Joint Graph-Sequence Learning for Molecular Property Prediction

Rom Uddamvathanak, Xin Zheng, Shirui Pan

Abstract: Molecular property prediction has achieved promising improvement for accelerating drug development with machine learning models. The emergence of graph neural networks especially benefits the discriminative representation learning of molecular graph data, which has become the key challenge of molecular property prediction. However, most of the existing works extract either graph features or sequence features of molecules, while the significant information from both graph and sequence representations is not well discovered and utilized. In this paper, we propose a Joint Graph-Sequence framework, JointGS, for learning high-quality molecular property representations by jointly capturing information from both graph and sequence molecular data. Specifically, JointGS contains a sequence encoder and a graph encoder working in parallel for learning sequence-level and graph-level molecular embeddings, respectively. Moreover, an attentional feature fusion mechanism is presented to better aggregate graph-sequence molecular embeddings. Extensive experiments demonstrate that the proposed JointGS can achieve superior molecular property prediction performance, especially in the SARS-CoV dataset for screening potential molecules benefiting the COVID-19 drug development.