Workshop: SELFIES and the future of molecular string representations
(Not that kind of selfie, the self-referencing embedded strings kind)
Join us on August 13, 2021, for the first workshop on SELFIES and the future of representations for AI in chemistry. Presented in partnership with IOP Publishing's Machine Learning: Science & Technology journal and the Acceleration Consortium (AC).
Less than one year ago, IOP Publishing's Machine Learning: Science & Technology (MLST) journal published SELFIES: a 100% robust molecular string representation. It has since then fuelled numerous Artificial Intelligence (AI) applications in material science and chemistry. To our delight, it has also been the most downloaded and cited paper published in MLST to date.
In partnership with IOP Publishing and the Acceleration Consortium, we want to celebrate this occasion with a mini workshop. Together with the community, we will look into the future and discuss open challenges and opportunities for string-based representations in chemistry. We will kick off new exciting applications to advance AI for material science in a number of working groups. Suggestions for working group topics are very welcome; please send to Mario Krenn at mario.krenn@utoronto.ca.
Workshop
SELFIES and the future of molecular string representations
August 13, 2021
9.00–12.00 EST / 14.00-17.00 BST / 15.00-18.00 CEST
Preliminary program (in EST):
09.00-10.00:
Introduction to SELFIES - Prof. Alan Aspuru-Guzik (University of Toronto)
Tutorial on the application of SELFIES - Akshat Nigam (University of Toronto & Stanford University)
10.00-12.00:
Working groups to kickoff new applications and extensions of SELFIES and general molecular string representations
Short conclusions from working groups and strategy of how to push further
Sign-up now, spaces are limited!
Organizers
Alán Aspuru-Guzik, Akshat Nigam, Robert Pollice, Gabe Gomes, Chong Sun, Mario Krenn, Kjell Jorner
Speakers
Alán Aspuru-Guzik is the Director of the Acceleration Consortium and the Canada 150 Research Chair in Theoretical and Quantum Chemistry. He is a professor in the Departments of Chemistry and Computer Science at the University of Toronto, and a CIFAR AI Chair at the Vector Institute. Alán is a renowned scientist in clean energy materials, computational chemistry, quantum computing, AI and autonomous experimentation.
AkshatKumar (Akshat) Nigam is a Computer Science PhD student at Stanford University. Before starting at Stanford, he studied at the University of Toronto, actively doing research in Alan Aspuru-Guzik's MatterLab. There, he helped in the development of SELFIES, along with its applications to inverse molecular design.
Partners
This workshop is presented in partnership with IOP Publishing's Machine Learning: Science & Technology journal and the Acceleration Consortium (AC).
IOP Publishing is a society-owned scientific publisher, providing impact, recognition and value for the scientific community. We work closely with researchers, librarians and partners worldwide to produce academic journals, books and conference series. Our aim is to cover the latest and best research in the physical sciences and beyond.
Machine Learning: Science and Technology is a multidisciplinary open access journal that bridges the application of machine learning across the sciences with advances in machine learning methods and theory as motivated by physical insights.
Based at the University of Toronto, the Acceleration Consortium is a global community of academia, government, industry and entrepreneurs dedicated to accelerating the discovery of new materials and molecules.
