Idea
System converting chemical literature images into accurate, machine-readable molecular and reaction data for research and development.
Research Paper
Core Innovation
This paper introduces MinerU.Chem, which integrates five chemistry-specific modules into a general document parsing pipeline to accurately extract molecular structures and reactions from images. It uses CARBON notation to preserve visual and chemical semantics, achieving a 93.02% SMILES exact-match accuracy, significantly outperforming prior systems.
Why It Matters
Chemical research and patent documents often contain complex images that are difficult to convert into usable data, limiting automation and AI applications in chemistry. MinerU.Chem streamlines data extraction, enabling faster knowledge base construction and improved AI-driven chemical analysis. This enhances efficiency and scalability in drug discovery, reaction prediction, and molecular design workflows.
Market Size (TAM)
$2–10B TAM for chemical data extraction and AI chemistry tools; $500M–$1B SAM from pharmaceutical and chemical research sectors. Driven by increasing AI adoption and demand for automated data processing.
Potential Customers & Pain Points
- Pharmaceutical companies – Need automated extraction of chemical data from literature
- Chemical research institutions – Require accurate molecular structure recognition for data analysis
- Patent offices – Need efficient parsing of chemical reaction schemes
- AI-driven chemistry startups – Require high-quality training data for models.
Business Model
Subscription-based SaaS platform integrated into MinerU with tiered pricing for academic, research, and enterprise users; potential licensing for API access and custom integrations.
Competitive Landscape
- GPT-5.6-Sol
- ChemDataExtractor
- OSRA
- ChemReader
Implementation Challenges
- Integration with diverse document formats and image qualities
- Adoption resistance due to existing manual workflows
- Need for continuous updates to handle new chemical notation styles
Validation Strategy
- Pilot deployments with pharmaceutical and chemical research labs
- Benchmarking against existing chemical structure recognition tools
- User feedback collection to improve accuracy and usability
- Partnerships with patent offices and AI chemistry startups for real-world testing
Research Paper Overview
MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition
Summary
MinerU.Chem is a document parsing system integrated into the MinerU platform that converts organic chemistry images into machine-readable molecular and reaction data. It uses five chemistry-specific modules to extract and recognize molecular structures and reactions with high accuracy, outperforming existing systems. The system supports export to standard chemical formats and is accessible online.