Install

The only pre-requirement is to install biomaRt bioconductor package as it cannot be installed automatically via CRAN.

All other dependencies should be installed when running the install command.

# install bioconductor
## try http:// if https:// URLs are not supported
source("https://bioconductor.org/biocLite.R")
biocLite()

# install the package
biocLite('loose.rock', dependencies = TRUE)

# use the package
library(loose.rock)

Overview

• coding.genes(): downloads protein coding genes from external databases
• gen.synth.xdata(): generate random matrix with pre-determined covariance
• balanced.cv.folds() and balanced.train.and.test(): get balanced train/test sets and cv folds.
• run.cache(): keep cache or results of a function
• proper() : Capitalize string using regexpression
• my.colors() : My own pallete
• my.symbols() : Same with symbols to plots
• … check out rest of Documentation

Libraries required for this vignette

library(dplyr)

Get a current list of protein coding genes

Showing only a random sample of 15

coding.genes() %>%
  arrange(external_gene_name) %>% {
   slice(., sample(seq(nrow(.)), 15)) 
  } %>%
  knitr::kable()
#> Coding genes from biomaRt: 22734 
#>    Coding genes from CCDS: 19632 
#>         Unique in biomaRt: 617 
#>            Unique in CCDS: 1229 
#> -------------------------------
#>                     genes: 23238

Balanced test/train dataset

This is specially relevant in survival or binary output with few cases of one category that need to be well distributed among test/train datasets or in cross-validation folds.

Example below sets aside 90% of the data to the training set. As samples are already divided in two sets (set1 and set2), it performs the 90% separation for each and then joins (with option join.all = T) the result.

set1 <- c(T,T,T,T,T,T,T,T,F,T,T,T,T,T,T,T,T,T,F,T)
set2 <- !set1
cat('Set1\n', set1, '\n\nSet2\n', set2, '\n\nTraining / Test set using logical indices\n\n')
set.seed(1985)
balanced.train.and.test(set1, set2, train.perc = .9)
#
set1 <- which(set1)
set2 <- which(set2)
cat('##### Same sets but using numeric indices\n\n', 'Set1\n', set1, '\n\nSet2\n', set2, '\n\nTraining / Test set using numeric indices\n')
set.seed(1985)
balanced.train.and.test(set1, set2, train.perc = .9)
#
#> Set1
#>  TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE 
#> 
#> Set2
#>  FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE 
#> 
#> Training / Test set using logical indices
#> 
#> $train
#>  [1]  1  2  3  4  5  6  7  8  9 10 11 12 14 15 17 18 20
#> 
#> $test
#> [1] 13 16 19
#> 
#> ##### Same sets but using numeric indices
#> 
#>  Set1
#>  1 2 3 4 5 6 7 8 10 11 12 13 14 15 16 17 18 20 
#> 
#> Set2
#>  9 19 
#> 
#> Training / Test set using numeric indices
#> $train
#>  [1]  1  2  3  4  5  6  7  8  9 10 11 12 14 15 17 18 20
#> 
#> $test
#> [1] 13 16 19

Generate synthetic matrix with covariance

xdata1 <- gen.synth.xdata(10, 5, .2)
xdata2 <- gen.synth.xdata(10, 5, .75)

#> Using .2^|i-j| to generate co-variance matrix
#> X generated
#>             X1         X2         X3          X4           X5
#> 1   0.58312957 -1.4177825 -1.5962307 -0.36925641  0.727465210
#> 2   0.41677037  1.1936101 -0.1339503 -1.76290605 -0.007014473
#> 3   1.42448267  1.4447604 -0.9234123  0.58587981 -1.055072673
#> 4  -1.05432665 -1.2694366 -0.7239440 -0.40329452 -1.907850014
#> 5   0.08636972 -0.1037405 -0.1262496  0.50288158  1.495560595
#> 6  -0.05170387  0.2428157  1.4867422 -0.65335638 -0.790914639
#> 7   1.26205122 -0.3761988  1.2515329 -0.05340056  0.339303448
#> 8  -0.91086475  1.0808547  0.6094629  1.50616045  0.683470155
#> 9  -0.04990854 -0.6898217  0.7417349  1.34572271 -0.007549189
#> 10 -1.70599973 -0.1050608 -0.5856860 -0.69843065  0.522601581
#> cov(X)
#>       X1    X2   X3    X4     X5
#> 1 1.0000 0.200 0.04 0.008 0.0016
#> 2 0.2000 1.000 0.20 0.040 0.0080
#> 3 0.0400 0.200 1.00 0.200 0.0400
#> 4 0.0080 0.040 0.20 1.000 0.2000
#> 5 0.0016 0.008 0.04 0.200 1.0000

