static void prAligns(struct sqlConnection *conn, struct cloneInfo *ci)
/* print table of alignments */
{
struct psl* pslList = getAlignments(conn, ci->pslTbl, ci->acc);
assert(pslList != NULL);
slSort(&pslList, pslCmpMatch);
// header, print note about order only if we have multiple alignments and didn't
// come from another details page
webNewSection("Alignments");
if ((pslList->next != NULL) && (winStart < winEnd))
printf("<span style='font-size:smaller;'><em>The alignment you clicked on is shown first.</em></span>\n");
webPrintLinkTableStart();
webPrintLabelCell("genomic (browser)");
webPrintLabelCell("span");
webPrintLabelCell(" ");
webPrintLabelCell("mRNA (alignment details)");
webPrintLabelCell("identity");
webPrintLabelCell("aligned");
// print with clicked alignment first
struct psl* psl;
int pass;
for (pass = 1; pass <= 2; pass++)
{
for (psl = pslList; psl != NULL; psl = psl->next)
if ((pass == 1) == (psl->tStart == ci->start))
{
webPrintLinkTableNewRow();
prAlign(conn, ci->pslTbl, psl);
}
}
webPrintLinkTableEnd();
}
void printIndex(struct section *sectionList)
/* Print index to section. */
{
int maxPerRow = 6, itemPos = 0;
int rowIx = 0;
struct section *section;
hPrintf("<BR>\n");
hPrintf("<BR>\n");
webPrintLinkTableStart();
webPrintLabelCell("Page Index");
itemPos += 1;
for (section=sectionList; section != NULL; section = section->next)
{
if (++itemPos > maxPerRow)
{
hPrintf("</TR><TR>");
itemPos = 1;
++rowIx;
}
webPrintLinkCellStart();
hPrintf("<A HREF=\"#%s\" class=\"toc\">%s</A>",
section->name, section->shortLabel);
webPrintLinkCellEnd();
}
webFinishPartialLinkTable(rowIx, itemPos, maxPerRow);
webPrintLinkTableEnd();
}
void webFilteredFieldedTable(struct cart *cart, struct fieldedTable *table,
char *returnUrl, char *varPrefix,
int maxLenField, struct hash *tagOutputWrappers, void *wrapperContext,
boolean withFilters, char *itemPlural,
int pageSize, struct fieldedTableSegment *largerContext, struct hash *suggestHash,
void (*addFunc)(void) )
/* Show a fielded table that can be sorted by clicking on column labels and optionally
* that includes a row of filter controls above the labels .
* The maxLenField is maximum character length of field before truncation with ...
* Pass in 0 for no max */
{
if (strchr(returnUrl, '?') == NULL)
errAbort("Expecting returnUrl to include ? in showFieldedTable\nIt's %s", returnUrl);
if (withFilters)
showTableFilterInstructionsEtc(table, itemPlural, largerContext, addFunc);
/* Set up our table within table look. */
webPrintLinkTableStart();
/* Draw optional filters cells ahead of column labels*/
if (withFilters)
showTableFilterControlRow(table, cart, varPrefix, maxLenField, suggestHash);
showTableSortingLabelRow(table, cart, varPrefix, returnUrl);
showTableDataRows(table, pageSize, maxLenField, tagOutputWrappers, wrapperContext);
/* Get rid of table within table look */
webPrintLinkTableEnd();
if (largerContext != NULL)
showTablePaging(table, cart, varPrefix, largerContext, pageSize);
}
static void prOrfeomeCloneLinks(struct sqlConnection *conn, char *acc, struct cloneInfo *ci)
/* print table of clone links */
{
webPrintLinkTableStart();
webPrintLabelCell("Links");
webPrintLinkTableNewRow();
if (ci->gi > 0)
prOrderLink("ORFeome", ci);
#if 0
// link to ORFeome database
// FIXME: this doesn't appear to work, need to ask Christa
// http://www.orfeomecollaboration.org/bin/cloneStatus.pl
#endif
if (ci->imageId > 0)
prImageLink(ci);
prGenbankLink(ci);
if (ci->refSeqAccv != NULL)
prRefSeqLinks(ci);
if (sqlTableExists(conn, "ccdsGene"))
prCcdsLinks(conn, ci);
if (sqlTableExists(conn, "knownGene"))
prUcscGenesLinks(conn, ci);
webPrintLinkTableEnd();
}
void doParDetails(struct trackDb *tdb, char *name)
/* show details of a PAR item. */
{
// load entire PAR table (t's tiny) and partition
struct bed *pars = loadParTable(tdb);
if (slCount(pars) & 1)
errAbort("par items not paired in %s", tdb->table);
struct bed *clickedPar = getClickedPar(name, &pars);
struct bed *homPar = getHomologousPar(clickedPar, &pars);
slSort(&pars, parCmp);
cartWebStart(cart, database, "Pseudoautosomal regions");
webPrintLinkTableStart();
// header
webPrintLabelCell("");
webPrintLabelCell("Selected PAR");
webPrintLabelCell("Homologous PAR");
// selected
webPrintLinkTableNewRow();
printHomPairRow(clickedPar, homPar);
if (pars != NULL)
printOtherPars(clickedPar, pars);
webPrintLinkTableEnd();
printTrackHtml(tdb);
webEnd();
bedFreeList(&pars);
bedFree(&clickedPar);
bedFree(&homPar);
}
void doPeakClusters(struct trackDb *tdb, char *item)
/* Display detailed info about a cluster of DNase peaks from other tracks. */
