Materials Discovery
It can take over 10 years to come up with new materials. At IBM Research, we’re looking to accelerate the discovery process using new AI methods, robotics, the hybrid cloud, and quantum computers. Our goal is to unlock new properties and materials to address global challenges in years not decades.
Our work
Computer simulations identify new ways to boost the skin’s natural protectors
ResearchHow to use AI to discover new drugs and materials with limited data
NewsWhat are generative AI models?
ExplainerMachine learning is helping harness the power of enzymes for greener chemistry
ResearchAccelerating molecular optimization with AI
Deep DiveThe first atomic-resolution images of extraterrestrial molecules
Research- See more of our work on Materials Discovery
Tools + code
RoboRXN for Chemistry
A unique tool for digital chemistry. Language models based on transformers can predict the most likely outcome of a chemical reaction and perform retrosynthetic analysis. RoboRXN can also program hardware to produce a molecule in a remotely accessible, autonomous chemical laboratory.
View project →IBM Molecule Generation Experience
An AI-driven molecular inverse-design platform, which automatically designs brand new molecular structures rapidly and diversely.
View project →RXNmapper
A chemically agnostic attention-guided reaction mapper.
View project →Deep Search Knowledge Graph of COVID-19 Literature
IBM is providing free access to its COVID-19 Knowledge Graph, which is part of its Corpus Processing Service. This knowledge graph integrates COVID-19 data from various sources.
View project →CIRCA
CIRCA enables easy search, visualization, and flexible export options of chemically-annotated data from publicly available patents and other data sources.
View project →
Publications
- 2022
- ACS Fall 2022
- 2022
- ISOEN 2022
- 2022
- Advanced Science
- 2022
- ICLR 2022
- 2022
- ICLR 2022
- 2022
- ACS Nano
Project Photoresist
We used our accelerated discovery process to identify and synthesize a novel photoacid generator in less than a year — far quicker than it usually takes.