Class to manage multiple varSets

An S4 class to manage varSets. varSets can be generated from annotations using the buildVarSet() method. Specific units and/or annotations can be retrieved using the getVarSet method. A varSetList can be used directly as input in assocTest() to perform burden/single variant association tests on the varSets included in the varSetList. The on-disk equivalent of a varSetList is varSetFile(), from which varSets can be retrieved in the same way as a varset list using the getVarSet method.

Build a varSetList

buildVarSet(x, ...): Generate a varSetList or varSetFile() that stores weighted variant sets for use in association testing. This can be based on 1) annotations uploaded to the gdb or 2) a data.frame including annotations. See buildVarSet() for details.

Getters

In the following code snippets, x is a varSetList object.

getVarSet(x, unit, varSetName): Retrieve varSets for specified units and/or varSetNames.
listUnits(x): Return a vector of all units included in the varSetList.
listVarSets(x): Return a vector of all varSetNames included in the varSetList.
getGdbId(x): Get gdb ID from metadata
metadata(x): Get metadata from varSetList

Subsetting

A varSetList can be subsetted in the same way as a normal R list, however, getVarSet is the most convenient way to select varSets (see above). Some examples, where x is a varSetList object:

x[[i]]: Return the i'th varSet
x[i:j]: Return the i'th till j'th varSets

Association testing

A varSetList can be directly supplied to the assocTest() gdb method, using the varSet parameter. Association tests will then be performed for each varSet included in the varSetList.

Miscellaneous

In the following code snippets, x is a varSetList object:

collapseVarSetList(x, unit = "unnamed", varSetName = "unnamed): Merge all varSets into one varSet. All weights will be set to 1. Optionally, the unit name and varSetName can be specified. This method is mainly used when you want to load the genotypes for all variants in a varSetList using getGT().
write(x, file = "data", append = "FALSE"): Write the varSetList to disk, in the varSetFile format.

Examples

library(rvatData)

# connect to varsetfile from rvatData package
# to build a varsetfile, see ?buildVarSet
varsetfile <- varSetFile(rvat_example("rvatData_varsetfile.txt.gz"))

# extract a couple of genes from the varSetFile, which whill return a varSetList
varsetlist <- getVarSet(varsetfile, c("SOD1", "FUS"))
varsetlist
#> varSetList
#> Contains 8 records
#> [[1]]
#> unit=FUS
#> varSetName=Moderate
#> VAR_id=1176,1177,1180,1182,1183,1186,1188,1192,1193,1194,1196,1198,1200,1202,1205,1206,1207,1208,1210,1211,1215,1216,1218,1219,1221,1222,1223,1224,1225,1226,1227,1228,1233,1234,1236,1239,1240,1241,1244,1245,1246,1248,1249,1250,1252,1253,1254,1256,1257,1258,1261,1262,1263,1265,1266
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
#> 
#> [[2]]
#> unit=FUS
#> varSetName=ModerateHigh
#> VAR_id=1175,1176,1177,1180,1182,1183,1186,1188,1192,1193,1194,1196,1198,1200,1202,1205,1206,1207,1208,1210,1211,1215,1216,1218,1219,1221,1222,1223,1224,1225,1226,1227,1228,1233,1234,1236,1239,1240,1241,1244,1245,1246,1248,1249,1250,1252,1253,1254,1256,1257,1258,1261,1262,1263,1265,1266
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
#> 
#> [[3]]
#> unit=FUS
#> varSetName=High
#> VAR_id=1175
#> w=1
#> 
#> [[4]]
#> unit=FUS
#> varSetName=CADD
#> VAR_id=1173,1174,1175,1176,1177,1178,1179,1180,1181,1182,1183,1184,1185,1186,1187,1188,1189,1190,1191,1192,1193,1194,1195,1196,1197,1198,1199,1200,1201,1202,1203,1204,1205,1206,1207,1208,1209,1210,1211,1212,1213,1214,1215,1216,1217,1218,1219,1220,1221,1222,1223,1224,1225,1226,1227,1228,1229,1230,1231,1232,1233,1234,1235,1236,1237,1238,1239,1240,1241,1242,1243,1244,1245,1246,1247,1248,1249,1250,1251,1252,1253,1254,1255,1256,1257,1258,1259,1260,1261,1262,1263,1264,1265,1266,1267
#> w=.,.,.,26.5,22.4,.,.,32,.,24.7,24.5,.,.,.,.,13.68,.,.,.,22.1,13.66,15.72,.,26.4,.,26,.,22.7,.,19.21,.,.,17.9,.,23.3,24,.,0.058,1.247,.,.,.,7.445,17.84,.,16.16,24.8,.,21.6,23.2,25.8,24.1,31,32,26.9,23.2,.,.,.,.,31,20.3,.,23.7,.,.,19.45,24.6,23.3,.,.,26,.,22.9,.,17.24,28.8,31,.,25,19.89,23.1,.,.,24.6,23.4,.,.,22,25.3,24.4,.,26.5,23.7,.
#> 
#> [[5]]
#> unit=SOD1
#> varSetName=Moderate
#> VAR_id=1268,1270,1271,1273,1275,1276,1277,1278,1279,1281,1282,1283,1284,1285,1287,1288,1289,1290,1291,1292,1293,1294,1296,1297,1298,1299,1300,1304,1305,1306,1307,1308,1309,1312,1313,1314,1315,1316
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
#> 
#> [[6]]
#> unit=SOD1
#> varSetName=ModerateHigh
#> VAR_id=1268,1270,1271,1273,1275,1276,1277,1278,1279,1281,1282,1283,1284,1285,1286,1287,1288,1289,1290,1291,1292,1293,1294,1296,1297,1298,1299,1300,1301,1302,1304,1305,1306,1307,1308,1309,1311,1312,1313,1314,1315,1316
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
#> 