{
int start = cartInt(cart, "o");
char *table = tdb->table;
int rowOffset = hOffsetPastBin(database, seqName, table);
char query[256];
struct sqlResult *sr;
char **row;
struct bed *cluster = NULL;
struct sqlConnection *conn = hAllocConn(database);
cartWebStart(cart, database, "%s item details", tdb->shortLabel);
sqlSafef(query, sizeof(query),
"select * from %s where name = '%s' and chrom = '%s' and chromStart = %d",
table, item, seqName, start);
sr = sqlGetResult(conn, query);
row = sqlNextRow(sr);
if (row != NULL)
cluster = bedLoadN(row+rowOffset, 5);
sqlFreeResult(&sr);
if (cluster != NULL)
{
/* Get list of subgroups to display */
char *inputTableFieldDisplay = trackDbSetting(tdb, "inputTableFieldDisplay");
if (inputTableFieldDisplay != NULL)
{
struct slName *fieldList = stringToSlNames(inputTableFieldDisplay);
char *inputTrackTable = trackDbRequiredSetting(tdb, "inputTrackTable");
/* Print out some information about the cluster overall. */
printf("<B>Items in Cluster:</B> %s of %d<BR>\n", cluster->name,
sqlRowCount(conn, sqlCheckIdentifier(inputTrackTable)));
printf("<B>Cluster Score (out of 1000):</B> %d<BR>\n", cluster->score);
printPos(cluster->chrom, cluster->chromStart, cluster->chromEnd, NULL, TRUE, NULL);
/* In a new section put up list of hits. */
webNewSection("List of Items in Cluster");
webPrintLinkTableStart();
printClusterTableHeader(fieldList, FALSE, FALSE, TRUE);
printPeakClusterInfo(tdb, cart, conn, inputTrackTable, fieldList, cluster);
}
else
errAbort("Missing required trackDb setting %s for track %s",
"inputTableFieldDisplay", tdb->track);
webPrintLinkTableEnd();
}
printf("<A HREF=\"%s&g=htcListItemsAssayed&table=%s\" TARGET_blank>", hgcPathAndSettings(),
tdb->track);
printf("List all items assayed");
printf("</A><BR>\n");
webNewSection("Track Description");
printTrackHtml(tdb);
hFreeConn(&conn);
}
void sequenceTablePrint(struct section *section, struct sqlConnection *conn,
char *geneId)
/* Print the sequence table. */
{
char *table = genomeSetting("knownGene");
struct dyString *query = newDyString(0);
char **row;
struct sqlResult *sr;
char *chrom;
int start,end;
/* Print the current position. */
webPrintLinkTableStart();
printGenomicSeqLink(conn, geneId, curGeneChrom, curGeneStart, curGeneEnd);
printMrnaSeqLink(conn,geneId);
printProteinSeqLink(conn,geneId);
webPrintLinkTableEnd();
/* Print out any additional positions. */
dyStringPrintf(query, "select chrom,txStart,txEnd from %s", table);
dyStringPrintf(query, " where name = '%s'", curGeneId);
dyStringPrintf(query, " and (chrom != '%s'", curGeneChrom);
dyStringPrintf(query, " or txStart != %d", curGeneStart);
dyStringPrintf(query, " or txEnd != %d)", curGeneEnd);
sr = sqlGetResult(conn, query->string);
while ((row = sqlNextRow(sr)) != NULL)
{
struct sqlConnection *conn2 = hAllocConn(database);
chrom = row[0];
start = atoi(row[1]);
end = atoi(row[2]);
webPrintLinkTableStart();
printGenomicSeqLink(conn2, geneId, chrom, start, end);
webPrintLinkTableEnd();
hFreeConn(&conn2);
}
sqlFreeResult(&sr);
freeDyString(&query);
}
static void prRefSeqSims(struct cloneInfo *ci)
/* print similarity information for RefSeqs */
{
webNewSection("RefSeq CDS isoform similarity of %s clone %s",
cdnaInfoDbName(ci), ci->acc);
webPrintLinkTableStart();
webPrintLabelCell("RefSeq");
webPrintLabelCell("Position");
webPrintLabelCell("Similarity");
struct geneSim *gs;
for (gs = ci->refSeqs->genes; gs != NULL; gs = gs->next)
prRefSeqSim(ci, gs);
webPrintLinkTableEnd();
printf("This table compares the similarity of the BLAT genomic alignments of "
"the CDS of this %s clone with alignment of RefSeq mRNA CDSs. This is a metric "
"of the similarity of the exon structure of the mRNAs, rather than a measure of their "
"nucleotide sequence similarity.", cdnaInfoDbName(ci));
}
static void prCloneInfo(struct cloneInfo *ci)
/* print table of clone information */
{
webPrintLinkTableStart();
prCellLabelVal("Gene", ci->geneName);
webPrintLinkTableNewRow();
prCellLabelVal("Product", ci->productName);
webPrintLinkTableNewRow();
prCellLabelVal("Tissue", ci->tissue);
webPrintLinkTableNewRow();
prCellLabelVal("Library", ci->library);
webPrintLinkTableNewRow();
prCellLabelVal("Development", ci->development);
webPrintLinkTableNewRow();
prCellLabelVal("CDS", ci->cds);
webPrintLinkTableNewRow();
prCellLabelVal("Modification date", ci->moddate);
webPrintLinkTableEnd();
}
static void linksPrint(struct section *section, struct sqlConnection *conn,
char *geneId)
/* Print the links section. */
{
int maxPerRow = 6, itemPos = 0;
int rowIx = 0;
