static int verifycodelists(const GtEncseq *encseq,
unsigned int kmersize,
unsigned int numofchars,
const GtArrayGtCodetype *codeliststream,
GtError *err)
{
bool haserr = false;
GtArrayGtCodetype codeliststring;
const GtUchar *characters;
GtUword stringtotallength;
gt_error_check(err);
stringtotallength = gt_encseq_total_length(encseq);
characters = gt_alphabet_characters(gt_encseq_alphabet(encseq));
GT_INITARRAY(&codeliststring,GtCodetype);
collectkmercode(&codeliststring,
encseq,
kmersize,
numofchars,
stringtotallength);
if (comparecodelists(codeliststream,
&codeliststring,
kmersize,
numofchars,
(const char *) characters,
err) != 0)
{
haserr = true;
}
GT_FREEARRAY(&codeliststring,GtCodetype);
return haserr ? -1 : 0;
}
int gt_test_trieins(bool onlyins,const char *indexname,GtError *err)
{
Suffixarray suffixarray;
bool haserr = false;
unsigned long totallength = 0;
gt_error_check(err);
if (streamsuffixarray(&suffixarray,
SARR_ESQTAB,
indexname,
NULL,
err) != 0)
{
haserr = true;
} else
{
totallength = gt_encseq_total_length(suffixarray.encseq);
}
if (!haserr)
{
Mergertrierep trierep;
const GtUchar *characters;
trierep.encseqreadinfo = gt_malloc(sizeof *trierep.encseqreadinfo);
trierep.encseqreadinfo->encseqptr = suffixarray.encseq;
trierep.encseqreadinfo->readmode = suffixarray.readmode;
characters
= gt_alphabet_characters(gt_encseq_alphabet(suffixarray.encseq));
gt_mergertrie_initnodetable(&trierep,totallength,1U);
maketrie(&trierep,characters,totallength);
if (onlyins)
{
#ifdef WITHTRIEIDENT
#ifdef WITHTRIESHOW
showtrie(&trierep,characters);
#endif
checktrie(&trierep,totallength+1,totallength,err);
#endif
} else
{
#ifdef WITHTRIEIDENT
#ifdef WITHTRIESHOW
showallnoderelations(trierep.root);
#endif
#endif
successivelydeletesmallest(&trierep,totallength,characters,err);
}
gt_mergertrie_delete(&trierep);
}
gt_freesuffixarray(&suffixarray);
return haserr ? -1 : 0;
}
void gth_compute_scores(GthSA *sa,
bool proteineop,
GthDPParam *dp_param,
void *dp_options_est,
const unsigned char *gen_seq_tran,
const unsigned char *ref_seq_tran,
const unsigned char *ref_seq_orig,
const GtTransTable *transtable,
unsigned long gen_dp_start,
unsigned long scoreminexonlen,
bool introncutout,
bool gs2out,
GthSplicedSeq *spliced_seq,
unsigned long ref_dp_length,
GtAlphabet *gen_alphabet,
GtAlphabet *ref_alphabet,
GthDPScoresProtein *dp_scores_protein)
{
Traversealignmentfunctions travfunctions;
Traversealignmentstate travstate;
Computebordersandscoresdata data;
GthFlt score, coverageofgenomicsegment, coverageofreferencesegment;
gt_assert(!gth_sa_num_of_exons(sa));
gt_assert(!gth_sa_num_of_introns(sa));
travfunctions.processmismatch = computescoresprocmismatch;
travfunctions.processdeletion = computescoresprocdeletion;
travfunctions.processinsertion = computebordersandscoresprocinsertion;
travfunctions.processmatch = computebordersandscoresprocmatch;
travfunctions.processintron = computebordersandscoresprocintron;
travfunctions.breakcondition = NULL;
/* additional functions for protein edit operations */
travfunctions.processintron_with_1_base_left =
computebordersandscoresprocintron;
