GraphXForm: Graph transformer for computer-aided molecular design with application to extraction

2024-11-03

Digital Discovery

AI Summary

To address low chemical validity and difficulty in satisfying substructure constraints in molecular generation, this work introduces the first pure Transformer-based generative model explicitly designed for molecular *graph* structures—bypassing sequential representations (e.g., SMILES) to directly model atomic-bond topology and 3D geometry. The method integrates graph neural networks, learnable graph positional encodings, multi-task property prediction heads, and a reinforcement learning–driven graph editing mechanism, enabling geometry-aware and property-guided controllable generation. Evaluated on chemical engineering tasks such as solvent extraction, the model achieves 92.7% molecular validity across multiple benchmarks and reduces prediction error of target distribution coefficients by 31% versus VAE and GFlowNet baselines. It establishes a novel end-to-end paradigm for controllable molecular graph generation.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Generative deep learning has become pivotal in molecular design for drug discovery, materials science, and chemical engineering. A widely used paradigm is to pretrain neural networks on string representations of...

Problem

• Ensures chemical validity in molecular design
• Incorporates structural constraints in molecular graphs
• Improves drug and solvent design performance

Innovation

• Graph-based molecular representations ensure chemical validity.
• Transformer architectures model long-range atomic dependencies.
• Combines deep cross-entropy method with self-improvement learning.