static void xml_showgthgenomicinformation(GthSA *sa,
GthInput *input,
unsigned int indentlevel,
GtFile *outfp)
{
gt_assert(gth_sa_gen_file_num(sa) != GT_UNDEF_ULONG);
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<gDNA_segment>\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<template temp_file=\"%s\" temp_id=\"%s\" "
"temp_strand=\"%c\" temp_description=\"",
gth_input_get_genomic_filename(input,
gth_sa_gen_file_num(sa)),
gth_sa_gen_id(sa),
gth_sa_gen_strand_char(sa));
gth_input_echo_genomic_description(input, gth_sa_gen_file_num(sa),
gth_sa_gen_seq_num(sa), outfp);
gt_file_xprintf(outfp, "\">\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<position start=\"%lu\" stop=\"%lu\"/>\n",
gth_sa_gen_dp_start_show(sa),
gth_sa_gen_dp_end_show(sa));
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</template>\n");
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</gDNA_segment>\n");
}
static void showgenomicfilename(GthSA *sa, GthInput *input,
unsigned int indentlevel, GtFile *outfp)
{
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genomicfile>\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genomicfilename>%s</genomicfilename>\n",
gth_input_get_genomic_filename(input,
gth_sa_gen_file_num(sa)));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genomicfilehash>%s</genomicfilehash>\n",
GTH_UNDEFINED_HASH);
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</genomicfile>\n");
}
static void showgthgenomicinformation(GthSA *sa, GthInput *input,
bool showseqnums, GtFile *outfp)
{
gt_assert(gth_sa_gen_file_num(sa) != GT_UNDEF_UWORD);
gt_file_xprintf(outfp, "Genomic Template: file=%s, strand=%c, from="GT_WU", "
"to="GT_WU", description=",
gth_input_get_genomic_filename(input,
gth_sa_gen_file_num(sa)),
gth_sa_gen_strand_char(sa),
gth_sa_gen_dp_start_show(sa),
gth_sa_gen_dp_end_show(sa));
gth_sa_echo_genomic_description(sa, input, outfp);
if (showseqnums)
gt_file_xprintf(outfp, ", seqnum="GT_WU"", gth_sa_gen_seq_num(sa));
gt_file_xfputc('\n', outfp);
gt_file_xfputc('\n', outfp);
}
static void make_sequence_region(GtHashmap *sequence_regions,
GtStr *sequenceid,
GthRegionFactory *srf,
GthInput *input,
GtUword filenum,
GtUword seqnum)
{
GtUword offset_is_defined = false;
GtRange range, descrange;
GtGenomeNode *sr = NULL;
gt_assert(sequence_regions && sequenceid && srf && input);
if (gth_input_use_substring_spec(input)) {
range.start = gth_input_genomic_substring_from(input);
range.end = gth_input_genomic_substring_to(input);
}
else {
range = gth_input_get_relative_genomic_range(input, filenum, seqnum);
}
if (srf->use_desc_ranges) {
GtStr *description = gt_str_new();
gth_input_get_genomic_description(input, description, filenum, seqnum);
if (!gt_parse_description_range(gt_str_get(description), &descrange))
offset_is_defined = true;
gt_str_delete(description);
}
if (offset_is_defined)
range = gt_range_offset(&range, descrange.start);
else
range = gt_range_offset(&range, 1); /* 1-based */
if (!gt_str_length(sequenceid) ||
(gt_cstr_table_get(srf->used_seqids, gt_str_get(sequenceid)) &&
!offset_is_defined)) {
/* sequenceid is empty or exists already (and no offset has been parsed)
-> make one up */
GtStr *seqid;
char *base;
base = gt_basename(gth_input_get_genomic_filename(input, filenum));
seqid = gt_str_new_cstr(base);
gt_free(base);
gt_str_append_char(seqid, '|');
gt_str_append_uword(seqid, seqnum + 1); /* 1-based */
seqid_store_add(srf->seqid_store, filenum, seqnum, seqid, GT_UNDEF_UWORD);
gt_assert(!gt_cstr_table_get(srf->used_seqids, gt_str_get(seqid)));
gt_cstr_table_add(srf->used_seqids, gt_str_get(seqid));
sr = gt_region_node_new(seqid_store_get(srf->seqid_store, filenum, seqnum),
range.start, range.end);
gt_hashmap_add(sequence_regions,
(void*) gt_cstr_table_get(srf->used_seqids,
