Keeping generative artificial intelligence reliable in omics biology

Overview & Synopsis

Generative artificial intelligence can be used to create realistic new data, even for complex real-word processes which cannot be exhaustively modelled: the model is simply learnt from pre-existing data. Generative artificial intelligence is therefore expected to be a game-changer in omics research, where data collection is hampered by considerable experimental constraints. However, it can also "hallucinate", i.e., create data which are too original to be realistic, which is critical in molecular biology, as hallucinated inferences could have devastating consequences. This article thus explores various use-cases to mitigate hallucination-induced risks and to safely unleash the full potential of generative methods.