ResPRE
ResPRE copied to clipboard
leeyang
ResPRE is an algorithm for protein residue-residue contact-map prediction
INSTALLATION AND IMPLEMENTATION OF ResPRE
(Copyright 2018 by Zhang Lab, University of Michigan, All rights reserved)
-
What is ResPRE? ResPRE is a program for protein contact-map prediction by coupling PREcision matrix with fully Residual neurl networks.
-
How to install the ResPRE?
- Prerequisites Python3 with numpy and scipy should be installed pytorch-0.3.0 (https://pytorch.org/get-started/previous-versions/) Anaconda is recommended to set up python environments
- There is an executable file under 'bin' path, Maybe you also need set executable permission to the bin file.
-
Bug report: Please visit https://zhanglab.ccmb.med.umich.edu/bbs/?q=forum/2
-
How to run the ResPRE? python respre.py [msa_file] [outfile] msa_file: Multiple Sequence Alignment file outfile: Output file, each line in this format: [position1 position2 score] where position index start from 1 [NOT 0]
-
Example You can test by fowllowing commands: ' python respre.py test/T0759-D1.aln test/T0759-D1.out ' It will generate 2 files: ' T0759-D1.out.weight ': Weights for each sequence in msa, you can just ignore it. ' T0759-D1.out ' : Output file
Reference Yang Li, Jun Hu, Chengxin Zhang, Dong-Jun Yu, and Yang Zhang, ResPRE: high-accuracy protein contact prediction by coupling precision matrix with deep residual neural networks.Bioinformatics.
leeyang