RFL: Simplifying Chemical Structure Recognition with Ring-Free Language

2024-12-10

arXiv.org

AI Summary

Existing chemical structure recognition methods struggle to accurately parse 2D molecular graphs containing fused rings and complex branching. To address this, we propose Ring-Free Language (RFL), a novel hierarchical representation that decouples molecules into an acyclic skeleton and independent ring or branch components—ensuring uniqueness, conciseness, and human interpretability. We further design the Molecular Skeleton Decoder (MSD), a unified framework that explicitly separates skeleton generation from ring/branch prediction. MSD comprises three core modules: progressive skeleton generation, ring detection, and branch classification, and is compatible with both OCR- and GNN-based backbones. Evaluated on both printed and handwritten chemical structure recognition benchmarks, our method achieves state-of-the-art performance, significantly improving accuracy and cross-domain generalization. The source code is publicly available.

Technology Category

• Machine Learning: Structured Learning
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The primary objective of Optical Chemical Structure Recognition is to identify chemical structure images into corresponding markup sequences. However, the complex two-dimensional structures of molecules, particularly those with rings and multiple branches, present significant challenges for current end-to-end methods to learn one-dimensional markup directly. To overcome this limitation, we propose a novel Ring-Free Language (RFL), which utilizes a divide-and-conquer strategy to describe chemical structures in a hierarchical form. RFL allows complex molecular structures to be decomposed into multiple parts, ensuring both uniqueness and conciseness while enhancing readability. This approach significantly reduces the learning difficulty for recognition models. Leveraging RFL, we propose a universal Molecular Skeleton Decoder (MSD), which comprises a skeleton generation module that progressively predicts the molecular skeleton and individual rings, along with a branch classification module for predicting branch information. Experimental results demonstrate that the proposed RFL and MSD can be applied to various mainstream methods, achieving superior performance compared to state-of-the-art approaches in both printed and handwritten scenarios. The code is available at https://github.com/JingMog/RFL-MSD.

Problem

• Complex Molecular Structure Recognition
• Chemical Structure Identification
• Ring and Branching Structures

Innovation

• Ring-Free Language (RFL)
• Molecular Scaffold Decoder (MSD)
• Chemical Structure Recognition