bhaibeka/MetaGx0
R package for meta-analysis of breast cancer gene expressions

Package index
Search the bhaibeka/MetaGx0 package
Vignettes
Functions
12
Source code
23
Man pages
11
Home
/
GitHub
/
bhaibeka/MetaGx0
/
intersectList: x

intersectList: x
In bhaibeka/MetaGx0: R package for meta-analysis of breast cancer gene expressions

Usage Arguments Examples

Usage

1
intersectList(...)

Arguments

...

list of vectors of items

Examples

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (sbt.model = c("scmgene", "scmod2", "scmod1", "pam50", 
    "ssp2006", "ssp2003"), resdir = "cache", probegene.method, 
    remove.duplicates = TRUE, topvar.genes = 1000, duplicates.cor = 0.975, 
    datasets, nthread = 1, verbose = TRUE) 
{
    badchars <- "[\265]|[\n]|[,]|[;]|[:]|[-]|[+]|[*]|[%]|[$]|[#]|[{]|[}]|[[]|[]]|[|]|[\^]|[/]|[\]|[.]|[_]|[ ]"
    if (!file.exists(resdir)) {
        dir.create(resdir, showWarnings = FALSE, recursive = TRUE)
    }
    if (!file.exists(file.path(resdir, "processed"))) {
        dir.create(file.path(resdir, "processed"), showWarnings = FALSE, 
            recursive = TRUE)
    }
    availcore <- parallel::detectCores()
    if (nthread > availcore) {
        nthread <- availcore
    }
    options(mc.cores = nthread)
    if (missing(probegene.method)) {
        probegene.method <- rbind(c("MISC", "variance"), c("GPL8300", 
            "jetset"), c("GPL96", "jetset"), c("GPL97", "jetset"), 
            c("GPL570", "jetset"), c("GPL1352", "jetset"))
        colnames(probegene.method) <- c("platform", "method")
    }
    sbt.model <- match.arg(sbt.model)
    if (missing(datasets)) {
        datasets <- read.csv(system.file(file.path("extdata", 
            "datasets.csv"), package = "bcmeta"), stringsAsFactors = FALSE)
    }
    datasets <- datasets[datasets[, "Include"], , drop = FALSE]
    clin.info <- c("samplename", "id", "series", "dataset", "age", 
        "node", "er", "e.rfs", "e.os", "e.dmfs", "grade", "size", 
        "pgr", "her2", "t.rfs", "t.os", "t.dmfs", "treatment", 
        "tissue")
    InSilicoLogin(login = "bhaibeka@gmail.com", password = "747779bec8a754b91076d6cc1f700831")
    cinfo <- clin.info
    eset.all <- NULL
    for (i in 1:nrow(datasets)) {
        ddn <- as.character(datasets[i, "Dataset.ID"])
        if (verbose) {
            message(sprintf("Get dataset %s", ddn))
        }
        dataset.fn <- file.path(resdir, "processed", sprintf("%s_processed.RData", 
            ddn))
        if (!file.exists(dataset.fn)) {
            platf <- InSilicoDb::getPlatforms(dataset = ddn)
            esets <- InSilicoDb::getDatasets(dataset = ddn, 
                norm = as.character(datasets[i, "Normalization"]), 
                curation = datasets[i, "Curation.ID"], features = "PROBE")
            if (is.null(unlist(esets))) {
                stop("Rerun the script when data are ready to download from InSilicoDB")
            }
            platf <- unlist(platf[!sapply(esets, is.null)])
            esets <- esets[!sapply(esets, is.null)]
            if (verbose) {
                message("\tCheck feature and sample names")
            }
            esets <- lapply(esets, checkNames)
            if (verbose) {
                message("\tProbe-gene mapping")
            }
            platf2 <- platf
            platf2[!is.element(platf, probegene.method[, "platform"])] <- "MISC"
            esets <- mapply(probeGeneMapping, eset = esets, platform = platf2, 
