static void show_pgl(GthPGL *pgl, GtUword pglnum,
GtUword translationtable, GthInput *input,
unsigned int indentlevel, GthOutput *out)
{
GtUword i;
GtFile *outfp = out->outfp;
gt_assert(!out->gff3out);
if (out->xmlout) {
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<predicted_gene_location>\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<PGL_line PGL_serial=\"" GT_WU "\" "
"PGL_strand=\"%c\" PGL_start=\"" GT_WU "\" PGL_stop=\""
GT_WU "\"/>\n",
pglnum + OUTPUTOFFSET,
SHOWSTRAND(gth_pgl_is_forward(pgl)),
SHOWGENPOS(gth_pgl_is_forward(pgl),
gth_pgl_total_length(pgl),
gth_pgl_genomic_offset(pgl),
pgl->maxrange.start),
SHOWGENPOS(gth_pgl_is_forward(pgl),
gth_pgl_total_length(pgl),
gth_pgl_genomic_offset(pgl),
pgl->maxrange.end));
}
else {
gt_file_xprintf(outfp, "PGL %3" GT_WUS " (%c strand): " GT_WU " "
GT_WU,
pglnum + OUTPUTOFFSET,
SHOWSTRAND(gth_pgl_is_forward(pgl)),
SHOWGENPOS(gth_pgl_is_forward(pgl),
gth_pgl_total_length(pgl),
gth_pgl_genomic_offset(pgl),
pgl->maxrange.start),
SHOWGENPOS(gth_pgl_is_forward(pgl),
gth_pgl_total_length(pgl),
gth_pgl_genomic_offset(pgl),
pgl->maxrange.end));
if (out->pglgentemplate)
gt_file_xprintf(outfp, " (genomic template '%s')", gth_pgl_gen_id(pgl));
gt_file_xfputc('\n', outfp);
}
for (i = 0; i < gt_array_size(pgl->assemblies); i++) {
show_ags(gth_pgl_get_ags(pgl, i), pglnum, i, translationtable, input,
indentlevel, out);
}
if (out->xmlout) {
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</predicted_gene_location>\n");
}
}
static void xml_show_pgl(GthPGL *pgl, unsigned long pglnum,
unsigned long translationtable, GthInput *input,
unsigned int indentlevel, GthOutput *out)
{
unsigned long i;
gth_indent(out->outfp, indentlevel);
gt_file_xprintf(out->outfp, "<predicted_gene_location>\n");
indentlevel++;
gth_indent(out->outfp, indentlevel);
gt_file_xprintf(out->outfp,
"<PGL_line PGL_serial=\"%lu\" PGL_strand=\"%c\" "
"PGL_start=\"%lu\" PGL_stop=\"%lu\"/>\n",
pglnum + OUTPUTOFFSET,
SHOWSTRAND(gth_pgl_is_forward(pgl)),
SHOWGENPOS(gth_pgl_is_forward(pgl),
gth_pgl_total_length(pgl),
gth_pgl_genomic_offset(pgl),
pgl->maxrange.start),
SHOWGENPOS(gth_pgl_is_forward(pgl),
gth_pgl_total_length(pgl),
gth_pgl_genomic_offset(pgl),
pgl->maxrange.end));
for (i = 0; i < gth_pgl_num_of_ags(pgl); i++) {
xml_show_ags(gth_pgl_get_ags(pgl, i), pglnum, i, translationtable, input,
indentlevel, out);
}
indentlevel--;
gth_indent(out->outfp, indentlevel);
gt_file_xprintf(out->outfp, "</predicted_gene_location>\n");
}
static void show_chain_calc_status(GthShowVerbose showverbose,
GtUword chainnum,
GtUword numofchains,
GtUword numofmatches,
GtUword currentgen_file_num,
GtUword numofgenomicfiles,
GtUword currentreffilenum,
GtUword numofreffiles,
bool directmatches, bool verboseseqs,
GtUword genseqnum,
GtUword refseqnum)
{
char buf[SHOW_CHAIN_CALCULATION_STATUS_BUF_SIZE];
GT_UNUSED int rval;
gt_assert(numofchains > 0);
if (numofgenomicfiles == 1 && numofreffiles == 1) {
rval = snprintf(buf, SHOW_CHAIN_CALCULATION_STATUS_BUF_SIZE,
"d=%c, compute chains for bucket "GT_WU"/"GT_WU
" (matches in bucket="GT_WU")", SHOWSTRAND(directmatches),
chainnum, numofchains, numofmatches);
}
else {
rval = snprintf(buf, SHOW_CHAIN_CALCULATION_STATUS_BUF_SIZE,
"gf="GT_WU"/"GT_WU", d=%c, rf="GT_WU"/"GT_WU
", compute chains for bucket "GT_WU"/"GT_WU
" (matches in bucket="GT_WU")", currentgen_file_num + 1,