travfunctions.processintron_with_2_bases_left =
computebordersandscoresprocintron;
travfunctions.processmismatch_with_1_gap =
computescoresprocmismatchordeletionwithgap;
travfunctions.processmismatch_with_2_gaps =
computescoresprocmismatchordeletionwithgap;
travfunctions.processdeletion_with_1_gap =
computescoresprocmismatchordeletionwithgap;
travfunctions.processdeletion_with_2_gaps =
computescoresprocmismatchordeletionwithgap;
travstate.proteineop = proteineop;
travstate.processing_intron_with_1_base_left = false;
travstate.processing_intron_with_2_bases_left = false;
travstate.alignment = gth_sa_get_editoperations(sa);
travstate.alignmentlength = gth_sa_get_editoperations_length(sa);
travstate.eopptr = travstate.alignment + travstate.alignmentlength - 1;
travstate.genomicptr = gth_sa_genomiccutoff_start(sa);
travstate.referenceptr = gth_sa_referencecutoff_start(sa);
if (travstate.alignmentlength <= 0) {
/* in this case the alignmentscore is set to 0, which leads to discarding
this alignment later */
gth_sa_set_score(sa, 0.0);
return;
}
/* editoperations contain no zero base exons */
gt_assert(gth_sa_contains_no_zero_base_exons(sa));
/* editoperations contain no leading or terminal introns or insertions */
gt_assert(containsnoleadingorterminalintronsorinsertions(travstate.alignment,
travstate
.alignmentlength,
proteineop));
/* sum of edit operations equals referencelength */
gt_assert(gt_eops_equal_referencelength(travstate.alignment,
travstate.alignmentlength,
ref_dp_length
- gth_sa_referencecutoff_start(sa)
- gth_sa_referencecutoff_end(sa),
proteineop));
data.proteineop = proteineop;
data.newexon = true;
data.newintron = true;
data.firstexon = true;
data.introncutout = introncutout;
data.gs2out = gs2out;
data.spliced_seq = spliced_seq;
data.singleexonweight = (GthFlt) 0.0;
data.maxsingleexonweight = (GthFlt) 0.0;
data.overallexonweight = (GthFlt) 0.0;
data.maxoverallexonweight = (GthFlt) 0.0;
data.cumulativelengthofscoredexons = 0;
data.exon.leftgenomicexonborder = GT_UNDEF_ULONG;
data.exon.rightgenomicexonborder = GT_UNDEF_ULONG;
data.exon.leftreferenceexonborder = GT_UNDEF_ULONG;
data.exon.rightreferenceexonborder = GT_UNDEF_ULONG;
data.exon.exonscore = GTH_UNDEF_GTHDBL;
data.intron.donorsiteprobability = GTH_UNDEF_GTHFLT;
data.intron.acceptorsiteprobability = GTH_UNDEF_GTHFLT;
data.intron.donorsitescore = GTH_UNDEF_GTHDBL;
data.intron.acceptorsitescore = GTH_UNDEF_GTHDBL;
data.sa = sa;
data.dp_param = dp_param;
data.dp_options_est = dp_options_est;
data.gen_seq_tran = gen_seq_tran;
data.ref_seq_tran = ref_seq_tran;
data.ref_seq_orig = ref_seq_orig;
data.transtable = transtable;
data.gen_dp_start = gen_dp_start;
data.scoreminexonlen = scoreminexonlen;
data.ref_dp_length = ref_dp_length;
data.gen_alphabet = gen_alphabet;
data.gen_alphabet_characters = gen_alphabet
? gt_alphabet_characters(gen_alphabet)
: NULL;
data.dp_scores_protein = dp_scores_protein;
gthtraversealignment(true, &travstate, proteineop, &data, &travfunctions);
/* this is for saving the last exon */
evalnewintronifpossible(proteineop, &data.newexon, &data.newintron, true,
