Integrated multimodal hierarchical fusion and meta-learning for enhanced molecular property prediction.

Journal: Briefings in bioinformatics
Published Date:

Abstract

Accurately predicting the pharmacological and toxicological properties of molecules is a critical step in the drug development process. Owing to the heterogeneity of molecular property prediction tasks, most of the current methods rely on building a base model and fine-tuning it to address specific properties. However, constructing a high-quality base model is a time-consuming procedure and requires a carefully designed network architecture; in addition, in certain rare molecular property prediction tasks, the base model often does not transfer well to new tasks. In this work, we adopt a meta-learning-based training framework that enables our model to adapt to diverse tasks with limited data, thereby preventing data scarcity from impacting certain molecular property predictions. Additionally, this framework leverages the correlations between different tasks, allowing the constructed model to quickly adapt to new prediction tasks. Moreover, we propose a multimodal fusion framework that combines two-dimensional molecular graphs with molecular images. In the molecular graphs, node-, motif-, and graph-level features are hierarchically guided from low to high levels, fully exploiting the molecular representation and more efficiently conducting hierarchical fusion. Experimental results indicate that our model outperforms the baseline models across various performance indicators, thereby validating the effectiveness of our approach.

Authors

  • Xianjun Han
    Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 YongAn Road, Beijing, 100050, People's Republic of China.
  • Zhenglong Zhang
    University of Electronic Science and Technology of China, Chengdu, China.
  • Can Bai
    College of Acupuncture and Tuina, Anhui University of Chinese Medicine, Longzihu Road 350, Hefei 230012, Anhui, China.
  • Zijian Wu
    Laboratory for Computational Sensing and Robotics, The Johns Hopkins University, Baltimore, MD, 21218, USA.