Pablo Flores
| Snapshot Date: 2024-11-24 13:40 -0500 (Sun, 24 Nov 2024) |
| git_url: https://git.bioconductor.org/packages/goSorensen |
| git_branch: devel |
| git_last_commit: 88ed371 |
| git_last_commit_date: 2024-10-29 11:13:21 -0500 (Tue, 29 Oct 2024) |
| Back to Multiple platform build/check report for BioC 3.21: simplified long |
|
This page was generated on 2024-11-25 11:38 -0500 (Mon, 25 Nov 2024).
| Hostname | OS | Arch (*) | R version | Installed pkgs |
|---|---|---|---|---|
| nebbiolo1 | Linux (Ubuntu 24.04.1 LTS) | x86_64 | R Under development (unstable) (2024-10-21 r87258) -- "Unsuffered Consequences" | 4748 |
| palomino7 | Windows Server 2022 Datacenter | x64 | R Under development (unstable) (2024-10-26 r87273 ucrt) -- "Unsuffered Consequences" | 4459 |
| lconway | macOS 12.7.1 Monterey | x86_64 | R Under development (unstable) (2024-11-20 r87352) -- "Unsuffered Consequences" | 4349 |
| Click on any hostname to see more info about the system (e.g. compilers) (*) as reported by 'uname -p', except on Windows and Mac OS X | ||||
| Package 881/2272 | Hostname | OS / Arch | INSTALL | BUILD | CHECK | BUILD BIN | ||||||||
| goSorensen 1.9.0 (landing page) Pablo Flores
| nebbiolo1 | Linux (Ubuntu 24.04.1 LTS) / x86_64 | OK | OK | OK | | ||||||||
| palomino7 | Windows Server 2022 Datacenter / x64 | OK | OK | OK | OK | | ||||||||
| lconway | macOS 12.7.1 Monterey / x86_64 | OK | OK | OK | OK | | ||||||||
|
To the developers/maintainers of the goSorensen package: - Allow up to 24 hours (and sometimes 48 hours) for your latest push to git@git.bioconductor.org:packages/goSorensen.git to reflect on this report. See Troubleshooting Build Report for more information. - Use the following Renviron settings to reproduce errors and warnings. - If 'R CMD check' started to fail recently on the Linux builder(s) over a missing dependency, add the missing dependency to 'Suggests:' in your DESCRIPTION file. See Renviron.bioc for more information. |
| Package: goSorensen |
| Version: 1.9.0 |
| Command: E:\biocbuild\bbs-3.21-bioc\R\bin\R.exe CMD check --no-multiarch --install=check:goSorensen.install-out.txt --library=E:\biocbuild\bbs-3.21-bioc\R\library --no-vignettes --timings goSorensen_1.9.0.tar.gz |
| StartedAt: 2024-11-25 01:18:14 -0500 (Mon, 25 Nov 2024) |
| EndedAt: 2024-11-25 01:32:18 -0500 (Mon, 25 Nov 2024) |
| EllapsedTime: 844.1 seconds |
| RetCode: 0 |
| Status: OK |
| CheckDir: goSorensen.Rcheck |
| Warnings: 0 |
##############################################################################
##############################################################################
###
### Running command:
###
### E:\biocbuild\bbs-3.21-bioc\R\bin\R.exe CMD check --no-multiarch --install=check:goSorensen.install-out.txt --library=E:\biocbuild\bbs-3.21-bioc\R\library --no-vignettes --timings goSorensen_1.9.0.tar.gz
###
##############################################################################
##############################################################################
* using log directory 'E:/biocbuild/bbs-3.21-bioc/meat/goSorensen.Rcheck'
* using R Under development (unstable) (2024-10-26 r87273 ucrt)
* using platform: x86_64-w64-mingw32
* R was compiled by
gcc.exe (GCC) 13.2.0
GNU Fortran (GCC) 13.2.0
* running under: Windows Server 2022 x64 (build 20348)
* using session charset: UTF-8
* using option '--no-vignettes'
* checking for file 'goSorensen/DESCRIPTION' ... OK
* checking extension type ... Package
* this is package 'goSorensen' version '1.9.0'
* package encoding: UTF-8
* checking package namespace information ... OK
* checking package dependencies ... OK
* checking if this is a source package ... OK
* checking if there is a namespace ... OK
* checking for hidden files and directories ... OK
* checking for portable file names ... OK
* checking whether package 'goSorensen' can be installed ... OK
* checking installed package size ... OK
* checking package directory ... OK
* checking 'build' directory ... OK
* checking DESCRIPTION meta-information ... OK
* checking top-level files ... OK
* checking for left-over files ... OK
* checking index information ... OK
* checking package subdirectories ... OK
* checking code files for non-ASCII characters ... OK
* checking R files for syntax errors ... OK
* checking whether the package can be loaded ... OK
* checking whether the package can be loaded with stated dependencies ... OK
* checking whether the package can be unloaded cleanly ... OK
* checking whether the namespace can be loaded with stated dependencies ... OK
* checking whether the namespace can be unloaded cleanly ... OK
* checking dependencies in R code ... OK
* checking S3 generic/method consistency ... OK
* checking replacement functions ... OK
* checking foreign function calls ... OK
* checking R code for possible problems ... OK
* checking Rd files ... OK
* checking Rd metadata ... OK
* checking Rd cross-references ... OK
* checking for missing documentation entries ... OK
* checking for code/documentation mismatches ... OK
* checking Rd \usage sections ... OK
* checking Rd contents ... OK
* checking for unstated dependencies in examples ... OK
* checking contents of 'data' directory ... OK
* checking data for non-ASCII characters ... OK
* checking data for ASCII and uncompressed saves ... OK
* checking installed files from 'inst/doc' ... OK
* checking files in 'vignettes' ... OK
* checking examples ... OK
Examples with CPU (user + system) or elapsed time > 5s
user system elapsed
hclustThreshold 270.29 25.95 296.24
buildEnrichTable 69.45 4.30 76.56
enrichedIn 63.33 3.58 66.94
* checking for unstated dependencies in 'tests' ... OK
* checking tests ...