data.introncutout, data.gs2out, data.spliced_seq,
&data.exon, &data.intron, &data.singleexonweight,
&data.maxsingleexonweight, &data.overallexonweight,
&data.maxoverallexonweight,
&data.cumulativelengthofscoredexons, sa, &travstate,
gen_alphabet, data.dp_param, data.dp_options_est,
data.gen_seq_tran, data.ref_seq_tran,
data.gen_dp_start, data.scoreminexonlen);
/* saving the scores for the whole alignment */
if (data.maxoverallexonweight > 0.0) {
score = data.overallexonweight / data.maxoverallexonweight;
/* XXX: the way the alignmentscore is computed, it is possible to get a
score > 1.0. Since we don't want this, we cap it */
if (score > 1.0)
score = 1.0;
}
else
score = 0.0;
gth_sa_set_score(sa, score);
gth_sa_set_cumlen_scored_exons(sa, data.cumulativelengthofscoredexons);
/* fraction of the gen_dp_length which is scored/weighted */
coverageofgenomicsegment = (GthFlt) data.cumulativelengthofscoredexons /
(GthFlt) gth_sa_gen_dp_length(sa);
/* coverage of genomic segment is valid value */
gt_assert(coverageofgenomicsegment >= 0.0 && coverageofgenomicsegment <= 1.0);
/* fraction of the referencelength which is scored/weighted */
coverageofreferencesegment = (GthFlt) data.cumulativelengthofscoredexons /
(GthFlt) ((proteineop ? GT_CODON_LENGTH : 1) *
gth_sa_ref_total_length(sa));
if (coverageofgenomicsegment > coverageofreferencesegment) {
gth_sa_set_coverage(sa, coverageofgenomicsegment);
gth_sa_set_highest_cov(sa, true);
}
else {
gth_sa_set_coverage(sa, coverageofreferencesegment);
gth_sa_set_highest_cov(sa, false);
}
/* test the assumption that the coverage is never larger then the default */
gt_assert(gth_sa_coverage(sa) <= GTH_DEFAULT_MAX_COVERAGE);
/* compute poly(A) tail position */
gth_sa_calc_polyAtailpos(sa, ref_seq_tran, ref_alphabet);
/* determined exons are forward and consecutive */
gt_assert(gth_sa_exons_are_forward_and_consecutive(sa));
}
static int gt_linspace_align_runner(GT_UNUSED int argc,
GT_UNUSED const char **argv,
GT_UNUSED int parsed_args,
void *tool_arguments,
GtError *err)
{
GtLinspaceArguments *arguments = tool_arguments;
int had_err = 0;
GtAlignment *align;
GtWord left_dist = 0, right_dist = 0;
GtSequenceTable *sequence_table1, *sequence_table2;
GtLinspaceManagement *spacemanager;
GtScoreHandler *scorehandler = NULL;
GtTimer *linspacetimer = NULL;
GtAlphabet *alphabet = NULL;
gt_error_check(err);
gt_assert(arguments);
sequence_table1 = gt_sequence_table_new();
sequence_table2 = gt_sequence_table_new();
align = gt_alignment_new();
spacemanager = gt_linspace_management_new();
gt_linspace_management_set_TSfactor(spacemanager,arguments->timesquarefactor);
/* get sequences */
if (gt_str_array_size(arguments->strings) > 0)
{
get_onesequence(sequence_table1, arguments->strings, 0);
sequence_table1->size++;
get_onesequence(sequence_table2, arguments->strings, 1);
sequence_table2->size++;
}
else if (gt_str_array_size(arguments->files) > 0)
{
had_err = get_fastasequences(sequence_table1,
gt_str_array_get_str(arguments->files,0),err);
if (!had_err)
{
had_err = get_fastasequences(sequence_table2,
gt_str_array_get_str(arguments->files,1),err);
