static int show_entry(GtStr *description, GtStr *sequence, bool translate,
GtUword width, GtFile *outfp)
{
int had_err = 0;
if (translate) {
GtTranslatorStatus status;
unsigned int frame;
char translated;
GtStr *protein = gt_str_new();
GtCodonIterator *ci = gt_codon_iterator_simple_new(gt_str_get(sequence),
gt_str_length(sequence),
NULL);
GtTranslator* tr = gt_translator_new(ci);
status = gt_translator_next(tr, &translated, &frame, NULL);
while (status == GT_TRANSLATOR_OK) {
if (frame == 0)
gt_str_append_char(protein, translated);
status = gt_translator_next(tr, &translated, &frame, NULL);
}
if (status == GT_TRANSLATOR_ERROR)
had_err = -1;
gt_fasta_show_entry(gt_str_get(description), gt_str_get(protein),
gt_str_length(protein), width, outfp);
gt_str_delete(protein);
gt_translator_delete(tr);
gt_codon_iterator_delete(ci);
}
else {
gt_fasta_show_entry(gt_str_get(description), gt_str_get(sequence),
gt_str_length(sequence), width, outfp);
}
return had_err;
}
static int gt_seqmutate_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
MutateArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
unsigned long i;
GtBioseq *bioseq;
GtSeq *mutated_seq;
int had_err;
gt_error_check(err);
gt_assert(arguments);
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) && bioseq) {
for (i = 0; i < gt_bioseq_number_of_sequences(bioseq); i++) {
mutated_seq = gt_mutate_seq(gt_bioseq_get_description(bioseq, i),
gt_bioseq_get_sequence(bioseq, i),
gt_bioseq_get_sequence_length(bioseq, i),
gt_bioseq_get_alphabet(bioseq),
arguments->rate);
gt_fasta_show_entry(gt_seq_get_description(mutated_seq),
gt_seq_get_orig(mutated_seq),
gt_seq_length(mutated_seq),
arguments->width, arguments->outfp);
gt_seq_delete(mutated_seq);
}
gt_bioseq_delete(bioseq);
}
gt_bioseq_iterator_delete(bsi);
return had_err;
}
static int gff3_visitor_sequence_node(GtNodeVisitor *nv, GtSequenceNode *sn,
GT_UNUSED GtError *err)
{
GtGFF3Visitor *gff3_visitor;
gt_error_check(err);
gff3_visitor = gff3_visitor_cast(nv);
gt_assert(nv && sn);
gff3_version_string(nv);
if (!gff3_visitor->fasta_directive_shown) {
if (!gff3_visitor->outstr)
gt_file_xprintf(gff3_visitor->outfp, "%s\n", GT_GFF_FASTA_DIRECTIVE);
else {
gt_str_append_cstr(gff3_visitor->outstr, GT_GFF_FASTA_DIRECTIVE);
gt_str_append_char(gff3_visitor->outstr, '\n');
}
gff3_visitor->fasta_directive_shown = true;
}
if (!gff3_visitor->outstr) {
gt_fasta_show_entry(gt_sequence_node_get_description(sn),
gt_sequence_node_get_sequence(sn),
gt_sequence_node_get_sequence_length(sn),
gff3_visitor->fasta_width, gff3_visitor->outfp);
} else {
gt_fasta_show_entry_str(gt_sequence_node_get_description(sn),
gt_sequence_node_get_sequence(sn),
gt_sequence_node_get_sequence_length(sn),
gff3_visitor->fasta_width, gff3_visitor->outstr);
}
return 0;
}
static bool show_target(GT_UNUSED unsigned long pos, void *data)
{
TargetInfo *ti = data;
gt_assert(ti);
gt_fasta_show_entry(gt_bioseq_get_description(ti->bioseq, ti->seqnum),
gt_bioseq_get_sequence(ti->bioseq, ti->seqnum),
gt_bioseq_get_sequence_length(ti->bioseq, ti->seqnum), 0);
return true;
}
void gt_bioseq_show_as_fasta(GtBioseq *bs, GtUword width, GtFile *outfp)
{
GtUword i;
gt_assert(bs);
for (i = 0; i < gt_bioseq_number_of_sequences(bs); i++) {
char *seq = gt_bioseq_get_sequence(bs, i);
gt_fasta_show_entry(gt_bioseq_get_description(bs, i),
seq,
gt_bioseq_get_sequence_length(bs, i), width, outfp);
gt_free(seq);
}
}
void gt_bioseq_show_sequence_as_fasta(GtBioseq *bs, GtUword seqnum,
