Deep learning-based automatic action extraction from structured chemical synthesis procedures

Mantas Vaškevičius; Jurgita Kapočiūtė-Dzikienė; Arnas Vaškevičius; Liudas Šlepikas

doi:10.7717/peerj-cs.1511

Deep learning-based automatic action extraction from structured chemical synthesis procedures

PeerJ Comput Sci. 2023 Aug 18:9:e1511. doi: 10.7717/peerj-cs.1511. eCollection 2023.

Authors

Mantas Vaškevičius^{1

2}, Jurgita Kapočiūtė-Dzikienė¹, Arnas Vaškevičius³, Liudas Šlepikas²

Affiliations

¹ Department of Applied Informatics, Vytautas Magnus University, Kaunas, Lithuania.
² JSC Synhet, Kaunas, Lithuania.
³ Faculty of Mechanical Engineering and Design, Kaunas University of Technology, Kaunas, Lithuania.

Abstract

This article proposes a methodology that uses machine learning algorithms to extract actions from structured chemical synthesis procedures, thereby bridging the gap between chemistry and natural language processing. The proposed pipeline combines ML algorithms and scripts to extract relevant data from USPTO and EPO patents, which helps transform experimental procedures into structured actions. This pipeline includes two primary tasks: classifying patent paragraphs to select chemical procedures and converting chemical procedure sentences into a structured, simplified format. We employ artificial neural networks such as long short-term memory, bidirectional LSTMs, transformers, and fine-tuned T5. Our results show that the bidirectional LSTM classifier achieved the highest accuracy of 0.939 in the first task, while the Transformer model attained the highest BLEU score of 0.951 in the second task. The developed pipeline enables the creation of a dataset of chemical reactions and their procedures in a structured format, facilitating the application of AI-based approaches to streamline synthetic pathways, predict reaction outcomes, and optimize experimental conditions. Furthermore, the developed pipeline allows for creating a structured dataset of chemical reactions and procedures, making it easier for researchers to access and utilize the valuable information in synthesis procedures.

Keywords: Artificial intelligence; Data mining; Data science; Deep learning; Machine learning; Natural language processing; Organic chemistry; Synthesis procedures; Text classification; Text generation.

Grants and funding

This work was supported by the Vytautas Magnus University and JSC Synhet. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.