• Publications
  • Influence
Unified rational protein engineering with sequence-based deep representation learning
TLDR
We apply deep learning to unlabeled 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. Expand
  • 95
  • 14
  • PDF
Unified rational protein engineering with sequence-only deep representation learning
TLDR
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. Expand
  • 34
  • 5
Low-N protein engineering with data-efficient deep learning
TLDR
We introduce a machine learning-guided paradigm that can use as few as 24 functionally assayed mutant sequences to build an accurate virtual fitness landscape and screen ten million sequences via in silico directed evolution. Expand
  • 26
Bidirectional contact tracing is required for reliable COVID-19 control
TLDR
We find that "bidirectional" tracing to identify infector individuals robustly outperforms forward-only approaches across a wide range of scenarios. Expand
  • 14
Bidirectional contact tracing could dramatically improve COVID-19 control
Contact tracing is critical to controlling COVID-19, but most protocols only “forward-trace” to notify people who were recently exposed. Using a stochastic branching-process model, we find thatExpand
  • 4
A machine learning toolkit for genetic engineering attribution to facilitate biosecurity
TLDR
The promise of biotechnology is tempered by its potential for accidental or deliberate misuse. Expand
  • 1
Low-N protein engineering with data-efficient deep learning.
Protein engineering has enormous academic and industrial potential. However, it is limited by the lack of experimental assays that are consistent with the design goal and sufficiently high throughputExpand
Attribution of genetic engineering: A practical and accurate machine-learning toolkit for biosecurity
TLDR
The promise of biotechnology is tempered by its potential for accidental or deliberate misuse. Expand
The biosecurity benefits of genetic engineering attribution
Biology can be misused, and the risk of this causing widespread harm increases in step with the rapid march of technological progress. A key security challenge involves attribution: determining, inExpand