static void showgs2referenceinformation(GthSA *sa, GtFile *outfp)
{
gt_file_xprintf(outfp, "EST sequence %4"GT_WUS" %cstrand (File: %s%c)\n\n",
gth_sa_call_number(sa),
gth_sa_ref_strand_char(sa),
gth_sa_ref_id(sa),
gth_sa_ref_strand_char(sa));
}
static void xml_showgthreferenceinformation(GthSA *sa,
GthInput *input,
unsigned int indentlevel,
GtFile *outfp)
{
gt_assert(gth_sa_ref_file_num(sa) != GT_UNDEF_ULONG);
gth_indent(outfp, indentlevel);
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
gt_file_xprintf(outfp, "<reference ref_file=\"%s\" ref_id=\"%s\" "
"ref_strand=\"%c\" ref_description=\"",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)),
gth_sa_ref_id(sa),
gth_sa_ref_strand_char(sa));
break;
case PROTEIN_ALPHA:
gt_file_xprintf(outfp, "<reference ref_file=\"%s\" ref_id=\"%s\" "
"ref_description=\"",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)),
gth_sa_ref_id(sa));
break;
default: gt_assert(0);
}
gth_input_echo_reference_description(input, gth_sa_ref_file_num(sa),
gth_sa_ref_seq_num(sa), outfp);
gt_file_xprintf(outfp, "\">\n");
}
/* The following function prints the "classic" GeneSeqer2 MATCH line */
static void xml_showmatchline(GthSA *sa, unsigned int indentlevel,
GtFile *outfp)
{
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<MATCH_line gen_id=\"%s\" gen_strand=\"%c\" ",
gth_sa_gen_id(sa),
gth_sa_gen_strand_char(sa));
if (gth_sa_alphatype(sa) == DNA_ALPHA) {
gt_file_xprintf(outfp, "ref_id=\"%s\" ref_strand=\"%c\">\n",
gth_sa_ref_id(sa),
gth_sa_ref_strand_char(sa));
}
else
gt_file_xprintf(outfp, "ref_id=\"%s\">\n", gth_sa_ref_id(sa));
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp,
"<total_alignment_score>%.3f</total_alignment_score>\n",
gth_sa_score(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<cumulative_length_of_scored_exons>%lu"
"</cumulative_length_of_scored_exons>\n",
gth_sa_cumlen_scored_exons(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<coverage percentage=\"%.3f\" high_type=\"",
gth_sa_coverage(sa));
gt_file_xfputc(gth_sa_coverage_char(sa), outfp);
gt_file_xprintf(outfp, "\"/>\n");
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</MATCH_line>\n");
}
static void showgthreferenceinformation(GthSA *sa, GthInput *input,
bool showseqnums,
GtFile *outfp)
{
gt_assert(gth_sa_ref_file_num(sa) != GT_UNDEF_UWORD);
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
gt_file_xprintf(outfp,
"EST Sequence: file=%s, strand=%c, description=",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)),
gth_sa_ref_strand_char(sa));
break;
case PROTEIN_ALPHA:
gt_file_xprintf(outfp, "Protein Sequence: file=%s, description=",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)));
break;
default: gt_assert(0);
}
gth_sa_echo_reference_description(sa, input, outfp);
if (showseqnums)
gt_file_xprintf(outfp, ", seqnum="GT_WU"", gth_sa_ref_seq_num(sa));
gt_file_xfputc('\n', outfp);
gt_file_xfputc('\n', outfp);
}
/* The following function prints the "classic" GeneSeqer2 MATCH line */
static void showmatchline(GthSA *sa, GtFile *outfp)
{
gt_file_xprintf(outfp, "MATCH\t%s%c\t%s%c\t%5.3f\t"GT_WU"\t%5.3f\t%c\n",
gth_sa_gen_id(sa),
gth_sa_gen_strand_char(sa),
gth_sa_ref_id(sa),
gth_sa_ref_strand_char(sa),
gth_sa_score(sa),
gth_sa_cumlen_scored_exons(sa),
gth_sa_coverage(sa),
gth_sa_coverage_char(sa));
}
static void xml_outputPGSlines(GtArray *alignments, unsigned int indentlevel,
GtFile *outfp)
{
unsigned long i, j;
GthSA *sa;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<supporting_evidence xmlns=\""