struct link *link, *linkList = section->items;
webPrintLinkTableStart();
printGenomicSeqLink(conn, geneId, curGeneChrom, curGeneStart, curGeneEnd);
printMrnaSeqLink(conn,geneId);
printProteinSeqLink(conn,geneId);
hPrintf("</TR>\n<TR>");
++rowIx;
for (link = linkList; link != NULL; link = link->next)
{
char *url = linkGetUrl(link, conn, geneId);
if (url != NULL)
{
boolean fakeOut = link->useHgsid &&
differentWord(link->name,"wikiTrack");
char *target = (fakeOut ? "" : " TARGET=_blank");
if (++itemPos > maxPerRow)
{
hPrintf("</TR>\n<TR>");
itemPos = 1;
++rowIx;
}
if (fakeOut)
webPrintLinkCellStart();
else
webPrintLinkOutCellStart();
hPrintf("<A HREF=\"%s\"%s class=\"toc\">", url, target);
hPrintf("%s", link->shortLabel);
hPrintf("</A>");
webPrintLinkCellEnd();
freez(&url);
}
}
webFinishPartialLinkOutTable(rowIx, itemPos, maxPerRow);
webPrintLinkTableEnd();
}
static void prMiscDiffs(struct sqlConnection *conn, char *acc)
/* print any gbMiscDiff rows for the accession */
{
struct gbMiscDiff *gmds = NULL, *gmd;
if (sqlTableExists(conn, "gbMiscDiff"))
gmds = sqlQueryObjs(conn, (sqlLoadFunc)gbMiscDiffLoad, sqlQueryMulti,
"select * from gbMiscDiff where acc=\"%s\"", acc);
webNewSection("NCBI Clone Validation");
if (gmds != NULL)
{
unsigned miscDiffFlds = getMiscDiffFields(gmds);
webPrintLinkTableStart();
prMiscDiffHdr(miscDiffFlds);
for (gmd = gmds; gmd != NULL; gmd = gmd->next)
prMiscDiff(gmd, miscDiffFlds);
webPrintLinkTableEnd();
}
else
printf("<EM>No clone discrepancies annotated</EM><BR><BR>\n");
}
static void prSeqLinks(struct sqlConnection *conn, struct cloneInfo *ci)
/* print table of sequence links */
{
webNewSection("Sequences");
webPrintLinkTableStart();
webPrintLinkCellStart();
hgcAnchorSomewhere("htcDisplayMrna", ci->acc, ci->pslTbl, seqName);
printf("mRNA</a>");
webPrintLinkCellEnd();
webPrintLinkCellStart();
hgcAnchorSomewhere("htcTranslatedMRna", ci->acc, ci->pslTbl, seqName);
printf("Protein</A><br>");
webPrintLinkCellEnd();
webPrintLinkCellStart();
hgcAnchorSomewhere("htcGeneInGenome", ci->acc, ci->gpTbl, seqName);
printf("Genomic</A>");
webPrintLinkCellEnd();
webPrintLinkTableNewRow();
webPrintLinkCellStart();
hgcAnchorSomewhere("htcDisplayMrna", ci->acc, ci->gpTbl, seqName);
printf("Reference genome mRNA</A>");
webPrintLinkCellEnd();
#if BROKEN
// FIXME: doesn't work when genePred table is not the track; not that important
webPrintLinkCellStart();
hgcAnchorSomewhereTbl("htcTranslatedPredMRna", ci->acc, ci->pslTbl, seqName, ci->gpTbl);
printf("Reference genome protein</A>");
webPrintLinkCellEnd();
webFinishPartialLinkTable(1, 2, 3);
#else
webFinishPartialLinkTable(1, 1, 3);
#endif
webPrintLinkTableEnd();
}
void correlatePage(struct sqlConnection *conn)
/* Put up correlation page. */
{
cartWebStart(cart, database, "Correlations of all pairs of graphs");
hPrintf("<FORM ACTION=\"../cgi-bin/hgGenome\" METHOD=GET>\n");
cartSaveSession(cart);
struct slRef *ggRefList = ggAllVisible(conn);
struct slRef *aRef, *bRef;
hPrintf("<TABLE><TR><TD>");
webPrintLinkTableStart();
webPrintLabelCell("Graph A");
webPrintLabelCell("Graph B");
webPrintLabelCell("R");
webPrintLabelCell("R-Squared");
for (aRef = ggRefList; aRef != NULL; aRef = aRef->next)
{
for (bRef = aRef->next; bRef != NULL; bRef = bRef->next)
{
hPrintf("</TR><TR>");
correlateGraphs(aRef->val, bRef->val);
}
}
webPrintLinkTableEnd();
hPrintf("</TD><TD>");
hPrintf("<CENTER>");
cgiMakeButton("submit", "return to graphs");
hPrintf("</CENTER>");
hPrintf("</TD></TR></TABLE>");
hPrintf("<P>R, also known as Pearson's correlation coefficient, is a measure ");
hPrintf("of the extent that two graphs move together. The value of R ranges ");
hPrintf("between -1 and 1. A positive R indicates that the graphs tend to ");
hPrintf("move in the same direction, while a negative R indicates that they ");
hPrintf("tend to move in opposite directions.</P>\n");
hPrintf("<P>R-Squared (which is indeed just R*R) measures how much of the ");
hPrintf("variation in one graph can be explained by a linear dependence on ");
hPrintf("the other graph. R-Squared ranges between 0 when the two graphs are ");
hPrintf("independent to 1 when the graphs are completely dependent.</P>");
hPrintf("</FORM>");
cartWebEnd();
}
void doPeakClusterListItemsAssayed()
/* Put up a page that shows all experiments associated with a cluster track. */
{
struct trackDb *clusterTdb = tdbForTableArg();
cartWebStart(cart, database, "List of items assayed in %s", clusterTdb->shortLabel);
struct sqlConnection *conn = hAllocConn(database);
char *inputTableFieldDisplay = trackDbSetting(clusterTdb, "inputTableFieldDisplay");
