void gt_bioseq_show_seqlengthdistri(GtBioseq *bs, GtFile *outfp)
{
GtDiscDistri *d;
GtUword i;
gt_assert(bs);
d = gt_disc_distri_new();
for (i = 0; i < gt_bioseq_number_of_sequences(bs); i++)
gt_disc_distri_add(d, gt_bioseq_get_sequence_length(bs, i));
gt_file_xprintf(outfp, "sequence length distribution:\n");
gt_disc_distri_show(d, outfp);
gt_disc_distri_delete(d);
}
void gt_Outlcpinfo_delete(GtOutlcpinfo *outlcpinfo)
{
if (outlcpinfo == NULL)
{
return;
}
gt_turningwheel_delete(outlcpinfo->turnwheel);
if (outlcpinfo->lcpsubtab.lcp2file != NULL)
{
if (!outlcpinfo->swallow_tail_lcpvalues &&
outlcpinfo->lcpsubtab.lcp2file->countoutputlcpvalues <
outlcpinfo->numsuffixes2output)
{
outlcpinfo->lcpsubtab.lcp2file->countoutputlcpvalues
+= outmany0lcpvalues(outlcpinfo->numsuffixes2output -
outlcpinfo->lcpsubtab.lcp2file
->countoutputlcpvalues,
outlcpinfo->lcpsubtab.lcp2file->outfplcptab);
}
gt_assert(outlcpinfo->swallow_tail_lcpvalues ||
outlcpinfo->lcpsubtab.lcp2file->countoutputlcpvalues ==
outlcpinfo->numsuffixes2output);
GT_FREEARRAY(&outlcpinfo->lcpsubtab.lcp2file->largelcpvalues,
Largelcpvalue);
gt_fa_fclose(outlcpinfo->lcpsubtab.lcp2file->outfplcptab);
gt_fa_fclose(outlcpinfo->lcpsubtab.lcp2file->outfpllvtab);
gt_free(outlcpinfo->lcpsubtab.lcp2file->reservoir);
outlcpinfo->lcpsubtab.lcp2file->smalllcpvalues = NULL;
outlcpinfo->lcpsubtab.lcp2file->reservoir = NULL;
outlcpinfo->lcpsubtab.lcp2file->sizereservoir = 0;
gt_free(outlcpinfo->lcpsubtab.lcp2file);
} else
{
gt_free(outlcpinfo->lcpsubtab.tableoflcpvalues.bucketoflcpvalues);
#ifndef NDEBUG
gt_free(outlcpinfo->lcpsubtab.tableoflcpvalues.isset);
#endif
}
gt_free(outlcpinfo->lcpsubtab.lcpprocess);
outlcpinfo->lcpsubtab.tableoflcpvalues.bucketoflcpvalues = NULL;
#ifndef NDEBUG
outlcpinfo->lcpsubtab.tableoflcpvalues.isset = NULL;
#endif
outlcpinfo->lcpsubtab.tableoflcpvalues.numofentries = 0;
if (outlcpinfo->lcpsubtab.distlcpvalues != NULL)
{
gt_disc_distri_show(outlcpinfo->lcpsubtab.distlcpvalues,NULL);
gt_disc_distri_delete(outlcpinfo->lcpsubtab.distlcpvalues);
}
gt_free(outlcpinfo);
}
void gth_stat_show(GthStat *stat, bool show_full_stats, bool xmlout,
GtFile *outfp)
{
char *timestring;
gt_assert(stat);
/* begin XML comment */
if (xmlout)
gt_file_xprintf(outfp, "<!--\n");
/* output exon length distribution */
if (stat->exondistri) {
gt_file_xprintf(outfp, "%c length distribution of all exons:\n",
COMMENTCHAR);
gt_disc_distri_show(stat->exondistribution, outfp);
}
/* output intron length distribution */
if (stat->introndistri) {
if (stat->exondistri)
gt_file_xprintf(outfp, "%c\n", COMMENTCHAR);
gt_file_xprintf(outfp, "%c length distribution of all introns:\n",
COMMENTCHAR);
gt_disc_distri_show(stat->introndistribution, outfp);
}
/* output match number distribution */
if (stat->matchnumdistri) {
if (stat->exondistri || stat->introndistri)
gt_file_xprintf(outfp, "%c\n", COMMENTCHAR);
gt_file_xprintf(outfp, "%c distribution of match numbers (per genomic "
"file, per reference sequence:\n", COMMENTCHAR);
gt_disc_distri_show(stat->matchnumdistribution, outfp);
}
/* output reference sequence coverage distribution */
if (stat->refseqcovdistri) {
if (stat->exondistri || stat->introndistri || stat->matchnumdistri)
gt_file_xprintf(outfp, "%c\n", COMMENTCHAR);
gt_file_xprintf(outfp, "%c reference sequence coverage distribution (of "
"global chains):\n", COMMENTCHAR);
gt_disc_distri_show(stat->refseqcoveragedistribution, outfp);
}
/* output spliced alignment statistics */
if (stat->sa_stats) {
if (stat->exondistri || stat->introndistri ||
stat->matchnumdistri || stat->refseqcovdistri) {
gt_file_xprintf(outfp, "%c\n", COMMENTCHAR);
}
INFOCHAR;
gt_file_xprintf(outfp,
"spliced alignment alignment score distribution:\n");
gt_disc_distri_show(stat->sa_alignment_score_distribution, outfp);
INFOCHAR;
gt_file_xfputc('\n', outfp);
INFOCHAR;
gt_file_xprintf(outfp, "spliced alignment coverage distribution:\n");
gt_disc_distri_show(stat->sa_coverage_distribution, outfp);
}
/* output general statistics */
outputgeneralstatistics(stat, show_full_stats, outfp);
INFOCHAR;
gt_file_xfputc('\n', outfp);
/* output the memory statistics */
outputmemorystatistics(stat, show_full_stats, outfp);
/* output time */
