PDCG: A Diffusion Model Guided by Pre-Training for Molecular Conformation Generation
Open Access
Abstract
Background: While machine learning has advanced molecular conformation generation, existing models often suffer from limited generalization and inaccuracies, especially for complex molecular structures. These limitations hinder their reliability in downstream applications. Methods: We proposed a molecular conformation model combined with a molecular graph pre-training module and a diffusion model (PDCG). Feature embeddings are obtained from a pre-trained model and concatenated with the molecular graph information. Fusion features are used for generating conformations in the model. The model was trained and evaluated on the GEOM-QM9 and GEOM-Drugs datasets. Results: PDCG significantly outperforms existing baselines, which shows markedly superior results. Furthermore, in downstream molecular property prediction tasks, conformations generated by PDCG yield results comparable to those derived from DFT-optimized geometries. Conclusions: Our work provides a robust and generalizable model for accurate conformation generation. PDCG offers a reliable tool for downstream computational tasks, such as the virtual screening of functional materials and drug-like molecules.Keywords
Funding Information
- National Natural Science Foundation of China (22173083)
- the Fundamental Research Funds of State Key Laboratory of Cotton Bio-breeding and Integrated Utilization (CBIUZ2025001)
This publication has 23 references indexed in Scilit:
- Conf-GEM: A geometric information-assisted direct conformation generation modelArtificial Intelligence Chemistry, 2024
- COSMIC: Molecular Conformation Space Modeling in Internal Coordinates with an Adversarial FrameworkJournal of Chemical Information and Modeling, 2024
- Leveraging 2D molecular graph pretraining for improved 3D conformer generation with graph neural networksComputers & Chemical Engineering, 2024
- A knowledge-guided pre-training framework for improving molecular representation learningNature Communications, 2023
- Small-Molecule Conformer Generators: Evaluation of Traditional Methods and AI Models on High-Quality Data SetsJournal of Chemical Information and Modeling, 2023
- Direct generation of protein conformational ensembles via machine learningNature Communications, 2023
- Highly accurate protein structure prediction with AlphaFoldNature, 2021
- Cryo-EM in drug discovery: achievements, limitations and prospectsNature Reviews Drug Discovery, 2018
- Conformation Generation: The State of the ArtJournal of Chemical Information and Modeling, 2017
- ConfGen: A Conformational Search Method for Efficient Generation of Bioactive ConformersJournal of Chemical Information and Modeling, 2010