Rxivist logo

Unified rational protein engineering with sequence-only deep representation learning

By Ethan C Alley, Grigory Khimulya, Surojit Biswas, Mohammed AlQuraishi, George M. Church

Posted 26 Mar 2019
bioRxiv DOI: 10.1101/589333 (published DOI: 10.1038/s41592-019-0598-1)

Rational protein engineering requires a holistic understanding of protein function. Here, we apply deep learning to unlabelled amino acid sequences to distill the fundamental features of a protein into a statistical representation that is semantically rich and structurally, evolutionarily, and biophysically grounded. We show that the simplest models built on top of this unified representation (UniRep) are broadly applicable and generalize to unseen regions of sequence space. Our data-driven approach reaches near state-of-the-art or superior performance predicting stability of natural and de novo designed proteins as well as quantitative function of molecularly diverse mutants. UniRep further enables two orders of magnitude cost savings in a protein engineering task. We conclude UniRep is a versatile protein summary that can be applied across protein engineering informatics.

Download data

  • Downloaded 9,353 times
  • Download rankings, all-time:
    • Site-wide: 282 out of 92,091
    • In synthetic biology: 4 out of 867
  • Year to date:
    • Site-wide: 511 out of 92,091
  • Since beginning of last month:
    • Site-wide: 1,162 out of 92,091

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)