Unravel the inner workings of the cell with a groundbreaking new artificial intelligence (AI) tool that can draw logical inferences about the function of unknown proteins. The research, featured in Nature Machine Intelligence, introduces DeepGO-SE, a model that utilizes large language models similar to those used by generative AI tools like Chat-GPT. By employing logical entailment, DeepGO-SE can draw meaningful conclusions about molecular functions based on general biological principles governing protein behavior. This empowers computers to logically process outcomes by constructing models of protein function and inferring the most plausible scenarios based on common sense and reasoning.
Robert Hoehndorf, head of the KAUST Bio-Ontology Research Group, who supervised this research, emphasizes the wide-ranging applications of this method, particularly in reasoning over data and hypotheses generated by neural networks or other machine learning models.
2024-02-14 10:00:05
Post from phys.org