Source code for paper Determining the subcellular location of new proteins from microscope images using local features by Coelho et al. in Bioinformatics
This repository is for reproduction of the results in the paper. If you want to apply the methods to your data, check out the tutorial on doing so. It is a step by step manual on applying the methods to your data.
sudo apt-get install python python-pip python-virtualenv sudo apt-get install dvipng
For the Human Protein Atas data, please download from http://murphylab.web.cmu.edu/software/2012_PLoS_ONE_Reannotation/
Edit the file
sources/hpa.pyto point to where you downloaded all the data.
Get the randtag data from http://murphylab.web.cmu.edu/software/2013_Bioinformatics_LocalFeatures/ or from Data Dryad
The remaining data should be automatically downloaded when you run:
This will also run the computation.
If you want to take advantage of multiple processors, edit the file
doitall.sh and set the
NR_CPUS variable. Note that the whole
computation (i) takes a very long time (days) on a single core and (ii) is
designed to take full advantage of multiples cores.
For referring to this work, please cite:
Determining the subcellular location of new proteins from microscope images using local features by 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). Bioinformatics, [DOI]