webPrintLinkTableStart();
if (inputTableFieldDisplay)
{
struct slName *fieldList = stringToSlNames(inputTableFieldDisplay);
printClusterTableHeader(fieldList, FALSE, FALSE, FALSE);
char *inputTrackTable = trackDbRequiredSetting(clusterTdb, "inputTrackTable");
printPeakClusterInfo(clusterTdb, cart, conn, inputTrackTable, fieldList, NULL);
}
else
errAbort("Missing required trackDb setting %s for track %s", "inputTableFieldDisplay",
clusterTdb->track);
webPrintLinkTableEnd();
hFreeConn(&conn);
}
static void prMgcCloneLinks(struct sqlConnection *conn, struct mgcDb *mgcDb, struct cloneInfo *ci)
/* print table of clone links */
{
webPrintLinkTableStart();
webPrintLabelCell("Links");
if (ci->gi > 0)
prOrderLink(mgcDb->name, ci);
// link to MGC database
webPrintLinkTableNewRow();
webPrintLinkCellStart();
printf("<a href=\"");
printMgcUrl(ci->imageId);
printf("\" TARGET=_blank>%s clone database</a>", mgcDb->name);
webPrintLinkCellEnd();
prImageLink(ci);
prGenbankLink(ci);
if (ci->refSeqAccv != NULL)
prRefSeqLinks(ci);
if (sqlTableExists(conn, "ccdsGene"))
prCcdsLinks(conn, ci);
if (sqlTableExists(conn, "knownGene"))
prUcscGenesLinks(conn, ci);
// Brent lab validation database
if (isInMBLabValidDb(ci->acc))
{
webPrintLinkTableNewRow();
webPrintLinkCellStart();
printf("<a href=\"");
printMBLabValidDbUrl(ci->acc);
printf("\" TARGET=_blank>Brent Lab Clone Validation</a>");
webPrintLinkCellEnd();
}
webPrintLinkTableEnd();
}
void showCdsEvidence(char *geneName, struct trackDb *tdb, char *evTable)
/* Print out stuff from cdsEvidence table. */
{
struct sqlConnection *conn = hAllocConn(database);
double bestScore = 0;
if (sqlTableExists(conn, evTable))
{
webNewSection("CDS Prediction Information");
char query[512];
sqlSafef(query, sizeof(query),
"select count(*) from %s where name='%s'", evTable, geneName);
if (sqlQuickNum(conn, query) > 0)
{
sqlSafef(query, sizeof(query),
"select * from %s where name='%s' order by score desc", evTable, geneName);
struct sqlResult *sr = sqlGetResult(conn, query);
char **row;
webPrintLinkTableStart();
webPrintLabelCell("ORF<BR>size");
webPrintLabelCell("start in<BR>transcript");
webPrintLabelCell("end in<BR>transcript");
webPrintLabelCell("source");
webPrintLabelCell("accession");
webPrintLabelCell("ad-hoc<BR>score");
webPrintLabelCell("start<BR>codon");
webPrintLabelCell("end<BR>codon");
webPrintLabelCell("piece<BR>count");
webPrintLabelCell("piece list");
webPrintLabelCell("frame");
webPrintLinkTableNewRow();
while ((row = sqlNextRow(sr)) != NULL)
{
struct cdsEvidence *ev = cdsEvidenceLoad(row);
webPrintIntCell(ev->end - ev->start);
int i;
webPrintIntCell(ev->start+1);
webPrintIntCell(ev->end);
webPrintLinkCell(ev->source);
webPrintLinkCell(ev->accession);
webPrintLinkCellRightStart();
printf("%3.2f", ev->score);
bestScore = max(ev->score, bestScore);
webPrintLinkCellEnd();
webPrintLinkCell(ev->startComplete ? "yes" : "no");
webPrintLinkCell(ev->endComplete ? "yes" : "no");
webPrintIntCell(ev->cdsCount);
webPrintLinkCellRightStart();
for (i=0; i<ev->cdsCount; ++i)
{
int start = ev->cdsStarts[i];
int end = start + ev->cdsSizes[i];
printf("%d-%d ", start+1, end);
}
webPrintLinkCellEnd();
webPrintLinkCellRightStart();
for (i=0; i<ev->cdsCount; ++i)
{
if (i>0) printf(",");
printf("%d", ev->cdsStarts[i]%3 + 1);
}
webPrintLinkCellEnd();
webPrintLinkTableNewRow();
}
sqlFreeResult(&sr);
webPrintLinkTableEnd();
printf("This table shows CDS predictions for this transcript from a number of "
"sources including alignments against UniProtKB proteins, alignments against Genbank "
"mRNAs with CDS regions annotated by the sequence submitter, and "
"Victor Solovyev's bestorf program. Each prediction is assigned an ad-hoc score "
"score is based on several factors including the quality of "
"any associated alignments, the quality of the source, and the length of the "
"prediction. For RefSeq transcripts with annotated CDSs the ad-hoc score "
"is over a million unless there are severe problems mapping the mRNA to the "
"genome. In other cases the score generally ranges from 0 to 50,000. "
"The highest scoring prediction in this table is used to define the CDS "
"boundaries for this transcript.<P>If no score is 2000 or more, the transcript "
"is considered non-coding. In cases where the CDS is subject to "
"nonsense-mediated decay the CDS is removed. The CDS is also removed "
"from transcripts when evidence points to it being in an artifact of an "
"incompletely processed transcript. Specifically if the CDS is entirely "
"enclosed in the 3' UTR or an intron of a refSeq or other high quality "
