Molecular Odor Prediction Based on Multi-Feature Graph Attention Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xie, HongXin, Sun, JianDe, Shao, Yi, Li, Shuai, Hou, Sujuan, Sun, YuLong, Wang, Jian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909473460715520
author Xie, HongXin
Sun, JianDe
Shao, Yi
Li, Shuai
Hou, Sujuan
Sun, YuLong
Wang, Jian
author_facet Xie, HongXin
Sun, JianDe
Shao, Yi
Li, Shuai
Hou, Sujuan
Sun, YuLong
Wang, Jian
contents Olfactory perception plays a critical role in both human and organismal interactions, yet understanding of its underlying mechanisms and influencing factors remain insufficient. Molecular structures influence odor perception through intricate biochemical interactions, and accurately quantifying structure-odor relationships presents significant challenges. The Quantitative Structure-Odor Relationship (QSOR) task, which involves predicting the associations between molecular structures and their corresponding odors, seeks to address these challenges. To this end, we propose a method for QSOR, utilizing Graph Attention Networks to model molecular structures and capture both local and global features. Unlike conventional QSOR approaches reliant on predefined descriptors, our method leverages diverse molecular feature extraction techniques to automatically learn comprehensive representations. This integration enhances the model's capacity to handle complex molecular information, improves prediction accuracy. Our approach demonstrates clear advantages in QSOR prediction tasks, offering valuable insights into the application of deep learning in cheminformatics.
format Preprint
id arxiv_https___arxiv_org_abs_2502_01430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Molecular Odor Prediction Based on Multi-Feature Graph Attention Networks
Xie, HongXin
Sun, JianDe
Shao, Yi
Li, Shuai
Hou, Sujuan
Sun, YuLong
Wang, Jian
Machine Learning
Quantitative Methods
Olfactory perception plays a critical role in both human and organismal interactions, yet understanding of its underlying mechanisms and influencing factors remain insufficient. Molecular structures influence odor perception through intricate biochemical interactions, and accurately quantifying structure-odor relationships presents significant challenges. The Quantitative Structure-Odor Relationship (QSOR) task, which involves predicting the associations between molecular structures and their corresponding odors, seeks to address these challenges. To this end, we propose a method for QSOR, utilizing Graph Attention Networks to model molecular structures and capture both local and global features. Unlike conventional QSOR approaches reliant on predefined descriptors, our method leverages diverse molecular feature extraction techniques to automatically learn comprehensive representations. This integration enhances the model's capacity to handle complex molecular information, improves prediction accuracy. Our approach demonstrates clear advantages in QSOR prediction tasks, offering valuable insights into the application of deep learning in cheminformatics.
title Molecular Odor Prediction Based on Multi-Feature Graph Attention Networks
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2502.01430