numofgenomicfiles, SHOWSTRAND(directmatches),
currentreffilenum + 1, numofreffiles, chainnum, numofchains,
numofmatches);
}
/* buf[SHOW_CHAIN_CALCULATION_STATUS_BUF_SIZE] is large enough */
gt_assert(rval < SHOW_CHAIN_CALCULATION_STATUS_BUF_SIZE);
showverbose(buf);
if (verboseseqs) {
rval = snprintf(buf, SHOW_CHAIN_CALCULATION_STATUS_BUF_SIZE,
"genseqnum="GT_WU", refseqnum="GT_WU"", genseqnum,
refseqnum);
/* buf[SHOW_CHAIN_CALCULATION_STATUS_BUF_SIZE] is large enough */
gt_assert(rval < SHOW_CHAIN_CALCULATION_STATUS_BUF_SIZE);
showverbose(buf);
}
}
static void show_matrix_calculation_status(GthShowVerbose showverbose,
bool gen_strand_forward,
bool ref_strand_forward,
bool introncutout,
GtUword chainctr,
GtUword num_of_chains,
GtUword icdelta,
GtUword gen_file_num,
GtUword num_of_gen_files,
GtUword ref_file_num,
GtUword num_of_ref_files,
bool directmatches,
bool verboseseqs,
const char *gen_id,
const char *ref_id)
{
char buf[SHOW_MATRIX_CALCULATION_STATUS_BUF_SIZE],
icdeltastring[ICDELTASTRINGLENGTH];
GT_UNUSED int rval;
if (introncutout) {
rval = snprintf(icdeltastring, ICDELTASTRINGLENGTH, ", icdelta=" GT_WU ,
icdelta);
/* buffer icdeltastring[ICDELTASTRINGLENGTH] is large enough */
gt_assert(rval < ICDELTASTRINGLENGTH);
}
if (num_of_gen_files == 1 && num_of_ref_files == 1) {
rval = snprintf(buf, SHOW_MATRIX_CALCULATION_STATUS_BUF_SIZE,
"d=%c, compute spliced alignment, genseq=%c, "
"chain=" GT_WU "/" GT_WU ", refseq=%c%s",
SHOWSTRAND(directmatches), SHOWSTRAND(gen_strand_forward),
chainctr + 1, num_of_chains, SHOWSTRAND(ref_strand_forward),
introncutout ? icdeltastring : "");
}
else {
rval = snprintf(buf, SHOW_MATRIX_CALCULATION_STATUS_BUF_SIZE,
"gf=" GT_WU "/" GT_WU ", d=%c, rf=" GT_WU "/" GT_WU
", compute spliced alignment, gs=%c, chain=" GT_WU "/"
GT_WU ", rs=%c%s",
gen_file_num + 1, num_of_gen_files,
SHOWSTRAND(directmatches), ref_file_num + 1,
num_of_ref_files, SHOWSTRAND(gen_strand_forward),
chainctr + 1, num_of_chains, SHOWSTRAND(ref_strand_forward),
introncutout ? icdeltastring : "");
}
/* buf[SHOW_MATRIX_CALCULATION_STATUS_BUF_SIZE] is large enough */
gt_assert(rval < SHOW_MATRIX_CALCULATION_STATUS_BUF_SIZE);
showverbose(buf);
if (verboseseqs) {
rval = snprintf(buf, SHOW_MATRIX_CALCULATION_STATUS_BUF_SIZE,
"genomicid=%s, referenceid=%s", gen_id, ref_id);
/* buf[SHOW_MATRIX_CALCULATION_STATUS_BUF_SIZE] is large enough */
gt_assert(rval < SHOW_MATRIX_CALCULATION_STATUS_BUF_SIZE);
showverbose(buf);
}
}
void gth_save_chain(GtChain *chain, GtFragment *fragments,
unsigned long num_of_fragments,
GT_UNUSED unsigned long max_gap_width,
void *data)
{
GthSaveChainInfo *info = (GthSaveChainInfo*) data;
GtRange range;
GthChain *gth_chain;
unsigned long i, fragnum;
gt_assert(chain_is_colinear(chain, fragments));
if (info->comments) {
gt_file_xprintf(info->outfp, "%c process global chain with score %ld\n",
COMMENTCHAR, gt_chain_get_score(chain));
gt_file_xprintf(info->outfp, "%c process global chain with the "
"following fragments\n", COMMENTCHAR);
for (i = 0; i < gt_chain_size(chain); i++)
showfragment(fragments + gt_chain_get_fragnum(chain, i), info->outfp);
}
/* init */
gth_chain = gth_chain_new();
gth_chain->gen_file_num = info->gen_file_num;
gth_chain->gen_seq_num = info->gen_seq_num;
gth_chain->ref_file_num = info->ref_file_num;
gth_chain->ref_seq_num = info->ref_seq_num;
/* chain has a minimum length of 1 */
