MolMole: Molecule Mining from Scientific Literature
By: LG AI Research , Sehyun Chun , Jiye Kim and more
Potential Business Impact:
Lets computers understand chemistry from papers.
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}.
Similar Papers
Assay2Mol: large language model-based drug design using BioAssay context
Machine Learning (CS)
Finds new medicines by reading old science notes.
MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning
CV and Pattern Recognition
Helps computers read chemical pictures accurately.
Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization
Biomolecules
Finds better medicines faster.