                method = probegene.method[match(platf2, probegene.method[, 
                  "platform"]), "method"])
            eset <- platformMerging(esets)
            colnames(Biobase::phenoData(eset)@data) <- gsub(" ", 
                ".", colnames(Biobase::phenoData(eset)@data))
            cinfo <- intersect(cinfo, colnames(Biobase::phenoData(eset)@data))
            Biobase::phenoData(eset)@data <- data.frame(apply(Biobase::phenoData(eset)@data, 
                2, function(x) {
                  if (is.factor(x)) {
                    x <- as.character(x)
                  }
                  return(x)
                }), stringsAsFactors = FALSE)
            Biobase::phenoData(eset)@data[Biobase::phenoData(eset)@data == 
                "NA"] <- NA
            save(list = c("eset"), compress = TRUE, file = dataset.fn)
            if (verbose) {
                message("")
            }
        }
        else {
            load(file = dataset.fn)
        }
        switch(datasets[i, "Dataset.ID"], GSE2034 = {
            if ("GSE5327" %in% names(eset.all)) {
                if (verbose) {
                  message("\tMerge GSE2034 and GSE5327")
                }
                cg <- union(rownames(Biobase::exprs(eset.all[["GSE5327"]])), 
                  rownames(Biobase::exprs(eset)))
                cs <- c(colnames(Biobase::exprs(eset.all[["GSE5327"]])), 
                  colnames(Biobase::exprs(eset)))
                ee <- matrix(NA, nrow = length(cg), ncol = length(cs), 
                  dimnames = list(cg, cs))
                ee[rownames(Biobase::exprs(eset.all[["GSE5327"]])), 
                  colnames(Biobase::exprs(eset.all[["GSE5327"]]))] <- Biobase::exprs(eset.all[["GSE5327"]])
                ee[rownames(Biobase::exprs(eset)), colnames(Biobase::exprs(eset))] <- Biobase::exprs(eset)
                Biobase::exprs(eset.all[["GSE5327"]]) <- ee
                cf <- c(colnames(Biobase::featureData(eset.all[["GSE5327"]])@data), 
                  colnames(Biobase::featureData(eset)@data))
                ee <- data.frame(matrix(NA, nrow = length(cg), 
                  ncol = length(cf), dimnames = list(cg, cf)))
                ee[rownames(Biobase::featureData(eset.all[["GSE5327"]])@data), 
                  colnames(Biobase::featureData(eset.all[["GSE5327"]])@data)] <- Biobase::featureData(eset.all[["GSE5327"]])@data
                ee[rownames(Biobase::featureData(eset)@data), 
                  colnames(Biobase::featureData(eset)@data)] <- Biobase::featureData(eset)@data
                Biobase::featureData(eset.all[["GSE5327"]]) <- ee
                cp <- intersect(colnames(Biobase::phenoData(eset.all[["GSE5327"]])@data), 
                  colnames(Biobase::phenoData(eset)@data))
                ee <- data.frame(matrix(NA, nrow = length(cs), 
                  ncol = length(cp), dimnames = list(cs, cp)))
                ee[rownames(Biobase::phenoData(eset.all[["GSE5327"]])@data), 
                  cp] <- Biobase::phenoData(eset.all[["GSE5327"]])@data[, 
                  cp]
                ee[rownames(Biobase::phenoData(eset)@data), cp] <- Biobase::phenoData(eset)@data[, 
                  cp]
                Biobase::phenoData(eset.all[["GSE5327"]]) <- ee
                names(eset.all)[names(eset.all) == "GSE2034"] <- "GSE2034.GSE5327"
            } else {
                eset.all <- c(eset.all, eset)
                names(eset.all)[length(eset.all)] <- datasets[i, 
                  "Dataset.ID"]
            }