gt_assert(gt_chain_size(chain));
/* global chain filter */
if (globalchainislongenough(chain, fragments,
>h_chain->refseqcoverage, info->gcmincoverage,
info->referencelength, info->stat, info->comments,
info->outfp)) {
/* save all potential exons */
for (i = 0; i < gt_chain_size(chain); i++) {
fragnum = gt_chain_get_fragnum(chain, i);
range.start = fragments[fragnum].startpos2;
range.end = fragments[fragnum].endpos2;
/* check for overlap */
if (i > 0 &&
range.start <=
((GtRange*) gt_array_get_last(gth_chain->forwardranges))->end) {
/* overlap found -> modify last range */
gt_assert(((GtRange*) gt_array_get_last(gth_chain->forwardranges))
->end <= range.end);
((GtRange*) gt_array_get_last(gth_chain->forwardranges))->end =
range.end;
}
else {
#ifndef NDEBUG
if (i > 0) {
/* gap width is smaller or equal than the maximum gap width */
gt_assert((range.start - 1 -
((GtRange*) gt_array_get_last(gth_chain->forwardranges))
->end + 1 - 1) <= max_gap_width);
}
#endif
/* save range */
gt_array_add(gth_chain->forwardranges, range);
}
}
GtRange genomicrange = chain_get_genomicrange(gth_chain);
if (info->enrichchains) {
enrich_chain(gth_chain, fragments, num_of_fragments, info->comments,
info->outfp);
}
gt_assert(gt_ranges_are_consecutive(gth_chain->forwardranges));
/* copy ranges to opposite strand */
gt_ranges_copy_to_opposite_strand(gth_chain->reverseranges,
gth_chain->forwardranges,
info->gen_total_length,
info->gen_offset);
/* compute jump table if necessary */
if (info->jump_table) {
GthJumpTable *forward_jump_table, *reverse_jump_table;
GtArray *chain_fragments;
chain_fragments = make_list_of_chain_fragments(chain, fragments,
num_of_fragments,
info->enrichchains,
&genomicrange);
forward_jump_table =
info->jump_table_new(gt_array_get_space(chain_fragments),
gt_array_size(chain_fragments), info->jtdebug);
reverse_jump_table =
info->jump_table_new_reverse(forward_jump_table,
info->gen_total_length, info->gen_offset,
info->ref_total_length, info->ref_offset);
gt_assert(!gth_chain->forward_jump_table);
gth_chain->forward_jump_table = forward_jump_table;
gt_assert(!gth_chain->reverse_jump_table);
gth_chain->reverse_jump_table = reverse_jump_table;
gt_array_delete(chain_fragments);
gth_chain->jump_table_delete = info->jump_table_delete;
}
/* save array of potential exons */
gth_chain_collection_add(info->chain_collection, gth_chain);
if (info->comments) {
gt_file_xprintf(info->outfp, "%c global chain with the following "
"ranges has been saved\n",COMMENTCHAR);
gt_file_xprintf(info->outfp, "%c forward ranges:\n", COMMENTCHAR);
gt_file_xprintf(info->outfp, "%c ", COMMENTCHAR);
gt_ranges_show(gth_chain->forwardranges, info->outfp);
gt_file_xprintf(info->outfp, "%c reverse ranges:\n", COMMENTCHAR);
gt_file_xprintf(info->outfp, "%c ", COMMENTCHAR);
gt_ranges_show(gth_chain->reverseranges, info->outfp);
}
/* output stored chains here
(Mohamed needed this to compare the chaining phase of gth with CHAINER)
*/
if (info->stopafterchaining) {
gt_file_xprintf(info->outfp,
"%c gl. chain with coverage=%.2f and score %ld "
"(genseq=%lu, str.=%c, refseq=%lu)\n", COMMENTCHAR,
gth_chain->refseqcoverage, gt_chain_get_score(chain),
gth_chain->gen_seq_num, SHOWSTRAND(info->directmatches),
gth_chain->ref_seq_num);
for (i = 0; i < gt_chain_size(chain); i++)
showfragment(fragments + gt_chain_get_fragnum(chain, i), info->outfp);
}