"transcript, the CDS is removed.");
}
else
{
printf("no significant CDS prediction found, likely %s is noncoding",
geneName);
}
}
hFreeConn(&conn);
}
void doFactorSource(struct sqlConnection *conn, struct trackDb *tdb, char *item, int start, int end)
/* Display detailed info about a cluster of TFBS peaks from other tracks. */
{
char extraWhere[256];
safef(extraWhere, sizeof extraWhere, "name='%s'", item);
int rowOffset;
struct sqlResult *sr = hRangeQuery(conn, tdb->table, seqName, start, end, extraWhere, &rowOffset);
char **row = sqlNextRow(sr);
struct factorSource *cluster = NULL;
if (row != NULL)
cluster = factorSourceLoad(row + rowOffset);
sqlFreeResult(&sr);
if (cluster == NULL)
errAbort("Error loading cluster from track %s", tdb->track);
char *sourceTable = trackDbRequiredSetting(tdb, "sourceTable");
char *factorLink = cluster->name;
char *vocab = trackDbSetting(tdb, "controlledVocabulary");
if (vocab != NULL)
{
char *file = cloneFirstWord(vocab);
factorLink = wgEncodeVocabLink(file, "term", factorLink, factorLink, factorLink, "");
}
printf("<B>Factor:</B> %s<BR>\n", factorLink);
printf("<B>Cluster Score (out of 1000):</B> %d<BR>\n", cluster->score);
printPos(cluster->chrom, cluster->chromStart, cluster->chromEnd, NULL, TRUE, item);
/* Get list of tracks we'll look through for input. */
char *inputTrackTable = trackDbRequiredSetting(tdb, "inputTrackTable");
char query[256];
sqlSafef(query, sizeof(query), "select tableName from %s where factor='%s' order by source",
inputTrackTable,
cluster->name);
/* Next do the lists of hits and misses. We have the hits from the non-zero signals in
* cluster->expScores. We need to figure out the sources actually assayed though
* some other way. We'll do this by one of two techniques. */
char *inputTableFieldDisplay = trackDbSetting(tdb, "inputTableFieldDisplay");
if (inputTableFieldDisplay != NULL)
{
struct slName *fieldList = stringToSlNames(inputTableFieldDisplay);
char *vocab = trackDbSetting(tdb, "controlledVocabulary");
/* In a new section put up list of hits. */
webNewSection("Assays for %s in Cluster", cluster->name);
webPrintLinkTableStart();
printClusterTableHeader(fieldList, TRUE, FALSE, TRUE);
printFactorSourceTableHits(cluster, conn, sourceTable,
inputTrackTable, fieldList, FALSE, vocab);
webPrintLinkTableEnd();
webNewSectionHeaderStart();
char sectionTitle[128];
safef(sectionTitle,
sizeof(sectionTitle),"Assays for %s Without Hits in Cluster", cluster->name);
jsBeginCollapsibleSectionOldStyle(cart, tdb->track, "cellNoHits", sectionTitle, FALSE);
webNewSectionHeaderEnd();
webPrintLinkTableStart();
printClusterTableHeader(fieldList, TRUE, FALSE, FALSE);
printFactorSourceTableHits(cluster, conn, sourceTable,
inputTrackTable, fieldList, TRUE, vocab);
webPrintLinkTableEnd();
jsEndCollapsibleSection();
}
else
{
errAbort("Missing required trackDb setting %s for track %s",
"inputTableFieldDisplay", tdb->track);
}
webNewSectionHeaderStart();
jsBeginCollapsibleSectionOldStyle(cart, tdb->track, "cellSources", "Cell Abbreviations", FALSE);
webNewSectionHeaderEnd();
hPrintFactorSourceAbbrevTable(conn, tdb);
jsEndCollapsibleSection();
doClusterMotifDetails(conn, tdb, cluster);
}
static void rnaStructurePrint(struct section *section,
struct sqlConnection *conn, char *geneId)
/* Print out rnaStructure table. */
{
static boolean firstTime = TRUE;
static char *names[2] =
{"5' UTR", "3' UTR"};
static char *tables[2] = {"foldUtr5", "foldUtr3"};
int side;
if (firstTime)
{
rnaTrashDirsInit(tables, ArraySize(tables));
firstTime = FALSE;
}
webPrintLinkTableStart();
webPrintLabelCell("Region");
webPrintLabelCell("Fold Energy");
webPrintLabelCell("Bases");
webPrintLabelCell("Energy/Base");
webPrintWideCenteredLabelCell("Display As", 3);
for (side = 0; side < ArraySize(names); ++side)
{
char *table = tables[side];
struct sqlResult *sr;
char query[256], **row;
safef(query, sizeof(query), "select * from %s where name = '%s'",
table, geneId);
sr = sqlGetResult(conn, query);
if ((row = sqlNextRow(sr)) != NULL)
{
struct rnaFold fold;
int bases;
char psName[128];
/* Load fold and save it as postScript. */
rnaFoldStaticLoad(row, &fold);
safef(psName, sizeof(psName), "../trash/%s/%s_%s.ps", table, table, geneId);
if (!fileExists(psName))
{
FILE *f;
f = popen("../cgi-bin/RNAplot", "w");
if (f != NULL)
{
fprintf(f, ">%s\n", psName); /* This tells where to put file. */
fprintf(f, "%s\n%s\n", fold.seq, fold.fold);
pclose(f);
}
}
/* Print row of table, starting with energy terms . */
hPrintf("</TR><TR>");
bases = strlen(fold.seq);
webPrintLinkCell(names[side]);
webPrintLinkCellStart();
