Digital Co-Expert combines machine learning, computational screening, and expert knowledge to accelerate chemical reaction discovery by 180-fold. Our hybrid human-AI workflow identifies novel cycloaddition reactions in days instead of years, demonstrating practical reaction discovery that's fully compatible with existing laboratory infrastructure.
📖 Citation
If you use this tool or data in your research, please cite:
Kolomoets, N. I., Boiko, D. A., Romashov, L. V., Kozlov, K. S., Gordeev, E. G., Galushko, A. S., & Ananikov, V. P. (2026).
Reaction Discovery Involving Digital co-Expert with a Practical Application in Atom-Economic Cycloaddition.
Angewandte Chemie International Edition. Wiley-VCH.
DOI: 10.1002/anie.202523905
AI-Assisted Screening
Candidate reactions are generated from quantum chemical data, filtered through unsupervised machine learning, and prioritized by our digital co-expert for rapid validation.
180× Faster Discovery
Accelerate reaction discovery from over 1200 days to just 7 days. Two novel cycloaddition reactions were identified and experimentally confirmed within one week.
Human-AI Collaboration
Practical approach combining computational screening, machine learning, and expert knowledge—fully compatible with current laboratory infrastructure without requiring expensive robotic platforms.
Open Source & Collaborative
Digital Co-Expert is open-source and continuously evolving with community contributions.
View on GitHub