Running 'test_gosorensen_funcs.R'
OK
* checking for unstated dependencies in vignettes ... NOTE
'library' or 'require' calls not declared from:
'GO.db' 'ggplot2' 'ggrepel'
* checking package vignettes ... OK
* checking running R code from vignettes ... SKIPPED
* checking re-building of vignette outputs ... SKIPPED
* checking PDF version of manual ... OK
* DONE
Status: 1 NOTE
See
'E:/biocbuild/bbs-3.21-bioc/meat/goSorensen.Rcheck/00check.log'
for details.
goSorensen.Rcheck/00install.out
############################################################################## ############################################################################## ### ### Running command: ### ### E:\biocbuild\bbs-3.21-bioc\R\bin\R.exe CMD INSTALL goSorensen ### ############################################################################## ############################################################################## * installing to library 'E:/biocbuild/bbs-3.21-bioc/R/library' * installing *source* package 'goSorensen' ... ** using staged installation Warning in person1(given = given[[i]], family = family[[i]], middle = middle[[i]], : Invalid ORCID iD: '0000-0002-4736-699'. ** R ** data ** inst ** byte-compile and prepare package for lazy loading ** help *** installing help indices ** building package indices ** installing vignettes ** testing if installed package can be loaded from temporary location ** testing if installed package can be loaded from final location ** testing if installed package keeps a record of temporary installation path * DONE (goSorensen)
goSorensen.Rcheck/tests/test_gosorensen_funcs.Rout
R Under development (unstable) (2024-10-26 r87273 ucrt) -- "Unsuffered Consequences"
Copyright (C) 2024 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(goSorensen)
Attaching package: 'goSorensen'
The following object is masked from 'package:utils':
upgrade
>
> # A contingency table of GO terms mutual enrichment
> # between gene lists "atlas" and "sanger":
> data(tab_atlas.sanger_BP3)
> tab_atlas.sanger_BP3
Enriched in sanger
Enriched in atlas TRUE FALSE
TRUE 38 31
FALSE 2 452
> ?tab_atlas.sanger_BP3
> class(tab_atlas.sanger_BP3)
[1] "table"
>
> # Sorensen-Dice dissimilarity on this contingency table:
> ?dSorensen
> dSorensen(tab_atlas.sanger_BP3)
[1] 0.3027523
>
> # Standard error of this Sorensen-Dice dissimilarity estimate:
> ?seSorensen
> seSorensen(tab_atlas.sanger_BP3)
[1] 0.05058655
>
> # Upper 95% confidence limit for the Sorensen-Dice dissimilarity:
> ?duppSorensen
> duppSorensen(tab_atlas.sanger_BP3)
[1] 0.3859598
> # This confidence limit is based on an assimptotic normal N(0,1)
> # approximation to the distribution of (dSampl - d) / se, where
> # dSampl stands for the sample dissimilarity, d for the true dissimilarity
> # and se for the sample dissimilarity standard error estimate.
>
> # Upper confidence limit but using a Student's t instead of a N(0,1)
> # (just as an example, not recommended -no theoretical justification)
> df <- sum(tab_atlas.sanger_BP3[1:3]) - 2
> duppSorensen(tab_atlas.sanger_BP3, z.conf.level = qt(1 - 0.95, df))
[1] 0.3870921
>
> # Upper confidence limit but using a bootstrap approximation
> # to the sampling distribution, instead of a N(0,1)
> set.seed(123)
> duppSorensen(tab_atlas.sanger_BP3, boot = TRUE)
[1] 0.3941622
attr(,"eff.nboot")
[1] 10000
>
> # Some computations on diverse data structures:
> badConti <- as.table(matrix(c(501, 27, 36, 12, 43, 15, 0, 0, 0),
+ nrow = 3, ncol = 3,
+ dimnames = list(c("a1","a2","a3"),
+ c("b1", "b2","b3"))))
> tryCatch(nice2x2Table(badConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(badConti): Not a 2x2 table>
>
> incompleteConti <- badConti[1,1:min(2,ncol(badConti)), drop = FALSE]
> incompleteConti
b1 b2
a1 501 12
> tryCatch(nice2x2Table(incompleteConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(incompleteConti): Not a 2x2 table>
>
> contiAsVector <- c(32, 21, 81, 1439)
> nice2x2Table(contiAsVector)
[1] TRUE
> contiAsVector.mat <- matrix(contiAsVector, nrow = 2)
> contiAsVector.mat
[,1] [,2]
[1,] 32 81
[2,] 21 1439
> contiAsVectorLen3 <- c(32, 21, 81)
> nice2x2Table(contiAsVectorLen3)
[1] TRUE
>
> tryCatch(dSorensen(badConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(x): Not a 2x2 table>
>
> # Apparently, the next order works fine, but returns a wrong value!