INFOCHAR;
gt_file_xfputc('\n', outfp);
INFOCHAR;
timestring = gth_get_time();
gt_file_xprintf(outfp, "date finished: %s\n", timestring);
gt_free(timestring);
/* output important messages */
if (stat->numofremovedzerobaseexons ||
stat->numofautointroncutoutcalls ||
stat->numofunsuccessfulintroncutoutDPs ||
stat->numoffailedDPparameterallocations ||
stat->numoffailedmatrixallocations ||
stat->numofundeterminedSAs ||
stat->numoffilteredpolyAtailmatches) {
gt_file_xprintf(outfp, "%c\n", COMMENTCHAR);
gt_file_xprintf(outfp, "%c important messages:\n", COMMENTCHAR);
if (stat->numofremovedzerobaseexons > 0) {
gt_file_xprintf(outfp, "%c %lu removed zero base exons\n",
COMMENTCHAR, stat->numofremovedzerobaseexons);
}
if (stat->numofautointroncutoutcalls > 0) {
gt_file_xprintf(outfp, "%c %lu times the intron cutout technique was "
"used automatically\n", COMMENTCHAR,
stat->numofautointroncutoutcalls);
}
if (stat->numofunsuccessfulintroncutoutDPs > 0) {
gt_file_xprintf(outfp, "%c %lu unsuccessful DP calls using intron "
"cutout technique\n", COMMENTCHAR,
stat->numofunsuccessfulintroncutoutDPs);
}
if (stat->numoffailedDPparameterallocations > 0) {
gt_file_xprintf(outfp, "%c %lu DP parameter allocations failed\n",
COMMENTCHAR, stat->numoffailedDPparameterallocations);
}
if (stat->numoffailedmatrixallocations > 0) {
gt_file_xprintf(outfp, "%c %lu matrix allocations failed\n",
COMMENTCHAR, stat->numoffailedmatrixallocations);
}
if (stat->numofundeterminedSAs > 0) {
gt_file_xprintf(outfp, "%c %lu undetermined spliced alignments\n",
COMMENTCHAR, stat->numofundeterminedSAs);
}
if (stat->numoffilteredpolyAtailmatches > 0) {
gt_file_xprintf(outfp,
"%c %lu matches containing a poly(A) tail filtered\n",
COMMENTCHAR, stat->numoffilteredpolyAtailmatches);
}
}
/* end XML comment */
if (xmlout)
gt_file_xprintf(outfp, "-->\n");
}
void gt_stat_visitor_show_stats(GtNodeVisitor *nv, GtFile *outfp)
{
GtStatVisitor *sv = stat_visitor_cast(nv);
if (sv->number_of_sequence_regions) {
gt_file_xprintf(outfp, "sequence regions: %lu (total length: %llu)\n",
sv->number_of_sequence_regions,
sv->total_length_of_sequence_regions);
}
if (sv->number_of_multi_features) {
gt_file_xprintf(outfp, "multi-features: %lu\n",
sv->number_of_multi_features);
}
if (sv->number_of_genes)
gt_file_xprintf(outfp, "genes: %lu\n", sv->number_of_genes);
if (sv->number_of_protein_coding_genes) {
gt_file_xprintf(outfp, "protein-coding genes: %lu\n",
sv->number_of_protein_coding_genes);
}
if (sv->number_of_mRNAs)
gt_file_xprintf(outfp, "mRNAs: %lu\n", sv->number_of_mRNAs);
if (sv->number_of_protein_coding_mRNAs) {
gt_file_xprintf(outfp, "protein-coding mRNAs: %lu\n",
sv->number_of_protein_coding_mRNAs);
}
if (sv->number_of_exons)
gt_file_xprintf(outfp, "exons: %lu\n", sv->number_of_exons);
if (sv->number_of_CDSs)
gt_file_xprintf(outfp, "CDSs: %lu\n", sv->number_of_CDSs);
if (sv->number_of_LTR_retrotransposons) {
gt_file_xprintf(outfp, "LTR_retrotransposons: %lu\n",
sv->number_of_LTR_retrotransposons);
}
if (sv->gene_length_distribution) {
gt_file_xprintf(outfp, "gene length distribution:\n");
gt_disc_distri_show(sv->gene_length_distribution, outfp);
}
if (sv->gene_score_distribution) {
gt_file_xprintf(outfp, "gene score distribution:\n");
gt_disc_distri_show(sv->gene_score_distribution, outfp);
}
if (sv->exon_length_distribution) {
gt_file_xprintf(outfp, "exon length distribution:\n");
gt_disc_distri_show(sv->exon_length_distribution, outfp);
}
if (sv->exon_number_distribution) {
gt_file_xprintf(outfp, "exon number distribution:\n");
gt_disc_distri_show(sv->exon_number_distribution, outfp);
}
if (sv->intron_length_distribution) {
gt_file_xprintf(outfp, "intron length distribution:\n");
gt_disc_distri_show(sv->intron_length_distribution, outfp);
}
if (sv->cds_length_distribution) {
gt_file_xprintf(outfp, "CDS length distribution:\n");
gt_disc_distri_show(sv->cds_length_distribution, outfp);
}
if (sv->used_sources) {
GtStrArray *sources;
unsigned long i;
gt_file_xprintf(outfp, "used source tags:\n");
sources = gt_cstr_table_get_all(sv->used_sources);
for (i = 0; i < gt_str_array_size(sources); i++)
gt_file_xprintf(outfp, "%s\n", gt_str_array_get(sources, i));
gt_str_array_delete(sources);
}
}
