Your browser doesn't support javascript.
loading
Boosting the performance of molecular property prediction via graph-text alignment and multi-granularity representation enhancement.
Zhao, Zhuoran; Zhou, Qing; Wu, Chengkai; Su, Renbin; Xiong, Weihong.
Afiliación
  • Zhao Z; College of Computer Science, Chongqing University, Chongqing 400044, China. Electronic address: 202114131105@stu.cqu.edu.cn.
  • Zhou Q; College of Computer Science, Chongqing University, Chongqing 400044, China. Electronic address: tzhou@cqu.edu.cn.
  • Wu C; Department of Ultrasound, Xinxiang Medical University Henan Provincial People's Hospital, Zhengzhou 450003, China. Electronic address: wuchengkai825@gmail.com.
  • Su R; Central China Branch of State Grid Corporation of China, Wuhan 430000, China.
  • Xiong W; Central China Branch of State Grid Corporation of China, Wuhan 430000, China.
J Mol Graph Model ; 132: 108843, 2024 Nov.
Article en En | MEDLINE | ID: mdl-39173218
ABSTRACT
Deep learning is playing an increasingly important role in accurate prediction of molecular properties. Prior to being processed by a deep learning model, a molecule is typically represented in the form of a text or a graph. While some methods attempt to integrate these two forms of molecular representations, the misalignment of graph and text embeddings presents a significant challenge to fuse two modalities. To solve this problem, we propose a method that aligns and fuses graph and text features in the embedding space by using contrastive loss and cross attentions. Additionally, we enhance the molecular representation by incorporating multi-granularity information of molecules on the levels of atoms, functional groups, and molecules. Extensive experiments show that our model outperforms state-of-the-art models in downstream tasks of molecular property prediction, achieving superior performance with less pretraining data. The source codes and data are available at https//github.com/zzr624663649/multimodal_molecular_property.
Asunto(s)
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Algoritmos / Aprendizaje Profundo Idioma: En Revista: J Mol Graph Model Asunto de la revista: BIOLOGIA MOLECULAR Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Algoritmos / Aprendizaje Profundo Idioma: En Revista: J Mol Graph Model Asunto de la revista: BIOLOGIA MOLECULAR Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos