_version_ 1866916725833859072
author Research, LG AI
Chun, Sehyun
Kim, Jiye
Jo, Ahra
Jo, Yeonsik
Oh, Seungyul
Lee, Seungjun
Ryoo, Kwangrok
Lee, Jongmin
Kim, Seung Hwan
Kang, Byung Jun
Lee, Soonyoung
Park, Jun Ha
Moon, Chanwoo
Ham, Jiwon
Lee, Haein
Han, Heejae
Byun, Jaeseung
Do, Soojong
Ha, Minju
Kim, Dongyun
Bae, Kyunghoon
Lim, Woohyung
Lee, Edward Hwayoung
Park, Yongmin
Yu, Jeongsang
Jo, Gerrard Jeongwon
Hong, Yeonjung
Yoo, Kyungjae
Han, Sehui
Lee, Jaewan
Park, Changyoung
Jeon, Kijeong
Yi, Sihyuk
author_facet Research, LG AI
Chun, Sehyun
Kim, Jiye
Jo, Ahra
Jo, Yeonsik
Oh, Seungyul
Lee, Seungjun
Ryoo, Kwangrok
Lee, Jongmin
Kim, Seung Hwan
Kang, Byung Jun
Lee, Soonyoung
Park, Jun Ha
Moon, Chanwoo
Ham, Jiwon
Lee, Haein
Han, Heejae
Byun, Jaeseung
Do, Soojong
Ha, Minju
Kim, Dongyun
Bae, Kyunghoon
Lim, Woohyung
Lee, Edward Hwayoung
Park, Yongmin
Yu, Jeongsang
Jo, Gerrard Jeongwon
Hong, Yeonjung
Yoo, Kyungjae
Han, Sehui
Lee, Jaewan
Park, Changyoung
Jeon, Kijeong
Yi, Sihyuk
contents The extraction of molecular structures and reaction data from scientific documents is challenging due to their varied, unstructured chemical formats and complex document layouts. To address this, we introduce MolMole, a vision-based deep learning framework that unifies molecule detection, reaction diagram parsing, and optical chemical structure recognition (OCSR) into a single pipeline for automating the extraction of chemical data directly from page-level documents. Recognizing the lack of a standard page-level benchmark and evaluation metric, we also present a testset of 550 pages annotated with molecule bounding boxes, reaction labels, and MOLfiles, along with a novel evaluation metric. Experimental results demonstrate that MolMole outperforms existing toolkits on both our benchmark and public datasets. The benchmark testset will be publicly available, and the MolMole toolkit will be accessible soon through an interactive demo on the LG AI Research website. For commercial inquiries, please contact us at \href{mailto:contact_ddu@lgresearch.ai}{contact\_ddu@lgresearch.ai}.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03777
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MolMole: Molecule Mining from Scientific Literature
Research, LG AI
Chun, Sehyun
Kim, Jiye
Jo, Ahra
Jo, Yeonsik
Oh, Seungyul
Lee, Seungjun
Ryoo, Kwangrok
Lee, Jongmin
Kim, Seung Hwan
Kang, Byung Jun
Lee, Soonyoung
Park, Jun Ha
Moon, Chanwoo
Ham, Jiwon
Lee, Haein
Han, Heejae
Byun, Jaeseung
Do, Soojong
Ha, Minju
Kim, Dongyun
Bae, Kyunghoon
Lim, Woohyung
Lee, Edward Hwayoung
Park, Yongmin
Yu, Jeongsang
Jo, Gerrard Jeongwon
Hong, Yeonjung
Yoo, Kyungjae
Han, Sehui
Lee, Jaewan
Park, Changyoung
Jeon, Kijeong
Yi, Sihyuk
Machine Learning
The extraction of molecular structures and reaction data from scientific documents is challenging due to their varied, unstructured chemical formats and complex document layouts. To address this, we introduce MolMole, a vision-based deep learning framework that unifies molecule detection, reaction diagram parsing, and optical chemical structure recognition (OCSR) into a single pipeline for automating the extraction of chemical data directly from page-level documents. Recognizing the lack of a standard page-level benchmark and evaluation metric, we also present a testset of 550 pages annotated with molecule bounding boxes, reaction labels, and MOLfiles, along with a novel evaluation metric. Experimental results demonstrate that MolMole outperforms existing toolkits on both our benchmark and public datasets. The benchmark testset will be publicly available, and the MolMole toolkit will be accessible soon through an interactive demo on the LG AI Research website. For commercial inquiries, please contact us at \href{mailto:contact_ddu@lgresearch.ai}{contact\_ddu@lgresearch.ai}.
title MolMole: Molecule Mining from Scientific Literature
topic Machine Learning
url https://arxiv.org/abs/2505.03777