AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dai, Yifan, Ren, Xuanbai, Ma, Tengfei, Yan, Qipeng, Liu, Yiping, Liu, Yuansheng, Zeng, Xiangxiang
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918023559905280
author Dai, Yifan
Ren, Xuanbai
Ma, Tengfei
Yan, Qipeng
Liu, Yiping
Liu, Yuansheng
Zeng, Xiangxiang
author_facet Dai, Yifan
Ren, Xuanbai
Ma, Tengfei
Yan, Qipeng
Liu, Yiping
Liu, Yuansheng
Zeng, Xiangxiang
contents Accurate molecular property prediction (MPP) is a critical step in modern drug development. However, the scarcity of experimental validation data poses a significant challenge to AI-driven research paradigms. Under few-shot learning scenarios, the quality of molecular representations directly dictates the theoretical upper limit of model performance. We present AdaptMol, a prototypical network integrating Adaptive multimodal fusion for Molecular representation. This framework employs a dual-level attention mechanism to dynamically integrate global and local molecular features derived from two modalities: SMILES sequences and molecular graphs. (1) At the local level, structural features such as atomic interactions and substructures are extracted from molecular graphs, emphasizing fine-grained topological information; (2) At the global level, the SMILES sequence provides a holistic representation of the molecule. To validate the necessity of multimodal adaptive fusion, we propose an interpretable approach based on identifying molecular active substructures to demonstrate that multimodal adaptive fusion can efficiently represent molecules. Extensive experiments on three commonly used benchmarks under 5-shot and 10-shot settings demonstrate that AdaptMol achieves state-of-the-art performance in most cases. The rationale-extracted method guides the fusion of two modalities and highlights the importance of both modalities.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11878
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery
Dai, Yifan
Ren, Xuanbai
Ma, Tengfei
Yan, Qipeng
Liu, Yiping
Liu, Yuansheng
Zeng, Xiangxiang
Machine Learning
Artificial Intelligence
Molecular Networks
J.3; I.2.7
Accurate molecular property prediction (MPP) is a critical step in modern drug development. However, the scarcity of experimental validation data poses a significant challenge to AI-driven research paradigms. Under few-shot learning scenarios, the quality of molecular representations directly dictates the theoretical upper limit of model performance. We present AdaptMol, a prototypical network integrating Adaptive multimodal fusion for Molecular representation. This framework employs a dual-level attention mechanism to dynamically integrate global and local molecular features derived from two modalities: SMILES sequences and molecular graphs. (1) At the local level, structural features such as atomic interactions and substructures are extracted from molecular graphs, emphasizing fine-grained topological information; (2) At the global level, the SMILES sequence provides a holistic representation of the molecule. To validate the necessity of multimodal adaptive fusion, we propose an interpretable approach based on identifying molecular active substructures to demonstrate that multimodal adaptive fusion can efficiently represent molecules. Extensive experiments on three commonly used benchmarks under 5-shot and 10-shot settings demonstrate that AdaptMol achieves state-of-the-art performance in most cases. The rationale-extracted method guides the fusion of two modalities and highlights the importance of both modalities.
title AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery
topic Machine Learning
Artificial Intelligence
Molecular Networks
J.3; I.2.7
url https://arxiv.org/abs/2505.11878