hPrintf("%1.2f", fold.energy);
webPrintLinkCellEnd();
webPrintLinkCellStart();
hPrintf("%d", bases);
webPrintLinkCellEnd();
webPrintLinkCellStart();
hPrintf("%1.3f", fold.energy/bases);
webPrintLinkCellEnd();
/* Print link to png image. */
webPrintLinkCellStart();
hPrintf("<A HREF=\"%s?%s&%s=%s&%s=%s&%s=%s\" class=\"toc\" TARGET=_blank>",
geneCgi, cartSidUrlString(cart),
hggMrnaFoldRegion, table,
hggMrnaFoldPs, psName,
hggDoRnaFoldDisplay, "picture");
hPrintf(" Picture ");
hPrintf("</A>");
webPrintLinkCellEnd();
/* Print link to PostScript. */
webPrintLinkCellStart();
hPrintf("<A HREF=\"%s\" class=\"toc\">", psName);
hPrintf(" PostScript ");
hPrintf("</A>");
webPrintLinkCellEnd();
/* Print link to text. */
webPrintLinkCellStart();
hPrintf("<A HREF=\"%s?%s&%s=%s&%s=%s\" class=\"toc\" TARGET=_blank>",
geneCgi, cartSidUrlString(cart),
hggMrnaFoldRegion, table,
hggDoRnaFoldDisplay, "text");
hPrintf(" Text ");
hPrintf("</A>");
webPrintLinkCellEnd();
}
sqlFreeResult(&sr);
}
webPrintLinkTableEnd();
hPrintf("<BR>The RNAfold program from the ");
hPrintf("<A HREF=\"http://www.tbi.univie.ac.at/~ivo/RNA/\" TARGET=_blank>");
hPrintf("Vienna RNA Package</A> is used to perform the ");
hPrintf("secondary structure predictions and folding calculations. ");
hPrintf("The estimated folding energy is in kcal/mol. The more ");
hPrintf("negative the energy, the more secondary structure the RNA ");
hPrintf("is likely to have.");
}
static void otherOrgsPrint(struct section *section, struct sqlConnection *conn,
char *geneId)
/* Print the otherOrgs section. */
{
struct otherOrg *otherOrg, *otherOrgList = section->items;
hPrintf(
"Orthologies between human, mouse, and rat are computed by taking the "
"best BLASTP hit, and filtering out non-syntenic hits. For "
"more distant species reciprocal-best BLASTP hits are used. "
"Note that the absence of an ortholog in the table below may "
"reflect incomplete annotations in the other species rather than "
"a true absence of the orthologous gene.");
webPrintLinkTableStart();
for (otherOrg = otherOrgList; otherOrg != NULL; otherOrg = otherOrg->next)
webPrintLabelCell(otherOrg->shortLabel);
hPrintf("</TR>\n<TR>");
for (otherOrg = otherOrgList; otherOrg != NULL; otherOrg = otherOrg->next)
{
char *pos = otherOrgPosition(otherOrg, conn, geneId);
otherOrgPrintLink(otherOrg, "Genome Browser", "No ortholog", TRUE,
pos, otherOrg->genomeUrl);
freeMem(pos);
}
hPrintf("</TR>\n<TR>");
for (otherOrg = otherOrgList; otherOrg != NULL; otherOrg = otherOrg->next)
{
char *id = otherOrgId(otherOrg, conn, geneId);
otherOrgPrintLink(otherOrg, "Gene Details", " ", TRUE,
id, otherOrg->geneUrl);
freeMem(id);
}
hPrintf("</TR>\n<TR>");
for (otherOrg = otherOrgList; otherOrg != NULL; otherOrg = otherOrg->next)
{
char *id = otherOrgId(otherOrg, conn, geneId);
otherOrgPrintLink(otherOrg, "Gene Sorter", " ", TRUE,
id, otherOrg->sorterUrl);
freeMem(id);
}
hPrintf("</TR>\n<TR>");
for (otherOrg = otherOrgList; otherOrg != NULL; otherOrg = otherOrg->next)
{
char *id = otherOrgId(otherOrg, conn, geneId);
id = otherOrgExternalId(otherOrg, id);
otherOrgPrintLink(otherOrg, otherOrg->otherName, " ", FALSE,
id, otherOrg->otherUrl);
freeMem(id);
}
hPrintf("</TR>\n<TR>");
for (otherOrg = otherOrgList; otherOrg != NULL; otherOrg = otherOrg->next)
{
char *id = otherOrgProteinId(otherOrg, conn, geneId);
otherOrgPepLink(otherOrg, hggDoOtherProteinSeq, "Protein Sequence", id, conn);
freeMem(id);
}
hPrintf("</TR>\n<TR>");
for (otherOrg = otherOrgList; otherOrg != NULL; otherOrg = otherOrg->next)
{
char *id = otherOrgProteinId(otherOrg, conn, geneId);
otherOrgPepLink(otherOrg, hggDoOtherProteinAli, "Alignment", id, conn);
freeMem(id);
}
webPrintLinkTableEnd();
}
void showTxInfo(char *geneName, struct trackDb *tdb, char *txInfoTable)
/* Print out stuff from txInfo table. */
{
struct sqlConnection *conn = hAllocConn(database);
if (sqlTableExists(conn, txInfoTable))
{
char query[512];
sqlSafef(query, sizeof(query), "select * from %s where name='%s'", txInfoTable, geneName);
struct sqlResult *sr = sqlGetResult(conn, query);
char **row;
if ((row = sqlNextRow(sr)) != NULL)
{
struct txInfo *info = txInfoLoad(row);
webNewSection("Transcript Information");
webPrintLinkTableStart();
webPrintLinkCell("<B>category:</B>");
webPrintLinkCell(info->category);
webPrintLinkCell("<B>nonsense-mediated-decay:</B>");
webPrintLinkCell(info->nonsenseMediatedDecay ? "yes" : "no");
webPrintLinkCell("<B>RNA accession:</B>");
webPrintLinkCell(info->sourceAcc);
webPrintLinkTableNewRow();
webPrintLinkCell("<B>exon count:</B>");
webPrintIntCell(info->exonCount);
