static bool cluster_is_consistent(GtArray *pgls)
{
GtUword i, j, maxright = GT_UNDEF_UWORD, gen_file_num = GT_UNDEF_UWORD;
GthPGL *pgl;
bool strandsign = GT_UNDEF_BOOL;
GthSA *sa;
GtRange range;
for (i = 0; i < gt_array_size(pgls); i++) {
pgl = *(GthPGL**) gt_array_get(pgls, i);
for (j = 0; j < gt_array_size(pgl->alignments); j++) {
sa = *(GthSA**) gt_array_get(pgl->alignments, j);
if (j == 0) {
/* save genomic file number of this cluster */
gen_file_num = gth_sa_gen_file_num(sa);
/* save strand sign of this cluster */
strandsign = gth_sa_gen_strand_forward(sa);
/* set maxright to right border of first SA */
range = gth_sa_range_forward(sa);
maxright = range.end;
}
else {
/* check if all genomic file numbers are the same */
if (gth_sa_gen_file_num(sa) != gen_file_num)
return false;
/* check if all strand signs of this cluster are equal */
if (gth_sa_gen_strand_forward(sa) != strandsign)
return false;
/* check for cluster condition */
range = gth_sa_range_forward(sa);
if (range.start > maxright)
return false;
if (range.end > maxright)
maxright = range.end;
}
}
}
return true;
}
static void storeSAinnewPGL(GtArray *pgls, GtUword *currentPGLindex,
GthSA *sa)
{
GthPGL *pgl;
pgl = gth_pgl_new(gth_sa_gen_strand_forward(sa));
pgl->maxrange.start = gth_sa_get_exon(sa, 0)->leftgenomicexonborder;
pgl->maxrange.end = gth_sa_get_exon(sa,gth_sa_num_of_exons(sa)-1)
->rightgenomicexonborder;
gth_pgl_add_sa(pgl, sa);
gt_array_add(pgls, pgl);
/* set the current PGL index */
*currentPGLindex = gt_array_size(pgls) - 1;
}
void gthclusterSAstoPGLs(GtArray *pgls, GthSACollection *sa_collection)
{
GtUword forwardgen_file_num, /* the genomic file number of the
current forward cluster */
forwardmaxright, /* the maximal right position of the
current forward cluster */
forward_currentPGLindex, /* the current forward PGL index */
reversegen_file_num, /* the genomic file number of the
current reverse cluster */
reversemaxright, /* the maximal right position of the
current reverse cluster */
reverse_currentPGLindex; /* the current reverse PGL index */
GthSACollectionIterator *iterator;
GthSA *sa;
gt_assert(sa_collection);
/* init */
forwardgen_file_num = GT_UNDEF_UWORD;
forwardmaxright = GT_UNDEF_UWORD;
forward_currentPGLindex = GT_UNDEF_UWORD;
reversegen_file_num = GT_UNDEF_UWORD;
reversemaxright = GT_UNDEF_UWORD;
reverse_currentPGLindex = GT_UNDEF_UWORD;
/* cluster the SAs */
iterator = gth_sa_collection_iterator_new(sa_collection);
while ((sa = gth_sa_collection_iterator_next(iterator))) {
if (gth_sa_gen_strand_forward(sa)) {
saveSAtoPGLs(&forwardgen_file_num, &forwardmaxright,
&forward_currentPGLindex, pgls, sa);
}
else {
saveSAtoPGLs(&reversegen_file_num, &reversemaxright,
&reverse_currentPGLindex, pgls, sa);
}
}
gth_sa_collection_iterator_delete(iterator);
/* cluster is consistent */
gt_assert(cluster_is_consistent(pgls));
}
static void xml_inter_show_spliced_alignment(GthSA *sa, GthInput *input,
unsigned int indentlevel,
GtFile *outfp)
{
bool dnaalpha = true;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp,
"<spliced_alignment xmlns=\"http://www.GenomeThreader.org/"
"SplicedAlignment/spliced_alignment/\">\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<referencealphatype>");
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
gt_file_xprintf(outfp, "DNA_ALPHA");
break;
case PROTEIN_ALPHA:
gt_file_xprintf(outfp, "PROTEIN_ALPHA");
dnaalpha = false;
break;
default: gt_assert(0);
}
gt_file_xprintf(outfp, "</referencealphatype>\n");
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<editoperations>\n");
indentlevel++;
