PharmacoMatch: Efficient 3D Pharmacophore Screening through Neural Subgraph Matching

2024-09-10

arXiv.org

AI Summary

Traditional 3D pharmacophore screening suffers from prohibitive computational cost and poor scalability when applied to ultra-large compound libraries. Method: This work reformulates pharmacophore matching as a neural subgraph matching problem and introduces a contrastive learning framework to efficiently encode query–target relationships in the molecular 3D conformational embedding space. The method jointly encodes geometric and chemical pharmacophore features, enabling end-to-end differentiable matching and zero-shot pre-screening without target-specific training. Contribution/Results: Evaluated on billion-scale databases, our approach achieves 10–100× speedup in pre-screening over conventional tools while maintaining hit rates comparable to state-of-the-art pharmacophore methods. It overcomes the fundamental scalability limitations of classical pharmacophore approaches, establishing a new paradigm for large-scale virtual screening that balances computational efficiency with generalization capability.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: 3D Computer Vision

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The increasing size of screening libraries poses a significant challenge for the development of virtual screening methods for drug discovery, necessitating a re-evaluation of traditional approaches in the era of big data. Although 3D pharmacophore screening remains a prevalent technique, its application to very large datasets is limited by the computational cost associated with matching query pharmacophores to database molecules. In this study, we introduce PharmacoMatch, a novel contrastive learning approach based on neural subgraph matching. Our method reinterprets pharmacophore screening as an approximate subgraph matching problem and enables efficient querying of conformational databases by encoding query-target relationships in the embedding space. We conduct comprehensive investigations of the learned representations and evaluate PharmacoMatch as pre-screening tool in a zero-shot setting. We demonstrate significantly shorter runtimes and comparable performance metrics to existing solutions, providing a promising speed-up for screening very large datasets.

Problem

• Addresses computational cost in 3D pharmacophore screening.
• Introduces neural subgraph matching for efficient database querying.
• Improves runtime for screening large datasets in drug discovery.

Innovation

• Neural subgraph matching for pharmacophore screening
• Contrastive learning encodes query-target relationships
• Efficient pre-screening with zero-shot evaluation