MS DeNovoML
A generative AI interface for autonomous molecular design to accelerate the discovery of next-generation materials with optimized performance profiles.
MS DeNovoML enables researchers to leverage state-of-the-art generative AI to autonomously produce novel molecular structures optimized for specific performance criteria and material properties. By providing a streamlined graphical environment, the platform allows scientists to navigate complex chemical spaces while balancing multiple design objectives – such as incorporating predictive DeepAutoQSAR models and enforcing physical constraints, like molecular weight and chemical composition. This solution bridges the gap between high-level generative modeling and practical materials science, offering an accessible interface for AI-driven property optimization and design exploration.
Key Capabilities
GUI-powered REINVENT integration
that transforms the REINVENT generative engine into an accessible, panel-based workflow for code-free molecular and materials design
Seamless DeepAutoQSAR model support
to plug in custom-trained predictive models that provide real-time scoring of generated molecules against target properties
Granular structural and property filters
to enforce essential boundaries on molecular weight, molecular descriptors, and specific chemical features to ensure candidates meet project specifications
Autonomous molecular generation using reinforcement learning
to explore vast chemical spaces and generate high-quality candidates that satisfy precise functional requirements
Broad applications across materials science research areas
Related Product
DeepAutoQSAR
Automated, scalable solution for the training and application of predictive machine learning models
MS Informatics
Automated machine learning tools for materials science applications
Schedule a demo on MS DeNovoML
Form submitted
Thank you, we’ll be in touch soon.
Software and services to meet your organizational needs
Software Platform
Deploy digital materials discovery workflows with a comprehensive and user-friendly platform grounded in physics-based molecular modeling, machine learning, and team collaboration.
Research Services
Leverage Schrödinger’s expert computational scientists to assist at key stages in your materials discovery and development process.
Support & Training
Access expert support, educational materials, and training resources designed for both novice and experienced users.