Dave Tang davetang

## read_bam.R
#install if necessary
source("http://bioconductor.org/biocLite.R")
biocLite("Rsamtools")

#load library
library(Rsamtools)

#read in entire BAM file
bam <- scanBam("wgEncodeRikenCageHchCellPapAlnRep1.bam")

## ec2_docker_setup.sh
#!/usr/bin/env bash

set -euo pipefail

sudo apt-get update
sudo apt-get install -y \
    ca-certificates \
    curl \
    gnupg \
    lsb-release \

## biomart_refseq.R
#install if necessary
source("http://bioconductor.org/biocLite.R")
biocLite("biomaRt")

#load library
library("biomaRt")

#use ensembl mart
ensembl <- useMart("ensembl",dataset="hsapiens_gene_ensembl")

## split_search.sh
#!/usr/bin/env bash

set -euo pipefail

usage() {
   >&2 echo "Usage: $0 [ -l search_list ] [ -f file_to_grep ] [ -n split_num ] [ -p num_threads ]"
   exit 1
}

num_param=4

## transpose.pl
#!/usr/bin/env perl

use strict;
use warnings;

my $data   = [];
my $t_data = [];

while(<>){
   chomp;

## psl_to_bed_best_score.pl
#!/usr/bin/env perl

use strict;
use warnings;

=head1 NAME

This scripts converts a psl file into a bed file written by Dave Tang.

=head1 SYNOPSIS

## mutate_fasta.pl
#!/usr/bin/env perl

# Takes a fasta file as input and randomly mutates bases

use strict;
use warnings;

my $usage = "Usage: $0 <infile.fa> <mutation percent> <seed>\n";
my $infile = shift or die $usage;
my $mutation = shift or die $usage;

## keybase.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                davetang
                / keybase.md
            
            
              Created
              September 10, 2019 06:09
            
          
    Keybase proof

I hereby claim:

I am davetang on github.
I am davetang (https://keybase.io/davetang) on keybase.
I have a public key ASD791k70QUxQTjAu2NfaNCa4dhCxY0EnzWk-AT0uqFOSQo

To claim this, I am signing this object:

  
## intersect_coordinate.R
#install if necessary
source("http://bioconductor.org/biocLite.R")
biocLite("GenomicRanges")

#load library
library(GenomicRanges)

#create a GRanges object given an object, my_refseq_loci
head(my_refseq_loci,2)
#   refseq_mrna chromosome_name transcript_start transcript_end strand

## random_region.R
#how many regions to sample?
number <- 50000

#how many bp to add to start
span <- 4

#some necessary packages
#install if necessary
source("http://bioconductor.org/biocLite.R")
biocLite("BSgenome")
	#install if necessary
	source("http://bioconductor.org/biocLite.R")
	biocLite("Rsamtools")

	#load library
	library(Rsamtools)

	#read in entire BAM file
	bam <- scanBam("wgEncodeRikenCageHchCellPapAlnRep1.bam")
	#!/usr/bin/env bash

	set -euo pipefail

	sudo apt-get update
	sudo apt-get install -y \
	ca-certificates \
	curl \
	gnupg \
	lsb-release \
	#install if necessary
	source("http://bioconductor.org/biocLite.R")
	biocLite("biomaRt")

	#load library
	library("biomaRt")

	#use ensembl mart
	ensembl <- useMart("ensembl",dataset="hsapiens_gene_ensembl")
	#!/usr/bin/env bash

	set -euo pipefail

	usage() {
	>&2 echo "Usage: $0 [ -l search_list ] [ -f file_to_grep ] [ -n split_num ] [ -p num_threads ]"
	exit 1
	}

	num_param=4
	#!/usr/bin/env perl

	use strict;
	use warnings;

	my $data = [];
	my $t_data = [];

	while(<>){
	chomp;
	#!/usr/bin/env perl

	# Takes a fasta file as input and randomly mutates bases

	use strict;
	use warnings;

	my $usage = "Usage: $0 <infile.fa> <mutation percent> <seed>\n";
	my $infile = shift or die $usage;
	my $mutation = shift or die $usage;
	#install if necessary
	source("http://bioconductor.org/biocLite.R")
	biocLite("GenomicRanges")

	#load library
	library(GenomicRanges)

	#create a GRanges object given an object, my_refseq_loci
	head(my_refseq_loci,2)
	# refseq_mrna chromosome_name transcript_start transcript_end strand
	#how many regions to sample?
	number <- 50000

	#how many bp to add to start
	span <- 4

	#some necessary packages
	#install if necessary
	source("http://bioconductor.org/biocLite.R")
	biocLite("BSgenome")