> dSorensen(badConti, check.table = FALSE)
[1] 0.05915493
>
> tryCatch(dSorensen(incompleteConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(x): Not a 2x2 table>
> dSorensen(contiAsVector)
[1] 0.6144578
> dSorensen(contiAsVector.mat)
[1] 0.6144578
> dSorensen(contiAsVectorLen3)
[1] 0.6144578
> dSorensen(contiAsVectorLen3, check.table = FALSE)
[1] 0.6144578
> dSorensen(c(0,0,0,45))
[1] NaN
>
> tryCatch(seSorensen(badConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(x): Not a 2x2 table>
> tryCatch(seSorensen(incompleteConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(x): Not a 2x2 table>
> seSorensen(contiAsVector)
[1] 0.04818012
> seSorensen(contiAsVector.mat)
[1] 0.04818012
> seSorensen(contiAsVectorLen3)
[1] 0.04818012
> seSorensen(contiAsVectorLen3, check.table = FALSE)
[1] 0.04818012
> tryCatch(seSorensen(contiAsVectorLen3, check.table = "not"), error = function(e) {return(e)})
<simpleError in seSorensen.numeric(contiAsVectorLen3, check.table = "not"): Argument 'check.table' must be logical>
> seSorensen(c(0,0,0,45))
[1] NaN
>
> tryCatch(duppSorensen(badConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(x): Not a 2x2 table>
> tryCatch(duppSorensen(incompleteConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(x): Not a 2x2 table>
> duppSorensen(contiAsVector)
[1] 0.6937071
> duppSorensen(contiAsVector.mat)
[1] 0.6937071
> set.seed(123)
> duppSorensen(contiAsVector, boot = TRUE)
[1] 0.6922658
attr(,"eff.nboot")
[1] 10000
> set.seed(123)
> duppSorensen(contiAsVector.mat, boot = TRUE)
[1] 0.6922658
attr(,"eff.nboot")
[1] 10000
> duppSorensen(contiAsVectorLen3)
[1] 0.6937071
> # Bootstrapping requires full contingency tables (4 values)
> set.seed(123)
> tryCatch(duppSorensen(contiAsVectorLen3, boot = TRUE), error = function(e) {return(e)})
<simpleError in duppSorensen.numeric(contiAsVectorLen3, boot = TRUE): Bootstraping requires a numeric vector of 4 frequencies>
> duppSorensen(c(0,0,0,45))
[1] NaN
>
> # Equivalence test, H0: d >= d0 vs H1: d < d0 (d0 = 0.4444)
> ?equivTestSorensen
> equiv.atlas.sanger <- equivTestSorensen(tab_atlas.sanger_BP3)
> equiv.atlas.sanger
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab_atlas.sanger_BP3
(d - d0) / se = -2.801, p-value = 0.002547
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3859598
sample estimates:
Sorensen dissimilarity
0.3027523
attr(,"se")
standard error
0.05058655
> getTable(equiv.atlas.sanger)
Enriched in sanger
Enriched in atlas TRUE FALSE
TRUE 38 31
FALSE 2 452
> getPvalue(equiv.atlas.sanger)
p-value
0.002547349
>
> tryCatch(equivTestSorensen(badConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(x): Not a 2x2 table>
> tryCatch(equivTestSorensen(incompleteConti), error = function(e) {return(e)})
<simpleError in nice2x2Table.table(x): Not a 2x2 table>
> equivTestSorensen(contiAsVector)
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: contiAsVector
(d - d0) / se = 3.5287, p-value = 0.9998
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6937071
sample estimates:
Sorensen dissimilarity
0.6144578
attr(,"se")
standard error
0.04818012
> equivTestSorensen(contiAsVector.mat)
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: contiAsVector.mat
(d - d0) / se = 3.5287, p-value = 0.9998
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6937071
sample estimates:
Sorensen dissimilarity
0.6144578
attr(,"se")
standard error
0.04818012
> set.seed(123)
> equivTestSorensen(contiAsVector.mat, boot = TRUE)
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: contiAsVector.mat
(d - d0) / se = 3.5287, p-value = 0.9996
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6922658
sample estimates:
Sorensen dissimilarity
0.6144578
attr(,"se")
standard error
0.04818012
> equivTestSorensen(contiAsVectorLen3)
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: contiAsVectorLen3
(d - d0) / se = 3.5287, p-value = 0.9998
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6937071
sample estimates:
Sorensen dissimilarity
0.6144578
attr(,"se")
standard error
0.04818012
>
> tryCatch(equivTestSorensen(contiAsVectorLen3, boot = TRUE), error = function(e) {return(e)})
<simpleError in equivTestSorensen.numeric(contiAsVectorLen3, boot = TRUE): Bootstraping requires a numeric vector of 4 frequencies>
>
> equivTestSorensen(c(0,0,0,45))
No test performed due non finite (d - d0) / se statistic
data: c(0, 0, 0, 45)
(d - d0) / se = NaN, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
NaN
attr(,"se")
standard error
NaN
>
> # Sorensen-Dice computations from scratch, directly from gene lists
> data(allOncoGeneLists)
> ?allOncoGeneLists
>
> library(org.Hs.eg.db)
Loading required package: AnnotationDbi
Loading required package: stats4
Loading required package: BiocGenerics
Loading required package: generics
Attaching package: 'generics'
The following objects are masked from 'package:base':
as.difftime, as.factor, as.ordered, intersect, is.element, setdiff,
setequal, union
Attaching package: 'BiocGenerics'
The following objects are masked from 'package:stats':
IQR, mad, sd, var, xtabs
The following objects are masked from 'package:base':
Filter, Find, Map, Position, Reduce, anyDuplicated, aperm, append,
as.data.frame, basename, cbind, colnames, dirname, do.call,
duplicated, eval, evalq, get, grep, grepl, is.unsorted, lapply,
mapply, match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
rank, rbind, rownames, sapply, saveRDS, table, tapply, unique,
unsplit, which.max, which.min
Loading required package: Biobase
Welcome to Bioconductor
Vignettes contain introductory material; view with
'browseVignettes()'. To cite Bioconductor, see
'citation("Biobase")', and for packages 'citation("pkgname")'.