GtUword width, GtFile *outfp)
{
char *seq = NULL;
gt_assert(bs);
gt_assert(seqnum < gt_bioseq_number_of_sequences(bs));
seq = gt_bioseq_get_sequence(bs, seqnum);
gt_fasta_show_entry(gt_bioseq_get_description(bs, seqnum),
seq,
gt_bioseq_get_sequence_length(bs, seqnum), width, outfp);
gt_free(seq);
}
static int gt_seqfilter_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
SeqFilterArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
GtBioseq *bioseq;
unsigned long i;
unsigned long long passed = 0, filtered = 0, num_of_sequences = 0;
int had_err = 0;
gt_error_check(err);
gt_assert(tool_arguments);
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) && bioseq) {
for (i = 0; i < gt_bioseq_number_of_sequences(bioseq); i++) {
if ((arguments->minlength == GT_UNDEF_ULONG ||
gt_bioseq_get_sequence_length(bioseq, i) >= arguments->minlength) &&
(arguments->maxlength == GT_UNDEF_ULONG ||
gt_bioseq_get_sequence_length(bioseq, i) <= arguments->maxlength) &&
(arguments->maxseqnum == GT_UNDEF_ULONG ||
passed + 1 <= arguments->maxseqnum)) {
gt_fasta_show_entry(gt_bioseq_get_description(bioseq, i),
gt_bioseq_get_sequence(bioseq, i),
gt_bioseq_get_sequence_length(bioseq, i),
arguments->width, arguments->outfp);
passed++;
}
else
filtered++;
num_of_sequences++;
}
gt_bioseq_delete(bioseq);
}
/* show statistics */
if (!had_err) {
gt_assert(passed + filtered == num_of_sequences);
fprintf(stderr, "# %llu out of %llu sequences have been removed (%.3f%%)\n",
filtered, num_of_sequences,
((double) filtered / num_of_sequences) * 100.0);
}
gt_bioseq_iterator_delete(bsi);
return had_err;
}
static int gt_seqtranslate_do_translation(GtTranslateArguments *arguments,
const char *sequence,
GtUword length,
const char *desc,
GtStr **translations,
bool rev,
GtError *err)
{
GtTranslator *tr;
GT_UNUSED GtTranslatorStatus trst;
GtCodonIterator *ci;
char translated;
int had_err = 0;
GtStr *str;
unsigned int frame,
i;
ci = gt_codon_iterator_simple_new(sequence, length, err);
tr = gt_translator_new(ci);
trst = gt_translator_next(tr, &translated, &frame, err);
while (trst == GT_TRANSLATOR_OK) {
gt_str_append_char(translations[frame], translated);
trst = gt_translator_next(tr, &translated, &frame, err);
}
gt_codon_iterator_delete(ci);
gt_translator_delete(tr);
if (trst == GT_TRANSLATOR_ERROR)
return -1;
str = gt_str_new();
for (i = 0; i < 3; i++) {
if (gt_str_length(translations[i]) > 0) {
gt_str_append_cstr(str, desc);
gt_str_append_cstr(str, " (");
gt_str_append_ulong(str, i+1);
gt_str_append_cstr(str, rev ? "-" : "+");
gt_str_append_cstr(str, ")");
gt_fasta_show_entry(gt_str_get(str), gt_str_get(translations[i]),
gt_str_length(translations[i]),
arguments->fasta_width, arguments->outfp);
gt_str_reset(translations[i]);
gt_str_reset(str);
}
}
gt_str_delete(str);
return had_err;
}
static int gt_shredder_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
GtShredderArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
unsigned long i;
GtBioseq *bioseq;
int had_err;
GtStr *desc;
gt_error_check(err);
gt_assert(arguments);
/* init */
desc = gt_str_new();
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
/* shredder */
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) && bioseq) {
for (i = 0; i < arguments->coverage; i++) {
GtShredder *shredder;
unsigned long fragment_length;
const char *fragment;
shredder = gt_shredder_new(bioseq, arguments->minlength,
arguments->maxlength);
gt_shredder_set_overlap(shredder, arguments->overlap);
