OrgFlow: Generative Modeling of Organic Crystal Structures from Molecular Graphs

2026-02-22

AI Summary

Organic crystal structure prediction has long suffered from the absence of efficient data-driven approaches due to challenges such as large unit cells and strict chemical bonding constraints. This work addresses this gap by introducing flow matching to the field for the first time, proposing a molecular graph-based generative model that explicitly incorporates periodic boundary conditions and crystallographic symmetries. To ensure chemically realistic local environments, the authors design a bond-aware loss function that enforces correct atomic connectivity. A dedicated organic crystal dataset and an efficient preprocessing pipeline are also developed to support model training. Experimental results demonstrate that the proposed method achieves over tenfold improvement in matching rate compared to existing baselines while requiring fewer sampling steps, substantially enhancing both the efficiency and accuracy of crystal structure prediction.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Crystal structure prediction is a long-standing challenge in materials science, with most data-driven methods developed for inorganic systems. This leaves an important gap for organic crystals, which are central to pharmaceuticals, polymers, and functional materials, but present unique challenges, such as larger unit cells and strict chemical connectivity. We introduce a flow-matching model for predicting organic crystal structures directly from molecular graphs. The architecture integrates molecular connectivity with periodic boundary conditions while preserving the symmetries of crystalline systems. A bond-aware loss guides the model toward realistic local chemistry by enforcing distributions of bond lengths and connectivity. To support reliable and efficient training, we built a curated dataset of organic crystals, along with a preprocessing pipeline that precomputes bonds and edges, substantially reducing computational overhead during both training and inference. Experiments show that our method achieves a Match Rate more than 10 times higher than existing baselines while requiring fewer sampling steps for inference. These results establish generative modeling as a practical and scalable framework for organic crystal structure prediction.

Problem

• organic crystal structure prediction
• molecular graphs
• crystal structure prediction
• generative modeling
• chemical connectivity

Innovation

• flow-matching
• organic crystal structure prediction
• molecular graph
• bond-aware loss
• generative modeling