Loading required package: IRanges
Loading required package: S4Vectors
Attaching package: 'S4Vectors'
The following object is masked from 'package:utils':
findMatches
The following objects are masked from 'package:base':
I, expand.grid, unname
Attaching package: 'IRanges'
The following object is masked from 'package:grDevices':
windows
> humanEntrezIDs <- keys(org.Hs.eg.db, keytype = "ENTREZID")
> # First, the mutual GO node enrichment tables are built, then computations
> # proceed from these contingency tables.
> # Building the contingency tables is a slow process (many enrichment tests)
> normTest <- equivTestSorensen(allOncoGeneLists[["atlas"]], allOncoGeneLists[["sanger"]],
+ listNames = c("atlas", "sanger"),
+ onto = "BP", GOLevel = 5,
+ geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> normTest
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -7.6163, p-value = 1.306e-14
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3604408
sample estimates:
Sorensen dissimilarity
0.3373016
attr(,"se")
standard error
0.01406763
>
> # To perform a bootstrap test from scratch would be even slower:
> # set.seed(123)
> # bootTest <- equivTestSorensen(allOncoGeneLists[["atlas"]], allOncoGeneLists[["sanger"]],
> # listNames = c("atlas", "sanger"),
> # boot = TRUE,
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> # bootTest
>
> # It is much faster to upgrade 'normTest' to be a bootstrap test:
> set.seed(123)
> bootTest <- upgrade(normTest, boot = TRUE)
> bootTest
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -7.6163, p-value = 9.999e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3604667
sample estimates:
Sorensen dissimilarity
0.3373016
attr(,"se")
standard error
0.01406763
> # To know the number of planned bootstrap replicates:
> getNboot(bootTest)
[1] 10000
> # To know the number of valid bootstrap replicates:
> getEffNboot(bootTest)
[1] 10000
>
> # There are similar methods for dSorensen, seSorensen, duppSorensen, etc. to
> # compute directly from a pair of gene lists.
> # They are quite slow for the same reason as before (many enrichment tests).
> # dSorensen(allOncoGeneLists[["atlas"]], allOncoGeneLists[["sanger"]],
> # listNames = c("atlas", "sanger"),
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> # seSorensen(allOncoGeneLists[["atlas"]], allOncoGeneLists[["sanger"]],
> # listNames = c("atlas", "sanger"),
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> #
> # duppSorensen(allOncoGeneLists[["atlas"]], allOncoGeneLists[["sanger"]],
> # listNames = c("atlas", "sanger"),
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> #
> # set.seed(123)
> # duppSorensen(allOncoGeneLists[["atlas"]], allOncoGeneLists[["sanger"]],
> # boot = TRUE,
> # listNames = c("atlas", "sanger"),
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> # etc.
>
> # To build the contingency table first and then compute from it, may be a more flexible
> # and saving time strategy, in general:
> ?buildEnrichTable
> tab <- buildEnrichTable(allOncoGeneLists[["atlas"]], allOncoGeneLists[["sanger"]],
+ listNames = c("atlas", "sanger"),
+ onto = "BP", GOLevel = 5,
+ geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
>
> tab
Enriched in sanger
Enriched in atlas TRUE FALSE
TRUE 501 458
FALSE 52 9463
>
> # (Here, an obvious faster possibility would be to recover the enrichment contingency
> # table from the previous normal test result:)
> tab <- getTable(normTest)
> tab
Enriched in sanger
Enriched in atlas TRUE FALSE
TRUE 501 458
FALSE 52 9463
>
> tst <- equivTestSorensen(tab)
> tst
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -7.6163, p-value = 1.306e-14
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3604408
sample estimates:
Sorensen dissimilarity
0.3373016
attr(,"se")
standard error
0.01406763
> set.seed(123)
> bootTst <- equivTestSorensen(tab, boot = TRUE)
> bootTst
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -7.6163, p-value = 9.999e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3604667
sample estimates:
Sorensen dissimilarity
0.3373016
attr(,"se")
standard error
0.01406763
>
> dSorensen(tab)
[1] 0.3373016
> seSorensen(tab)
[1] 0.01406763
> # or:
> getDissimilarity(tst)
Sorensen dissimilarity
0.3373016
attr(,"se")
standard error
0.01406763
>
> duppSorensen(tab)
[1] 0.3604408
> getUpper(tst)
dUpper
0.3604408
>
> set.seed(123)
> duppSorensen(tab, boot = TRUE)
[1] 0.3604667
attr(,"eff.nboot")
[1] 10000
> getUpper(bootTst)
dUpper
0.3604667
>
> # To perform from scratch all pairwise tests (or other Sorensen-Dice computations)
> # is even much slower. For example, all pairwise...