gt_shredder_set_sample_probability(shredder,
arguments->sample_probability);
while ((fragment = gt_shredder_shred(shredder, &fragment_length, desc))) {
gt_str_append_cstr(desc, " [shreddered fragment]");
gt_fasta_show_entry(gt_str_get(desc), fragment, fragment_length, 0);
}
gt_shredder_delete(shredder);
}
gt_bioseq_delete(bioseq);
}
/* free */
gt_bioseq_iterator_delete(bsi);
gt_str_delete(desc);
return had_err;
}
static int extractseq_pos(GtFile *outfp, GtBioseq *bs,
unsigned long frompos, unsigned long topos,
unsigned long width, GtError *err)
{
int had_err = 0;
gt_error_check(err);
gt_assert(bs);
if (topos > gt_bioseq_get_raw_sequence_length(bs)) {
gt_error_set(err,
"argument %lu to option '-%s' is larger than sequence length %lu",
topos, TOPOS_OPTION_STR, gt_bioseq_get_raw_sequence_length(bs));
had_err = -1;
}
if (!had_err) {
gt_fasta_show_entry(NULL, gt_bioseq_get_raw_sequence(bs) + frompos - 1,
topos - frompos + 1, width, outfp);
}
return had_err;
}
static int split_description(const char *filename, GtStr *splitdesc,
unsigned long width, bool force, GtError *err)
{
unsigned long i;
GtBioseq *bioseq;
GtStr *descname;
int had_err = 0;
gt_error_check(err);
gt_assert(filename && splitdesc && gt_str_length(splitdesc));
descname = gt_str_new();
if (!(bioseq = gt_bioseq_new(filename, err)))
had_err = -1;
for (i = 0; !had_err && i < gt_bioseq_number_of_sequences(bioseq); i++) {
GtFile *outfp;
char *seq;
gt_str_reset(descname);
gt_str_append_str(descname, splitdesc);
gt_str_append_char(descname, '/');
gt_str_append_cstr(descname, gt_bioseq_get_description(bioseq, i));
gt_str_append_cstr(descname, gt_file_suffix(filename));
if (!(outfp = gt_output_file_xopen_forcecheck(gt_str_get(descname), "w",
force, err))) {
had_err = -1;
break;
}
seq = gt_bioseq_get_sequence(bioseq, i);
gt_fasta_show_entry(gt_bioseq_get_description(bioseq, i), seq,
gt_bioseq_get_sequence_length(bioseq, i), width,
outfp);
gt_free(seq);
gt_file_delete(outfp);
}
gt_bioseq_delete(bioseq);
gt_str_delete(descname);
return had_err;
}
static int extractseq_match(GtFile *outfp, GtBioseq *bs,
const char *pattern, unsigned long width,
GtError *err)
{
const char *desc;
unsigned long i;
bool match;
int had_err = 0;
gt_error_check(err);
gt_assert(bs && pattern);
for (i = 0; !had_err && i < gt_bioseq_number_of_sequences(bs); i++) {
desc = gt_bioseq_get_description(bs, i);
gt_assert(desc);
had_err = gt_grep(&match, pattern, desc, err);
if (!had_err && match) {
gt_fasta_show_entry(desc, gt_bioseq_get_sequence(bs, i),
gt_bioseq_get_sequence_length(bs, i), width, outfp);
}
}
return had_err;
}
static int write_pdom(GtLTRdigestFileOutStream *ls, GtArray *pdoms,
const char *pdomname, GT_UNUSED GtRegionMapping *rmap,
char *desc, GtError *err)
{
int had_err = 0;
GtFile *seqfile = NULL,
*alifile = NULL,
*aafile = NULL;
GtUword i = 0,
seq_length = 0;
GtStr *pdom_seq,
*pdom_aaseq;
gt_error_check(err);
pdom_seq = gt_str_new();
pdom_aaseq = gt_str_new();
/* get protein domain output file */
seqfile = (GtFile*) gt_hashmap_get(ls->pdomout_files, pdomname);
if (seqfile == NULL)
{
/* no file opened for this domain yet, do it */
char buffer[GT_MAXFILENAMELEN];
(void) snprintf(buffer, (size_t) (GT_MAXFILENAMELEN-1), "%s_pdom_%s.fas",
ls->fileprefix, pdomname);
seqfile = gt_file_xopen(buffer, "w+");
gt_hashmap_add(ls->pdomout_files, gt_cstr_dup(pdomname), seqfile);
}
/* get protein alignment output file */
if (ls->write_pdom_alignments)
{
alifile = (GtFile*) gt_hashmap_get(ls->pdomali_files, pdomname);