# many of the varSetFile methods are also available for a varSetList
# for example, getVarSet can also be used to extract specific genes or varSets from a varSetList
getVarSet(varsetlist, unit = "SOD1")
#> varSetList
#> Contains 4 records
#> [[1]]
#> unit=SOD1
#> varSetName=Moderate
#> VAR_id=1268,1270,1271,1273,1275,1276,1277,1278,1279,1281,1282,1283,1284,1285,1287,1288,1289,1290,1291,1292,1293,1294,1296,1297,1298,1299,1300,1304,1305,1306,1307,1308,1309,1312,1313,1314,1315,1316
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
#> 
#> [[2]]
#> unit=SOD1
#> varSetName=ModerateHigh
#> VAR_id=1268,1270,1271,1273,1275,1276,1277,1278,1279,1281,1282,1283,1284,1285,1286,1287,1288,1289,1290,1291,1292,1293,1294,1296,1297,1298,1299,1300,1301,1302,1304,1305,1306,1307,1308,1309,1311,1312,1313,1314,1315,1316
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
#> 
#> [[3]]
#> unit=SOD1
#> varSetName=High
#> VAR_id=1286,1301,1302,1311
#> w=1,1,1,1
#> 
#> [[4]]
#> unit=SOD1
#> varSetName=CADD
#> VAR_id=1268,1269,1270,1271,1272,1273,1274,1275,1276,1277,1278,1279,1280,1281,1282,1283,1284,1285,1286,1287,1288,1289,1290,1291,1292,1293,1294,1295,1296,1297,1298,1299,1300,1301,1302,1303,1304,1305,1306,1307,1308,1309,1310,1311,1312,1313,1314,1315,1316
#> w=31,.,23.4,.,.,13.44,.,23.9,24.9,22.7,24.9,24.5,.,29.6,26.5,27.1,31,26.2,34,26.6,32,29,14.85,26.2,25,16.46,23.2,.,24.3,17.52,22.8,27.4,27.6,.,25.1,.,.,23.4,28.2,27.9,16.67,27.4,.,42,25.7,.,29.2,22.4,27.3
#> 

# list included units and varSets 
units <- listUnits(varsetlist)
head(units)
#> [1] "FUS"  "FUS"  "FUS"  "FUS"  "SOD1" "SOD1"
varsets <- listVarSets(varsetlist)
head(varsets)
#> [1] "Moderate"     "ModerateHigh" "High"         "CADD"         "Moderate"    
#> [6] "ModerateHigh"

