), "") != 0) {
bencseq = gt_encseq_loader_load(encseq_loader,
gt_str_get(arguments->dbs_queryname),
err);
} else {
bencseq = gt_encseq_ref(aencseq);
}
if (bencseq == NULL) {
had_err = -1;
gt_encseq_delete(aencseq);
}
}
gt_encseq_loader_delete(encseq_loader);
/* set character access method */
if (!had_err && (gt_option_is_set(arguments->se_option_greedy) ||
gt_option_is_set(arguments->se_option_xdrop) ||
arguments->se_alignmentwidth > 0))
{
cam = gt_greedy_extend_char_access(gt_str_get
(arguments->se_char_access_mode),
err);
if ((int) cam == -1) {
had_err = -1;
gt_encseq_delete(aencseq);
gt_encseq_delete(bencseq);
}
}
/* Use bias dependent parameters, adapted from E. Myers' DALIGNER */
if (!had_err && arguments->bias_parameters) {
const GtAlphabet *alpha = gt_encseq_alphabet(aencseq);
const double bias_factor[10] = {.690, .690, .690, .690, .780,
.850, .900, .933, .966, 1.000};
if (gt_alphabet_is_dna(alpha)) {
GtUword at, cg;
at = gt_encseq_charcount(aencseq, gt_alphabet_encode(alpha, 'a'));
at += gt_encseq_charcount(aencseq, gt_alphabet_encode(alpha, 't'));
cg = gt_encseq_charcount(aencseq, gt_alphabet_encode(alpha, 'c'));
cg += gt_encseq_charcount(aencseq, gt_alphabet_encode(alpha, 'g'));
if (at + cg > 0) {
const double ratio = (double)MIN(at, cg) / (at + cg);
int bias_index = (int)MAX(0.0, (ratio + 0.025) * 20.0 - 1.0);
gt_assert(bias_index < 10);
arguments->se_maxalilendiff = 30;
arguments->se_perc_match_hist = (GtUword)(100.0 - errorpercentage *
bias_factor[bias_index]);
if (arguments->verbose) {
printf("# Base ratio = %4.2lf -> percmathistory = "GT_WU"\n",
ratio, arguments->se_perc_match_hist);
}
} else {
had_err = -1;
}
} else {
had_err = -1;
}
if (had_err) {
gt_error_set(err, "option \"-bias-parameters\" can only be applied to "
"the DNA alphabet");
gt_encseq_delete(aencseq);
gt_encseq_delete(bencseq);
}
}
/* Prepare options for greedy extension */
if (!had_err && gt_option_is_set(arguments->se_option_greedy)) {
grextinfo = gt_greedy_extend_matchinfo_new(errorpercentage,
arguments->se_maxalilendiff,
arguments->se_historysize,
arguments->se_perc_match_hist,
arguments->se_alignlength,
cam,
arguments->se_extendgreedy);
if (arguments->benchmark) {
gt_greedy_extend_matchinfo_silent_set(grextinfo);
}
}
/* Prepare options for xdrop extension */
if (!had_err && gt_option_is_set(arguments->se_option_xdrop)) {
xdropinfo = gt_xdrop_matchinfo_new(arguments->se_alignlength,
errorpercentage,
arguments->se_xdropbelowscore,
arguments->se_extendxdrop);
if (arguments->benchmark) {
gt_xdrop_matchinfo_silent_set(xdropinfo);
}
}
/* Prepare output options */
if (!had_err && (arguments->se_alignmentwidth > 0 ||
gt_option_is_set(arguments->se_option_xdrop)))
{
querymatchoutopt
= gt_querymatchoutoptions_new(arguments->se_alignmentwidth);
if (gt_option_is_set(arguments->se_option_xdrop) ||
gt_option_is_set(arguments->se_option_greedy))
{
const GtUword sensitivity = gt_option_is_set(arguments->se_option_greedy)
? arguments->se_extendgreedy : 100;
gt_querymatchoutoptions_extend(querymatchoutopt,
errorpercentage,
arguments->se_maxalilendiff,
arguments->se_historysize,
arguments->se_perc_match_hist,
cam,
sensitivity);
}
}
/* Start algorithm */
if (!had_err) {
GtDiagbandseed dbsarguments;
dbsarguments.errorpercentage = errorpercentage;
dbsarguments.userdefinedleastlength = arguments->se_alignlength;
dbsarguments.seedlength = arguments->dbs_seedlength;
dbsarguments.logdiagbandwidth = arguments->dbs_logdiagbandwidth;
dbsarguments.mincoverage = arguments->dbs_mincoverage;
dbsarguments.maxfreq = arguments->dbs_maxfreq;
dbsarguments.memlimit = arguments->dbs_memlimit;
dbsarguments.mirror = arguments->mirror;
dbsarguments.overlappingseeds = arguments->overlappingseeds;
dbsarguments.verify = arguments->dbs_verify;
dbsarguments.verbose = arguments->verbose;
dbsarguments.debug_kmer = arguments->dbs_debug_kmer;
dbsarguments.debug_seedpair = arguments->dbs_debug_seedpair;
dbsarguments.seed_display = arguments->seed_display;
dbsarguments.extendgreedyinfo = grextinfo;
dbsarguments.extendxdropinfo = xdropinfo;
dbsarguments.querymatchoutopt = querymatchoutopt;
