A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Zongru, Chen, Xingsheng, Wen, Honggang, Zhang, Regina Qianru, Li, Ming, Zhang, Xiaojin, Yin, Hongzhi, Yang, Qiang, Lam, Kwok-Yan, Lio, Pietro, Yiu, Siu-Ming
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917417683255296
author Li, Zongru
Chen, Xingsheng
Wen, Honggang
Zhang, Regina Qianru
Li, Ming
Zhang, Xiaojin
Yin, Hongzhi
Yang, Qiang
Lam, Kwok-Yan
Lio, Pietro
Yiu, Siu-Ming
author_facet Li, Zongru
Chen, Xingsheng
Wen, Honggang
Zhang, Regina Qianru
Li, Ming
Zhang, Xiaojin
Yin, Hongzhi
Yang, Qiang
Lam, Kwok-Yan
Lio, Pietro
Yiu, Siu-Ming
contents Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with physicochemical and biological behavior. This survey traces four complementary paradigms, including Quantum, Descriptor Machine Learning, Geometric Deep Learning, and Foundation Models, and outlines a unified taxonomy linking molecular representations, model architectures, and interdisciplinary applications. Benchmark analyses integrate evidence from both widely used datasets and datasets reflecting industry perspectives, encompassing quantum, physicochemical, physiological, and biophysical domains. The survey examines current standards in data curation, splitting strategies, and evaluation protocols, highlighting challenges including inconsistent stereochemistry, heterogeneous assay sources, and reproducibility limitations under random or poorly defined splits. These observations motivate the modernization of benchmark design toward more transparent, time- and scaffold-aware methodologies. We further propose three forward-looking directions: (i) physics-aware learning embedding quantum consistency, (ii) uncertainty-calibrated foundation models for trustworthy inference, and (iii) realistic multimodal benchmark ecosystems integrating computational and experimental data. Repository: https://github.com/Zongru-Li/Survey-and-Benchmarks-of-DL-for-Molecular-Property-Prediction-in-the-Foundation-Model-Era.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16586
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era
Li, Zongru
Chen, Xingsheng
Wen, Honggang
Zhang, Regina Qianru
Li, Ming
Zhang, Xiaojin
Yin, Hongzhi
Yang, Qiang
Lam, Kwok-Yan
Lio, Pietro
Yiu, Siu-Ming
Machine Learning
Artificial Intelligence
Quantitative Methods
Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with physicochemical and biological behavior. This survey traces four complementary paradigms, including Quantum, Descriptor Machine Learning, Geometric Deep Learning, and Foundation Models, and outlines a unified taxonomy linking molecular representations, model architectures, and interdisciplinary applications. Benchmark analyses integrate evidence from both widely used datasets and datasets reflecting industry perspectives, encompassing quantum, physicochemical, physiological, and biophysical domains. The survey examines current standards in data curation, splitting strategies, and evaluation protocols, highlighting challenges including inconsistent stereochemistry, heterogeneous assay sources, and reproducibility limitations under random or poorly defined splits. These observations motivate the modernization of benchmark design toward more transparent, time- and scaffold-aware methodologies. We further propose three forward-looking directions: (i) physics-aware learning embedding quantum consistency, (ii) uncertainty-calibrated foundation models for trustworthy inference, and (iii) realistic multimodal benchmark ecosystems integrating computational and experimental data. Repository: https://github.com/Zongru-Li/Survey-and-Benchmarks-of-DL-for-Molecular-Property-Prediction-in-the-Foundation-Model-Era.
title A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era
topic Machine Learning
Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2604.16586