Kyulux has announced that it has secured a license to Harvard University's Molecular Space Shuttle deep learning system for the discovery of materials for display and lighting applications.The Molecular Space Shuttle is an artificial intelligence platform designed by Alán Aspuru-Guzik's group at Harvard's Department of Chemistry and Chemical Biology.
The license agreement coordinated by Harvard's Office of Technology Development provides Kyulux with rights to the copyrighted software. The algorithms dramatically reduce the computational cost of testing candidate molecules for new technologies.
In addition to Kyulux's licensing of the software, three key researchers who developed the system in Aspuru-Guzik's research group and were co-authors on the Nature Materials publication have chosen to join Kyulux's computational chemistry group in Boston.
These three Harvard-trained researchers will be joining Kyulux's North America Office, which is opening this month in the Downtown Boston area to carry out computational discovery and experimental synthesis and characterisation.
In a publication last week in Nature Materials (Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach), co-authored by researchers at Harvard, Samsung Advanced Institute of Technology and MIT, Aspuru-Guzik and his group demonstrated the ability of the system to rapidly screen millions of molecules for stability and other characteristics necessary for a molecule to produce light with the characteristics necessary for use in commercial production of cell phone and television displays.
Professor Aspuru-Guzik will also join the company as a part-time scientific advisor. Aspuru-Guzik will be among three other TADF academic research leaders, Chihaya Adachi and Hajime Nakanotani from Kyushu University and Hironori Kaji from the University of Kyoto, joining a world-class team of scientific advisors to Kyulux.
Aspuru-Guzik, Professor of Chemistry and Chemical Biology, said, "By developing a sophisticated molecular builder, using state-of-the-art quantum chemistry and machine learning, in addition to drawing on the expertise of experimentalists, we discovered a large set of high-performing blue OLED materials." Aspuru-Guzikadded, "Following that validation, I am extremely excited to see this platform adopted for commercial development, utilizing its capabilities for the rapid screening of TADF materials."
Rafael Gómez-Bombarelli, a postdoctoral fellow in the Aspuru-Guzik lab and first author of the paper, said, "We were able to model these molecules in a way that was really predictive." Rafael added, "We could predict the color and the brightness of the molecules from a simple quantum chemical calculation and about 12 hours of computing per molecule."
Junji Adachi, CTO of Kyulux, said, "TADF molecules require very complicated material design rules to achieve highly efficient emission and long lifetimes for commercialization. The Molecular Space Shuttle enables us to access a wide variety of molecules which we have not designed yet within a short period. This is a key technology for enhancing the competitiveness of Kyulux.""Kyulux is excited to be able to incorporate the capabilities of these researchers. Kyulux has assembled one of the finest teams of organic chemists and device physicists in the OLED field in the world. Adding the incoming team and the Molecular Space Shuttle will allow us to rapidly accelerate our discovery and commercialization of the next generation of OLED materials," said Dr. Christopher Savoie, CEO of Kyulux.
Professor Chihaya Adachi of Kyushu University, said, "I am sure that an unlimited possibility for molecular design will change the world of organic electronics and photonics. We are very much excited to have a collaborative and productive relationship with Alan's group. The combined capabilities of the computational chemistry from Harvard and the vast experience in OLEDs at OPERA, Kyushu Univ. and Kyulux will pioneer a new direction in the study of organic electronics."
Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach
Rafael Gómez-Bombarelli | Jorge Aguilera-Iparraguirre | Timothy D. Hirze | David Duvenaud, Dougal Maclaurin | Martin A. Blood-Forsythe | Hyun Sik Chae | Markus Einzinger | Dong-Gwang Ha | Tony Wu | Georgios Markopoulos | Soonok Jeon | Hosuk Kang | Hiroshi Miyazaki | Masaki Numata | Sunghan Kim | Wenliang Huang | Seong Ik Hong | Marc Baldo | Ryan P. Adams | Alán Aspuru-Guzik
Nature Materials | (2016) | doi:10.1038/nmat4717
Received 18 December 2015 | Accepted 04 July 2016 | Published online 08 August 2016
Virtual screening is becoming a ground-breaking tool for molecular discovery due to the exponential growth of available computer time and constant improvement of simulation and machine learning techniques. We report an integrated organic functional material design process that incorporates theoretical insight, quantum chemistry, cheminformatics, machine learning, industrial expertise, organic synthesis, molecular characterization, device fabrication and optoelectronic testing. After exploring a search space of 1.6 million molecules and screening over 400,000 of them using time-dependent density functional theory, we identified thousands of promising novel organic light-emitting diode molecules across the visible spectrum. Our team collaboratively selected the best candidates from this set. The experimentally determined external quantum efficiencies for these synthesized candidates were as large as 22%.
Figure: Harvard University - Discovery pipeline
a, Diagram of the collaborative discovery approach: the search space decreases by over five orders of magnitude as the screening progresses. The cubes represent the size of the chemical space considered at any given stage of the process