Knowledge-informed Molecular Learning: A Survey on Paradigm Transfer

Machine learning, especially deep learning, has greatly advanced molecular studies in the biochemical domain. Most typically, modeling for most molecular tasks have converged to several paradigms. For example, we usually adopt the prediction paradigm to solve tasks of molecular property prediction. To improve the generation and interpretability of purely data-driven models, researchers have incorporated biochemical domain knowledge into these models for molecular studies. This knowledge incorporation has led to a rising trend of paradigm transfer, which is solving one molecular learning task by reformulating it as another one. In this paper, we present a literature review towards knowledge-informed molecular learning in perspective of paradigm transfer, where we categorize the paradigms, review their methods and analyze how domain knowledge contributes. Furthermore, we summarize the trends and point out interesting future directions for molecular learning.