How a researcher uses Codex and ChatGPT to search for new antimicrobial molecules
A concrete example of Codex and ChatGPT helping researchers search genomic data for antimicrobial candidates, though the material gives no workflow or validation details.
César de la Fuente’s lab uses **Codex and ChatGPT** to search **living and extinct genomes** for molecules that might work as antimicrobials against drug-resistant infections.
For builders, this is a useful pattern for research agents: connect model-assisted exploration to a bounded scientific search space and treat the output as candidates for further evaluation.
César de la Fuente’s lab uses **Codex and ChatGPT** to search **living and extinct genomes** for molecules that might work as antimicrobials against drug-resistant infections. For builders, this is a useful pattern for research agents: connect model-assisted exploration to a bounded scientific search space and treat the output as candidates for further evaluation. The material does not describe the agent workflow, datasets, candidate count, evaluation method, or experimental results, so it supports a use case rather than a reproducible approach.
This turns the broader scientific-adoption signal into a specific candidate-discovery use case: model-assisted exploration is bounded by genomic search spaces and followed by evaluation rather than treated as a final scientific result. It confirms interest in using coding agents beyond software modernization, but the missing workflow, datasets, and outcomes leave it as an adoption marker, not evidence of acceleration or a reusable method.