if (alifile == NULL)
{
/* no file opened for this domain yet, do it */
char buffer[GT_MAXFILENAMELEN];
(void) snprintf(buffer, (size_t) (GT_MAXFILENAMELEN-1), "%s_pdom_%s.ali",
ls->fileprefix, pdomname);
alifile = gt_file_xopen(buffer, "w+");
gt_hashmap_add(ls->pdomali_files, gt_cstr_dup(pdomname), alifile);
}
}
/* get amino acid sequence output file */
if (ls->write_pdom_aaseqs)
{
aafile = (GtFile*) gt_hashmap_get(ls->pdomaa_files, pdomname);
if (aafile == NULL)
{
/* no file opened for this domain yet, do it */
char buffer[GT_MAXFILENAMELEN];
(void) snprintf(buffer, (size_t) (GT_MAXFILENAMELEN-1),
"%s_pdom_%s_aa.fas",
ls->fileprefix, pdomname);
aafile = gt_file_xopen(buffer, "w+");
gt_hashmap_add(ls->pdomaa_files, gt_cstr_dup(pdomname), aafile);
}
}
if (gt_array_size(pdoms) > 1UL)
{
for (i=1UL; i<gt_array_size(pdoms); i++)
{
gt_assert(gt_genome_node_cmp(*(GtGenomeNode**)gt_array_get(pdoms, i),
*(GtGenomeNode**)gt_array_get(pdoms, i-1))
>= 0);
}
if (gt_feature_node_get_strand(*(GtFeatureNode**) gt_array_get(pdoms, 0UL))
== GT_STRAND_REVERSE)
{
gt_array_reverse(pdoms);
}
}
/* output protein domain data */
for (i=0;i<gt_array_size(pdoms);i++)
{
GtRange pdom_rng;
GtStr *ali,
*aaseq;
GtFeatureNode *fn;
int rval;
fn = *(GtFeatureNode**) gt_array_get(pdoms, i);
ali = gt_genome_node_get_user_data((GtGenomeNode*) fn, "pdom_alignment");
aaseq = gt_genome_node_get_user_data((GtGenomeNode*) fn, "pdom_aaseq");
pdom_rng = gt_genome_node_get_range((GtGenomeNode*) fn);
rval = gt_extract_feature_sequence(pdom_seq, (GtGenomeNode*) fn,
gt_symbol(gt_ft_protein_match), false,
NULL, NULL, rmap, err);
if (rval)
{
had_err = -1;
break;
}
if (ls->write_pdom_alignments && ali)
{
char buf[BUFSIZ];
/* write away alignment */
(void) snprintf(buf, BUFSIZ-1, "Protein domain alignment in translated "
"sequence for candidate\n'%s':\n\n",
desc);
gt_file_xwrite(alifile, buf, (size_t) strlen(buf) * sizeof (char));
gt_file_xwrite(alifile, gt_str_get(ali),
(size_t) gt_str_length(ali) * sizeof (char));
gt_file_xwrite(alifile, "---\n\n", 5 * sizeof (char));
}
if (ls->write_pdom_aaseqs && aaseq)
{
/* append amino acid sequence */
gt_str_append_str(pdom_aaseq, aaseq);
}
gt_genome_node_release_user_data((GtGenomeNode*) fn, "pdom_alignment");
gt_genome_node_release_user_data((GtGenomeNode*) fn, "pdom_aaseq");
seq_length += gt_range_length(&pdom_rng);
}
if (!had_err)
{
gt_fasta_show_entry(desc,
gt_str_get(pdom_seq),
seq_length,
GT_FSWIDTH,
seqfile);
if (ls->write_pdom_aaseqs)
{
gt_fasta_show_entry(desc,
gt_str_get(pdom_aaseq),
gt_str_length(pdom_aaseq),
GT_FSWIDTH,
aafile);
}
}
gt_str_delete(pdom_seq);
gt_str_delete(pdom_aaseq);
return had_err;
}
int gt_extractkeysfromfastafile(bool verbose,
GtFile *outfp,
unsigned long width,
const GtStr *fileofkeystoextract,
GtStrArray *referencefiletab,
GtError *err)
{
GtSeqIterator *seqit;
const GtUchar *sequence;
char *desc, *headerbufferspace = NULL, *keyspace = NULL;
const char *keyptr;
unsigned long allockeyspace = 0, len, keylen, numofqueries, keyposition,
countmarkhit = 0;
int had_err = 0;
off_t totalsize;
Fastakeyquery *fastakeyqueries;
size_t headerbuffersize = 0, headerlength;
gt_error_check(err);
fastakeyqueries = readfileofkeystoextract(verbose,&numofqueries,
fileofkeystoextract,err);
if (fastakeyqueries == NULL)
{
return -1;
}
totalsize = gt_files_estimate_total_size(referencefiletab);
if (verbose)
{
printf("# estimated total size is " Formatuint64_t "\n",
PRINTuint64_tcast(totalsize));