webPrintLinkCell("<B>CDS single in 3' UTR:</B>");
webPrintLinkCell(info->cdsSingleInUtr3 ? "yes" : "no");
webPrintLinkCell("<B>RNA size:</B>");
webPrintIntCell(info->sourceSize);
webPrintLinkTableNewRow();
webPrintLinkCell("<B>ORF size:</B>");
webPrintIntCell(info->orfSize);
webPrintLinkCell("<B>CDS single in intron:</B>");
webPrintLinkCell(info->cdsSingleInIntron ? "yes" : "no");
webPrintLinkCell("<B>Alignment % ID:</B>");
webPrintDoubleCell(info->aliIdRatio*100);
webPrintLinkTableNewRow();
webPrintLinkCell("<B>txCdsPredict score:</B>");
webPrintDoubleCell(info->cdsScore);
webPrintLinkCell("<B>frame shift in genome:</B>");
webPrintLinkCell(info->genomicFrameShift ? "yes" : "no");
webPrintLinkCell("<B>% Coverage:</B>");
webPrintDoubleCell(info->aliCoverage*100);
webPrintLinkTableNewRow();
webPrintLinkCell("<B>has start codon:</B>");
webPrintLinkCell(info->startComplete ? "yes" : "no");
webPrintLinkCell("<B>stop codon in genome:</B>");
webPrintLinkCell(info->genomicStop ? "yes" : "no");
webPrintLinkCell("<B># of Alignments:</B>");
webPrintIntCell(info->genoMapCount);
webPrintLinkTableNewRow();
webPrintLinkCell("<B>has end codon:</B>");
webPrintLinkCell(info->endComplete ? "yes" : "no");
webPrintLinkCell("<B>retained intron:</B>");
webPrintLinkCell(info->retainedIntron ? "yes" : "no");
webPrintLinkCell("<B># AT/AC introns</B>");
webPrintIntCell(info->atacIntrons);
webPrintLinkTableNewRow();
webPrintLinkCell("<B>selenocysteine:</B>");
webPrintLinkCell(info->selenocysteine ? "yes" : "no");
webPrintLinkCell("<B>end bleed into intron:</B>");
webPrintIntCell(info->bleedIntoIntron);
webPrintLinkCell("<B># strange splices:</B>");
webPrintIntCell(info->strangeSplice);
webPrintLinkTableEnd();
txInfoFree(&info);
}
sqlFreeResult(&sr);
}
hFreeConn(&conn);
printf("%s",
"The table above summarizes many aspects of this transcripts. Here is a more \n"
"detailed description of each of the fields than can fit in the label. Also\n"
"see the CDS Prediction Information table below for additional information\n"
"relevant to the predicted protein product if any.\n"
"\n"
"<UL>\n"
"<LI><B>category</B> - This is either <i>coding</i>, <i>noncoding</i>,\n"
"<i>antisense</i> or \n"
"<i>nearCoding</i>. A coding transcript is one where the evidence is relatively\n"
"good that it produces a protein. The nearCoding transcripts overlap coding\n"
"transcripts by at least 20 bases on the same strand, but themselves do not seem to produce \n"
"protein products. In many cases this is because they are splicing varients\n"
"with introns after the stop codon, that therefore undergo nonsense mediated decay. \n"
"Antisense transcripts overlap coding transcripts by at least 20 bases on the oppposite\n"
"strand.\n"
"The other transcripts, which are neither coding, nor overlapping coding,\n"
"are categorized as noncoding.</LI>\n"
"<LI><B>exon count</B> - The number of exons in the gene. Single exon genes are\n"
"generally somewhat less reliable than multi-exon genes, though there are\n"
"many well-known genuine single exon genes such as the Histones and the Sox \n"
"family.</LI>\n"
"<LI><B>ORF size</B> - The size of the open reading frame in the mRNA. Divide by\n"
"three to get the size of the protein.</LI>\n"
"<LI><B>txCdsPredict score</B> - The score from the txCdsPredict program. This\n"
"program weighs a variety of evidence including the presence of a Kozak consensus\n"
"sequence at the start codon, the length of the ORF, the presense of upstream\n"
"ORFs, homology in other species, and nonsense mediated decay. In general\n"
"a score over 1000 is almost certain to be a protein, and scores over 800 have\n"
"about a 90% chance of being a protein.</LI>\n"
"<LI><B>has start codon</B> - Indicates if the initial codon is an ATG.</LI>\n"
"<LI><B>has end codon</B> - Indicates if the last codon is TAA, TAG, or TGA.</LI>\n"
"<LI><B>selenocysteine</B> - Indicates if this is one of the special proteins where\n"
"TGA encodes the animo acid selenocysteine rather than encoding a stop codon.</LI>\n"
"<LI><B>nonsense-mediated-decay</B> - Indicates whether the final intron is more than\n"
"55 bases after the stop codon. If true, then generally the mRNA will be degraded\n"
"before it can produce a detectable amount of protein. Therefore when this condition\n"
"is true we remove the predicted coding region from the transcript.</LI>\n"
"<LI><B>CDS single in 3' UTR</B> - This is a strong indicator that the coding region\n"
"(CDS) is a coincedental open reading frame rather than a true indication \n"
"that the transcript codes for protein. This indicates that the coding sequence \n"
