static boolean localizationExists(struct section *section,
struct sqlConnection *conn, char *geneId)
/* Return TRUE if localization and existance tables exist and have something
* on this one. */
{
char query[256];
/* mitopred - prediction of nuclear-encoded mitochondrial proteins */
if (swissProtAcc != NULL && sqlTableExists(conn, "mitopred"))
{
sqlSafef(query, sizeof(query),
"select count(*) from mitopred where name = '%s' or name = '%s'",
swissProtAcc, spAnyAccToId(spConn, swissProtAcc));
if (sqlQuickNum(conn, query) > 0)
return TRUE;
}
/* SGD (Sacchromyces Genome Database) localization & abundance data */
if (sqlTablesExist(conn, "sgdLocalization sgdAbundance"))
{
sqlSafef(query, sizeof(query),
"select count(*) from sgdLocalization where name = '%s'", geneId);
if (sqlQuickNum(conn, query) > 0)
return TRUE;
sqlSafef(query, sizeof(query),
"select count(*) from sgdAbundance where name = '%s'", geneId);
if (sqlQuickNum(conn, query) > 0)
return TRUE;
}
return FALSE;
}
static boolean pathwayExists(struct pathwayLink *pl,
struct sqlConnection *conn, char *geneId)
/* Return TRUE if pathway exists and has data. */
{
if (!sqlTablesExist(conn, pl->tables))
return FALSE;
return pl->count(pl, conn, geneId) > 0;
}
void addVersion(boolean strict, char *database, char *dirName, char *raName,
struct hash *uniqHash,
struct hash *htmlHash,
struct hgFindSpec **pSpecList)
/* Read in specs from raName and add them to list/database if new. */
{
struct hgFindSpec *hfsList = NULL, *hfs = NULL;
struct hgFindSpec *hfsNext = NULL;
hfsList = hgFindSpecFromRa(database, raName, NULL);
/* prune records of the incorrect release */
hfsList = pruneRelease(hfsList);
if (strict)
{
for (hfs = hfsList; hfs != NULL; hfs = hfsNext)
{
hfsNext = hfs->next;
if (! hTableOrSplitExists(database, hfs->searchTable))
{
if (verboseLevel() > 1)
printf("%s missing\n", hfs->searchTable);
slRemoveEl(&hfsList, hfs);
}
else if (hfs->xrefTable[0] != 0)
{
// Use sqlTableExists because xrefTable might be $db.$table,
// not supported by hTableExists / hTableOrSplitExists
// NOTE hfs->xrefTable can sometimes contain a comma-separated table list,
// rather than just a single table.
struct sqlConnection *conn = hAllocConn(database);
char *tables = replaceChars(hfs->xrefTable, ",", " ");
boolean exists = sqlTablesExist(conn, tables);
hFreeConn(&conn);
freeMem(tables);
if (! exists)
{
if (verboseLevel() > 1)
printf("%s (xref) missing\n", hfs->xrefTable);
slRemoveEl(&hfsList, hfs);
}
}
}
}
for (hfs = hfsList; hfs != NULL; hfs = hfsNext)
{
hfsNext = hfs->next;
if (! hashLookup(uniqHash, hfs->searchName))
{
hashAdd(uniqHash, hfs->searchName, hfs);
slAddHead(pSpecList, hfs);
}
}
}
static char *getRefSeqAcc(char *id, char *table, char *idCol, struct sqlConnection *conn)
/* Finds RefSeq accession from a cross-reference table. */
{
char query[256];
struct sqlResult *sr = NULL;
char **row;
char *refSeqAcc = NULL;
if (sqlTablesExist(conn, table))
{
safef(query, sizeof(query), "select refSeq from %s where %s = '%s'", table, idCol, id);
sr = sqlGetResult(conn, query);
if (sr != NULL)
{
row = sqlNextRow(sr);
refSeqAcc = cloneString(row[0]);
}
}
sqlFreeResult(&sr);
return refSeqAcc;
}
char *descriptionString(char *id, struct sqlConnection *conn)
/* return description as it would be printed in html, can free after use */
{
char *descrBySql = NULL;
char *summaryTables = genomeOptionalSetting("summaryTables");
struct dyString *description = dyStringNew(0);
descrBySql = genoQuery(id, "descriptionSql", conn);
dyStringPrintf(description, "<B>Description:</B> ");
if (descrBySql != NULL)
dyStringPrintf(description, "%s<BR>\n", descrBySql);
else
dyStringPrintf(description, "%s<BR>\n", "No description available");