}
seqit = gt_seqiterator_sequence_buffer_new(referencefiletab, err);
if (!seqit)
{
had_err = -1;
}
if (!had_err && verbose)
{
gt_progressbar_start(gt_seqiterator_getcurrentcounter(seqit,
(unsigned long long)
totalsize),
(unsigned long long)
totalsize);
}
while (had_err != -1 && countmarkhit < numofqueries)
{
had_err = gt_seqiterator_next(seqit, &sequence, &len, &desc, err);
if (had_err != 1)
{
break;
}
keyptr = desc2key(&keylen,desc,err);
if (keyptr == NULL)
{
had_err = -1;
} else
{
if (allockeyspace < keylen)
{
keyspace = gt_realloc(keyspace,sizeof (*keyspace) * (keylen+1));
allockeyspace = keylen;
}
gt_assert(keyspace != NULL);
strncpy(keyspace,keyptr,(size_t) keylen);
keyspace[keylen] = '\0';
keyposition = searchdesinfastakeyqueries(keyspace,fastakeyqueries,
numofqueries);
if (keyposition < numofqueries)
{
while (keyposition < numofqueries &&
strcmp(fastakeyqueries[keyposition].fastakey,keyspace) == 0)
{
#ifndef NDEBUG
if (fastakeyqueries[keyposition].markhit)
{
fprintf(stderr,"key %s was already found before\n",
fastakeyqueries[keyposition].fastakey);
exit(GT_EXIT_PROGRAMMING_ERROR);
}
#endif
headerlength = strlen(desc);
if (headerbuffersize < headerlength + EXTRABUF + 1)
{
headerbuffersize = headerlength + EXTRABUF + 1;
headerbufferspace = gt_realloc(headerbufferspace,
sizeof (*headerbufferspace)
* headerbuffersize);
}
if (COMPLETE(fastakeyqueries + keyposition))
{
/*
(void) snprintf(headerbufferspace,headerbuffersize,
"%*.*s complete %s",
(int) keylen,(int) keylen,keyspace,
desc);
*/
gt_fasta_show_entry(desc, (const char *) sequence, len, width,
outfp);
} else
{
(void) snprintf(headerbufferspace,headerbuffersize,
"%*.*s %lu %lu %s",
(int) keylen,(int) keylen,keyspace,
fastakeyqueries[keyposition].frompos,
fastakeyqueries[keyposition].topos,
desc);
gt_fasta_show_entry(headerbufferspace,
(const char *)
(sequence+fastakeyqueries[keyposition].
frompos - 1),
fastakeyqueries[keyposition].topos -
fastakeyqueries[keyposition].frompos+1,
width, outfp);
}
fastakeyqueries[keyposition].markhit = true;
countmarkhit++;
keyposition++;
}
}
#ifdef SKDEBUG
printf("%s 1 %lu\n",keyspace, len);
#endif
}
}
gt_free(headerbufferspace);
gt_free(keyspace);
if (verbose)
{
gt_progressbar_stop();
}
if (verbose)
{
outputnonmarked(fastakeyqueries,numofqueries);
}
fastakeyqueries_delete(fastakeyqueries,numofqueries);
gt_seqiterator_delete(seqit);
return had_err;
}
static int gt_seqfilter_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
SeqFilterArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
GtBioseq *bioseq;
GtUint64 passed = 0, filtered = 0, num_of_sequences = 0, steps = 0;
int had_err = 0;
gt_error_check(err);
gt_assert(tool_arguments);
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) &&
bioseq != NULL) {
GtUword i;
GtUint64 current_num = gt_bioseq_number_of_sequences(bioseq);
for (i = 0;
i < current_num &&
(arguments->maxseqnum == GT_UNDEF_UWORD ||
passed + 1 <= arguments->maxseqnum);
i++) {
char *seq;
if ((arguments->step == 1 ||
steps + 1 == arguments->step) &&
(arguments->sample_prob == 1.0 ||
gt_rand_0_to_1() <= arguments->sample_prob) &&
(arguments->minlength == GT_UNDEF_UWORD ||
gt_bioseq_get_sequence_length(bioseq, i) >= arguments->minlength) &&
(arguments->maxlength == GT_UNDEF_UWORD ||
gt_bioseq_get_sequence_length(bioseq, i) <= arguments->maxlength)) {
seq = gt_bioseq_get_sequence(bioseq, i);
gt_fasta_show_entry(gt_bioseq_get_description(bioseq, i),
seq,
gt_bioseq_get_sequence_length(bioseq, i),
