Automate Chemical Data Extraction

Generate machine readable molecular structures from images and documents with high accuracy
Free for a limited time
Screenshot of LewisScreenshot of Card
What Lewis offers to you
Features
Save Time
Save Time
Simply upload individual images
or PDF documents and Lewis will do the rest
Use Structured Data
Use Structured Data
Export molecular structures in multiple file formats like: csv, sdf, smiles
Import datasets to tools of your choice
Expert Tool
Built for Experts
Reduced Error rate
Reduced Error rate
Lewis relies on automated rule generation by combining diverse Deep Neural Network Architectures, offering higher accuracy compared to methods using handwritten rules.
Recognition Versatility
Recognition Versatility
Lewis is trained to recognize a wide range of chemical drawing styles, image quality and representation types.
Designed for anybody who deals with chemical data
Upload a document, download and share the generated chemical library with others.
Lewis Beta
Beta offering
Beta Upload
Beta Center
Beta Export
Upload up to 100 pages per week
100 pages not enough? Get a refill at any time for free
Access your generated chemical library 24/7
Request error support & feature support
Illustration Science
Science behind lewis
Solving a recognized challenge of chemical data retrieval with the power of artificial intelligence

The need for a practical method for automated processing of image-based chemical structures

Most scientific and patent documents dealing with chemistry describe molecular structures either with systematic names or graphical images of Lewis structures. Graphical images pose inherent problems in automated processing when working with hundreds of thousands or even millions of documents since such representations cannot be directly interpreted by a computer.

Available image-based extraction methods are based on handwritten rules. A handwritten rule-based classification of structural features in molecular images is extremely error-prone because typical drawing styles of molecular structure follow no standard.

Application of Deep Neural
Network Technology

Lewis is a novel software tool based on deep neural network technology which reliably extracts machine-readable chemical structures from image representations in a convenient web platform. Instead of relying on handwritten rules, we rely on a strong combination of different neural network architectures that yield enhanced robustness.

Science behind lewis
Lewis Data Retrieval Procedure
Beta Upload
1
Extract image or page
2
Recognize structure
3
Detect all structuring elements
4
Rebuild molecular graph and convert structure to machine-readable representation
Illustration Communication
Lewis Beta
A message from the team

Please keep in mind Lewis is in Beta:

If you experience any issue you are welcome to reach out to the team via mail.
Lewis Team is dedicated to empowering scientists. We encourage you to share your Lewis experiences and features expectations with the team.
Coming Soon
API access and documentation for 3rd party application development (Get more information)
Parallel document upload and processing of multiple documents with high velocity
Molecular Search to search for specific chemicals in documents
Single Sign on