> # Dissimilarities:
> # # allPairDiss <- dSorensen(allOncoGeneLists,
> # # onto = "BP", GOLevel = 5,
> # # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> # # allPairDiss
> #
> # # Still time consuming but faster: build all tables computing in parallel:
> # allPairDiss <- dSorensen(allOncoGeneLists,
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db",
> # parallel = TRUE)
> # allPairDiss
>
> # Standard errors:
> # seSorensen(allOncoGeneLists,
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> #
> # Upper confidence interval limits:
> # duppSorensen(allOncoGeneLists,
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> # All pairwise asymptotic normal tests:
> # allTests <- equivTestSorensen(allOncoGeneLists,
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> # getPvalue(allTests, simplify = FALSE)
> # getPvalue(allTests)
> # p.adjust(getPvalue(allTests), method = "holm")
> # To perform all pairwise bootstrap tests from scratch is (slightly)
> # even more time consuming:
> # set.seed(123)
> # allBootTests <- equivTestSorensen(allOncoGeneLists,
> # boot = TRUE,
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> # Not all bootstrap replicates may conduct to finite statistics:
> # getNboot(allBootTests)
>
> # Given the normal tests (object 'allTests'), it is much faster to upgrade
> # it to have the bootstrap tests:
> # set.seed(123)
> # allBootTests <- upgrade(allTests, boot = TRUE)
> # getPvalue(allBootTests, simplify = FALSE)
>
> # Again, the faster and more flexible possibility may be:
> # 1) First, build all pairwise enrichment contingency tables (slow first step):
> # allTabsBP.4 <- buildEnrichTable(allOncoGeneLists,
> # onto = "BP", GOLevel = 5,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db")
> # allTabsBP.4
>
> # Better, directly use the dataset available at this package, goSorensen:
> data(allTabsBP.4)
> allTabsBP.4
$cangenes
$cangenes$atlas
Enriched in atlas
Enriched in cangenes TRUE FALSE
TRUE 0 0
FALSE 420 3383
attr(,"onto")
[1] "BP"
attr(,"GOLevel")
[1] 4
$cis
$cis$atlas
Enriched in atlas
Enriched in cis TRUE FALSE
TRUE 80 3
FALSE 340 3380
$cis$cangenes
Enriched in cangenes
Enriched in cis TRUE FALSE
TRUE 0 83
FALSE 0 3720
attr(,"onto")
[1] "BP"
attr(,"GOLevel")
[1] 4
$miscellaneous
$miscellaneous$atlas
Enriched in atlas
Enriched in miscellaneous TRUE FALSE
TRUE 198 21
FALSE 222 3362
$miscellaneous$cangenes
Enriched in cangenes
Enriched in miscellaneous TRUE FALSE
TRUE 0 219
FALSE 0 3584
attr(,"onto")
[1] "BP"
attr(,"GOLevel")
[1] 4
$miscellaneous$cis
Enriched in cis
Enriched in miscellaneous TRUE FALSE
TRUE 70 149
FALSE 13 3571
$sanger
$sanger$atlas
Enriched in atlas
Enriched in sanger TRUE FALSE
TRUE 209 24
FALSE 211 3359
$sanger$cangenes
Enriched in cangenes
Enriched in sanger TRUE FALSE
TRUE 0 233
FALSE 0 3570
attr(,"onto")
[1] "BP"
attr(,"GOLevel")
[1] 4
$sanger$cis
Enriched in cis
Enriched in sanger TRUE FALSE
TRUE 68 165
FALSE 15 3555
$sanger$miscellaneous
Enriched in miscellaneous
Enriched in sanger TRUE FALSE
TRUE 151 82
FALSE 68 3502
$Vogelstein
$Vogelstein$atlas
Enriched in atlas
Enriched in Vogelstein TRUE FALSE
TRUE 220 32
FALSE 200 3351
$Vogelstein$cangenes
Enriched in cangenes
Enriched in Vogelstein TRUE FALSE
TRUE 0 252
FALSE 0 3551
attr(,"onto")
[1] "BP"
attr(,"GOLevel")
[1] 4
$Vogelstein$cis
Enriched in cis
Enriched in Vogelstein TRUE FALSE
TRUE 68 184
FALSE 15 3536
$Vogelstein$miscellaneous
Enriched in miscellaneous
Enriched in Vogelstein TRUE FALSE
TRUE 156 96
FALSE 63 3488
$Vogelstein$sanger
Enriched in sanger
Enriched in Vogelstein TRUE FALSE
TRUE 217 35
FALSE 16 3535
$waldman
$waldman$atlas
Enriched in atlas
Enriched in waldman TRUE FALSE
TRUE 264 39
FALSE 156 3344
$waldman$cangenes
Enriched in cangenes
Enriched in waldman TRUE FALSE
TRUE 0 303
FALSE 0 3500
attr(,"onto")
[1] "BP"
attr(,"GOLevel")
[1] 4
$waldman$cis
Enriched in cis
Enriched in waldman TRUE FALSE
TRUE 77 226
FALSE 6 3494
$waldman$miscellaneous
Enriched in miscellaneous
Enriched in waldman TRUE FALSE
TRUE 203 100
FALSE 16 3484
$waldman$sanger
Enriched in sanger
Enriched in waldman TRUE FALSE
TRUE 181 122
FALSE 52 3448
$waldman$Vogelstein
Enriched in Vogelstein
Enriched in waldman TRUE FALSE
TRUE 192 111
FALSE 60 3440
attr(,"onto")
[1] "BP"
attr(,"GOLevel")
[1] 4
attr(,"class")
[1] "tableList" "list"
> class(allTabsBP.4)
[1] "tableList" "list"
> # 2) Then perform all required computatios from these enrichment contingency tables...
