An algorithm for predicting human disease-associated amino acid mutations from sequence entropy and predicted protein structures

This server will fast retrieve pre-computed mutation scores (average exome coverage is 90%, score >0.45 is disease-associated).

Notice: This server is free for non-commercial users. Commercial users, to use this server or request a download of all pre-computed scores, please send email to Dr. Skolnick: skolnick@gatech.edu

Citation: H.Zhou, M.Gao & J.Skolnick, submitted

Training & test datasets:
Download ENTPRISE-TR benchmarking training set
Download ENTPRISE-TR benchmarking training set with duplicated samples
Download ENTPRISE-TE benchmarking test set
Download ENTPRISE-balance benchmarking test set (a subset of ENTPRISE-TE)
Download protein sequences for ENTPRISE dataset
Download 1k-Genome test set
Download protein sequences for 1k-Genome test set

Predictions for proteins of human transcription machinery:
Download "hot" spot predictions

Server results will be better than benchmarking results since server has used all data including the above benchmarking test set for training.

Submit your protein variation list here

( Sample input 1 , sample input 2 , Sample output )


or upload :

Sent questions to hzhou3@gatech.edu