Learned Conformational Space and Pharmacophore Into Molecular Foundational Model
Top Cited Papers
Open Access
- 4 January 2026
- journal article
- Published by Wiley in Advanced Science
- Vol. 13 (17) , e13556
Abstract
The emergence of large‐scale chemical pre‐trained models has significantly advanced our ability to capture complex relationships between molecular structures and their functions. Despite the growing interest in molecular foundational model that provide versatile representations and support molecular optimization for downstream tasks, few efforts have integrated explicit chemical knowledge—such as conformational and pharmacophore information—into pre‐training. Given the highly dynamic nature of small molecules in solution, their conformational changes upon target binding, and the critical role of pharmacophore complementarity, it is essential to incorporate these factors into molecular foundational modeling. Here, we present a molecular foundational model that integrates conformational‐space and pharmacophore‐similarity projections during pre‐training to regularize the representation space. The model adopts an Ouroboros‐like architecture, where the molecular graphs are encoded into 1D representation vectors via a graph neural network and subsequently reconstructed back into SMILES sequences through an autoregressive Transformer module. This dual‐module design establishes a flexible and extensible framework for both representation learning and molecular generation within a unified latent space. Extensive experiments demonstrate that our model effectively addresses a variety of practical chemical challenges, including similarity‐based virtual screening, targeted poly‐pharmacology design, chemical property prediction, and directed molecular optimization.Keywords
Funding Information
- Agency for Science, Technology and Research (A*STAR H25J6a0034)
This publication has 68 references indexed in Scilit:
- Generative artificial intelligence for small molecule drug designCurrent Opinion in Biotechnology, 2024
- UCSF ChimeraX: Structure visualization for researchers, educators, and developersProtein Science, 2020
- LIT-PCBA: An Unbiased Data Set for Machine Learning and Virtual ScreeningJournal of Chemical Information and Modeling, 2020
- Sigmoid-weighted linear units for neural network function approximation in reinforcement learningNeural Networks, 2018
- Discovery of triazines as potent, selective and orally active PDE4 inhibitorsBioorganic & Medicinal Chemistry Letters, 2013
- Pyrazolopyridines as potent PDE4B inhibitors: 5-Heterocycle SARBioorganic & Medicinal Chemistry Letters, 2010
- Ligand efficiency and fragment-based drug discoveryDrug Discovery Today, 2009
- The use of pH measurements to predict the potential of chemicals to cause acute dermal and ocular toxicityToxicology, 2001
- Effect of standardization on fragment-based measures of structural similarityJournal of Chemometrics, 1993
- Macromodel—an integrated software system for modeling organic and bioorganic molecules using molecular mechanicsJournal of Computational Chemistry, 1990