> # All pairwise tests:
> allTests <- equivTestSorensen(allTabsBP.4)
> allTests
$cangenes
$cangenes$atlas
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$cis
$cis$atlas
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = 8.807, p-value = 1
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.7262589
sample estimates:
Sorensen dissimilarity
0.6819085
attr(,"se")
standard error
0.02696312
$cis$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$miscellaneous
$miscellaneous$atlas
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -2.8406, p-value = 0.002252
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.4174355
sample estimates:
Sorensen dissimilarity
0.3802817
attr(,"se")
standard error
0.02258792
$miscellaneous$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$miscellaneous$cis
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = 2.5804, p-value = 0.9951
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.5950555
sample estimates:
Sorensen dissimilarity
0.5364238
attr(,"se")
standard error
0.03564549
$sanger
$sanger$atlas
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -3.8566, p-value = 5.748e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3959452
sample estimates:
Sorensen dissimilarity
0.3598775
attr(,"se")
standard error
0.02192764
$sanger$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$sanger$cis
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = 3.5799, p-value = 0.9998
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6271347
sample estimates:
Sorensen dissimilarity
0.5696203
attr(,"se")
standard error
0.03496631
$sanger$miscellaneous
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -4.3974, p-value = 5.479e-06
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3739718
sample estimates:
Sorensen dissimilarity
0.3318584
attr(,"se")
standard error
0.02560313
$Vogelstein
$Vogelstein$atlas
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -4.6585, p-value = 1.593e-06
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3802668
sample estimates:
Sorensen dissimilarity
0.3452381
attr(,"se")
standard error
0.02129595
$Vogelstein$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$Vogelstein$cis
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = 4.4076, p-value = 1
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6498536
sample estimates:
Sorensen dissimilarity
0.5940299
attr(,"se")
standard error
0.03393844
$Vogelstein$miscellaneous
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -4.2339, p-value = 1.148e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3790962
sample estimates:
Sorensen dissimilarity
0.3375796
attr(,"se")
standard error
0.02524032
$Vogelstein$sanger
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -23.128, p-value < 2.2e-16
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.1292852
sample estimates:
Sorensen dissimilarity
0.1051546
attr(,"se")
standard error
0.01467036
$waldman
$waldman$atlas
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -9.3848, p-value < 2.2e-16
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3003348
sample estimates:
Sorensen dissimilarity
0.2697095
attr(,"se")
standard error
0.01861884
$waldman$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$waldman$cis
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = 4.9573, p-value = 1
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6529946
sample estimates:
Sorensen dissimilarity
0.6010363
attr(,"se")
standard error
0.03158842
$waldman$miscellaneous
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -11.029, p-value < 2.2e-16
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.2553636
sample estimates:
Sorensen dissimilarity
0.2222222
attr(,"se")
standard error
0.02014852
$waldman$sanger
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -5.1402, p-value = 1.372e-07
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3629683
sample estimates:
Sorensen dissimilarity
0.3246269
attr(,"se")
standard error
0.02330993
$waldman$Vogelstein
Normal asymptotic test for 2x2 contingency tables based on the
Sorensen-Dice dissimilarity
data: tab
(d - d0) / se = -6.0739, p-value = 6.243e-10
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.000000 0.345029
sample estimates:
Sorensen dissimilarity
0.3081081
attr(,"se")
standard error
0.02244631
attr(,"class")
[1] "equivSDhtestList" "list"
> class(allTests)
[1] "equivSDhtestList" "list"
> set.seed(123)
> allBootTests <- equivTestSorensen(allTabsBP.4, boot = TRUE)
> allBootTests
$cangenes
$cangenes$atlas
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$cis
$cis$atlas
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = 8.807, p-value = 1
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.000000 0.725535
sample estimates:
Sorensen dissimilarity
0.6819085
attr(,"se")
standard error
0.02696312
