How a researcher uses Codex and ChatGPT to search for new antimicrobial molecules

Bioengineer César de la Fuente's lab is using OpenAI's Codex and ChatGPT alongside custom deep-learning models to accelerate early-stage antimicrobial discovery, reducing the initial search for candidate molecules from years to hours. The lab mines genomic and protein databases across living and extinct organisms for biologically active peptides, treating biology as an information system whose patterns AI can decode at scale. ChatGPT serves as a cross-disciplinary bridge, enabling biologists to write code and programmers to engage with biological problems, while also allowing non-native English speakers to work in their native languages. Antimicrobial resistance is linked to roughly 5 million deaths annually in 2021, a toll projected to double by 2050, underscoring the urgency of faster discovery pipelines. De la Fuente emphasizes that AI predictions must be validated by laboratory experiments and that human oversight—including accuracy checks—remains essential.