gt_str_get(seqid)),
sr);
gt_str_delete(seqid);
}
else {
/* sequenceid does not exists already (or an offset has been parsed)
-> use this one */
if (!gt_cstr_table_get(srf->used_seqids, gt_str_get(sequenceid))) {
/* no sequence region with this id exists -> create one */
gt_cstr_table_add(srf->used_seqids, gt_str_get(sequenceid));
seqid_store_add(srf->seqid_store, filenum, seqnum, sequenceid,
offset_is_defined ? descrange.start : GT_UNDEF_UWORD);
sr = gt_region_node_new(seqid_store_get(srf->seqid_store, filenum,
seqnum), range.start, range.end);
gt_hashmap_add(sequence_regions,
(void*) gt_cstr_table_get(srf->used_seqids,
gt_str_get(sequenceid)),
sr);
}
else {
GtRange prev_range, new_range;
/* sequence region with this id exists already -> modify range */
sr = gt_hashmap_get(sequence_regions, gt_str_get(sequenceid));
gt_assert(sr);
prev_range = gt_genome_node_get_range(sr);
new_range = gt_range_join(&prev_range, &range);
gt_genome_node_set_range(sr, &new_range);
seqid_store_add(srf->seqid_store, filenum, seqnum, sequenceid,
offset_is_defined ? descrange.start : GT_UNDEF_UWORD);
}
}
gt_assert(sr);
}
void gth_chaining(GthChainCollection *chain_collection,
GtUword gen_file_num,
GtUword ref_file_num,
GthCallInfo *call_info,
GthInput *input,
GthStat *stat,
bool directmatches,
const GthPlugins *plugins)
{
GtUword i, numofsequences = 0;
GtArray *matches;
GthChainingInfo chaining_info;
void *matcher_arguments;
GtFile *outfp = call_info->out->outfp;
GthMatchProcessorInfo match_processor_info;
bool refseqisdna = gth_input_ref_file_is_dna(input, ref_file_num);
/* make sure matcher is defined */
gt_assert(plugins);
gt_assert(plugins->matcher_arguments_new);
gt_assert(plugins->matcher_arguments_delete);
gt_assert(plugins->matcher_runner);
/* init */
matches = gt_array_new(sizeof (GthMatch));
chaining_info_init(&chaining_info, directmatches, refseqisdna, call_info,
input, stat, gen_file_num, ref_file_num);
matcher_arguments =
plugins->matcher_arguments_new(true,
input,
call_info->simfilterparam.inverse || !refseqisdna
? gth_input_get_genomic_filename(input, gen_file_num)
: gth_input_get_reference_filename(input,
ref_file_num),
call_info->simfilterparam.inverse || !refseqisdna
? gth_input_get_reference_filename(input,
ref_file_num)
: gth_input_get_genomic_filename(input, gen_file_num),
directmatches,
refseqisdna,
call_info->progname,
gt_str_get(gth_input_proteinsmap(input)),
call_info->simfilterparam.exact,
call_info->simfilterparam.edist,
false,
0,
call_info->simfilterparam.minmatchlength,
call_info->simfilterparam.seedlength,
call_info->simfilterparam.exdrop,
call_info->simfilterparam.prminmatchlen,
call_info->simfilterparam.prseedlength,
call_info->simfilterparam.prhdist,
call_info->translationtable,
call_info->simfilterparam.online,
call_info->simfilterparam.noautoindex,
call_info->simfilterparam.maskpolyAtails,
false);
match_processor_info_init(&match_processor_info, matches, chain_collection,
directmatches, refseqisdna,
call_info->simfilterparam.online,
call_info->simfilterparam.inverse, stat,
&chaining_info,
call_info->simfilterparam.maxnumofmatches,
call_info->simfilterparam.rare,
call_info->fragweightfactor,
plugins->jump_table_new,
plugins->jump_table_new_reverse,
plugins->jump_table_delete);
if (call_info->simfilterparam.maxnumofmatches > 0 ||
gth_stat_get_matchnumdistri(stat)) {
/* alloc space of match number counter */
numofsequences = gth_input_num_of_ref_seqs(input, ref_file_num);
match_processor_info.matchnumcounter = gt_malloc(sizeof (GtUword) *
numofsequences);
/* init match number counter to 0 */
memset(match_processor_info.matchnumcounter, 0,
(size_t) numofsequences * sizeof (GtUword));
}
/* free input, which contains the virtual trees.
because vmatch loads the virtual trees into memory, too.