$cis$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$miscellaneous
$miscellaneous$atlas
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -2.8406, p-value = 0.004
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.000000 0.418077
sample estimates:
Sorensen dissimilarity
0.3802817
attr(,"se")
standard error
0.02258792
$miscellaneous$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$miscellaneous$cis
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = 2.5804, p-value = 0.9933
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.000000 0.595412
sample estimates:
Sorensen dissimilarity
0.5364238
attr(,"se")
standard error
0.03564549
$sanger
$sanger$atlas
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -3.8566, p-value = 3e-04
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3960626
sample estimates:
Sorensen dissimilarity
0.3598775
attr(,"se")
standard error
0.02192764
$sanger$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$sanger$cis
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = 3.5799, p-value = 0.9996
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6278561
sample estimates:
Sorensen dissimilarity
0.5696203
attr(,"se")
standard error
0.03496631
$sanger$miscellaneous
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -4.3974, p-value = 2e-04
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3765829
sample estimates:
Sorensen dissimilarity
0.3318584
attr(,"se")
standard error
0.02560313
$Vogelstein
$Vogelstein$atlas
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -4.6585, p-value = 2e-04
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3809169
sample estimates:
Sorensen dissimilarity
0.3452381
attr(,"se")
standard error
0.02129595
$Vogelstein$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$Vogelstein$cis
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = 4.4076, p-value = 1
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6489965
sample estimates:
Sorensen dissimilarity
0.5940299
attr(,"se")
standard error
0.03393844
$Vogelstein$miscellaneous
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -4.2339, p-value = 9.999e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3796934
sample estimates:
Sorensen dissimilarity
0.3375796
attr(,"se")
standard error
0.02524032
$Vogelstein$sanger
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -23.128, p-value = 9.999e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.1312585
sample estimates:
Sorensen dissimilarity
0.1051546
attr(,"se")
standard error
0.01467036
$waldman
$waldman$atlas
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -9.3848, p-value = 9.999e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3006583
sample estimates:
Sorensen dissimilarity
0.2697095
attr(,"se")
standard error
0.01861884
$waldman$cangenes
No test performed due not finite (d - d0) / se statistic
data: tab
(d - d0) / se = Inf, p-value = NA
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0 NaN
sample estimates:
Sorensen dissimilarity
1
attr(,"se")
standard error
0
$waldman$cis
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = 4.9573, p-value = 1
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.6525683
sample estimates:
Sorensen dissimilarity
0.6010363
attr(,"se")
standard error
0.03158842
$waldman$miscellaneous
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -11.029, p-value = 9.999e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.2577849
sample estimates:
Sorensen dissimilarity
0.2222222
attr(,"se")
standard error
0.02014852
$waldman$sanger
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -5.1402, p-value = 9.999e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3639666
sample estimates:
Sorensen dissimilarity
0.3246269
attr(,"se")
standard error
0.02330993
$waldman$Vogelstein
Bootstrap test for 2x2 contingency tables based on the Sorensen-Dice
dissimilarity (10000 bootstrap replicates)
data: tab
(d - d0) / se = -6.0739, p-value = 9.999e-05
alternative hypothesis: true equivalence limit d0 is less than 0.4444444
95 percent confidence interval:
0.0000000 0.3470915
sample estimates:
Sorensen dissimilarity
0.3081081
attr(,"se")
standard error
0.02244631
attr(,"class")
[1] "equivSDhtestList" "list"
> class(allBootTests)
[1] "equivSDhtestList" "list"
> getPvalue(allBootTests, simplify = FALSE)
atlas cangenes cis miscellaneous sanger Vogelstein
atlas 0.00000000 NaN 1.0000000 0.00399960 0.00029997 0.00019998
cangenes NaN 0 NaN NaN NaN NaN
cis 1.00000000 NaN 0.0000000 0.99330067 0.99960004 1.00000000
miscellaneous 0.00399960 NaN 0.9933007 0.00000000 0.00019998 0.00009999
sanger 0.00029997 NaN 0.9996000 0.00019998 0.00000000 0.00009999
Vogelstein 0.00019998 NaN 1.0000000 0.00009999 0.00009999 0.00000000
waldman 0.00009999 NaN 1.0000000 0.00009999 0.00009999 0.00009999
waldman
atlas 9.999e-05
cangenes NaN
