slowkow

#!/usr/bin/env python
# encoding: utf8
"""
merge_lanes.py
Kamil Slowikowski
July 17, 2015

Broad Technology labs provides sequencing data in a directory structure like
this:

slowkow

#!/usr/bin/env bash
# toggle-trackpoint.sh

set -uoe pipefail

# xinput list

# ⎡ Virtual core pointer                    	id=2	[master pointer  (3)]
# ⎜   ↳ Virtual core XTEST pointer              	id=4	[slave  pointer  (2)]
# ⎜   ↳ SynPS/2 Synaptics TouchPad              	id=14	[slave  pointer  (2)]

slowkow

(*
  Put this script in:
  
    /Users/USERNAME/Library/Scripts/
    
  Download and install FastScripts to assign this script to a keyboard shortcut:
  
    http://www.red-sweater.com/fastscripts/
    
  Source: http://apple.stackexchange.com/a/49546/123845

slowkow

#!/usr/bin/env bash
# make_aspera_manifest.sh
# Kamil Slowikowski
#
# Make a manifest file suitable for Aspera.
#
# Example
# -------
#
# Suppose we wish to send a folder full of files called "data". We want

slowkow

#!/usr/bin/env bash
# sra-paired.sh
# Kamil Slowikowski
# April 23, 2014
#
# Check if an SRA file contains paired-end sequencing data.
#
# See documentation for the SRA Toolkit:
# http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=toolkit_doc&f=fastq-dump

slowkow

#!/usr/bin/env python
"""
pathway_genes.py
Kamil Slowikowski
[email protected]

Updated 2021-03-22


Usage

slowkow

#' Get the variance explained by principal components
#' @param plist A list with class "prcomp" containing: sdev, rotation, x.
variance_explained <- function(plist) {
  rotation <- as.data.frame(plist$rotation)
  variance <- plist$sdev ^ 2  
  data.frame(
    Component = factor(1:ncol(rotation), levels = 1:ncol(rotation)),
    Variance = variance / sum(variance),
    CumulativeVariance = ( cumsum(variance) / sum(variance) )
  )

slowkow

Distance and Correlation

References:

• http://www.analytictech.com/mb876/handouts/distance_and_correlation.htm
• http://bioconductor.org/help/publications/books/bioinformatics-and-computational-biology-solutions/

Code:

slowkow

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:output omit-xml-declaration="yes" />
<!-- 
     Transform biosample XML to TSV.
     
     Usage: xsltproc biosample2tsv.xsl input.xml > output.tsv
-->
<xsl:template match="/">GEO<xsl:text>&#x9;</xsl:text>Title<xsl:text>&#x9;</xsl:text>CellLine<xsl:text>&#x9;</xsl:text>CellType<xsl:text>&#x9;</xsl:text>CdnaMethod<xsl:text>&#10;</xsl:text>
    <xsl:for-each select="//BioSample">

slowkow

# 1. Install biomart.

source("http://bioconductor.org/biocLite.R")
biocLite("biomaRt")

# 2. Load biomart.

library(biomaRt)

# 3. Get symbols for Ensembl IDs