"http://www.genomethreader.org/"
"GTH_output/PGL_module/predicted_gene_location/"
"AGS_information/supporting_evidence/\">\n");
indentlevel++;
for (i = 0; i < gt_array_size(alignments); i++) {
sa = *(GthSA**) gt_array_get(alignments, i);
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<PGS_line>\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<gDNA_exon_coordinates>\n");
indentlevel++;
for (j = 0; j < gth_sa_num_of_exons(sa); j++) {
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<exon start=\"%lu\" stop=\"%lu\"/>\n",
gth_sa_left_genomic_exon_border(sa, j),
gth_sa_right_genomic_exon_border(sa, j));
}
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</gDNA_exon_coordinates>\n");
gth_indent(outfp, indentlevel);
if (gth_sa_alphatype(sa) == DNA_ALPHA) {
gt_file_xprintf(outfp, "<referenceDNA id=\"%s\" strand=\"%c\"/>\n",
gth_sa_ref_id(sa),
gth_sa_ref_strand_char(sa));
}
else {
gt_file_xprintf(outfp, "<referenceProtein id=\"%s\"/>\n",
gth_sa_ref_id(sa));
}
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</PGS_line>\n");
}
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</supporting_evidence>\n");
}
/*
The following function prints the "classic" GeneSeqer2 PGS line
*/
static void showpgsline(GthSA *sa, GtFile *outfp)
{
GtUword i, numofexons;
gt_assert(sa);
numofexons = gth_sa_num_of_exons(sa);
gt_file_xprintf(outfp, "PGS_%s%c_%s%c\t(",
gth_sa_gen_id(sa),
gth_sa_gen_strand_char(sa),
gth_sa_ref_id(sa),
gth_sa_ref_strand_char(sa));
for (i = 0; i < numofexons; i++) {
gt_file_xprintf(outfp, ""GT_WU" "GT_WU"",
gth_sa_left_genomic_exon_border(sa, i),
gth_sa_right_genomic_exon_border(sa, i));
if (i == numofexons - 1)
gt_file_xprintf(outfp, ")\n\n");
else
gt_file_xfputc(',', outfp);
}
}
static void outputPGSlines(GtArray *alignments, GtFile *outfp)
{
GtUword i, j;
GthSA *sa;
for (i = 0; i < gt_array_size(alignments); i++) {
sa = *(GthSA**) gt_array_get(alignments, i);
gt_file_xprintf(outfp, " PGS (");
for (j = 0; j < gth_sa_num_of_exons(sa); j++) {
if (j > 0)
gt_file_xfputc(',', outfp);
gt_file_xprintf(outfp, GT_WU " " GT_WU ,
gth_sa_left_genomic_exon_border(sa, j),
gth_sa_right_genomic_exon_border(sa, j));
}
gt_file_xprintf(outfp, ")\t%s%c\n", gth_sa_ref_id(sa),
gth_sa_ref_strand_char(sa));
}
gt_file_xfputc('\n', outfp);
}
/*
The following function prints the "classic" GeneSeqer2 PGS line
*/
static void xml_showpgsline(GthSA *sa, unsigned int indentlevel,
GtFile *outfp)
{
unsigned long i, numofexons;
gt_assert(sa);
numofexons = gth_sa_num_of_exons(sa);
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<PGS_line>\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<gDNA gen_id=\"%s\" gen_strand=\"%c\"/>\n",
gth_sa_gen_id(sa), gth_sa_gen_strand_char(sa));
gth_indent(outfp, indentlevel);
if (gth_sa_alphatype(sa) == DNA_ALPHA) {
gt_file_xprintf(outfp, "<rDNA rDNA_id=\"%s\" rDNA_strand=\"%c\"/>\n",
gth_sa_ref_id(sa), gth_sa_ref_strand_char(sa));
}
else {
gt_file_xprintf(outfp, "<rProt rProt_id=\"%s\"/>\n",
gth_sa_ref_id(sa));
}
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<gDNA_exon_coordinates>\n");
indentlevel++;
for (i = 0; i < numofexons; i++) {
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<exon e_start=\"%lu\" e_stop=\"%lu\"/>\n",
gth_sa_left_genomic_exon_border(sa, i),
gth_sa_right_genomic_exon_border(sa, i));
}
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</gDNA_exon_coordinates>\n");
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</PGS_line>\n");
}
