Efficient 3D kernels for molecular property prediction
Open Access
- 1 July 2025
- journal article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 41 (Supplement) , i58-i67
Abstract
Motivation: This paper addresses the challenge of incorporating 3-dimensional (3D) structural information in graph kernels for machine learning-based virtual screening, a crucial task in drug discovery. Existing kernels that capture 3D information often suffer from high computational complexity, which limits their scalability. Results: To overcome this, we propose the 3D chain motif graph kernel, which effectively integrates essential 3D structural properties—bond length, bond angle, and torsion angle—within the three-hop neighborhood of each atom in a molecule. In addition, we introduce a more computationally efficient variant, the 3D graph hopper kernel (3DGHK), which reduces the complexity from the state-of-the-art O(n6) (for the 3D pharmacophore kernel) to O(n2(m+log(n)+δ2+dT6)). Here, n is the number of nodes, T is the highest degree of the node, m is the number of edges, δ is the diameter of the graph, and d is the dimension of the attributes of the nodes. We conducted experiments on 21 datasets, demonstrating that 3DGHK outperforms other state-of-the-art 2D and 3D graph kernels, but it also surpasses deep learning models in classification accuracy, offering a powerful and scalable solution for virtual screening tasks. Availability and implementation: Our code is publicly available at https://github.com/SantaAnkit/Efficient-3D-kernels-for-molecular-property-prediction.git.Keywords
This publication has 12 references indexed in Scilit:
- A brief review of protein–ligand interaction predictionComputational and Structural Biotechnology Journal, 2022
- Generating 3D molecules conditional on receptor binding sites with deep generative modelsChemical Science, 2022
- From atoms to bonds, angles and torsions: molecular metrics from crystal space, and two Excel implementationsJournal of Applied Crystallography, 2020
- A survey on graph kernelsApplied Network Science, 2020
- Graph convolutional networks: a comprehensive reviewComputational Social Networks, 2019
- Internal Coordinate Molecular Dynamics: A Foundation for Multiscale DynamicsThe Journal of Physical Chemistry B, 2014
- Open Babel: An open chemical toolboxJournal of Cheminformatics, 2011
- Recent Advances in Ligand-Based Drug Design: Relevance and Utility of the Conformationally Sampled Pharmacophore ApproachCurrent Computer-Aided Drug Design, 2011
- A structural alignment kernel for protein structuresBioinformatics, 2007
- The Pharmacophore Kernel for Virtual Screening with Support Vector MachinesJournal of Chemical Information and Modeling, 2006