#> Using .75^|i-j| to generate co-variance matrix (plotting correlation)
#> X generated
#>            X1          X2         X3          X4          X5
#> 1  -0.5352761  0.01866608 -0.3626905 -0.79410109 -1.23133292
#> 2  -1.3405531 -1.84315073 -1.2186326 -1.21589142 -0.08130708
#> 3   0.1230853 -0.15684536  0.5826062  1.11404563  0.92246564
#> 4   0.3834488  0.27160718  0.4574595 -0.23430815  0.92046339
#> 5  -1.6754005 -0.13201392  0.1192358  0.69832597  0.37141739
#> 6  -0.2885482 -0.74204784 -1.8912859 -0.90740440 -0.70642514
#> 7   0.2785362 -0.59850263 -0.5850362 -0.74983768 -1.57447837
#> 8   1.4110025  1.00281272  1.0552661  1.92476214  1.47005647
#> 9   1.2933359  1.86340386  0.7103639  0.04042754  0.45349389
#> 10  0.3503693  0.31607064  1.1327139  0.12398146 -0.54435325
#> cov(X)
#>          X1       X2     X3       X4        X5
#> 1 1.0000000 0.750000 0.5625 0.421875 0.3164062
#> 2 0.7500000 1.000000 0.7500 0.562500 0.4218750
#> 3 0.5625000 0.750000 1.0000 0.750000 0.5625000
#> 4 0.4218750 0.562500 0.7500 1.000000 0.7500000
#> 5 0.3164062 0.421875 0.5625 0.750000 1.0000000

Save in cache

Uses a cache to save and retrieve results. The cache is automatically created with the arguments and source code for function, so that if any of those changes, the cache is regenerated.

Caution: Files are not deleted so the cache directory can become rather big.

Set a temporary directory to save all caches (optional)

base.dir(tempdir())
#> [1] "/tmp/RtmpSvvxZK"

Run sum function twice

a <- run.cache(sum, 1, 2)
#> Saving in cache: /tmp/RtmpSvvxZK/561a/cache-generic_cache-H_561a43a3af7b265aed512a7995a46f89c382f78fdba4170e569495892b0076ba.RData
b <- run.cache(sum, 1, 2)
#> Loading from cache (not calculating): /tmp/RtmpSvvxZK/561a/cache-generic_cache-H_561a43a3af7b265aed512a7995a46f89c382f78fdba4170e569495892b0076ba.RData
all(a == b)
#> [1] TRUE

Run rnorm function with an explicit seed (otherwise it would return the same random number)

a <- run.cache(rnorm, 5, seed = 1985)
#> Saving in cache: /tmp/RtmpSvvxZK/9636/cache-generic_cache-H_96360922babcb9eeb480fabc9811eab598abaf087c10f3ef49e9093607089531.RData
b <- run.cache(rnorm, 5, seed = 2000)
#> Saving in cache: /tmp/RtmpSvvxZK/ab76/cache-generic_cache-H_ab768ab59eab0e3848e3f5b8c133baaa381eb1e6d5fda439f10847d911b0ace7.RData
all(a == b)
#> [1] FALSE

Proper

One of such is a proper function that capitalizes a string.

x <- "OnE oF sUcH iS a proPer function that capitalizes a string."
proper(x)
#> [1] "One Of Such Is A Proper Function That Capitalizes A String."

Custom colors and symbols

my.colors() and my.symbols() can be used to improve plot readability.

xdata <- -10:10
plot(xdata, 1/10 * xdata * xdata + 1, type="l", pch = my.symbols(1), col = my.colors(1), cex = .9,
     xlab = '', ylab = '', ylim = c(0, 20))
grid(NULL, NULL, lwd = 2) # grid only in y-direction
for (ix in 2:22) {
  points(xdata, 1/10 * xdata * xdata + ix, pch = my.symbols(ix), col = my.colors(ix), cex = .9)
}