Johan Dahlberg johandahlberg

## MinimalKmerProblemExample.scala
package example

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.rdd.ADAMContext
import org.bdgenomics.formats.avro.NucleotideContigFragment

/**
 * Created by dahljo on 7/14/15.
 */

## ParallelShellJobManager.scala
/*
* Copyright (c) 2012 The Broad Institute
*
* Permission is hereby granted, free of charge, to any person
* obtaining a copy of this software and associated documentation
* files (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use,
* copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following

## designer.html
<link rel="import" href="../polymer/polymer.html">

<polymer-element name="my-element">

  <template>
    <style>
      :host {
        position: absolute;
        width: 100%;
        height: 100%;

## shiny-server.conf
# Instruct Shiny Server to run applications as the user "shiny"
run_as shiny;

# Define a server that listens on port 3838
server {
  listen 3838;

  # Define a location at the base URL
  location / {

## contriesAndParticipantsForKP2014.R
library(ggplot2)
library(reshape2)
library(maps)

# A tab separated file with contries and participats.
# Note that Unites States needs to be changed to USA and United Kingdom
# to UK.
path.to.contry.and.participants.file <- "~/Desktop/contries.csv"

participants <-

## prepareReference.sh
#!/bin/bash -l
#SBATCH -A b2010028
#SBATCH -p core
#SBATCH -n 2
#SBATCH -t 10:00:00
#SBATCH -J prepare_ref
#SBATCH -o prepare_ref-%j.out
#SBATCH -e prepare_ref-%j.error

# Author: Johan D

## DemoIteratorSkipsRecords.scala
package molmed

import net.sf.samtools.util.SortingCollection
import net.sf.samtools.BAMRecordCodec
import net.sf.picard.fastq.FastqRecord
import java.util.Comparator
import java.io.InputStream
import java.io.PrintStream
import net.sf.picard.fastq.FastqConstants

## plotCoverageProportions.R
library(ggplot2)

setwd("<my working directory>")

removeExtraLine <- function(x) {
  x[,2:length(x)]
}

createInitialDataset <- function(x, sampleName) {
  extraLineRemoved <- t(removeExtraLine(x))

## GCCounter.scala
import scala.io.Source
import java.io.File

object GCCounter extends App {

  val file = new File("Homo_sapiens.GRCh37.67.dna_rm.chromosome.Y.fa")

  // The actual GC counting function
  def countGCOnLine(line: String): (Long, Long) = {
    if (line.startsWith(">"))

## BetterCodeExampleUnitTests.scala
import org.scalatest.FunSuite

import BetterCodeExample._

class BetterCodeExampleUnitTests extends FunSuite {

    test("Burrow wheelers transform of ^BANANA|") {
        assert(BetterCodeExample.burrowsWheelersTransform("^BANANA|") === """BNN^AA|A""")
    }
	package example

	import org.apache.spark.{SparkConf, SparkContext}
	import org.apache.spark.rdd.RDD
	import org.bdgenomics.adam.rdd.ADAMContext
	import org.bdgenomics.formats.avro.NucleotideContigFragment

	/**
	* Created by dahljo on 7/14/15.
	*/
	/*
	* Copyright (c) 2012 The Broad Institute
	*
	* Permission is hereby granted, free of charge, to any person
	* obtaining a copy of this software and associated documentation
	* files (the "Software"), to deal in the Software without
	* restriction, including without limitation the rights to use,
	* copy, modify, merge, publish, distribute, sublicense, and/or sell
	* copies of the Software, and to permit persons to whom the
	* Software is furnished to do so, subject to the following
	<link rel="import" href="../polymer/polymer.html">

	<polymer-element name="my-element">

	<template>
	<style>
	:host {
	position: absolute;
	width: 100%;
	height: 100%;
	# Instruct Shiny Server to run applications as the user "shiny"
	run_as shiny;

	# Define a server that listens on port 3838
	server {
	listen 3838;

	# Define a location at the base URL
	location / {
	library(ggplot2)
	library(reshape2)
	library(maps)

	# A tab separated file with contries and participats.
	# Note that Unites States needs to be changed to USA and United Kingdom
	# to UK.
	path.to.contry.and.participants.file <- "~/Desktop/contries.csv"

	participants <-
	#!/bin/bash -l
	#SBATCH -A b2010028
	#SBATCH -p core
	#SBATCH -n 2
	#SBATCH -t 10:00:00
	#SBATCH -J prepare_ref
	#SBATCH -o prepare_ref-%j.out
	#SBATCH -e prepare_ref-%j.error

	# Author: Johan D
	package molmed

	import net.sf.samtools.util.SortingCollection
	import net.sf.samtools.BAMRecordCodec
	import net.sf.picard.fastq.FastqRecord
	import java.util.Comparator
	import java.io.InputStream
	import java.io.PrintStream
	import net.sf.picard.fastq.FastqConstants
	library(ggplot2)

	setwd("<my working directory>")

	removeExtraLine <- function(x) {
	x[,2:length(x)]
	}

	createInitialDataset <- function(x, sampleName) {
	extraLineRemoved <- t(removeExtraLine(x))
	import scala.io.Source
	import java.io.File

	object GCCounter extends App {

	val file = new File("Homo_sapiens.GRCh37.67.dna_rm.chromosome.Y.fa")

	// The actual GC counting function
	def countGCOnLine(line: String): (Long, Long) = {
	if (line.startsWith(">"))
	import org.scalatest.FunSuite

	import BetterCodeExample._

	class BetterCodeExampleUnitTests extends FunSuite {

	test("Burrow wheelers transform of ^BANANA\|") {
	assert(BetterCodeExample.burrowsWheelersTransform("^BANANA\|") === """BNN^AA\|A""")
	}