this prevents that the virtual trees are loaded twice. */
gth_input_delete_current(input);
/* call matcher */
if (call_info->out->showverbose)
call_info->out->showverbose("call vmatch to compute matches");
plugins->matcher_runner(matcher_arguments, call_info->out->showverbose,
call_info->out->showverboseVM, &match_processor_info);
/* free matcher stuff here, because otherwise the reference file is mapped
twice below */
plugins->matcher_arguments_delete(matcher_arguments);
/* free sequence collections (if they have been filled by the matcher) */
gth_seq_con_delete(match_processor_info.gen_seq_con);
gth_seq_con_delete(match_processor_info.ref_seq_con);
/* save match numbers of match number distribution, if necessary */
if (gth_stat_get_matchnumdistri(stat)) {
for (i = 0; i < numofsequences; i++) {
if (match_processor_info.matchnumcounter[i] > 0) {
gth_stat_add_to_matchnumdistri(stat,
match_processor_info.matchnumcounter[i]);
}
}
}
/* free match number counter */
gt_free(match_processor_info.matchnumcounter);
/* return if no match has been found */
if (!gt_array_size(matches)) {
if (call_info->out->comments)
gt_file_xprintf(outfp, "%c no match has been found\n", COMMENTCHAR);
gt_array_delete(matches);
return;
}
/* load genomic file back into memory */
gth_input_load_genomic_file(input, gen_file_num, true);
/* load reference file back into memory */
gth_input_load_reference_file(input, ref_file_num, true);
/* compute chains from matches */
calc_chains_from_matches(chain_collection, matches, &chaining_info,
gth_input_current_gen_seq_con(input),
gth_input_current_ref_seq_con(input),
call_info->simfilterparam.rare,
call_info->fragweightfactor,
plugins->jump_table_new,
plugins->jump_table_new_reverse,
plugins->jump_table_delete);
if (call_info->out->showverbose) {
call_info->out->showverbose("sort global chains according to reference "
"sequence coverage");
}
/* sort chains */
gth_chain_collection_sort(chain_collection);
/* free */
gt_array_delete(matches);
}
static void show_xml_run_header(GthCallInfo *call_info, GthInput *input,
const char *timestring, const char *gth_version,
unsigned int indentlevel, const char **args)
{
GtFile *outfp = call_info->out->outfp;
GtUword i;
gth_indent(outfp, indentlevel);
if (call_info->intermediate) {
gt_file_xprintf(outfp, "<header xmlns=\"http://www.GenomeThreader.org/"
"SplicedAlignment/header/\">\n");
}
else {
gt_file_xprintf(outfp,
"<header xmlns=\"http://www.genomethreader.org/GTH_output/"
"header/\">\n");
}
/* at least one genomic file defined */
gt_assert(gth_input_num_of_gen_files(input));
/* at least one reference file defined */
gt_assert(gth_input_num_of_ref_files(input));
/* show a readable version of GthCallInfo. That is, it is shown with wich
parameters the program was called */
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<source program=\"GenomeThreader\" version=\"%s\" "
"build_date=\"%s\" run_date=\"%s\"/>\n", gth_version,
GT_BUILT, timestring);
/* show genomic file names */
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<gDNA_template_files>\n");
indentlevel++;
for (i = 0; i < gth_input_num_of_gen_files(input); i++) {
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<temp_name>%s</temp_name>\n",
gth_input_get_genomic_filename(input, i));
}
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</gDNA_template_files>\n");
/* show reference file names */
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<reference_files>\n");
indentlevel++;
for (i = 0; i < gth_input_num_of_ref_files(input); i++) {
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<file ref_name=\"%s\" type=\"%s\"/>\n",
gth_input_get_reference_filename(input, i),
gth_input_get_alphatype(input, i) == DNA_ALPHA
? "ESTcDNA" : "Protein");
}
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</reference_files>\n");
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<splice_site_parameters parameter_type=\"%s\" "
"species=\"%s\"/>\n", SPLICE_SITE_MODEL_NAME,
call_info->speciesnum == NUMOFSPECIES
? GENERIC_SPECIES_NAME
: speciestab[call_info->speciesnum]);
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<parameters>\n");
indentlevel++;
/* output name of BSSM file */
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<parameter name=\"bssmfile\" value=\"%s\"/>\n",
gth_input_bssmfilename(input));
/* output name of scorematrix */
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<parameter name=\"scorematrixfile\" value=\"%s\"/>\n",
gt_str_get(call_info->scorematrixfile));
/* output searchmode */
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<parameter name=\"searchmode\" "
"value=\"forward=%s,reverse=%s)\"/>\n",
GTH_SHOWBOOL(gth_input_forward(input)),
GTH_SHOWBOOL(gth_input_reverse(input)));
/* output arguments as comment */
gt_file_xprintf(outfp, "<!--\n%c Arguments: ", COMMENTCHAR);
gt_cstr_array_show_genfile(args, outfp);
gt_file_xprintf(outfp, "-->\n");
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</parameters>\n");
show_overall_reference_type(gth_input_overall_alphatype(input),
indentlevel, outfp);
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</header>\n");
}