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 gt_seqtransform_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
SeqtransformArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
unsigned long i;
GtBioseq *bioseq;
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) {
GtAlphabet *alphabet;
bool is_protein;
alphabet = gt_bioseq_get_alphabet(bioseq);
is_protein = gt_alphabet_is_protein(alphabet);
for (i = 0; i < gt_bioseq_number_of_sequences(bioseq); i++) {
const char *desc, *suffix = NULL;
char *seq;
unsigned long seqlen;
desc = gt_bioseq_get_description(bioseq, i);
seq = gt_bioseq_get_sequence(bioseq, i);
seqlen = gt_bioseq_get_sequence_length(bioseq, i);
if (arguments->addstopaminos && is_protein && seqlen &&
seq[seqlen-1] != GT_STOP_AMINO) {
suffix = GT_STOP_AMINO_CSTR;
}
gt_fasta_show_entry_with_suffix(desc, seq, seqlen, suffix,
arguments->width, arguments->outfp);
gt_free(seq);
}
gt_bioseq_delete(bioseq);
}
gt_bioseq_iterator_delete(bsi);
return had_err;
}
int gth_bssm_param_parameterize(GthBSSMParam *bssm_param, const char *path,
Termtype termtype, bool gzip, GtError *err)
{
GtAlphabet *alphabet = NULL;
GtBioseq *bioseq;
GtStr *file2proc;
GtUword i, j;
int had_err = 0;
gt_error_check(err);
file2proc = gt_str_new();
/* set version number */
bssm_param->version_num = (unsigned char) MYVERSION;
/* set model to true and set window sizes */
switch (termtype) {
case GT_DONOR_TYPE:
bssm_param->gt_donor_model_set = true;
set_window_sizes_in_Bssmmodel(&bssm_param->gt_donor_model);
break;
case GC_DONOR_TYPE:
bssm_param->gc_donor_model_set = true;
set_window_sizes_in_Bssmmodel(&bssm_param->gc_donor_model);
break;
case AG_ACCEPTOR_TYPE:
bssm_param->ag_acceptor_model_set = true;
set_window_sizes_in_Bssmmodel(&bssm_param->ag_acceptor_model);
break;
default:
gt_assert(0);
}
for (i = 0; !had_err && i < NUMOFFILES; i++) {
/* process datafile */
gt_str_append_cstr(file2proc, path);
switch (termtype) {
case GT_DONOR_TYPE:
gt_str_append_cstr(file2proc, "/GT_donor/");
gt_str_append_cstr(file2proc, filenames[i]);
break;
case GC_DONOR_TYPE:
gt_str_append_cstr(file2proc, "/GC_donor/");
gt_str_append_cstr(file2proc, filenames[i]);
break;
case AG_ACCEPTOR_TYPE:
gt_str_append_cstr(file2proc, "/AG_acceptor/");
gt_str_append_cstr(file2proc, filenames[i]);
break;
default:
gt_assert(0);
}
if (gzip)
gt_str_append_cstr(file2proc, ".gz");
if (!(bioseq = gt_bioseq_new(gt_str_get(file2proc), err)))
had_err = -1;
if (!had_err)
alphabet = gt_bioseq_get_alphabet(bioseq);
/* check here if all sequences have the length 102 and correct bases at
positions 51 and 52 (i.e., GT, GC, or AG) */
for (j = 0; !had_err && j < gt_bioseq_number_of_sequences(bioseq); j++) {
GtUchar encoded_seq[2];
/* check length */
if (gt_bioseq_get_sequence_length(bioseq, j) != STRINGSIZE) {
gt_error_set(err,
"sequence "GT_WU" in file \"%s\" does not have length %u",
j, gt_str_get(file2proc), STRINGSIZE);
had_err = -1;
}
encoded_seq[0] = gt_bioseq_get_encoded_char(bioseq, j, 50);
encoded_seq[1] = gt_bioseq_get_encoded_char(bioseq, j, 51);
if (!had_err) {
/* check base correctness */
switch (termtype) {
case GT_DONOR_TYPE:
if (encoded_seq[0] != gt_alphabet_encode(alphabet, 'G') ||
encoded_seq[1] != gt_alphabet_encode(alphabet, 'T')) {
gt_error_set(err, "sequence "GT_WU" in file \"%s\" is not a GT "
"sequence", j, gt_str_get(file2proc));
had_err = -1;
}
break;
case GC_DONOR_TYPE:
if (encoded_seq[0] != gt_alphabet_encode(alphabet, 'G') ||
encoded_seq[1] != gt_alphabet_encode(alphabet, 'C')) {
gt_error_set(err, "sequence "GT_WU" in file \"%s\" is not a GC "
"sequence", j, gt_str_get(file2proc));
had_err = -1;
}
break;
case AG_ACCEPTOR_TYPE:
if (encoded_seq[0] != gt_alphabet_encode(alphabet, 'A') ||
encoded_seq[1] != gt_alphabet_encode(alphabet, 'G')) {
gt_error_set(err, "sequence "GT_WU" in file \"%s\" is not a AG "
"sequence", j, gt_str_get(file2proc));
had_err = -1;
}
break;
default:
gt_assert(0);
}
}
}
if (!had_err) {
switch (termtype) {
case GT_DONOR_TYPE:
build_bssm(bioseq, &bssm_param->gt_donor_model, i);
break;
case GC_DONOR_TYPE:
build_bssm(bioseq, &bssm_param->gc_donor_model, i);
break;
case AG_ACCEPTOR_TYPE:
build_bssm(bioseq, &bssm_param->ag_acceptor_model, i);
break;
default:
gt_assert(0);
}
}
/* reset */
gt_str_reset(file2proc);
/* free space */
gt_bioseq_delete(bioseq);
}
gt_str_delete(file2proc);
return had_err;
}
