crazyhottommy

library(Biobase)
library(GEOquery)


# load series and platform data from GEO

gset <- getGEO("GSE34412", GSEMatrix =TRUE)
gset<- gset[[1]]

# make proper column names to match toptable 

crazyhottommy

with open ("C:/Users/Tang Ming/Desktop/anotation.txt", "r") as annotation:
    anotation_dict = {}
    for line in annotation:
        line = line.split()
        if line: #test whether it is an empty line
            anotation_dict[line[0]]=line[1:]
        else:
            continue

# really should not parse the fasta file by myself. there are

crazyhottommy

#linux commands basics
#http://software-carpentry.org/v5/novice/shell/index.html
# practise, practise, practise, google, google, google and you will get it :)

pwd  # print working directory
cd   # change directory
sudo  # super user privilege
chmod 775 # change the privileges  http://en.wikipedia.org/wiki/Chmod
git clone # version control! get to know git and github! http://git-scm.com/ 
sudo bash  # bad habit

crazyhottommy

#2014 MSU NGS R basics tutorial
#http://angus.readthedocs.org/en/2014/R_Introductory_tutorial_2014.html
#https://github.com/jrherr/quick_basic_R_tutorial/blob/master/R_tutorial.md

#pick one language, and learn it well!

#pick up a dataset, play with it!

#object-oriented programming
#functional programming

crazyhottommy

!# /usr/bin/bash
while read name
do
    echo "Name read from file - $name"
    touch $name
done < $1

crazyhottommy

for fspec1 in *.gz
do
#echo $fspec1
fspec2=$(echo ${fspec1} | sed "s/\([1-4]egg\)_r\([1-2]\)_0\([1-2]\)_sub.fastq.gz/\1_R\3_00\2.fastq.gz/")
echo $fspec2
mv ${fspec1} ${fspec2}
done

crazyhottommy

#! /usr/bin/env python

# ID mapping using mygene
# https://pypi.python.org/pypi/mygene
# http://nbviewer.ipython.org/gist/newgene/6771106
# http://mygene-py.readthedocs.org/en/latest/
# 08/30/14

__author__ = 'tommy'

crazyhottommy

##### use bioconductor annotation packages #######

source("http://Bioconductor.org/biocLite.R")
biocLite("org.Hs.eg.db")
biocLite(c("GenomicFeatures", "AnnotationDbi"))

library("org.Hs.eg.db")
library("AnnotationDbi")
library("GenomicFeatures")

crazyhottommy

library(dplyr)
setwd("/home/tommy/annotations/human/ensemble/")

# set the colClasses for faster reading in the data
gtf_cols <- c(seqname="factor", source="factor", feature="factor",
              start="integer", end="integer", score="character",
              strand="factor", frame="factor", attribute="character")

hs_gtf <- read.delim('Homo_sapiens.GRCh37.74.gtf.gz', header=FALSE,
                     col.names=names(gtf_cols), comment.char="#")

crazyhottommy

#! /bin/bash

for bam in *bam
do 
echo $bam 
genomeCoverageBed -ibam $bam -bg -g hg19.genome.info > $(basename $bam .bam).bdg
done

for bdg in *bdg
do