\n", item);
+struct togaDataBB *info = togaDataBBLoad(&fields[11], bbi->fieldCount); // Bogdan: why 11? 0-11 are bed-like fields likely
printf("Reference transcript: %s ", info->ref_link);
printf("Genomic locus in reference: %s \n", info->ref_region);
printf("Genomic locus in query: %s \n", info->query_region);
printf("Projection classification: %s \n", info->status);
printf("Probability that query locus is orthologous: %s \n", info->chain_score);
// list of chain features (for orthology classification)
printf("Show features used for ortholog probability\n");
printf("
"global CDS fraction" as C / A. Chains with a high value have alignments that largely overlap coding exons,");
printf("which is a hallmark of paralogous or processed pseudogene chains. In contrast, chains with a low value also align many ");
printf("intronic and intergenic regions, which is a hallmark of orthologous chains.
\n");
printf("
"local CDS fraction" as c / a. Orthologous chains tend to have a lower value, as intronic ");
printf("regions partially align. This feature is not computed for single-exon genes.
\n");
printf("
"local intron fraction" as i / I. Orthologous chains tend to have a higher value.");
printf("This feature is not computed for single-exon genes.
\n");
printf("
"flank fraction" as f / 20,000. Orthologous chains tend to have higher values,");
printf("as flanking intergenic regions partially align. This feature is important to detect orthologous loci of single-exon genes.
\n");
printf("
"synteny" as log10 of the number of genes, whose coding exons overlap by at least one base aligning");
printf("blocks of this chain. Orthologous chains tend to cover several genes located in a conserved order, resulting in higher synteny values.
\n");
printf("
"local CDS coverage" as c / CDS, which is only used for single-exon genes.
Visualization of inactivating mutations on exon-intron structure
\n");
-printf("%s \n", info->svg_line);
+printf("%s\n", info->svg_line);
printf(" Exons shown in grey are missing (often overlap assembly gaps).\nExons shown in");
printf(" red or blue are deleted or do not align at all.\nRed indicates that the exon deletion ");
printf("shifts the reading frame, while blue indicates that exon deletion(s) are framepreserving. \n");
// GLP features
printf("Show features used for transcript classification\n");
printf("
\n");
printf("
\n");
printf("
Percent intact, ignoring missing sequence: %s
\n", info->perc_intact_ign_M);
printf("
Percent intact, treating missing as intact sequence: %s
\n", info->perc_intact_int_M);
printf("
Proportion of intact codons: %s
\n", info->intact_codon_prop);
printf("
Percent of CDS not covered by this chain (0 unless the chain covers only a part of the gene): %s
\n", info->ouf_prop);
if (sameWord(info->mid_intact, ONE_))
{
printf("
Middle 80 percent of CDS intact: %s
\n", YES_);
} else {
printf("
Middle 80 percent of CDS intact: %s
\n", NO_);
}
if (sameWord(info->mid_pres, ONE_))
{
printf("
\n");
// printf("{protein seq of the query without dashes or other things. Should end with *}\n");
printf("");
HLprintQueryProtSeqForAli(info->prot_alignment);
-printf("\n \n\n
\n");
// TODO: check whether I need this
hPrintf("");
hPrintf("");
hPrintf("");
printTrackHtml(tdb); // and do I need this?
}
void doHillerLabTOGAGene(char *database, struct trackDb *tdb, char *item, char *table_name)
/* Put up TOGA Gene track info. */
{
//int start = cartInt(cart, "o");