Elsevier and LG AI Research unlock more chemistry hidden in scientific images

Elsevier and LG AI Research today announced that researchers can now identify chemistry that has often sat beyond the reach of search: the substances that appear only as images, drawings and reaction schemes in patents and scientific literature.

Visual chemistry of this kind has long been difficult for both humans and machines to index at scale. Now, chemistry-specific AI vision technology developed by LG AI Research is being used within Elsevier’s content extraction and curation processes for Reaxys, Elsevier’s discovery chemistry solution. Substance information from images in patent and journal content is captured far more quickly, accurately, and at far greater scale than was previously possible. This work enhances Elsevier’s leading content extraction and scientific curation of substances, reactions, bioactivities, biological targets and substance properties for Reaxys.

Why it matters

Much of the substance and reaction information chemists rely on is communicated through figures, drawings and reaction schemes rather than searchable text. When that chemistry isn’t searchable, researchers can be left checking documents by hand to confirm whether a compound or reaction has already been described. Making that chemistry discoverable at scale is a specialist AI challenge. Chemical drawings encode meaning through bonds, atoms, stereochemistry and spatial relationships. A model that misreads a bond may identify the wrong compound; one that misses a structure gives chemists an incomplete picture. This matters most in areas such as novelty searching, competitive intelligence and synthesis planning, and in inorganic and organometallic chemistry, where complex structures are harder to extract and index.

Built for chemical drawings

The novel chemistry-specific AI vision technology from LG AI Research combines molecule detection, reaction-diagram parsing and optical chemical structure recognition (OCSR) in a single model. In the company’s published benchmarkingopens in new tab/window, it outperforms alternatives at extracting chemistry from a full document page, placing the technology at the forefront of innovation for reading chemistry across formats. Each extraction pipeline is validated against existing Reaxys benchmarks before it goes live, so accuracy is not traded for scale. The full pipeline has undergone a rigorous period of testing across Elsevier’s data and workflow tools to ensure accuracy and quality before wider use.

Mirit Eldor, Managing Director, Life Sciences, Elsevier, said: “Every hour a chemist spends deciphering figures or images to see what has already been made is an hour that could instead be spent on chemistry discovery. Our partnership with LG AI Research gives that time back, lifting more chemistry out of the image and into Reaxys - curated, searchable and ready to act on. A structure buried in a figure should be evidence rather than a dead end.”

Hwayoung Edward Lee, lead of the AI Biz Transformation Unit at LG AI Research, said: “Understanding scientific images requires AI engineered specifically for chemistry — where every bond and spatial layout holds critical meaning. We designed our AI vision model to decode these complex visual representations with human-expert precision. Through our integration with Elsevier, we are proving that advanced chemistry-specific AI can seamlessly convert raw visual data into structured knowledge for global researchers.”

Extending the partnership

Reaction extraction is the next stage of the collaboration, extending image-based extraction beyond individual substances to broaden the reaction evidence available through Reaxys. Elsevier and LG AI Research are also exploring further customer challenges to tackle together, bringing together LG AI Research’s specialist AI capabilities with Elsevier’s chemistry content, scientific expertise and curation.

This work follows Elsevier’s Responsible AI Principles and Privacy Principles.

To learn more, visit www.elsevier.com/products/reaxys

About LG AI Research

Established in December 2020, LG AI Research serves as the AI think tank for the LG Group. Its mission is to enhance AI capabilities by addressing business challenges, conducting cutting-edge AI research, and establishing and implementing ethical principles for AI technology. Leveraging EXAONE (Expert AI for Everyone), a proprietary large-scale AI model developed since 2021, the center has been driving innovation across various industries.

Furthermore, by successfully passing the technological evaluation in the ‘National AI Foundation Model Project’ — an initiative launched to resolve dependency on global models — LG AI Research has firmly solidified its position as Korea’s flagship AI company.

關於 Elsevier

身為科學資訊與分析的全球領導者，Elsevier 協助研究人員與醫療照護專業人員推動科學發展，改善醫療成果，造福社會。我們以可信賴、以實證為基礎的內容和先進的 AI 數位技術為基礎，透過創新的解決方案促進洞察力和關鍵決策。

140 多年來，我們一直為研究和醫療保健界的工作提供支援。我們全球 9,500 名員工，包括 2,300 名技術人員，致力於支援研究人員、圖書館館長、學術領袖、資金提供者、政府、研發密集型公司、醫生、護士、未來醫療保健專業人員和教育工作者的重要工作。我們的 2,900 種科學期刊和經典參考工具書包括其領域中最重要的書籍，包括 Cell Press、The Lancet 和 Gray's Anatomy。 我們與愛思唯爾基金會 (Elsevier Foundationopens in new tab/window) 合作，與我們服務的社群攜手合作，在發展中國家和世界各地的科學、研究和醫療保健領域推動包容性和多樣性。 Elsevier 是 RELXopens in new tab/window 的一部分，RELXopens in new tab/window 是一家為專業和商業客戶提供以資訊為基礎的分析和決策工具的全球供應商。有關我們的工作、數位解決方案和內容的更多資訊，請造訪 www.elsevier.com 。