}
else {
/* for -paralogs this case is not supposed to occur */
gt_assert(!info->paralogs);
if (info->comments)
gt_file_xprintf(info->outfp, "%c global chain discarded\n",
COMMENTCHAR);
gth_chain_delete(gth_chain);
}
}
char gth_sa_ref_strand_char(const GthSA *sa)
{
gt_assert(sa);
return SHOWSTRAND(sa->ref_strand_forward);
}
void gt_outputtranslationandorf(unsigned long pglnum, const GthAGS *ags,
unsigned long agsnum,
unsigned long translationtable,
GthInput *input,
unsigned int indentlevel,
GthOutput *out)
{
unsigned long i;
unsigned int nframe;
const unsigned char *gen_seq_orig;
GtStr *frame[3];
char translated;
GtTranslatorStatus status;
GtTranslator *translator;
GtTransTable *transtable;
GtCodonIterator *ci;
GthSplicedSeq *spliced_seq;
GtArray *ranges;
GtFile *outfp = out->outfp;
/* output header */
if (out->xmlout) {
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<three_phase_translation "
"xmlns=\"http://www.genomethreader.org/GTH_output/"
"PGL_module/predicted_gene_location/AGS_information/"
"three_phase_translation/\">\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<description PGL_serial=\"%lu\" "
"AGS_serial=\"%lu\" gDNA_strand=\"%c\"/>\n",
pglnum + OUTPUTOFFSET, agsnum + OUTPUTOFFSET,
SHOWSTRAND(gth_ags_is_forward(ags)));
}
else {
gt_file_xprintf(outfp, "3-phase translation of AGS-%lu (%cstrand):\n\n",
agsnum + OUTPUTOFFSET,
SHOWSTRAND(gth_ags_is_forward(ags)));
}
ranges = gt_array_new(sizeof (GtRange));
for (i = 0; i < gt_array_size(ags->exons); i++)
gt_array_add(ranges, ((GthExonAGS*) gt_array_get(ags->exons, i))->range);
/* get genomic sequence */
gen_seq_orig = gth_input_original_genomic_sequence(input,
gth_ags_filenum(ags),
gth_ags_is_forward(ags));
spliced_seq = gth_spliced_seq_new(gen_seq_orig, ranges);
frame[0] = gt_str_new();
frame[1] = gt_str_new();
frame[2] = gt_str_new();
/* prepare for translation */
ci = gt_codon_iterator_simple_new((const char*) spliced_seq->splicedseq,
spliced_seq->splicedseqlen, NULL);
gt_assert(ci);
transtable = gt_trans_table_new(translationtable, NULL);
gt_assert(transtable);
/* translate the template in all three frames */
translator = gt_translator_new_with_table(transtable, ci);
status = gt_translator_next(translator, &translated, &nframe, NULL);
while (status == GT_TRANSLATOR_OK) {
gt_str_append_char(frame[nframe], translated);
status = gt_translator_next(translator, &translated, &nframe, NULL);
}
gt_assert(status != GT_TRANSLATOR_ERROR);
gt_translator_delete(translator);
gt_trans_table_delete(transtable);
gt_codon_iterator_delete(ci);
/* show the translation */
showtranslation(spliced_seq, gt_str_get(frame[0]), gt_str_get(frame[1]),
gt_str_get(frame[2]), ags->exons, gth_ags_is_forward(ags),
gth_ags_total_length(ags), gth_ags_genomic_offset(ags),
indentlevel, out);
/* show the (consolidated) ORFs */
gthshowORFs(gt_str_get(frame[0]), gt_str_get(frame[1]), gt_str_get(frame[2]),
gt_str_length(frame[0]), gt_str_length(frame[1]),
gt_str_length(frame[2]), gth_ags_is_forward(ags),
gth_ags_total_length(ags), gth_ags_genomic_offset(ags),
gt_str_get(ags->gen_id), pglnum, agsnum, spliced_seq,
indentlevel, out);
if (out->xmlout) {
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</three_phase_translation>\n");
}
gth_spliced_seq_delete(spliced_seq);
gt_array_delete(ranges);
gt_str_delete(frame[0]);
gt_str_delete(frame[1]);
gt_str_delete(frame[2]);
}
