Published July 11, 2023
| Version 1.0.0
Dataset
Open
CPT-1 whole-proteome feature matrices (no-EVE set)
Creators
- 1. University of California, Berkeley
Description
Cross-protein transfer learning for variant effect prediction
This repository contains the feature matrices for CPT-1 to make variant effect prediction on 15,557 human proteins NOT in the EVE set (Frazer et al., 2021), initially released with the manuscript "Cross-protein transfer learning substantially improves zero-shot prediction of disease variant effects".
Citation
Jagota, M.*, Ye, C.*, Albors, C., Rastogi, R., Koehl, A., Ioannidis, N., and Song, Y.S.†
"Cross-protein transfer learning substantially improves zero-shot prediction of disease variant effects", bioRxiv (2022)
*These authors contributed equally to this work.
†To whom correspondence should be addressed: yss@berkeley.edu
Files
feature_info.txt
Files
(43.5 GB)
Name | Size | Download all |
---|---|---|
md5:2a68747b8a5126fb19ff3ba186fcabb7
|
43.5 GB | Download |
md5:f63b0d1a68183f5bab47a8b52cfb6919
|
1.7 kB | Preview Download |