Bruce J. Wittmann; Tessa Alexanian; Craig Bartling; Jacob Beal; Adam Clore; James Diggans; Kevin Flyangolts; Bryan T. Gemler; Tom Mitchell; Steven T. Murphy; Nicole E. Wheeler; Eric Horvitz · 2025 · Science
Paper
Advances in artificial intelligence (AI)-assisted protein engineering are enabling breakthroughs in the life sciences but also introduce new biosecurity challenges. Synthesis of nucleic acids is a choke point in AI-assisted protein engineering pipelines. Thus, an important focus for efforts to enhance biosecurity given AI-enabled capabilities is bolstering methods used by nucleic acid synthesis providers to screen orders. We evaluated the ability of open-source AI-powered protein design software to create variants of proteins of concern that could evade detection by the biosecurity screening tools used by nucleic acid synthesis providers, identifying a vulnerability where AI-redesigned sequences could not be detected reliably by current tools. In response, we developed and deployed patches, greatly improving detection rates of synthetic homologs more likely to retain wild type-like function.
Analysis
This paper addresses the biosecurity risks posed by AI-driven protein design tools, specifically their ability to create novel protein sequences that evade current screening methods used by nucleic acid synthesis providers, and proposes solutions.
Discovery
Hoda M. Hammad; Anna M. Duraj‐Thatte
Jakob Agamia; Martin Zacharias
Yap V; Xu P; Mak FS; Foo K; Kang C; Anbazhagan P; Xu W
Hun Hee Cho; Tae Hyung Kim; Seung Gyu Hwang; Hongchul Shin
Guohao Zhang; Chuanyang Liu; Jiajie Lu; Shaowei Zhang; Lingyun Zhu
Uddalak Das
Source record