freez(&descrBySql);
if (summaryTables != NULL)
{
if (sqlTablesExist(conn, summaryTables))
{
char *summary = genoQuery(id, "summarySql", conn);
if (summary != NULL && summary[0] != 0)
{
summary = abbreviateSummary(summary);
dyStringPrintf(description, "<B>%s",
genomeSetting("summarySource"));
if (genomeOptionalSetting("summaryIdSql"))
{
char *summaryId = genoQuery(id, "summaryIdSql", conn);
if (summaryId != NULL)
dyStringPrintf(description, " (%s)", summaryId);
}
dyStringPrintf(description, ":</B> %s", summary);
freez(&summary);
dyStringPrintf(description, "<BR>\n");
}
}
}
return dyStringCannibalize(&description);
}
static struct link *getLinkList(struct sqlConnection *conn,
char *raFile)
/* Get list of links - starting with everything in .ra file,
* and making sure any associated tables and databases exist. */
{
struct hash *ra, *raList = readRa(raFile, NULL);
struct link *linkList = NULL, *link;
for (ra = raList; ra != NULL; ra = ra->next)
{
if (linkOptionalField(ra, "hide") == NULL)
{
if (checkDatabases(linkOptionalField(ra, "databases"))
&& sqlTablesExist(conn, linkOptionalField(ra, "tables")))
{
/* only include the wikiTrack if it is enabled */
if (sameWord(linkRequiredField(ra, "name"), "wikiTrack") &&
! wikiTrackEnabled(database, NULL))
continue;
AllocVar(link);
link->priority = atof(linkRequiredField(ra, "priority"));
link->name = linkRequiredField(ra, "name");
link->shortLabel = linkRequiredField(ra, "shortLabel");
link->idSql = linkRequiredField(ra, "idSql");
link->nameSql = linkOptionalField(ra, "nameSql");
link->nameFormat = linkOptionalField(ra, "nameFormat");
link->url = linkRequiredField(ra, "url");
link->useHgsid = (linkOptionalField(ra, "hgsid") != NULL);
link->useDb = (linkOptionalField(ra, "dbInUrl") != NULL);
link->preCutAt = linkOptionalField(ra, "preCutAt");
link->postCutAt = linkOptionalField(ra, "postCutAt");
slAddHead(&linkList, link);
}
}
}
slSort(&linkList, linkCmpPriority);
return linkList;
}
static struct otherOrg *getOtherOrgList(struct sqlConnection *conn,
char *raFile)
/* Get list of otherOrgs - starting with everything in .ra file,
* and making sure any associated tables and databases exist. */
{
struct hash *ra, *raList = readRa(raFile, NULL);
struct otherOrg *otherOrgList = NULL, *otherOrg;
for (ra = raList; ra != NULL; ra = ra->next)
{
if (otherOrgOptionalField(ra, "hide") == NULL)
{
if (checkDatabases(otherOrgOptionalField(ra, "databases"))
&& sqlTablesExist(conn, otherOrgOptionalField(ra, "tables")))
{
AllocVar(otherOrg);
otherOrg->priority = atof(otherOrgRequiredField(ra, "priority"));
otherOrg->name = otherOrgRequiredField(ra, "name");
otherOrg->shortLabel = otherOrgRequiredField(ra, "shortLabel");
otherOrg->idSql = otherOrgRequiredField(ra, "idSql");
otherOrg->idToProtIdSql = otherOrgOptionalField(ra, "idToProtIdSql");
otherOrg->otherIdSql = otherOrgOptionalField(ra, "otherIdSql");
otherOrg->otherIdSql2 = otherOrgOptionalField(ra, "otherIdSql2");
otherOrg->genomeUrl = otherOrgOptionalField(ra, "genomeUrl");
otherOrg->sorterUrl = otherOrgOptionalField(ra, "sorterUrl");
otherOrg->geneUrl = otherOrgOptionalField(ra, "geneUrl");
otherOrg->otherUrl = otherOrgOptionalField(ra, "otherUrl");
otherOrg->otherName = otherOrgOptionalField(ra, "otherName");
otherOrg->db = otherOrgRequiredField(ra, "db");
otherOrg->pepTable = otherOrgOptionalField(ra, "pepTable");
otherOrg->geneTable = otherOrgOptionalField(ra, "geneTable");
slAddHead(&otherOrgList, otherOrg);
}
}
}
slSort(&otherOrgList, otherOrgCmpPriority);
return otherOrgList;
}
static void printCcds(char *kgId, struct sqlConnection *conn)
/* Print out CCDS ids most closely matching the kg. */
{
struct ccdsGeneMap *ccdsKgs = NULL;