had_err = gt_diagbandseed_run(aencseq, bencseq, &dbsarguments, err);
/* clean up */
gt_encseq_delete(aencseq);
gt_encseq_delete(bencseq);
if (gt_option_is_set(arguments->se_option_greedy)) {
gt_greedy_extend_matchinfo_delete(grextinfo);
}
if (gt_option_is_set(arguments->se_option_xdrop)) {
gt_xdrop_matchinfo_delete(xdropinfo);
}
if (arguments->se_alignmentwidth > 0 ||
gt_option_is_set(arguments->se_option_xdrop)) {
gt_querymatchoutoptions_delete(querymatchoutopt);
}
}
if (gt_showtime_enabled()) {
if (!had_err) {
char *keystring
= gt_seed_extend_params_keystring(gt_option_is_set(arguments->
se_option_greedy),
gt_option_is_set(arguments->
se_option_xdrop),
arguments->dbs_seedlength,
arguments->se_alignlength,
arguments->se_minidentity,
arguments->se_maxalilendiff,
arguments->se_perc_match_hist,
arguments->se_extendgreedy,
arguments->se_extendxdrop,
arguments->se_xdropbelowscore);
printf("# TIME seedextend-%s", keystring);
gt_free(keystring);
gt_timer_show_formatted(seedextendtimer,
" overall " GT_WD ".%06ld\n",
stdout);
}
gt_timer_delete(seedextendtimer);
}
return had_err;
}
static int gt_encseq_info_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
GtEncseqInfoArguments *arguments = tool_arguments;
int had_err = 0;
GtAlphabet *alpha;
const GtUchar *chars;
gt_error_check(err);
gt_assert(arguments);
if (arguments->nomap) {
GtEncseqMetadata *emd = gt_encseq_metadata_new(argv[parsed_args], err);
if (!emd)
had_err = -1;
if (!had_err) {
if (!arguments->noindexname) {
gt_file_xprintf(arguments->outfp, "index name: ");
gt_file_xprintf(arguments->outfp, "%s\n", argv[parsed_args]);
}
gt_file_xprintf(arguments->outfp, "file format version: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_metadata_version(emd));
gt_file_xprintf(arguments->outfp, "64-bit file: ");
gt_file_xprintf(arguments->outfp, "%s\n", gt_encseq_metadata_is64bit(emd)
? "yes"
: "no");
gt_file_xprintf(arguments->outfp, "total length: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_metadata_total_length(emd));
gt_file_xprintf(arguments->outfp, "number of sequences: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_metadata_num_of_sequences(emd));
gt_file_xprintf(arguments->outfp, "number of files: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_metadata_num_of_files(emd));
gt_file_xprintf(arguments->outfp, "length of shortest/longest "
"sequence: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"/"GT_WU"\n",
gt_encseq_metadata_min_seq_length(emd),
gt_encseq_metadata_max_seq_length(emd));
gt_file_xprintf(arguments->outfp, "accesstype: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_access_type_str(gt_encseq_metadata_accesstype(emd)));
alpha = gt_encseq_metadata_alphabet(emd);
chars = gt_alphabet_characters(alpha);
gt_file_xprintf(arguments->outfp, "alphabet size: ");
gt_file_xprintf(arguments->outfp, "%u\n",
gt_alphabet_num_of_chars(alpha));
gt_file_xprintf(arguments->outfp, "alphabet characters: ");
gt_file_xprintf(arguments->outfp, "%.*s", gt_alphabet_num_of_chars(alpha),
(char*) chars);
if (gt_alphabet_is_dna(alpha))
gt_file_xprintf(arguments->outfp, " (DNA)");
if (gt_alphabet_is_protein(alpha))
gt_file_xprintf(arguments->outfp, " (Protein)");
gt_file_xprintf(arguments->outfp, "\n");
if (arguments->show_alphabet) {
GtStr *out = gt_str_new();
gt_alphabet_to_str(alpha, out);
gt_file_xprintf(arguments->outfp, "alphabet definition:\n");
gt_file_xprintf(arguments->outfp, "%s\n", gt_str_get(out));
gt_str_delete(out);
}
}
gt_encseq_metadata_delete(emd);
} else {
GtEncseqLoader *encseq_loader;
GtEncseq *encseq;
encseq_loader = gt_encseq_loader_new();
if (arguments->mirror)
gt_encseq_loader_mirror(encseq_loader);
if (!(encseq = gt_encseq_loader_load(encseq_loader,
argv[parsed_args], err)))
had_err = -1;
if (!had_err) {
const GtStrArray *filenames;
GtUword i;
if (!arguments->noindexname) {
gt_file_xprintf(arguments->outfp, "index name: ");
gt_file_xprintf(arguments->outfp, "%s\n", argv[parsed_args]);
}
gt_file_xprintf(arguments->outfp, "file format version: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n", gt_encseq_version(encseq));
