Generative artificial intelligence GPT-4 accelerates knowledge mining and machine learning for synthetic biology

Abstract

Abstract Knowledge mining from synthetic biology journal articles for machine learning (ML) applications is a labor-intensive process. The development of natural language processing (NLP) tools, such as GPT-4, can accelerate the extraction of published information related to microbial performance under complex strain engineering and bioreactor conditions. As a proof of concept, we used GPT-4 to extract knowledge from 176 publications on two oleaginous yeasts ( Yarrowia lipolytica and Rhodosporidium toruloides ). After integration with a molecule inventory database, the outcome is a total of 2037 data instances and 28 features, which serve as machine learning inputs. The structured datasets enabled ML approaches (e.g., a random forest model) to predict Yarrowia fermentation titers with high accuracy (R 2 of 0.86 for unseen test data). Via transfer learning, the trained model could also assess the production capability of the non-conventional yeast, R. toruloides , for which there are fewer published reports. This work demonstrated the potential of generative artificial intelligence to speed up information extraction from research articles, thereby improving design-build-test-learn (DBTL) cycles for commercial biomanufacturing development.