"resides in a single exon, and that this exon is located entirely in the 3' UTR \n"
"of another transcript that codes for a different protein not overlapping the \n"
"ORF in the same frame. We remove the CDS from non-refSeq transcripts that meet\n"
"this condition, which often results from a retained intron or from missing the\n"
"initial parts of a transcript.</LI>\n"
"<LI><B>CDS single in intron</B> - This is another strong indicator that the ORF is\n"
"not real. Here the coding region (CDS) lies entirely in the intron of another\n"
"transcript which has strong evidence of coding for a protein. We remove the CDS\n"
"from non-refSeq transcripts that meet this condition, which generally results\n"
"from a retained intron.</LI>\n"
"<LI><B>frame shift in genome</B> - This only occurs for RefSeq transcripts. Here\n"
"a frame shift is detected in the coding region when aligning the transcript against\n"
"the genome. Since RefSeq does examine these cases carefully, it is strong evidence\n"
"that the genome sequence is in error, or that the anonymous DNA doner carried\n"
"a frame-shift mutation in this gene. In general there will be multiple independent\n"
"cDNA clones supporting the RefSeq over the genome. In the gene display on the\n"
"browser, one or two bases will be removed from the gene to keep frame intact.</LI>\n"
"<LI><B>stop codon in genome</B> - This also only occurs for RefSeq transcripts, and\n"
"as with the frame shifts, there is generally multiple lines of evidence suggesting\n"
"sequencing error or mutation in the reference genome. In the gene display on the\n"
"browser three bases will be removed from the gene to avoid the stop.</LI>\n"
"<LI><B>retained intron</B> - The transcript contains what is an intron in \n"
"an overlapping transcript on the same strand. In many cases this indicates\n"
"that the transcript was not completely processed. Unless specific steps are\n"
"taken to isolate cytoplasmic rather than nuclear RNA, a certain fraction of the\n"
"RNA isolated for sequencing will be incompletely processed. Transcripts with\n"
"retained introns should be viewed suspiciously, especially if they are long.\n"
"However there are cases where fully mature mRNA transcripts are made with \n"
"and without a particular intron, so transcripts with retained introns are not\n"
"eliminated from this gene set.</LI>\n"
"<LI><B>end bleed into intron</B> - Very often when an intron is retained, it is so\n"
"long that the next exon is not reached and sequenced. In this case the retained\n"
"intron can't be detected directly. However high values of \"end bleed\" are\n"
"strongly suggestive of a retained intron. End bleed measures how far the end of a transcript extends into an intron defined by another overlapping transcript. Note\n"
"however that alternative promoters and alternative polyadenylation sites can\n"
"create end bleeds in fully mature transcripts.</LI>\n"
"<LI><B>RNA accession</B> - The RefSeq or Genbank/EMBL/DJJ accession on which\n"
"this transcript is most closely based. Note that the splice sites when possible\n"
"are taken from a consensus of RNA alignments rather than just from a single RNA.\n"
"For non-RefSeq genes the bases are taken from the genome rather than the RNA.\n"
"However the transcript does define which introns and exons are used to build\n"
"the transcript.</LI>\n"
"<LI><B>RNA size</B> - The size of the RNA on which this transcript is most\n"
"closely based, including the poly-A tail.</LI>\n"
"<LI><B>Alignment % ID</B> - Percentage identity within of alignment of RNA\n"
"to genome.</LI>\n"
"<LI><B>% Coverage</B> - The percentage of the RNA covered by the alignment to\n"
"genome. This excludes the poly-A tail.</LI>\n"
"<LI><B># of Alignments:</B> - The number of times this RNA aligns to the genome\n"
"at very high stringency. More care must be taken in interpreting genes based\n"
"on transcripts with multiple alignments. We do substantial filtering to avoid\n"
"pseudogenes, but extremely recent, extremely complete pseudogenes may still\n"
"pass these filters and cause multiple alignments.</LI>\n"
"<LI><B># of AT/AC introns</B> - The number of introns in this transcript with\n"
"AT/AC rather than the usual GT/AG ends. There are roughly 300 genes with\n"
"legitimate AT/AC introns.</LI>\n"
"<LI><B># of strange splices</B> - The number of introns that have ends which are\n"
"neither GT/AG, GC/AG, nor AT/AC. Many of these are the result of sequencing\n"
"errors, or polymorphisms between the DNA donors and the RNA donors.</LI>\n"
"</UL>\n");
}