gt_file_xprintf(arguments->outfp, "64-bit file: ");
gt_file_xprintf(arguments->outfp, "%s\n", gt_encseq_is_64_bit(encseq)
? "yes"
: "no");
gt_file_xprintf(arguments->outfp, "total length: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_total_length(encseq));
gt_file_xprintf(arguments->outfp, "compressed size: ");
gt_file_xprintf(arguments->outfp, ""GT_WU" bytes\n",
gt_encseq_sizeofrep(encseq));
gt_file_xprintf(arguments->outfp, "number of sequences: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_num_of_sequences(encseq));
gt_file_xprintf(arguments->outfp, "number of files: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_num_of_files(encseq));
gt_file_xprintf(arguments->outfp, "length of shortest/longest "
"sequence: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"/"GT_WU"\n",
gt_encseq_min_seq_length(encseq),
gt_encseq_max_seq_length(encseq));
filenames = gt_encseq_filenames(encseq);
gt_file_xprintf(arguments->outfp, "original filenames:\n");
for (i = 0; i < gt_str_array_size(filenames); i++) {
gt_file_xprintf(arguments->outfp, "\t%s ("GT_WU" characters)\n",
gt_str_array_get(filenames, i),
(GtUword)
gt_encseq_effective_filelength(encseq, i));
}
alpha = gt_encseq_alphabet(encseq);
chars = gt_alphabet_characters(alpha);
gt_file_xprintf(arguments->outfp, "alphabet size: ");
gt_file_xprintf(arguments->outfp, "%u\n",
gt_alphabet_num_of_chars(alpha));
gt_file_xprintf(arguments->outfp, "alphabet characters: ");
gt_file_xprintf(arguments->outfp, "%.*s", gt_alphabet_num_of_chars(alpha),
(char*) chars);
if (gt_alphabet_is_dna(alpha))
gt_file_xprintf(arguments->outfp, " (DNA)");
if (gt_alphabet_is_protein(alpha))
gt_file_xprintf(arguments->outfp, " (Protein)");
gt_file_xprintf(arguments->outfp, "\n");
if (arguments->show_alphabet) {
GtStr *out = gt_str_new();
gt_alphabet_to_str(alpha, out);
gt_file_xprintf(arguments->outfp, "alphabet definition:\n");
gt_file_xprintf(arguments->outfp, "%s\n", gt_str_get(out));
gt_str_delete(out);
}
gt_file_xprintf(arguments->outfp, "character distribution:\n");
for (i = 0; i < gt_alphabet_num_of_chars(alpha); i++) {
GtUword cc;
cc = gt_encseq_charcount(encseq, gt_alphabet_encode(alpha, chars[i]));
gt_file_xprintf(arguments->outfp, "\t%c: "GT_WU" (%.2f%%)\n",
(char) chars[i],
cc,
(cc /(double) (gt_encseq_total_length(encseq)
- gt_encseq_num_of_sequences(encseq)+1))*100);
}
gt_file_xprintf(arguments->outfp, "number of wildcards: ");
gt_file_xprintf(arguments->outfp, ""GT_WU" ("GT_WU" range(s))\n",
gt_encseq_wildcards(encseq),
gt_encseq_realwildcardranges(encseq));
gt_file_xprintf(arguments->outfp, "number of special characters: ");
gt_file_xprintf(arguments->outfp, ""GT_WU" ("GT_WU" range(s))\n",
gt_encseq_specialcharacters(encseq),
gt_encseq_realspecialranges(encseq));
gt_file_xprintf(arguments->outfp, "length of longest non-special "
"character stretch: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_lengthoflongestnonspecial(encseq));
gt_file_xprintf(arguments->outfp, "accesstype: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_access_type_str(gt_encseq_accesstype_get(encseq)));
gt_file_xprintf(arguments->outfp, "bits used per character: ");
gt_file_xprintf(arguments->outfp, "%f\n",
(double) ((uint64_t) CHAR_BIT *
(uint64_t) gt_encseq_sizeofrep(encseq)) /
(double) gt_encseq_total_length(encseq));
gt_file_xprintf(arguments->outfp, "has special ranges: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_has_specialranges(encseq)
? "yes"
: "no");
gt_file_xprintf(arguments->outfp, "has description support: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_has_description_support(encseq)
? "yes"
: "no");
if (gt_encseq_has_description_support(encseq)) {
gt_file_xprintf(arguments->outfp, "length of longest description: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_max_desc_length(encseq));
}
gt_file_xprintf(arguments->outfp, "has multiple sequence support: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_has_multiseq_support(encseq)
? "yes"
: "no");
}
gt_encseq_delete(encseq);
gt_encseq_loader_delete(encseq_loader);
}
return had_err;
}
