[an error occurred while processing this directive]

Murphy Lab

Home
Information
People
Addresses
Cytometry Development Workshop
FCS API

Research
Projects
Publications
Software
Presentations
Flow Cytometry

Affiliations
Carnegie Mellon University
Computational Biology Department
Center for Bioimage Informatics
Biological Sciences Department
Biomedical Engineering Department
Machine Learning Department
MBIC

[an error occurred while processing this directive]

Internal

Information
Lab FAQ
Lab Research Topics

Services
TypIX

Web Pages
Web Page Template
Visitation Statistics
Important Links

Software and Documentation
Matlab Docs
Khoros Docs
TN-Image Docs
Michael Boland's thesis

Murphy Lab - Software - Bioinformatics 2013 Local Features for Improved Generalization

The software and raw data used for the following paper can be downloaded below:

Luis Pedro Coelho, Joshua D. Kangas, Armaghan Naik, Elvira Osuna-Highley, Estelle Glory-Afshar, Margaret Fuhrman, Ramanuja Simha, Peter B. Berget, Jonathan W. Jarvik, and Robert F. Murphy (2013) Local Features Provide Better Generalization of Subcellular Location Classifiers to New Proteins. Bioinformatics 29: 2343-2349.

The following files are compressed with tar and gzip

Source Code

LocalFeaturesSource.tgz

Raw Data

RandTag Widefield Images (2D 3T3 RT Set 3)	2D3T3RTset3.tgz (2.0 GB)
RandTag Confocal Images (2D 3T3 RT Set 4)	2D3T3RTset4.tgz (612 MB)
Human Protein Atlas	http://murphylab.web.cmu.edu/software/2012_PLoS_ONE_Reannotation
2D HeLa	http://murphylab.web.cmu.edu/data/2Dhela_images.html
LOCATE endogenous and LOCATE transfected	http://locate.imb.uq.edu.au/info_files/SubCellLoc.zip
LOCATE Confocal	http://locate.imb.uq.edu.au
IICBU 2008 Benchmark	http://ome.grc.nia.nih.gov/iicbu2008

Recreating Results from Raw Image Data

To recreate the results from the article (i.e. the figures and tables) from the raw image data,

Download and expand the source code file above to the desired directory.
tar -xzf LocalFeaturesSource.tgz

Download and expand the raw images for the RandTag and HPA datasets above into the data subdirectory

Run the following command, which will download the rest of the images and run everything (this will take over a day on a single processor)
source doitall.sh

System requirements

python
python-pip
python-virtualenv
dvipng

This package has been tested using python 2.7 under CentOS in a 64bit architecture.

Last Updated: 21 Feb 2014