One Strike, You're Out: Detecting Markush Structures in Low Signal-to-Noise Ratio Images

TL;DR

This paper introduces a novel CNN-based method for accurately classifying Markush chemical structures in images, significantly improving the performance of Optical Chemical Structure Recognition systems.

Contribution

The study compares fixed-feature extraction with end-to-end CNN learning, demonstrating the superior effectiveness of the CNN approach for Markush structure classification.

Findings

CNN achieved 0.928 Macro F1 score, outperforming fixed-feature methods.

End-to-end learning provides a lower bound that can be further improved.

Method enhances OCSR pipeline accuracy and reliability.

Abstract

Modern research increasingly relies on automated methods to assist researchers. An example of this is Optical Chemical Structure Recognition (OCSR), which aids chemists in retrieving information about chemicals from large amounts of documents. Markush structures are chemical structures that cannot be parsed correctly by OCSR and cause errors. The focus of this research was to propose and test a novel method for classifying Markush structures. Within this method, a comparison was made between fixed-feature extraction and end-to-end learning (CNN). The end-to-end method performed significantly better than the fixed-feature method, achieving 0.928 (0.035 SD) Macro F1 compared to the fixed-feature method's 0.701 (0.052 SD). Because of the nature of the experiment, these figures are a lower bound and can be improved further. These results suggest that Markush structures can be filtered out effectively and accurately using the proposed method. When implemented into OCSR pipelines, this method can improve their performance and use to other researchers.