cis 1.000e+00
miscellaneous 9.999e-05
sanger 9.999e-05
Vogelstein 9.999e-05
waldman 0.000e+00
> getEffNboot(allBootTests)
cangenes.atlas cis.atlas cis.cangenes
NaN 10000 NaN
miscellaneous.atlas miscellaneous.cangenes miscellaneous.cis
10000 NaN 10000
sanger.atlas sanger.cangenes sanger.cis
10000 NaN 10000
sanger.miscellaneous Vogelstein.atlas Vogelstein.cangenes
10000 10000 NaN
Vogelstein.cis Vogelstein.miscellaneous Vogelstein.sanger
10000 10000 10000
waldman.atlas waldman.cangenes waldman.cis
10000 NaN 10000
waldman.miscellaneous waldman.sanger waldman.Vogelstein
10000 10000 10000
>
> # To adjust for testing multiplicity:
> p.adjust(getPvalue(allBootTests), method = "holm")
cangenes.atlas.p-value cis.atlas.p-value
NaN 1.00000000
cis.cangenes.p-value miscellaneous.atlas.p-value
NaN 0.02399760
miscellaneous.cangenes.p-value miscellaneous.cis.p-value
NaN 1.00000000
sanger.atlas.p-value sanger.cangenes.p-value
0.00209979 NaN
sanger.cis.p-value sanger.miscellaneous.p-value
1.00000000 0.00179982
Vogelstein.atlas.p-value Vogelstein.cangenes.p-value
0.00179982 NaN
Vogelstein.cis.p-value Vogelstein.miscellaneous.p-value
1.00000000 0.00149985
Vogelstein.sanger.p-value waldman.atlas.p-value
0.00149985 0.00149985
waldman.cangenes.p-value waldman.cis.p-value
NaN 1.00000000
waldman.miscellaneous.p-value waldman.sanger.p-value
0.00149985 0.00149985
waldman.Vogelstein.p-value
0.00149985
>
> # If only partial statistics are desired:
> dSorensen(allTabsBP.4)
atlas cangenes cis miscellaneous sanger Vogelstein
atlas 0.0000000 1 0.6819085 0.3802817 0.3598775 0.3452381
cangenes 1.0000000 0 1.0000000 1.0000000 1.0000000 1.0000000
cis 0.6819085 1 0.0000000 0.5364238 0.5696203 0.5940299
miscellaneous 0.3802817 1 0.5364238 0.0000000 0.3318584 0.3375796
sanger 0.3598775 1 0.5696203 0.3318584 0.0000000 0.1051546
Vogelstein 0.3452381 1 0.5940299 0.3375796 0.1051546 0.0000000
waldman 0.2697095 1 0.6010363 0.2222222 0.3246269 0.3081081
waldman
atlas 0.2697095
cangenes 1.0000000
cis 0.6010363
miscellaneous 0.2222222
sanger 0.3246269
Vogelstein 0.3081081
waldman 0.0000000
> duppSorensen(allTabsBP.4)
atlas cangenes cis miscellaneous sanger Vogelstein
atlas 0.0000000 NaN 0.7262589 0.4174355 0.3959452 0.3802668
cangenes NaN 0 NaN NaN NaN NaN
cis 0.7262589 NaN 0.0000000 0.5950555 0.6271347 0.6498536
miscellaneous 0.4174355 NaN 0.5950555 0.0000000 0.3739718 0.3790962
sanger 0.3959452 NaN 0.6271347 0.3739718 0.0000000 0.1292852
Vogelstein 0.3802668 NaN 0.6498536 0.3790962 0.1292852 0.0000000
waldman 0.3003348 NaN 0.6529946 0.2553636 0.3629683 0.3450290
waldman
atlas 0.3003348
cangenes NaN
cis 0.6529946
miscellaneous 0.2553636
sanger 0.3629683
Vogelstein 0.3450290
waldman 0.0000000
> seSorensen(allTabsBP.4)
atlas cangenes cis miscellaneous sanger
atlas 0.00000000 0 0.02696312 0.02258792 0.02192764
cangenes 0.00000000 0 0.00000000 0.00000000 0.00000000
cis 0.02696312 0 0.00000000 0.03564549 0.03496631
miscellaneous 0.02258792 0 0.03564549 0.00000000 0.02560313
sanger 0.02192764 0 0.03496631 0.02560313 0.00000000
Vogelstein 0.02129595 0 0.03393844 0.02524032 0.01467036
waldman 0.01861884 0 0.03158842 0.02014852 0.02330993
Vogelstein waldman
atlas 0.02129595 0.01861884
cangenes 0.00000000 0.00000000
cis 0.03393844 0.03158842
miscellaneous 0.02524032 0.02014852
sanger 0.01467036 0.02330993
Vogelstein 0.00000000 0.02244631
waldman 0.02244631 0.00000000
>
>
> # Tipically, in a real study it would be interesting to scan tests
> # along some ontologies and levels inside these ontologies:
> # (which obviously will be a quite slow process)
> # gc()
> # set.seed(123)
> # allBootTests_BP_MF_lev4to8 <- allEquivTestSorensen(allOncoGeneLists,
> # boot = TRUE,
> # geneUniverse = humanEntrezIDs, orgPackg = "org.Hs.eg.db",
> # ontos = c("BP", "MF"), GOLevels = 4:8)
> # getPvalue(allBootTests_BP_MF_lev4to8)
> # getEffNboot(allBootTests_BP_MF_lev4to8)
>
> proc.time()
user system elapsed
206.48 21.21 228.01
goSorensen.Rcheck/goSorensen-Ex.timings
| name | user | system | elapsed | |
| allBuildEnrichTable | 0 | 0 | 0 | |
| allEquivTestSorensen | 0.31 | 0.06 | 0.38 | |
| allHclustThreshold | 0.08 | 0.00 | 0.08 | |
| allSorenThreshold | 0.11 | 0.00 | 0.11 | |
| buildEnrichTable | 69.45 | 4.30 | 76.56 | |
| dSorensen | 0.17 | 0.05 | 0.99 | |
| duppSorensen | 0.20 | 0.04 | 0.25 | |
| enrichedIn | 63.33 | 3.58 | 66.94 | |
| equivTestSorensen | 0.52 | 0.02 | 0.53 | |
| getDissimilarity | 0.31 | 0.12 | 0.48 | |
| getEffNboot | 1.50 | 0.11 | 1.61 | |
| getNboot | 1.28 | 0.06 | 1.38 | |
| getPvalue | 0.33 | 0.11 | 0.43 | |
| getSE | 0.25 | 0.17 | 0.43 | |
| getTable | 0.44 | 0.11 | 0.54 | |
| getUpper | 0.33 | 0.24 | 0.56 | |
| hclustThreshold | 270.29 | 25.95 | 296.24 | |
| nice2x2Table | 0 | 0 | 0 | |
| seSorensen | 0 | 0 | 0 | |
| sorenThreshold | 0.26 | 0.06 | 0.33 | |
| upgrade | 1.14 | 0.13 | 1.32 | |