arguments->width, arguments->outfp);
gt_free(seq);
passed++;
}
else {
filtered++;
}
steps = (steps + 1 == arguments->step) ? 0 : steps + 1;
}
filtered += current_num - i;
num_of_sequences += current_num;
gt_bioseq_delete(bioseq);
}
/* show statistics */
if (!had_err) {
gt_assert(passed + filtered == num_of_sequences);
fprintf(stderr, "# " GT_LLU " out of " GT_LLU
" sequences have been removed (%.3f%%)\n",
filtered, num_of_sequences,
((double) filtered / num_of_sequences) * 100.0);
}
gt_bioseq_iterator_delete(bsi);
return had_err;
}
static int gt_sequniq_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
GtSequniqArguments *arguments = tool_arguments;
GtUint64 duplicates = 0, num_of_sequences = 0;
int i, had_err = 0;
GtMD5Set *md5set;
gt_error_check(err);
gt_assert(arguments);
md5set = gt_md5set_new(arguments->nofseqs);
if (!arguments->seqit) {
GtUword j;
GtBioseq *bs;
for (i = parsed_args; !had_err && i < argc; i++) {
if (!(bs = gt_bioseq_new(argv[i], err)))
had_err = -1;
if (!had_err) {
GtMD5SetStatus retval;
for (j = 0; j < gt_bioseq_number_of_sequences(bs) && !had_err; j++) {
char *seq = gt_bioseq_get_sequence(bs, j);
retval = gt_md5set_add_sequence(md5set, seq,
gt_bioseq_get_sequence_length(bs, j),
arguments->rev, err);
if (retval == GT_MD5SET_NOT_FOUND)
gt_fasta_show_entry(gt_bioseq_get_description(bs, j), seq,
gt_bioseq_get_sequence_length(bs, j),
arguments->width, arguments->outfp);
else if (retval != GT_MD5SET_ERROR)
duplicates++;
else
had_err = -1;
num_of_sequences++;
gt_free(seq);
}
gt_bioseq_delete(bs);
}
}
}
else {
GtSeqIterator *seqit;
GtStrArray *files;
off_t totalsize;
const GtUchar *sequence;
char *desc;
GtUword len;
files = gt_str_array_new();
for (i = parsed_args; i < argc; i++)
gt_str_array_add_cstr(files, argv[i]);
totalsize = gt_files_estimate_total_size(files);
seqit = gt_seq_iterator_sequence_buffer_new(files, err);
if (!seqit)
had_err = -1;
if (!had_err) {
if (arguments->verbose) {
gt_progressbar_start(gt_seq_iterator_getcurrentcounter(seqit,
(GtUint64) totalsize),
(GtUint64) totalsize);
}
while (!had_err) {
GtMD5SetStatus retval;
if ((gt_seq_iterator_next(seqit, &sequence, &len, &desc, err)) != 1)
break;
retval = gt_md5set_add_sequence(md5set, (const char*) sequence, len,
arguments->rev, err);
if (retval == GT_MD5SET_NOT_FOUND)
gt_fasta_show_entry(desc, (const char*) sequence, len,
arguments->width, arguments->outfp);
else if (retval != GT_MD5SET_ERROR)
duplicates++;
else
had_err = -1;
num_of_sequences++;
}
if (arguments->verbose)
gt_progressbar_stop();
gt_seq_iterator_delete(seqit);
}
gt_str_array_delete(files);
}
/* show statistics */
if (!had_err) {
fprintf(stderr,
"# "GT_WU" out of "GT_WU" sequences have been removed (%.3f%%)\n",
(GtUword)duplicates, (GtUword)num_of_sequences,
((double) duplicates / (double)num_of_sequences) * 100.0);
}
gt_md5set_delete(md5set);
return had_err;
}
int gt_ltrfileout_stream_next(GtNodeStream *ns, GtGenomeNode **gn, GtError *err)
{
GtLTRdigestFileOutStream *ls;
GtFeatureNode *fn;
GtRange lltr_rng = {GT_UNDEF_UWORD, GT_UNDEF_UWORD},
rltr_rng = {GT_UNDEF_UWORD, GT_UNDEF_UWORD},
ppt_rng = {GT_UNDEF_UWORD, GT_UNDEF_UWORD},
pbs_rng = {GT_UNDEF_UWORD, GT_UNDEF_UWORD};
int had_err;
GtUword i=0;
gt_error_check(err);
ls = gt_ltrdigest_file_out_stream_cast(ns);
/* initialize this element */
memset(&ls->element, 0, sizeof (GtLTRElement));
/* get annotations from parser */
had_err = gt_node_stream_next(ls->in_stream, gn, err);
if (!had_err && *gn)
