tgirke

##################################################
## Create mappability file for reference genome ##
##################################################
## Thomas Girke
## Date: May 16, 2018
## PeakSeq docs: 
##   https://github.com/gersteinlab/PeakSeq
##   http://gensoft.pasteur.fr/docs/PeakSeq/1.1/PeakSeq.readme

## Note: mappability step should be skipped in newer version of PeakSeq

tgirke

How to Setup and Maintain Jekyll Doc Theme

---

Table of Content

1. Install
2. Run Jekyll server locally (optional)
3. Maintain site
4. Miscellaneous items

tgirke

x <- 1:12

tgirke

########################################
## Import of DrugBank Annotation Data ##
########################################
## Function to import DrugBank XML to data.frame
## Last step gives error. To debug, the following function may help.
## Note, this functions needs some major speed improvements. Ideally,
## it should be replaced with a standard XML import method. 
## (1) Download
##     - download DrugBank XML (https://www.drugbank.ca/releases/latest)
##     - name uncompressed file 'drugbank.xml'

tgirke

Maintain Bioconductor Package on GitHub

---

Table of Content

1. Overview
2. Script to create/update Bioc branches
3. Create GitHub repository of your package
4. Commit changes to GitHub and Bioc SVN
5. Update repository after a new Bioconductor release

tgirke

#####################################
## Quality Trimming of FASTQ Reads ##
#####################################
## Author: Thomas Girke
## Last update: May 30, 2016
## Usage of below function combined with preprocessReads form systemPipeR:
# qcTrim <- "qualityTrimming(fq, phred_cutoff=20, cutoff_occurrences=1, N_cutoff=1, minreadlength=100)"
# preprocessReads(args=args, Fct=qcTrim, batchsize=100000, overwrite=TRUE, compress=TRUE)

## Arguments: 

tgirke

Project Name

TODO: Write a project description

Installation

TODO: Describe the installation process

Usage

tgirke

############################
## appendCounter Function ##
############################
## Author: Thomas Girke
## Last update: 04-Oct-15

## Function to append occurrence counter to entries in character 
## vector and return the results as named vector where the 
## original data are in the same order in the data slot
## and the counting result in the name slot.

tgirke

#############################
## Source R code from Gist ##
#############################
## Display code snippet as raw by pressing Raw button on top right corner of Gist
## Save URL in address bar of browser
# library(RCurl)
## (a) Source specific commit of code
# source(textConnection(getURL("https://gist.githubusercontent.com/tgirke/c26daac0f647f1732a58/raw/521292eca2d4daeab8911df2552f0c55b0e58e6b/Source_Gist_in_R")))
## (b) Source latest version of code (delete commit ID in URL after .../raw/...)
# source(textConnection(getURL("https://gist.githubusercontent.com/tgirke/c26daac0f647f1732a58/raw/Source_Gist_in_R")))

tgirke

my_frame[!duplicated(my_frame[,2]),] # Removes rows with duplicated values in selected column.
my_frame[my_frame$y2 > my_frame$y3,] # Prints all rows of data frame where values of col1 > col2. Comparison operators are: == (equal), != (not equal), >= (greater than or equal), etc. Logical operators are & (and), | (or) and ! (not).
x <- 0.5:10; x[x<1.0] <- -1/x[x<1.0] # Replaces all values in vector or data frame that are below 1 with their reciprocal value.
x <-data.frame(month=month.abb[1:12], AB=LETTERS[1:2], no1=1:48, no2=1:24); x[x$month == "Apr" & (x$no1 == x$no2 | x$no1 > x$no2),] # Prints all records of frame 'x' that contain 'Apr' AND have equal values in columns 'no1' and 'no2' OR have greater values in column 'no1'.
x[x[,1] %in% c("Jun", "Aug"),] # Retrieves rows with column matches specified in a query vector.
x[c(grep("\\d{2}", as.character(x$no1), perl = TRUE)),] # Possibility to print out all rows of a data frame where a regular expression matches (here all double digit values in col 'no1').
x[c(g