gireeshkbogu

# Aim: Identifying genes that are at least 2 fold higher mRNA levels (FPKM) in a particular tissue as 
# -compared to all other tissues. 

# Author: Gireesh Bogu
# Date: Jun 25th, 2017
# Location: CRG, Barcelona

# Problem: How to idenitfy tissue-specific genes especially when you have 
# - large number of tissues (>50) and even larger number of samples per tissue (>100 for example).
# GTEx (2) has 53 tissue sites and each tissue site has 10 to 400 samples

gireeshkbogu

# Author: Gireesh Bogu                                                                   
# Location: CRG, Barcelona                                                               
# Date: June 1, 2017                                                                     

#@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@

# what it does: joins multiple files (by using their location instead of specifying each file name) with --
# ---similar repeat_ids and renames the columns with file names.                                          

# file1 =  SRRX10101

gireeshkbogu

# Author: Gireesh Bogu, Date: 27th May 2017, Place: CRG, Barcelona

# worked on a file with 200 million rows and 3 columns (50 GB file) (Python 2.7)
# make sure the file has 3 columns with a proper header
# make sure there are no duplicates in the file
# make sure the file is tab delimited
###################################################################################

# USE THIS IF IT IS NOT A BIG FILE
import pandas as pd

gireeshkbogu

# How to plot a BIG data set (600 million rows/values with 8555 keys)
# Use the follow example!!

library(dplyr)
library(ggplot2)

data(diamonds)

# plot density of different keys
ggplot(diamonds, aes(x=depth)) + geom_line(aes(color= cut), stat="density", size=0.4, alpha=0.4)

gireeshkbogu

# Author: Gireesh Bogu
# Location: Barcelona
# Time: Dec 21, 2016

# Aim-1 [Accomplished]: Sending Flat Rental And Utilities Bills To My Forgetful Flatmate Every First Day Of The Month :/
# Aim-2 [Pending]: Calculating bills from the bank account automatically (This is tricky because of two reasons: (1) probably bank information is hard to access and (2) bills timing on bank statemenet often do not match with the actual monthly bills)
# Aim-3 [Pending]: Aim-1 is using gmail but it is nice to extend this to Facebook as she checks it more often than gmail ;)

# Add the below usage code to crontab (open it using this command: crontab -e)
# Usage: * 09 1 * * /fullpath/annoyingFlatmateAlerts.py (sends email at 9 A.M at every first day of the month)

gireeshkbogu

# see below for UPDATES that include more shorter ways of conversions

# How to convert GTF format into BED12 format (Human-hg19)?
# How to convert GTF or BED format into BIGBED format?
# Why BIGBED (If GTF or BED file is very large to upload in UCSC, you can use trackHubs. However trackHubs do not accept either of the formats. Therefore you would need bigBed format)

# First, download UCSC scripts
wget http://hgdownload.cse.ucsc.edu/admin/exe/linux.x86_64/gtfToGenePred
wget http://hgdownload.cse.ucsc.edu/admin/exe/linux.x86_64/genePredToBed
wget http://hgdownload.cse.ucsc.edu/admin/exe/linux.x86_64/bedToBigBed

gireeshkbogu

wget https://github.com/downloads/taoliu/MACS/MACS-1.4.2-1.tar.gz

tar -zxvf MACS-1.4.2-1.tar.gz

python setup.py install --prefix /users/rg/gbogu/software/MACS-1.4.2

export PYTHONPATH=/users/rg/gbogu/software/MACS-1.4.2/lib/python2.7/site-packages/:$PYTHONPATH

export PATH="/users/rg/gbogu/software/MACS-1.4.2/bin/:$PATH"

gireeshkbogu

library(pheatmap)

a <-read.table("expression", head=T)
head(a)
                GTEX.ZP4G.0526.SM.4YCED GTEX.ZYFD.2126.SM.5E43D
a1                3.469363                2.903798
a2                2.551825               -1.003092
a3                 2.841332                2.903798
a6                 4.936489                5.225726
a7                 6.300763                6.574336

gireeshkbogu

MYdata <- data.frame(Age = rep(c(0,1,3,6,9,12), each=20),
                    Richness = rnorm(120, 10000, 2500))



ggplot(data = MYdata, aes(x = Age, y = Richness)) + 
  geom_boxplot(aes(fill=factor(Age))) + 
  geom_point(aes(color = factor(Age))) +
  scale_x_continuous(breaks = c(0, 1, 3, 6, 9, 12)) +

gireeshkbogu

library(ggplot2)
ggplot(mtcars, aes(x=wt, y=disp, colour=cyl, size=gear)) + 
  geom_point(shape=19, alpha=0.8)+ scale_colour_gradientn(colours=rainbow(10)) + 
  stat_smooth( method="lm", size=0.5, colour="black")