Drug-resistant microbes including bacteria, fungi, parasites, and viruses are a growing global threat. About five million deaths in 2021 were associated with bacterial antimicrobial resistance—an annual toll projected to roughly double by 2050. It can take years to find molecules with the potential to become antimicrobials.

Researchers are using AI to accelerate this early stage of discovery. César de la Fuente, a bioengineer whose cross-disciplinary lab searches for antimicrobial candidates, said antimicrobial resistance is one of the greatest existential threats to humanity. His lab uses deep-learning models trained to recognize patterns in biological sequences to search vast genome and protein datasets for potential antimicrobials, reducing the initial search from years to hours.

Alongside its own AI models, the lab uses Chat GPT and Codex to brainstorm hypotheses, write and refine code, process datasets, analyze results, and connect ideas across scientific disciplines. The approach focuses on biology as an information system, where nucleotides and amino acids form an alphabet to decipher life’s organizing principles. Only a fraction of a genome has a clearly understood function, and fewer still encode molecules that can fight infectious microbes.

AI helps identify promising signals among enormous datasets, prioritizing candidates for experimental testing. However, identifying a candidate does not guarantee it will become an effective medicine. Scientists must confirm the molecule kills the target microbe, determine effective dosage, test effects on human cells, optimize for safety and stability, assess toxicity and resistance development, and ensure manufacturability.

Candidates that clear these hurdles still face regulatory review and clinical trials before reaching patients. For de la Fuente, AI and laboratory biology must advance together, as ground-truth experiments are essential to validate AI predictions in the life sciences.