Eric Horvitz

This study evaluates the effectiveness of biosecurity screening tools against AI-generated synthetic homologs of proteins of concern, finding some tools can detect fragments as short as 50 nucleotides.

This paper introduces DynamicsPLM, a protein language model that uses conformational ensembles to improve predictions of protein interactions, localization, and function.

The paper integrates ligand-protein interaction data into protein representation learning to improve predictive models for drug discovery and biological mechanisms.

This study evaluates the risks of AI-driven protein design by testing synthetic homologs against biosecurity screening software.

The paper evaluates biosecurity screening tools for detecting AI-generated synthetic protein homologs and reports improved detection rates through patches.

SciSight enables exploratory search of COVID-19 research by linking biomedical facets and visualizing researcher networks.