if (sqlTablesExist(conn, "ccdsKgMap"))
ccdsKgs = ccdsGeneMapSelectByGene(conn, "ccdsKgMap", kgId, 0.0);
if (ccdsKgs != NULL)
{
struct ccdsGeneMap *ccdsKg;
hPrintf("<B>CCDS:</B> ");
/* since kg is not by location (even though we have a
* curGeneStart/curGeneEnd), we need to use the location in the
* ccdsGeneMap */
for (ccdsKg = ccdsKgs; ccdsKg != NULL; ccdsKg = ccdsKg->next)
{
if (ccdsKg != ccdsKgs)
hPrintf(", ");
hPrintf("<A href=\"../cgi-bin/hgc?%s&g=ccdsGene&i=%s&c=%s&o=%d&l=%d&r=%d&db=%s\">%s</A>",
cartSidUrlString(cart), ccdsKg->ccdsId, ccdsKg->chrom, ccdsKg->chromStart, ccdsKg->chromStart,
ccdsKg->chromEnd, database, ccdsKg->ccdsId);
}
hPrintf("<BR>\n");
}
}
static void printGeneSymbol (char *geneId, char *table, char *idCol, struct sqlConnection *conn)
/* Print out official Entrez gene symbol from a cross-reference table.*/
{
char query[256];
struct sqlResult *sr = NULL;
char **row;
char *geneSymbol;
if (sqlTablesExist(conn, table))
{
hPrintf("<B>Entrez Gene Official Symbol:</B> ");
safef(query, sizeof(query), "select geneSymbol from %s where %s = '%s'", table, idCol, geneId);
sr = sqlGetResult(conn, query);
if (sr != NULL)
{
row = sqlNextRow(sr);
geneSymbol = cloneString(row[0]);
if (!sameString(geneSymbol, ""))
hPrintf("%s<BR>", geneSymbol);
}
}
sqlFreeResult(&sr);
}
static void synonymPrint(struct section *section,
struct sqlConnection *conn, char *id)
/* Print out SwissProt comments - looking up typeId/commentVal. */
{
char *protAcc = getSwissProtAcc(conn, spConn, id);
char *spDisplayId;
char *refSeqAcc = "";
char *mrnaAcc = "";
char *oldDisplayId;
char condStr[255];
char *kgProteinID;
char *parAcc; /* parent accession of a variant splice protein */
char *chp;
if (isRgdGene(conn))
{
rgdGene2SynonymPrint(section,conn, id);
return;
}
if (sqlTablesExist(conn, "kgAlias"))
printAlias(id, conn);
if (sameWord(genome, "Zebrafish"))
{
char *xrefTable = "ensXRefZfish";
char *geneIdCol = "ensGeneId";
/* get Gene Symbol and RefSeq accession from Zebrafish-specific */
/* cross-reference table */
printGeneSymbol(id, xrefTable, geneIdCol, conn);
refSeqAcc = getRefSeqAcc(id, xrefTable, geneIdCol, conn);
hPrintf("<B>ENSEMBL ID:</B> %s", id);
}
else
{
char query[256];
char *toRefTable = genomeOptionalSetting("knownToRef");
if (toRefTable != NULL && sqlTableExists(conn, toRefTable))
{
safef(query, sizeof(query), "select value from %s where name='%s'", toRefTable,
id);
refSeqAcc = emptyForNull(sqlQuickString(conn, query));
}
if (sqlTableExists(conn, "kgXref"))
{
safef(query, sizeof(query), "select mRNA from kgXref where kgID='%s'", id);
mrnaAcc = emptyForNull(sqlQuickString(conn, query));
}
if (sameWord(genome, "C. elegans"))
hPrintf("<B>WormBase ID:</B> %s<BR>", id);
else
hPrintf("<B>UCSC ID:</B> %s<BR>", id);
}
if (refSeqAcc[0] != 0)
{
hPrintf("<B>RefSeq Accession: </B> <A HREF=\"");
printOurRefseqUrl(stdout, refSeqAcc);
hPrintf("\">%s</A><BR>\n", refSeqAcc);
}
else if (mrnaAcc[0] != 0)
{
safef(condStr, sizeof(condStr), "acc = '%s'", mrnaAcc);
if (sqlGetField(database, "gbCdnaInfo", "acc", condStr) != NULL)
{
hPrintf("<B>Representative RNA: </B> <A HREF=\"");
printOurMrnaUrl(stdout, mrnaAcc);
hPrintf("\">%s</A><BR>\n", mrnaAcc);
}
else
/* do not show URL link if it is not found in gbCdnaInfo */
{
hPrintf("<B>Representative RNA: %s </B>", mrnaAcc);
}
}
if (protAcc != NULL)
{
kgProteinID = cloneString("");
if (hTableExists(sqlGetDatabase(conn), "knownGene")
&& (isNotEmpty(cartOptionalString(cart, hggChrom)) &&
differentWord(cartOptionalString(cart, hggChrom),"none")))
{
safef(condStr, sizeof(condStr), "name = '%s' and chrom = '%s' and txStart=%s and txEnd=%s",
id, cartOptionalString(cart, hggChrom),