{
GtFeatureNodeIterator* gni;
GtFeatureNode *mygn;
/* only process feature nodes */
if (!(fn = gt_feature_node_try_cast(*gn)))
return 0;
ls->element.pdomorder = gt_array_new(sizeof (const char*));
/* fill LTRElement structure from GFF3 subgraph */
gni = gt_feature_node_iterator_new(fn);
for (mygn = fn; mygn != NULL; mygn = gt_feature_node_iterator_next(gni))
(void) gt_genome_node_accept((GtGenomeNode*) mygn,
(GtNodeVisitor*) ls->lv,
err);
gt_feature_node_iterator_delete(gni);
}
if (!had_err && ls->element.mainnode != NULL)
{
char desc[GT_MAXFASTAHEADER];
GtFeatureNode *ltr3, *ltr5;
GtStr *sdesc, *sreg, *seq;
/* find sequence in GtEncseq */
sreg = gt_genome_node_get_seqid((GtGenomeNode*) ls->element.mainnode);
sdesc = gt_str_new();
had_err = gt_region_mapping_get_description(ls->rmap, sdesc, sreg, err);
if (!had_err) {
GtRange rng;
ls->element.seqid = gt_calloc((size_t) ls->seqnamelen+1, sizeof (char));
(void) snprintf(ls->element.seqid,
MIN((size_t) gt_str_length(sdesc),
(size_t) ls->seqnamelen)+1,
"%s", gt_str_get(sdesc));
gt_cstr_rep(ls->element.seqid, ' ', '_');
if (gt_str_length(sdesc) > (GtUword) ls->seqnamelen)
ls->element.seqid[ls->seqnamelen] = '\0';
(void) gt_ltrelement_format_description(&ls->element,
ls->seqnamelen,
desc,
(size_t) (GT_MAXFASTAHEADER-1));
gt_str_delete(sdesc);
/* output basic retrotransposon data */
lltr_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.leftLTR);
rltr_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.rightLTR);
rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.mainnode);
gt_file_xprintf(ls->tabout_file,
GT_WU"\t"GT_WU"\t"GT_WU"\t%s\t"GT_WU"\t"GT_WU"\t"GT_WU"\t"
GT_WU"\t"GT_WU"\t"GT_WU"\t",
rng.start, rng.end, gt_ltrelement_length(&ls->element),
ls->element.seqid, lltr_rng.start, lltr_rng.end,
gt_ltrelement_leftltrlen(&ls->element), rltr_rng.start,
rltr_rng.end, gt_ltrelement_rightltrlen(&ls->element));
}
seq = gt_str_new();
/* output TSDs */
if (!had_err && ls->element.leftTSD != NULL)
{
GtRange tsd_rng;
tsd_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.leftTSD);
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.leftTSD,
gt_symbol(gt_ft_target_site_duplication),
false,
NULL, NULL, ls->rmap, err);
if (!had_err) {
gt_file_xprintf(ls->tabout_file,
""GT_WU"\t"GT_WU"\t%s\t",
tsd_rng.start,
tsd_rng.end,
gt_str_get(seq));
}
gt_str_reset(seq);
} else gt_file_xprintf(ls->tabout_file, "\t\t\t");
if (!had_err && ls->element.rightTSD != NULL)
{
GtRange tsd_rng;
tsd_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.rightTSD);
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.rightTSD,
gt_symbol(gt_ft_target_site_duplication),
false,
NULL, NULL, ls->rmap, err);
if (!had_err) {
gt_file_xprintf(ls->tabout_file,
""GT_WU"\t"GT_WU"\t%s\t",
tsd_rng.start,
tsd_rng.end,
gt_str_get(seq));
}
gt_str_reset(seq);
} else gt_file_xprintf(ls->tabout_file, "\t\t\t");
/* output PPT */
if (!had_err && ls->element.ppt != NULL)
{
GtStrand ppt_strand = gt_feature_node_get_strand(ls->element.ppt);
ppt_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.ppt);
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.ppt,
gt_symbol(gt_ft_RR_tract), false,
NULL, NULL, ls->rmap, err);
if (!had_err) {
gt_fasta_show_entry(desc, gt_str_get(seq), gt_range_length(&ppt_rng),
GT_FSWIDTH, ls->pptout_file);
gt_file_xprintf(ls->tabout_file,
""GT_WU"\t"GT_WU"\t%s\t%c\t%d\t",
ppt_rng.start,
ppt_rng.end,
gt_str_get(seq),
GT_STRAND_CHARS[ppt_strand],
(ppt_strand == GT_STRAND_FORWARD ?
