elowy01

#getting the insert size from a BAM file
samtools view -F 0x4 accepted_hits.bam |  awk '{if ($9 >0) {sum+=$9;sumsq+=$9*$9;N+=1}} END {print "mean = " sum/N " SD=" sqrt(sumsq/N - (sum/N)**2)}'

#slicing a BAM file
samtools view aln.sorted.bam chr2:20100000-20200000

# extract a subsequence from a FASTA file
# 1) Index the Fasta file
samtools faidx hs37d5.ch20.fa
# 2) Fetch the sequence

elowy01

# HAPS/SAMPLE format
Explanation of format can be found at https://mathgen.stats.ox.ac.uk/genetics_software/shapeit/shapeit.html#hapsample

elowy01

// # Environment variables:
CPLUS_INCLUDE_PATH=/opt/gdbm-1.8.3/includ
export CPLUS_INCLUDE_PATH

/ Link path:
LIBRARY_PATH=/opt/gdbm-1.8.3/lib
export LIBRARY_PATH

# C-style guide
http://archive.oreilly.com/oreillyschool/courses/cplusplus1/style.html#functions

elowy01

//
In CMake we use # for adding comments
//
On the top level of a CMake file we have:

project(MyProject VERSION 1.0
                  DESCRIPTION "Very nice project"
                  LANGUAGES CXX)
//
Making an executable

elowy01

# One can insert images in jupyter nb in different ways:
a) Insert this in a Code type cell
%%html
<img src="img/folder_str1.png",width=100,height=100>
Where you have a folder named img at the same level of your notebook

b) Insert this in a Markdown type cell:
![alt text](img/folder_str1.png)
#
# Enabling Table of Contents (TOC) extention in jupyter:

elowy01

1) conda install -c anaconda boost
2) Boost libraries will be placed within /path/to/installation/miniconda3/include/ 
3) Then,modify CMakeList for Clion to point to your Boost folder:

cmake_minimum_required(VERSION 3.15)
project(test)

set(CMAKE_CXX_STANDARD 14)

add_executable(test main.cpp gzip.h)

elowy01

#include <string>
#include <boost/algorithm/string.hpp>

using namespace std;

int main()
{
    //split tab-separated string into vector of strs
    string line("test\ttest2\ttest3");
    vector<string> strs;

elowy01

# how to make iterm to move cursor back and forwards one work at a time
Follow instructions at:
https://medium.com/@jonnyhaynes/jump-forwards-backwards-and-delete-a-word-in-iterm2-on-mac-os-43821511f0a

elowy01

# Command lsid
View LSF version, cluster name, and current master host

# Command lsclusters
Run lsclusters to find out who your cluster administrator is and see a summary of your cluster:

# bparams
Run bparams to display the generic configuration parameters of LSF. These include default queues, job dispatch interval, job checking interval, and job accepting interval.

# modifyng limits for a certain job group

elowy01

# Reading multiple .csv files
# files/input.cova
# files/input.covb
# .....

import dask.dataframe as dd

df = dd.read_csv('files/input.cov*', names=['chr','pos','cov'], sep='\t')

print("Descriptors: {0}".format(df['cov'].describe().compute()))