# several basic list operations work on a varSetList
length(varsetlist)
#> [1] 8
varsetlist[1:2]
#> varSetList
#> Contains 2 records
#> [[1]]
#> unit=FUS
#> varSetName=Moderate
#> VAR_id=1176,1177,1180,1182,1183,1186,1188,1192,1193,1194,1196,1198,1200,1202,1205,1206,1207,1208,1210,1211,1215,1216,1218,1219,1221,1222,1223,1224,1225,1226,1227,1228,1233,1234,1236,1239,1240,1241,1244,1245,1246,1248,1249,1250,1252,1253,1254,1256,1257,1258,1261,1262,1263,1265,1266
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
#> 
#> [[2]]
#> unit=FUS
#> varSetName=ModerateHigh
#> VAR_id=1175,1176,1177,1180,1182,1183,1186,1188,1192,1193,1194,1196,1198,1200,1202,1205,1206,1207,1208,1210,1211,1215,1216,1218,1219,1221,1222,1223,1224,1225,1226,1227,1228,1233,1234,1236,1239,1240,1241,1244,1245,1246,1248,1249,1250,1252,1253,1254,1256,1257,1258,1261,1262,1263,1265,1266
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
#> 
varsetlist[[1]]
#> unit=FUS
#> varSetName=Moderate
#> VAR_id=1176,1177,1180,1182,1183,1186,1188,1192,1193,1194,1196,1198,1200,1202,1205,1206,1207,1208,1210,1211,1215,1216,1218,1219,1221,1222,1223,1224,1225,1226,1227,1228,1233,1234,1236,1239,1240,1241,1244,1245,1246,1248,1249,1250,1252,1253,1254,1256,1257,1258,1261,1262,1263,1265,1266
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1

# extract metadata
metadata(varsetlist)
#> $rvatVersion
#> [1] "0.3.1"
#> 
#> $gdbId
#> [1] "vmo8w57mh9lhjhijqf5ja9fu0suj"
#> 
#> $genomeBuild
#> [1] "GRCh38"
#> 
#> $creationDate
#> [1] "2024-11-20 11:42:04"
#> 
getRvatVersion(varsetlist)
#> [1] "0.3.1"
getGdbId(varsetlist)
#> [1] "vmo8w57mh9lhjhijqf5ja9fu0suj"

# all varsets in in a varsetlist can be collapsed into one varSet using the
# collapseVarSetList method
collapseVarSetList(varsetlist)
#> unit=unnamed
#> varSetName=unnamed
#> VAR_id=1176,1177,1180,1182,1183,1186,1188,1192,1193,1194,1196,1198,1200,1202,1205,1206,1207,1208,1210,1211,1215,1216,1218,1219,1221,1222,1223,1224,1225,1226,1227,1228,1233,1234,1236,1239,1240,1241,1244,1245,1246,1248,1249,1250,1252,1253,1254,1256,1257,1258,1261,1262,1263,1265,1266,1175,1173,1174,1178,1179,1181,1184,1185,1187,1189,1190,1191,1195,1197,1199,1201,1203,1204,1209,1212,1213,1214,1217,1220,1229,1230,1231,1232,1235,1237,1238,1242,1243,1247,1251,1255,1259,1260,1264,1267,1268,1270,1271,1273,1275,1276,1277,1278,1279,1281,1282,1283,1284,1285,1287,1288,1289,1290,1291,1292,1293,1294,1296,1297,1298,1299,1300,1304,1305,1306,1307,1308,1309,1312,1313,1314,1315,1316,1286,1301,1302,1311,1269,1272,1274,1280,1295,1303,1310
#> w=1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1

# varSetLists can be written to a varSetFile on disk using the write method
output <- tempfile() 
write(varsetlist, output)
varsetfile <- varSetFile(output)
varsetfile
#> varSetFile object
#> Path:/var/folders/cl/wvc0rvjx4vd5rzt2_fhpmfth0000gp/T//RtmpRC6myU/file1825c7edb50fd
#> Units:8

# see e.g., ?assocTest and ?aggregate for downstream methods that can loop through varSets included in a varSetlist