gth_backtrace_path_show_complete(gth_sa_backtrace_path(sa), true, indentlevel,
outfp);
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</editoperations>\n");
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<indelcount>"GT_WU"</indelcount>\n",
gth_sa_indelcount(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genomiclengthDP>"GT_WU"</genomiclengthDP>\n",
gth_sa_gen_dp_length(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genomiclengthtotal>"GT_WU"</genomiclengthtotal>\n",
gth_sa_gen_total_length(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genomicoffset>"GT_WU"</genomicoffset>\n",
gth_sa_gen_offset(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<referencelength>"GT_WU"</referencelength>\n",
gth_sa_ref_total_length(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<dpstartpos>"GT_WU"</dpstartpos>\n",
gth_sa_gen_dp_start(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<dpendpos>"GT_WU"</dpendpos>\n",
gth_sa_gen_dp_end(sa));
showgenomicfilename(sa, input, indentlevel, outfp);
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genomicseqnum>"GT_WU"</genomicseqnum>\n",
gth_sa_gen_seq_num(sa));
showreferencefilename(sa, input, indentlevel, outfp);
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<referenceseqnum>"GT_WU"</referenceseqnum>\n",
gth_sa_ref_seq_num(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genomicid>%s</genomicid>\n", gth_sa_gen_id(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<referenceid>%s</referenceid>\n",
gth_sa_ref_id(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp,
"<genomicstrandisforward>%s</genomicstrandisforward>\n",
GTH_SHOWBOOL(gth_sa_gen_strand_forward(sa)));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp,
"<referencestrandisforward>%s</referencestrandisforward>\n",
GTH_SHOWBOOL(gth_sa_ref_strand_forward(sa)));
showalignmentcutoffs(sa, indentlevel, outfp);
showexons(sa, indentlevel, outfp);
showintrons(sa, dnaalpha, indentlevel, outfp);
showpolyAtailpos(sa, indentlevel, outfp);
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<alignmentscore>%.*f</alignmentscore>\n",
PRECISION, gth_sa_score(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<coverage>%.*f</coverage>\n", PRECISION,
gth_sa_coverage(sa));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<coverageofgenomicsegmentishighest>%s"
"</coverageofgenomicsegmentishighest>\n",
GTH_SHOWBOOL(gth_sa_genomic_cov_is_highest(sa)));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<cumulativelengthofscoredexons>"GT_WU""
"</cumulativelengthofscoredexons>\n",
gth_sa_cumlen_scored_exons(sa));
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</spliced_alignment>\n");
}
static void xml_final_show_spliced_alignment(GthSA *sa, GthInput *input,
unsigned long minintronlength,
unsigned long translationtable,
unsigned int indentlevel,
GtFile *outfp)
{
unsigned char *first_line, *second_line, *third_line;
GT_UNUSED bool reverse_subject_pos = false;
unsigned long cols;
gt_assert(sa && input);
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp,
"<spliced_alignment xmlns=\"http://www.genomethreader.org/"
"GTH_output/alignment_module/spliced_alignment/\">\n");
indentlevel++;
/* If the reverse complement of the genomic DNA is considered, this
opition is needed for correct output of the genomic sequence positions
by the function showalignmentgeneric() */
if (!gth_sa_gen_strand_forward(sa))
reverse_subject_pos = true;
xml_showgthreferenceinformation(sa, input, indentlevel, outfp);
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<seq>");