}
}
if (arguments->dna)
{
alphabet = gt_alphabet_new_dna();
} else
{
gt_assert(arguments->protein);
alphabet = gt_alphabet_new_protein();
}
gt_encode_sequence_table(alphabet,sequence_table1);
gt_encode_sequence_table(alphabet,sequence_table2);
if (!had_err)
{
scorehandler = gt_arguments2scorehandler(arguments,err);
if (scorehandler == NULL)
{
had_err = -1;
} else
{
if (arguments->global && arguments->protein && !arguments->has_costmatrix)
{
GtScoreHandler *costhandler = gt_scorehandler2costhandler(scorehandler);
gt_scorehandler_delete(scorehandler);
scorehandler = costhandler;
}
}
}
/* get diagonal band */
if (!had_err && arguments->diagonal)
{
if (gt_str_array_size(arguments->diagonalbonds) > 0)
{
had_err = gt_parse_score_value(__LINE__,&left_dist,
gt_str_array_get(arguments->diagonalbonds,0),
false, err);
if (!had_err)
{
had_err = gt_parse_score_value(__LINE__,&right_dist,
gt_str_array_get(arguments->diagonalbonds,1),
false, err);
}
}
}
if (!had_err && arguments->spacetime)
{
linspacetimer = gt_timer_new();
}
/* alignment functions with linear gap costs */
if (!had_err)
{
bool affine;
if (gt_str_array_size(arguments->linearcosts) > 0)
{
affine = false;
} else
{
gt_assert(gt_str_array_size(arguments->affinecosts) > 0);
affine = true;
}
had_err = gt_all_against_all_alignment_check (
affine, align, arguments,
spacemanager,
scorehandler,
gt_alphabet_characters(alphabet),
gt_alphabet_wildcard_show(alphabet),
sequence_table1,
sequence_table2,
left_dist,
right_dist,
linspacetimer,err);
}
/*spacetime option*/
if (!had_err && arguments->spacetime)
{
printf("# combined space peak in kilobytes: %f\n",
GT_KILOBYTES(gt_linspace_management_get_spacepeak(spacemanager)));
gt_timer_show_formatted(linspacetimer,"# TIME overall " GT_WD ".%02ld\n",
stdout);
}
gt_timer_delete(linspacetimer);
gt_linspace_management_delete(spacemanager);
gt_sequence_table_delete(sequence_table1);
gt_sequence_table_delete(sequence_table2);
gt_alignment_delete(align);
gt_alphabet_delete(alphabet);
gt_scorehandler_delete(scorehandler);
return had_err;
}
int gt_runidxlocali(const IdxlocaliOptions *idxlocalioptions,GtError *err)
{
Genericindex *genericindex = NULL;
bool haserr = false;
GtLogger *logger;
const GtEncseq *encseq = NULL;
logger = gt_logger_new(idxlocalioptions->verbose,
GT_LOGGER_DEFLT_PREFIX, stdout);
if (idxlocalioptions->doonline)
{
GtEncseqLoader *el;
el = gt_encseq_loader_new();
gt_encseq_loader_require_multiseq_support(el);
gt_encseq_loader_drop_description_support(el);
gt_encseq_loader_set_logger(el, logger);
encseq = gt_encseq_loader_load(el, gt_str_get(idxlocalioptions->indexname),
err);
gt_encseq_loader_delete(el);
if (encseq == NULL)
{
haserr = true;
}
} else
{
genericindex = genericindex_new(gt_str_get(idxlocalioptions->indexname),
idxlocalioptions->withesa,
idxlocalioptions->withesa ||
idxlocalioptions->docompare,
false,
true,
0,
logger,
err);
if (genericindex == NULL)
{
haserr = true;
} else
{
encseq = genericindex_getencseq(genericindex);
}
}
if (!haserr)
{
GtSeqIterator *seqit;
const GtUchar *query;
unsigned long querylen;
char *desc = NULL;
int retval;
