← all projects
ARIA Opportunity Space: Programmable Plants
AI for Designable Biomolecules
Recent experiments have shown how increasing scale and applying reinforcement learning to natural language models leads to impressive emergent capabilities in generative AI systems. Genomic language models, despite their shared history, have not benefited from these training breakthroughs as of yet. Encode fellow McClain Thiel is working with Chris Barnes at UCL to develop a biologically informed, probabilistic reinforcement learning framework that fine-tunes biomolecular language models to generate plasmids that express proteins antagonistic to specific diseases. This could radically accelerate the design of programmable therapeutics, enabling rapid, low-cost generation of custom inhibitors for use in medicine, diagnostics, and synthetic biology.
Chris Barnes' Lab
University College London
,
London
Barnes Lab
↗
McClain holds a BS in Data Science from Berkeley and MS in CS from Georgia Tech. He was a senior ML Engineer at SnorkelAI, transforming manual AI development processes into programmatic solutions. He previously worked as an ML Scientist at Tempus AI, where he conceived, developed and deployed several large-scale user-facing machine learning projects bringing the latest and greatest in LLMs to clinical and genomic applications.
Chris Barnes
Professor of Systems and Synthetic Biology
Chris Barnes is a Professor in the Division of Biosciences at UCL. He has spanned multiple fields including particle physics, genetics, statistics, computational systems biology and synthetic biology. In addition to research, he is also actively engaged in training the next generation of researchers; he developed the BBSRC-funded e-learning resource SysMIC to train life scientists in computational and mathematical skills.
