mdozmorov

# Source: Additional file 1 from Łabaj, Paweł P., and David P. Kreil. “Sensitivity, Specificity, and Reproducibility of RNA-Seq Differential Expression Calls.” Biology Direct 11, no. 1 (December 20, 2016): 66. doi:10.1186/s13062-016-0169-7.
# https://static-content.springer.com/esm/art%3A10.1186%2Fs13062-016-0169-7/MediaObjects/13062_2016_169_MOESM1_ESM.pdf

samples.fc <- c()
for (x in colnames(data.in)) {
    sampl <- substr(x, 5, 5)
    samples.fc <- c(samples.fc, sampl)
}
group = as.factor(samples.fc)
mod1 = model.matrix(~group)

mdozmorov

# autoloess.R: compute loess metaparameters automatically
# Kyle Gorman <gormanky@ohsu.edu>

aicc.loess <- function(fit) {
    # compute AIC_C for a LOESS fit, from:
    # 
    # Hurvich, C.M., Simonoff, J.S., and Tsai, C. L. 1998. Smoothing 
    # parameter selection in nonparametric regression using an improved 
    # Akaike Information Criterion. Journal of the Royal Statistical 
    # Society B 60: 271–293.

mdozmorov

# Eric Minikel
# CureFFI.org
# 2013-07-04
# Bash script to generate FPKMs from Ensembl Human Bodymap 2.0 RNA-seq data

# Announcement of Human BodyMap 2.0 data availability: http://www.ensembl.info/blog/2011/05/24/human-bodymap-2-0-data-from-illumina/
# BAM list: ftp://ftp.ensembl.org/pub/release-70/bam/homo_sapiens/genebuild/

# STEP 1: DOWNLOAD THE BAMS FROM ENSEMBL

mdozmorov

@article{Dozmorov2012,
abstract = {MOTIVATION: One of the challenges in interpreting high-throughput genomic studies such as a genome-wide associations, microarray or ChIP-seq is their open-ended nature-once a set of experimentally identified regions is identified as statistically significant, at least two questions arise: (i) besides P-value, do any of these significant regions stand out in terms of biological implications? (ii) Does the set of significant regions, as a whole, have anything in common genome wide? These issues are difficult to address because of the growing number of annotated genomic features (e.g. single nucleotide polymorphisms, transcription factor binding sites, methylation peaks, etc.), and it is difficult to know a priori which features would be most fruitful to analyze. Our goal is to provide partial automation of this process to begin examining associations between experimental features and annotated genomic regions in a hypothesis-free, data-driven manner.

RESULTS: We created Genom

mdozmorov

chr1	173191474	173191475	rs2205960
chr10	50110014	50110015	rs7068839
chr10	50110231	50110232	rs7069142
chr10	50119053	50119054	rs1913517
chr10	50120706	50120707	rs6537583
chr10	63803471	63803472	rs12357548
chr10	63805375	63805376	rs12355313
chr10	63805616	63805617	rs4948496
chr10	63805734	63805735	rs6479781
chr10	63811677	63811678	rs10821949

mdozmorov

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

mdozmorov

AN1 = foo
AN2 = bar

#Variable 'an' serves as proxy for a function, executed depending on targer $@
define an
echo $@
touch $@
endef

all:		$(AN1).txt $(AN2).txt