Limdfsresources *limdfsresources = NULL;
const AbstractDfstransformer *dfst;
SWdpresource *swdpresource = NULL;
Showmatchinfo showmatchinfo;
ProcessIdxMatch processmatch;
GtAlphabet *a;
void *processmatchinfoonline, *processmatchinfooffline;
Storematchinfo storeonline, storeoffline;
a = gt_encseq_alphabet(encseq);
if (idxlocalioptions->docompare)
{
processmatch = storematch;
gt_initstorematch(&storeonline,encseq);
gt_initstorematch(&storeoffline,encseq);
processmatchinfoonline = &storeonline;
processmatchinfooffline = &storeoffline;
} else
{
processmatch = showmatch;
showmatchinfo.encseq = encseq;
showmatchinfo.characters = gt_alphabet_characters(a);
showmatchinfo.wildcardshow = gt_alphabet_wildcard_show(a);
showmatchinfo.showalignment = idxlocalioptions->showalignment;
processmatchinfoonline = processmatchinfooffline = &showmatchinfo;
}
if (idxlocalioptions->doonline || idxlocalioptions->docompare)
{
swdpresource = gt_newSWdpresource(idxlocalioptions->matchscore,
idxlocalioptions->mismatchscore,
idxlocalioptions->gapextend,
idxlocalioptions->threshold,
idxlocalioptions->showalignment,
processmatch,
processmatchinfoonline);
}
dfst = gt_locali_AbstractDfstransformer();
if (!idxlocalioptions->doonline || idxlocalioptions->docompare)
{
gt_assert(genericindex != NULL);
limdfsresources = gt_newLimdfsresources(genericindex,
true,
0,
0, /* maxpathlength */
true, /* keepexpandedonstack */
processmatch,
processmatchinfooffline,
NULL, /* processresult */
NULL, /* processresult info */
dfst);
}
seqit = gt_seq_iterator_sequence_buffer_new(idxlocalioptions->queryfiles,
err);
if (!seqit)
haserr = true;
if (!haserr)
{
gt_seq_iterator_set_symbolmap(seqit, gt_alphabet_symbolmap(a));
for (showmatchinfo.queryunit = 0; /* Nothing */;
showmatchinfo.queryunit++)
{
retval = gt_seq_iterator_next(seqit,
&query,
&querylen,
&desc,
err);
if (retval < 0)
{
haserr = true;
break;
}
if (retval == 0)
{
break;
}
printf("process sequence " Formatuint64_t " of length %lu\n",
PRINTuint64_tcast(showmatchinfo.queryunit),querylen);
if (idxlocalioptions->doonline || idxlocalioptions->docompare)
{
gt_multiapplysmithwaterman(swdpresource,encseq,query,querylen);
}
if (!idxlocalioptions->doonline || idxlocalioptions->docompare)
{
gt_indexbasedlocali(limdfsresources,
idxlocalioptions->matchscore,
idxlocalioptions->mismatchscore,
idxlocalioptions->gapstart,
idxlocalioptions->gapextend,
idxlocalioptions->threshold,
query,
querylen,
dfst);
}
if (idxlocalioptions->docompare)
{
gt_checkandresetstorematch(showmatchinfo.queryunit,
&storeonline,&storeoffline);
}
}
if (limdfsresources != NULL)
{
gt_freeLimdfsresources(&limdfsresources,dfst);
}
if (swdpresource != NULL)
{
gt_freeSWdpresource(swdpresource);
swdpresource = NULL;
}
gt_seq_iterator_delete(seqit);
}
if (idxlocalioptions->docompare)
{
gt_freestorematch(&storeonline);
gt_freestorematch(&storeoffline);
}
}
if (genericindex == NULL)
{
gt_encseq_delete((GtEncseq *) encseq);
encseq = NULL;
} else
{
genericindex_delete(genericindex);
}
gt_logger_delete(logger);
logger = NULL;
return haserr ? -1 : 0;
}
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;
}