nilesh-tawari

#!/usr/bin/env Rscript

################################################
################################################
## REQUIREMENTS                               ##
################################################
################################################

## DIFFERENTIAL ANALYSIS, SCATTERPLOTS AND PCA FOR SAMPLES IN FEATURECOUNTS FILE
		## - FIRST SIX COLUMNS OF FEATURECOUNTS_FILE SHOULD BE INTERVAL INFO. REMAINDER OF COLUMNS SHOULD BE SAMPLES-SPECIFIC COUNTS.

nilesh-tawari

#!/bin/bash
# $1 is PATH
args=("$@")
input_dir=${args[0]}
output_dir=${args[1]}

main() {
    set -e -x -o pipefail
    # get R1
    declare -a fastq1=($(ls -d $input_dir/*R1*.fastq.gz))    #($(ls *_R1_001.fastq.gz))

nilesh-tawari

## RNA-seq analysis with DESeq2
## Stephen Turner, @genetics_blog

# RNA-seq data from GSE52202
# http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse52202. All patients with
# ALS, 4 with C9 expansion ("exp"), 4 controls without expansion ("ctl")

# Import & pre-process ----------------------------------------------------

# Import data from featureCounts

nilesh-tawari

# -*- coding: utf-8 -*-
"""
Created on Mon Mar  5 14:21:42 2018

@author: nilesh-tawari
email: tawari.nilesh@gmail.com
GitHub: https://github.com/nilesh-tawari
"""
from __future__ import print_function
import os

nilesh-tawari

# -*- coding: utf-8 -*-
"""
Created on Tue Mar 13 09:40:36 2018

@author: rameshtn
"""

from __future__ import print_function
import os
import argparse

nilesh-tawari

# Deploy a python package on DNAnexus

## Step 1: find installation path of module
python
import imp
imp.find_module("pandas")

## Step 2: copy module and put in tarball
cp -r /mnt/software/unstowable/anaconda/lib/python2.7/site-packages/pandas .

nilesh-tawari

# Create git repository and push to remote
cd workspace/Clinical_genomics_framework/
git init
git add .
git commit -m "Clinical genomics framework"
echo "# Clinical_genomics_framework" >> README.md
git add README.md
git commit -m "Readme file"

Create a repo online using browser  then push local to remote

nilesh-tawari

# Install cyvcf2 in ubuntu 16.04
sudo apt-get install build-essential autoconf libtool pkg-config python-opengl python-imaging python-pyrex python-pyside.qtopengl idle-python2.7 qt4-dev-tools qt4-designer libqtgui4 libqtcore4 libqt4-xml libqt4-test libqt4-script libqt4-network libqt4-dbus python-qt4 python-qt4-gl libgle3 python-dev libssl-dev

sudo easy_install greenlet

sudo easy_install gevent

nilesh-tawari

import pandas as pd

# fix SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Either of following
pd.options.mode.chained_assignment = None  # default='warn'
df.is_copy = False


# read big csv
df = pd.read_csv(FILE_PATH, sep='\t', comment = '#', chunksize=1000, \
                low_memory=False, iterator = True, compression='gzip')

nilesh-tawari

https://asia.ensembl.org/info/docs/tools/vep/script/vep_options.html

# Instructions for installing and running new VEP 

## 1. Install new version of VEP:
git clone https://github.com/Ensembl/ensembl-vep.git
cd ensembl-vep
perl INSTALL.pl

## 2. Install merged cache