abs((int) (rltr_rng.start - ppt_rng.end)) :
abs((int) (lltr_rng.end - ppt_rng.start))));
}
gt_str_reset(seq);
} else gt_file_xprintf(ls->tabout_file, "\t\t\t\t\t");
/* output PBS */
if (!had_err && ls->element.pbs != NULL)
{
GtStrand pbs_strand;
pbs_strand = gt_feature_node_get_strand(ls->element.pbs);
pbs_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.pbs);
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.pbs,
gt_symbol(gt_ft_primer_binding_site),
false, NULL, NULL, ls->rmap, err);
if (!had_err) {
gt_fasta_show_entry(desc, gt_str_get(seq), gt_range_length(&pbs_rng),
GT_FSWIDTH, ls->pbsout_file);
gt_file_xprintf(ls->tabout_file,
""GT_WU"\t"GT_WU"\t%c\t%s\t%s\t%s\t%s\t%s\t",
pbs_rng.start,
pbs_rng.end,
GT_STRAND_CHARS[pbs_strand],
gt_feature_node_get_attribute(ls->element.pbs, "trna"),
gt_str_get(seq),
gt_feature_node_get_attribute(ls->element.pbs,
"pbsoffset"),
gt_feature_node_get_attribute(ls->element.pbs,
"trnaoffset"),
gt_feature_node_get_attribute(ls->element.pbs,
"edist"));
}
gt_str_reset(seq);
} else gt_file_xprintf(ls->tabout_file, "\t\t\t\t\t\t\t\t");
/* output protein domains */
if (!had_err && ls->element.pdoms != NULL)
{
GtStr *pdomorderstr = gt_str_new();
for (i=0; !had_err && i<gt_array_size(ls->element.pdomorder); i++)
{
const char* key = *(const char**) gt_array_get(ls->element.pdomorder,
i);
GtArray *entry = (GtArray*) gt_hashmap_get(ls->element.pdoms, key);
had_err = write_pdom(ls, entry, key, ls->rmap, desc, err);
}
if (GT_STRAND_REVERSE == gt_feature_node_get_strand(ls->element.mainnode))
gt_array_reverse(ls->element.pdomorder);
for (i=0 ;!had_err && i<gt_array_size(ls->element.pdomorder); i++)
{
const char* name = *(const char**) gt_array_get(ls->element.pdomorder,
i);
gt_str_append_cstr(pdomorderstr, name);
if (i != gt_array_size(ls->element.pdomorder)-1)
gt_str_append_cstr(pdomorderstr, "/");
}
gt_file_xprintf(ls->tabout_file, "%s", gt_str_get(pdomorderstr));
gt_str_delete(pdomorderstr);
}
/* output LTRs (we just expect them to exist) */
switch (gt_feature_node_get_strand(ls->element.mainnode))
{
case GT_STRAND_REVERSE:
ltr5 = ls->element.rightLTR;
ltr3 = ls->element.leftLTR;
break;
case GT_STRAND_FORWARD:
default:
ltr5 = ls->element.leftLTR;
ltr3 = ls->element.rightLTR;
break;
}
if (!had_err) {
had_err = gt_extract_feature_sequence(seq, (GtGenomeNode*) ltr5,
gt_symbol(gt_ft_long_terminal_repeat),
false,
NULL, NULL, ls->rmap, err);
}
if (!had_err) {
gt_fasta_show_entry(desc, gt_str_get(seq), gt_str_length(seq),
GT_FSWIDTH, ls->ltr5out_file);
gt_str_reset(seq);
}
if (!had_err) {
had_err = gt_extract_feature_sequence(seq, (GtGenomeNode*) ltr3,
gt_symbol(gt_ft_long_terminal_repeat),
false,
NULL, NULL, ls->rmap, err);
}
if (!had_err) {
gt_fasta_show_entry(desc, gt_str_get(seq), gt_str_length(seq),
GT_FSWIDTH, ls->ltr3out_file);
gt_str_reset(seq);
}
/* output complete oriented element */
if (!had_err) {
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.mainnode,
gt_symbol(gt_ft_LTR_retrotransposon),
false,
NULL, NULL, ls->rmap, err);
}
if (!had_err) {
gt_fasta_show_entry(desc,gt_str_get(seq), gt_str_length(seq),
GT_FSWIDTH, ls->elemout_file);
gt_str_reset(seq);
}
gt_file_xprintf(ls->tabout_file, "\n");
gt_str_delete(seq);
}
gt_hashmap_delete(ls->element.pdoms);
gt_array_delete(ls->element.pdomorder);
gt_free(ls->element.seqid);
return had_err;
}