Semantic knowledge graph as a companion for catalyst recommendation

Abstract

Our ability to perceive the correlation of different substances in the world is one of the key aspects of human intelligence. The passing of this faculty to artificial intelligence (AI) represents arguably one of the long-standing challenges in the application of AI to scientific problems. To meet this challenge in the burgeoning field of AI for chemistry, we may adopt the paradigm of knowledge graph. Herein, focusing on catalytic chemical reactions, we have developed a semantic knowledge graph framework based on both structured and unstructured data, the latter of which are extracted from the text of 220,000 articles on catalysts for organic molecules. The framework captures the latent knowledge of reactant-catalyst-product relationships and can therefore provide accurate recommendation on potential catalysts for targeted reaction, which especially facilitates the research involving large molecules. This study presents a viable pathway towards the implementation of literature-based data management in a catalyst recommendation platform.

Keywords

• knowledge graph
• text mining
• catalysts
• organic molecules
• natural language processing