34dc2bb14c176fb8f788df267fdb3fd4c8f461b4 braney Fri Feb 17 07:00:46 2023 -0800 fix some encoding issues and an errant printf on the TOGO hgc page. diff --git src/hg/hgc/togaClick.c src/hg/hgc/togaClick.c index 5608e5c..00a4c8c 100644 --- src/hg/hgc/togaClick.c +++ src/hg/hgc/togaClick.c @@ -327,42 +327,42 @@ printf("We define the following variables:\n<ul>\n"); printf("<li>c: number of reference bases in the intersection between chain blocks and coding exons of the gene under consideration.</li>\n"); printf("<li>C: number of reference bases in the intersection between chain blocks and coding exons of all genes. </li>\n"); printf("<li>a: number of reference bases in the intersection between chain blocks and coding exons and introns of the gene under consideration. </li>\n"); printf("<li>A: number of reference bases in the intersection between chain blocks and coding exons and introns of all genes and the intersection\n"); printf("between chain blocks and intergenic regions (excludes UTRs). </li>\n"); printf("<li>f: number of reference bases in chain blocks overlapping the 10 kb flanks of the gene under consideration.\n"); printf("Alignment blocks overlapping exons of another gene that is located in these 10 kb flanks are ignored. </li>\n"); printf("<li>i: number of reference bases in the intersection between chain blocks and introns of the gene under consideration. </li>\n"); printf("<li>CDS (coding sequence): length of the coding region of the gene under consideration. </li>\n"); printf("<li>I: sum of all intron lengths of the gene under consideration. </li>\n"); printf("</ul>\n"); printf("Using these variables, TOGA computes the following features:\n"); printf("<ul>\n"); -printf("<li>“global CDS fraction” as C / A. Chains with a high value have alignments that largely overlap coding exons,"); +printf("<li>"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. </li>\n"); -printf("<li>“local CDS fraction” as c / a. Orthologous chains tend to have a lower value, as intronic "); +printf("<li>"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. </li>\n"); -printf("<li>“local intron fraction” as i / I. Orthologous chains tend to have a higher value."); +printf("<li>"local intron fraction" as i / I. Orthologous chains tend to have a higher value."); printf("This feature is not computed for single-exon genes. </li>\n"); -printf("<li>“flank fraction” as f / 20,000. Orthologous chains tend to have higher values,"); +printf("<li>"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. </li>\n"); -printf("<li>“synteny” as log10 of the number of genes, whose coding exons overlap by at least one base aligning"); +printf("<li>"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. </li>\n"); -printf("<li>“local CDS coverage” as c / CDS, which is only used for single-exon genes. </li>\n"); +printf("<li>"local CDS coverage" as c / CDS, which is only used for single-exon genes. </li>\n"); printf("</ul>\n"); printf("</ul>\n</div>\n<BR>\n"); htmlHorizontalLine(); // show inact mut plot printf("<h4>Visualization of inactivating mutations on exon-intron structure</h4>\n"); printf("%s<BR>\n", info->svg_line); printf("<BR>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.<br>\n"); // GLP features printf("<a data-toggle=\"collapse\" href=\"#collapseGLP\">Show features used for transcript classification</a>\n"); @@ -419,31 +419,30 @@ printf("</div>\n<BR>\n"); // show exons data htmlHorizontalLine(); printf("<h4>Exon alignments</h4><BR>\n"); printf("<a data-toggle=\"collapse\" href=\"#collapseExons\">Show exon sequences and features</a><BR><BR>\n"); printf("<div id=\"collapseExons\" class=\"panel-collapse collapse\">\n"); // printf("%s\n", info->exon_ali_string); printf("%s\n", info->exon_ali_html); htmlHorizontalLine(); printf("</div>\n<BR>\n"); // TODO: check whether I need this -printf("%s", hgTracksPathAndSettings()); hPrintf("<link rel=\"stylesheet\" href=\"https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css\">"); hPrintf("<script src=\"https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js\"></script>"); hPrintf("<script src=\"https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/js/bootstrap.min.js\"></script>"); 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"); char headerTitle[512]; char suffix[512]; @@ -516,42 +515,42 @@ printf("We define the following variables:\n<ul>\n"); printf("<li>c: number of reference bases in the intersection between chain blocks and coding exons of the gene under consideration.</li>\n"); printf("<li>C: number of reference bases in the intersection between chain blocks and coding exons of all genes. </li>\n"); printf("<li>a: number of reference bases in the intersection between chain blocks and coding exons and introns of the gene under consideration. </li>\n"); printf("<li>A: number of reference bases in the intersection between chain blocks and coding exons and introns of all genes and the intersection\n"); printf("between chain blocks and intergenic regions (excludes UTRs). </li>\n"); printf("<li>f: number of reference bases in chain blocks overlapping the 10 kb flanks of the gene under consideration.\n"); printf("Alignment blocks overlapping exons of another gene that is located in these 10 kb flanks are ignored. </li>\n"); printf("<li>i: number of reference bases in the intersection between chain blocks and introns of the gene under consideration. </li>\n"); printf("<li>CDS (coding sequence): length of the coding region of the gene under consideration. </li>\n"); printf("<li>I: sum of all intron lengths of the gene under consideration. </li>\n"); printf("</ul>\n"); printf("Using these variables, TOGA computes the following features:\n"); printf("<ul>\n"); - printf("<li>“global CDS fraction” as C / A. Chains with a high value have alignments that largely overlap coding exons,"); + printf("<li>"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. </li>\n"); - printf("<li>“local CDS fraction” as c / a. Orthologous chains tend to have a lower value, as intronic "); + printf("<li>"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. </li>\n"); - printf("<li>“local intron fraction” as i / I. Orthologous chains tend to have a higher value."); + printf("<li>"local intron fraction" as i / I. Orthologous chains tend to have a higher value."); printf("This feature is not computed for single-exon genes. </li>\n"); - printf("<li>“flank fraction” as f / 20,000. Orthologous chains tend to have higher values,"); + printf("<li>"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. </li>\n"); - printf("<li>“synteny” as log10 of the number of genes, whose coding exons overlap by at least one base aligning"); + printf("<li>"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. </li>\n"); - printf("<li>“local CDS coverage” as c / CDS, which is only used for single-exon genes. </li>\n"); + printf("<li>"local CDS coverage" as c / CDS, which is only used for single-exon genes. </li>\n"); printf("</ul>\n"); printf("</ul>\n</div>\n<BR>\n"); htmlHorizontalLine(); // show inact mut plot printf("<h4>Visualization of inactivating mutations on exon-intron structure</h4>\n"); printf("%s<BR>\n", info->svg_line); printf("<BR>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.<br>\n"); // GLP features printf("<a data-toggle=\"collapse\" href=\"#collapseGLP\">Show features used for transcript classification</a>\n");