Fourth Eon Bio is a research and development organization exploring capabilities, applications, and risks of AI bio models to advance global biosecurity and build robust safeguards.
Exploring the limits of AI protein design
Biological foundation models and biodesign tools are transforming our ability to create novel proteins and pushing the boundaries of synthetic biology. They also pose new challenges for biosecurity due to the potential for engineering dangerous functions.
Fourth Eon Bio is evaluating AI-enabled protein design in the context of biosecurity screening, and seeking to understand the capabilities of current models in generating novel proteins that could challenge existing safeguards.
Predicting hazardous function from sequence
DNA sequences encode a highly compressed representation of biological function, which is executed by the cellular environment through the processes of molecular biology. Screening sequences for hazardous functions has traditionally relied on homology to known genes and proteins, but this approach is being strained as synthetic biology pushes beyond the space explored by nature.
Biological foundation models can learn a rich and nuanced representation of biomolecules by mapping their sequence-structure-function relationships to a high-dimensional embedding space. Fourth Eon Bio is evaluating foundation model capabilities for predicting structure, binding, function, and other molecular properties directly from sequence, and exploring how this could be used for detecting biological threats that do not closely resemble anything found in nature.
Gary Abel — Founder & Principal Scientist
Gary is Principal Scientist at Fourth Eon Bio, and a Contributing Scholar at the Johns Hopkins Center for Health Security. His expertise includes biochemistry, molecular biophysics, surface science, and sequencing technology. He has spent nearly two decades studying how DNA, RNA, and proteins behave and interact. Gary holds a BS in Physics from San Jose State University and a PhD in Chemistry & Chemical Biology from University of California Merced.
Elias Nehring — Research Fellow
Elias recently completed his MSc in Computational Biology and Bioinformatics from ETH Zürich, where he specialized in ML for protein design. He is interested in AI capabilities and biosecurity risk. He has contributed to publications on LLM risks in agriculture and computational methods in ecology. Previously, he worked at McKinsey on geospatial analytics and generative AI for agriculture.
Hanna Pálya — Research Fellow
Hanna Pálya is a PhD student in Mathematical Epidemiology at the University of Warwick, applying ML to syndromic surveillance data for early outbreak detection with the UK Health Security Agency. Beyond this, their biosecurity work includes co-developing an AI Know-Your-Customer tool for DNA providers, scoping a research programme for function-based screening of nucleic acid sequences with the Centre for Long-Term Resilience, and AI-bio threat modelling as a GovAI Winter Fellow. They hold a BSc in Biology and Philosophy from the University of St Andrews.
Ian Beatty — Research Fellow
Ian Beatty is a Physics Professor at the University of North Carolina Greensboro, with experience in Physics Education Research and Computational Physics. Driven by a desire to make the world safer, he's diving into the AI-biosecurity nexus, trying to reduce catastrophic pandemic risk by improving DNA synthesis screening methods. Ian holds a PhD in Physics from University of Massachusetts Amherst.