        }, GSE5327 = {
            if ("GSE2034" %in% names(eset.all)) {
                if (verbose) {
                  message("\tMerge GSE2034 and GSE5327")
                }
                cg <- union(rownames(Biobase::exprs(eset.all[["GSE2034"]])), 
                  rownames(Biobase::exprs(eset)))
                cs <- c(colnames(Biobase::exprs(eset.all[["GSE2034"]])), 
                  colnames(Biobase::exprs(eset)))
                ee <- matrix(NA, nrow = length(cg), ncol = length(cs), 
                  dimnames = list(cg, cs))
                ee[rownames(Biobase::exprs(eset)), colnames(Biobase::exprs(eset))] <- Biobase::exprs(eset)
                ee[rownames(Biobase::exprs(eset.all[["GSE2034"]])), 
                  colnames(Biobase::exprs(eset.all[["GSE2034"]]))] <- Biobase::exprs(eset.all[["GSE2034"]])
                Biobase::exprs(eset.all[["GSE2034"]]) <- ee
                cf <- intersect(colnames(Biobase::featureData(eset.all[["GSE2034"]])@data), 
                  colnames(Biobase::featureData(eset)@data))
                ee <- data.frame(matrix(NA, nrow = length(cg), 
                  ncol = length(cf), dimnames = list(cg, cf)))
                ee[rownames(Biobase::featureData(eset)@data), 
                  colnames(Biobase::featureData(eset)@data)] <- Biobase::featureData(eset)@data
                ee[rownames(Biobase::featureData(eset.all[["GSE2034"]])@data), 
                  colnames(Biobase::featureData(eset.all[["GSE2034"]])@data)] <- Biobase::featureData(eset.all[["GSE2034"]])@data
                Biobase::featureData(eset.all[["GSE2034"]])@data <- ee
                cp <- intersect(colnames(Biobase::phenoData(eset.all[["GSE2034"]])@data), 
                  colnames(Biobase::phenoData(eset)@data))
                ee <- data.frame(matrix(NA, nrow = length(cs), 
                  ncol = length(cp), dimnames = list(cs, cp)))
                ee[rownames(Biobase::phenoData(eset.all[["GSE2034"]])@data), 
                  cp] <- Biobase::phenoData(eset.all[["GSE2034"]])@data[, 
                  cp]
                ee[rownames(Biobase::phenoData(eset)@data), cp] <- Biobase::phenoData(eset)@data[, 
                  cp]
                Biobase::phenoData(eset.all[["GSE2034"]])@data <- ee
                names(eset.all)[names(eset.all) == "GSE2034"] <- "GSE2034.GSE5327"
            } else {
                eset.all <- c(eset.all, eset)
                names(eset.all)[length(eset.all)] <- datasets[i, 
                  "Dataset.ID"]
            }
        }, GSE2109 = {
            iix <- Biobase::phenoData(eset)@data[, "Anatomical.site"] == 
                "breast"
            Biobase::exprs(eset) <- Biobase::exprs(eset)[, iix, 
                drop = FALSE]
            Biobase::phenoData(eset)@data <- Biobase::phenoData(eset)@data[iix, 
                , drop = FALSE]
            eset.all <- c(eset.all, eset)
            names(eset.all)[length(eset.all)] <- datasets[i, 
                "Dataset.ID"]
        }, {
            eset.all <- c(eset.all, eset)
            names(eset.all)[length(eset.all)] <- datasets[i, 
                "Dataset.ID"]
        })
    }
    if (verbose) {
        message("Update clinical information")
    }
    for (j in 1:length(eset.all)) {
        Biobase::phenoData(eset.all[[j]])@data <- Biobase::phenoData(eset.all[[j]])@data[, 
            cinfo, drop = FALSE]
        tt <- intersect(colnames(Biobase::phenoData(eset.all[[j]])@data), 
            c("age", "size", "er", "her2", "pgr", "grade", c(paste(c("t", 