cartOptionalString(cart, hggStart),
cartOptionalString(cart, hggEnd));
kgProteinID = sqlGetField(database, "knownGene", "proteinID", condStr);
}
hPrintf("<B>Protein: ");
if (strstr(kgProteinID, "-") != NULL)
{
parAcc = cloneString(kgProteinID);
chp = strstr(parAcc, "-");
*chp = '\0';
/* show variant splice protein and the UniProt link here */
hPrintf("<A HREF=\"http://www.uniprot.org/uniprot%s\" "
"TARGET=_blank>%s</A></B>, splice isoform of ",
kgProteinID, kgProteinID);
hPrintf("<A HREF=\"http://www.uniprot.org/uniprot/%s\" "
"TARGET=_blank>%s</A></B>\n",
parAcc, parAcc);
}
else
{
hPrintf("<A HREF=\"http://www.uniprot.org/uniprot/%s\" "
"TARGET=_blank>%s</A></B>\n",
protAcc, protAcc);
}
/* show SWISS-PROT display ID if it is different than the accession ID */
/* but, if display name is like: Q03399 | Q03399_HUMAN, then don't show display name */
spDisplayId = spAnyAccToId(spConn, protAcc);
if (spDisplayId == NULL)
{
errAbort("<br>%s seems to no longer be a valid protein ID in our latest UniProtKB DB.", protAcc);
}
if (strstr(spDisplayId, protAcc) == NULL)
{
hPrintf(" (aka %s", spDisplayId);
/* show once if the new and old displayId are the same */
oldDisplayId = oldSpDisplayId(spDisplayId);
if (oldDisplayId != NULL)
{
if (!sameWord(spDisplayId, oldDisplayId)
&& !sameWord(protAcc, oldDisplayId))
{
hPrintf(" or %s", oldDisplayId);
}
}
hPrintf(")<BR>\n");
}
}
printCcds(id, conn);
}
static boolean associationOrderExists(struct order *ord,
struct sqlConnection *conn)
/* This returns true if needed tables exist. */
{
return sqlTablesExist(conn, ord->tables);
}
static void localizationPrint(struct section *section,
struct sqlConnection *conn, char *geneId)
/* Print out localization and abundance links. */
{
char query[256], **row, *s = NULL;
struct sqlResult *sr;
boolean firstTime = TRUE;
/* mitopred - prediction of nuclear-encoded mitochondrial proteins */
if (swissProtAcc != NULL && sqlTableExists(conn, "mitopred"))
{
sqlSafef(query, sizeof(query),
"select confidence from mitopred where name = '%s' or name = '%s'",
swissProtAcc, spAnyAccToId(spConn, swissProtAcc));
sr = sqlGetResult(conn, query);
firstTime = TRUE;
while ((row = sqlNextRow(sr)) != NULL)
{
if (firstTime)
{
hPrintf("<B>Mitopred:</B> mitochondrion, confidence level: ");
firstTime = FALSE;
}
else
{
hPrintf(", ");
}
hPrintf("%s", row[0]);
}
sqlFreeResult(&sr);
if (!firstTime)
{
hPrintf("<BR>");
hPrintf("Prediction of nuclear-encoded mitochondrial proteins from "
"Guda et al., Bioinformatics. 2004 Jul 22;20(11):1785-94.<BR>"
"For more information see "
"<A HREF=\"http://mitopred.sdsc.edu/\" TARGET=_blank>"
"http://mitopred.sdsc.edu/</A>.<P>");
}
}
/* SGD (Sacchromyces Genome Database) localization & abundance data */
if (sqlTablesExist(conn, "sgdLocalization sgdAbundance"))
{
sqlSafef(query, sizeof(query),
"select value from sgdLocalization where name = '%s'", geneId);
sr = sqlGetResult(conn, query);
firstTime = TRUE;
while ((row = sqlNextRow(sr)) != NULL)
{
if (firstTime)
{
hPrintf("<B>SGD Localization:</B> ");
firstTime = FALSE;
}
else
{
hPrintf(", ");
}
hPrintf("%s", row[0]);
}
sqlFreeResult(&sr);
if (!firstTime)
{
hPrintf("<BR>");
}
sqlSafef(query, sizeof(query),
"select abundance from sgdAbundance where name = '%s'", geneId);
s = sqlQuickString(conn, query);
if (s != NULL)
{
hPrintf("<B>SGD Abundance:</B> %s (range from 41 to 1590000)<BR>\n",
s);
freez(&s);
}
hPrintf("Protein localization data from "
"Huh et al. (2003), Nature 425:686-691<BR>"
"Protein abundance data from "
"Ghaemmaghami et al. (2003) Nature 425:737-741<BR>"
"For more information see "
"<A HREF=\"http://yeastgfp.yeastgenome.org\" TARGET=_blank>"
"http://yeastgfp.yeastgenome.org</A>.");
}
}