gth_sa_echo_reference_sequence(sa, input, false, outfp);
gt_file_xprintf(outfp, "</seq>\n");
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</reference>\n");
xml_showgthgenomicinformation(sa, input, indentlevel, outfp);
xml_showalignmentheader(sa, minintronlength, indentlevel, outfp);
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<alignment>\n");
/* compute the alignment lines */
cols = gth_sa_get_alignment_lines(sa, &first_line, &second_line, &third_line,
translationtable, input);
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<genome_strand>");
showconcreteline(first_line, cols, outfp);
gt_file_xprintf(outfp, "</genome_strand>\n");
gth_indent(outfp, indentlevel);
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
gt_file_xprintf(outfp, "<mrna_strand>");
showconcreteline(second_line, cols, outfp);
gt_file_xprintf(outfp, "</mrna_strand>\n");
break;
case PROTEIN_ALPHA:
gt_file_xprintf(outfp, "<genomeProt>");
showconcreteline(second_line, cols, outfp);
gt_file_xprintf(outfp, "</genomeProt>\n");
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<queryProt>");
showconcreteline(third_line, cols, outfp);
gt_file_xprintf(outfp, "</queryProt>\n");
break;
default: gt_assert(0);
}
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</alignment>\n");
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</predicted_gene_structure>\n");
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</spliced_alignment>\n");
/* free */
gt_free(first_line);
gt_free(second_line);
gt_free(third_line);
}
GtUword gth_sa_get_alignment_lines(const GthSA *sa,
unsigned char **first_line,
unsigned char **second_line,
unsigned char **third_line,
GtUword translationtable,
GthInput *input)
{
GtUword genomicstartcutoff, genomicendcutoff, genomictotalcutoff,
referencestartcutoff, referenceendcutoff, referencetotalcutoff;
GT_UNUSED bool reverse_subject_pos = false;
gt_assert(sa && first_line && second_line && third_line && input);
/* only for cosmetic reasons */
genomicstartcutoff = gth_sa_genomiccutoff_start(sa);
genomicendcutoff = gth_sa_genomiccutoff_end(sa);
genomictotalcutoff = genomicstartcutoff + genomicendcutoff;
referencestartcutoff = gth_sa_referencecutoff_start(sa);
referenceendcutoff = gth_sa_referencecutoff_end(sa);
referencetotalcutoff = referencestartcutoff + referenceendcutoff;
/* sequences */
unsigned char *gen_seq_orig, *ref_seq_orig;
GtUword cols = 0;
GthSeqCon *ref_seq_con;
/* make sure that the correct files are loaded */
gth_input_load_reference_file(input, gth_sa_ref_file_num(sa), false);
ref_seq_con = gth_input_current_ref_seq_con(input);
/* If the reverse complement of the genomic DNA is considered, this
opition is needed for correct output of the genomic sequence positions
by the function showalignmentgeneric() */
if (!gth_sa_gen_strand_forward(sa))
reverse_subject_pos = true;
/* get genomic sequence */
gen_seq_orig = (unsigned char*)
gth_input_original_genomic_sequence(input, gth_sa_gen_file_num(sa),
gth_sa_gen_strand_forward(sa))
+ gth_sa_gen_dp_start(sa);
/* get reference sequence */
if (gth_sa_ref_strand_forward(sa)) {
ref_seq_orig =
gth_seq_con_get_orig_seq(ref_seq_con, gth_sa_ref_seq_num(sa));
}
else {
ref_seq_orig =
gth_seq_con_get_orig_seq_rc(ref_seq_con, gth_sa_ref_seq_num(sa));
}
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
/* compute the two alignment lines */
cols = gthfillthetwoalignmentlines(first_line,
second_line,
gen_seq_orig +
genomicstartcutoff,
gth_sa_gen_dp_length(sa) -
genomictotalcutoff,
ref_seq_orig +
referencestartcutoff,
gth_sa_ref_total_length(sa) -
referencetotalcutoff,
