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);
}
}
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 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]);
}