                "e"), rep(c("rfs", "dmfs", "os"), each = 2), 
                sep = "."))))
        Biobase::phenoData(eset.all[[j]])@data[, tt] <- data.frame(apply(Biobase::phenoData(eset.all[[j]])@data[, 
            tt, drop = FALSE], 2, as.numeric), stringsAsFactors = FALSE)
        surv.time <- Biobase::phenoData(eset.all[[j]])@data[, 
            "t.rfs"]
        surv.time[is.na(Biobase::phenoData(eset.all[[j]])@data[, 
            "t.rfs"])] <- Biobase::phenoData(eset.all[[j]])@data[is.na(Biobase::phenoData(eset.all[[j]])@data[, 
            "t.rfs"]), "t.dmfs"]
        surv.event <- Biobase::phenoData(eset.all[[j]])@data[, 
            "e.rfs"]
        surv.event[is.na(Biobase::phenoData(eset.all[[j]])@data[, 
            "e.rfs"])] <- Biobase::phenoData(eset.all[[j]])@data[is.na(Biobase::phenoData(eset.all[[j]])@data[, 
            "e.rfs"]), "e.dmfs"]
        Biobase::phenoData(eset.all[[j]])@data <- cbind(Biobase::phenoData(eset.all[[j]])@data, 
            t.dfs = surv.time, e.dfs = surv.event)
    }
    if (verbose) {
        message("Subtype classification")
    }
    for (j in 1:length(eset.all)) {
        eset.all[[j]] <- subtypeClassification(eset = eset.all[[j]], 
            model = sbt.model)
    }
    if (verbose) {
        message("Merge datasets")
    }
    eset.merged <- datasetMerging(esets = eset.all, nthread = nthread)
    duplicates <- duplicateFinder(eset = eset.merged, var.genes = topvar.genes, 
        dupl.cor = duplicates.cor)
    tt <- sapply(duplicates, paste, collapse = "///")
    Biobase::pData(eset.merged) <- cbind(Biobase::pData(eset.merged), 
        duplicates = NA)
    Biobase::pData(eset.merged)[names(tt), "duplicates"] <- tt
    eset.all <- lapply(eset.all, function(x, y) {
        Biobase::pData(x) <- cbind(Biobase::pData(x), duplicates = NA)
        nn <- intersect(rownames(pData(x)), y)
        Biobase::pData(x)[nn, "duplicates"] <- y[nn]
        return(x)
    }, y = tt)
    if (remove.duplicates) {
        rmix <- duplicates
        ii <- 1
        while (length(rmix) > ii) {
            rmix <- rmix[!is.element(names(rmix), rmix[[ii]])]
            ii <- ii + 1
        }
        rmix <- unique(unlist(rmix))
        keepix <- setdiff(sampleNames(eset.merged), rmix)
        Biobase::exprs(eset.merged) <- Biobase::exprs(eset.merged)[, 
            keepix, drop = FALSE]
        Biobase::pData(eset.merged) <- Biobase::pData(eset.merged)[keepix, 
            , drop = FALSE]
        eset.all <- lapply(eset.all, function(x, y) {
            keepix <- setdiff(sampleNames(x), y)
            Biobase::exprs(x) <- Biobase::exprs(x)[, keepix, 
                drop = FALSE]
            Biobase::pData(x) <- Biobase::pData(x)[keepix, , 
                drop = FALSE]
            return(x)
        }, y = rmix)
    }
    InSilicoLogout()
    return(list(merged = eset.merged, each = eset.all))
  }

bhaibeka/MetaGx0 documentation built on May 12, 2019, 8:22 p.m.

Related to intersectList in bhaibeka/MetaGx0...

bhaibeka/MetaGx0 index
README.md

R Package Documentation

rdrr.io home R language documentation Run R code online

Browse R Packages

CRAN packages Bioconductor packages R-Forge packages GitHub packages

We want your feedback!

Note that we can't provide technical support on individual packages. You should contact the package authors for that.
GitHub issue tracker
ian@mutexlabs.com
Personal blog

 
Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.

Close