gth_sa_get_editoperations(sa),
gth_sa_get_editoperations_length(sa),
0, /* linewidth not important here */
0, /* no short introns here */
NULL,/* therefore no shortintroninfo */
gth_sa_indelcount(sa));
*third_line = NULL;
break;
case PROTEIN_ALPHA:
/* compute the three alignment lines */
cols = gthfillthethreealignmentlines(first_line,
second_line,
third_line,
gth_sa_get_editoperations(sa),
gth_sa_get_editoperations_length(sa),
gth_sa_indelcount(sa),
gen_seq_orig +
genomicstartcutoff,
gth_sa_gen_dp_length(sa) -
genomictotalcutoff,
ref_seq_orig +
referencestartcutoff,
gth_sa_ref_total_length(sa) -
referencetotalcutoff,
translationtable);
break;
default: gt_assert(0);
}
return cols;
}
void gth_sa_echo_alignment(const GthSA *sa, GtUword showintronmaxlen,
GtUword translationtable,
bool wildcardimplosion, GthInput *input,
GtFile *outfp)
{
GtUword genomicstartcutoff, genomicendcutoff, genomictotalcutoff,
referencestartcutoff, referenceendcutoff, referencetotalcutoff;
bool reverse_subject_pos = false;
const unsigned char *gen_seq_orig, *ref_seq_orig;
GthSeqCon *ref_seq_con;
GtAlphabet *ref_alphabet;
gt_assert(sa && input);
/* only for cosmetic reasons */
genomicstartcutoff = gth_sa_genomiccutoff_start(sa);
genomicendcutoff = gth_sa_genomiccutoff_end(sa);
genomictotalcutoff = genomicstartcutoff + genomicendcutoff;
referencestartcutoff = gth_sa_referencecutoff_start(sa);
referenceendcutoff = gth_sa_referencecutoff_end(sa);
referencetotalcutoff = referencestartcutoff + referenceendcutoff;
/* make sure that the correct files are loaded */
gth_input_load_reference_file(input, gth_sa_ref_file_num(sa), false);
ref_seq_con = gth_input_current_ref_seq_con(input);
ref_alphabet = gth_input_current_ref_alphabet(input);
/* If the reverse complement of the genomic DNA is considered, this
opition is needed for correct output of the genomic sequence positions
by the function showalignmentgeneric() */
if (!gth_sa_gen_strand_forward(sa))
reverse_subject_pos = true;
/* get genomic sequence */
gen_seq_orig =
gth_input_original_genomic_sequence(input, sa->gen_file_num,
sa->gen_strand_forward)
+ gth_sa_gen_dp_start(sa);
/* get reference sequence */
if (gth_sa_ref_strand_forward(sa)) {
ref_seq_orig =
gth_seq_con_get_orig_seq(ref_seq_con, gth_sa_ref_seq_num(sa));
}
else {
ref_seq_orig =
gth_seq_con_get_orig_seq_rc(ref_seq_con, gth_sa_ref_seq_num(sa));
}
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
gthshowalignmentdna(outfp,ALIGNMENTLINEWIDTH,
gth_sa_get_editoperations(sa),
gth_sa_get_editoperations_length(sa),
gth_sa_indelcount(sa),
gen_seq_orig + genomicstartcutoff,
gth_sa_gen_dp_length(sa) - genomictotalcutoff,
ref_seq_orig + referencestartcutoff,
gth_sa_ref_total_length(sa) -
referencetotalcutoff,
gth_sa_gen_dp_start(sa) + genomicstartcutoff -
gth_sa_gen_offset(sa), referencestartcutoff,
gth_sa_gen_total_length(sa), showintronmaxlen,
ref_alphabet, reverse_subject_pos,
wildcardimplosion);
break;
case PROTEIN_ALPHA:
gthshowalignmentprotein(outfp, ALIGNMENTLINEWIDTH,
gth_sa_get_editoperations(sa),
gth_sa_get_editoperations_length(sa),
gth_sa_indelcount(sa),
gen_seq_orig + genomicstartcutoff,
gth_sa_gen_dp_length(sa) - genomictotalcutoff,
ref_seq_orig + referencestartcutoff,
gth_sa_ref_total_length(sa) -
referencetotalcutoff,
gth_sa_gen_dp_start(sa) + genomicstartcutoff -
gth_sa_gen_offset(sa), referencestartcutoff,
gth_sa_gen_total_length(sa), showintronmaxlen,
ref_alphabet, translationtable,
gth_input_score_matrix(input),
gth_input_score_matrix_alpha(input),
reverse_subject_pos, wildcardimplosion);
break;
default: gt_assert(0);
}
}
