Events Calendar

Eigencages: Learning a Latent Space of Porous Cage Molecules

Cory Simon, Assistant Professor
Chemical, Biological, and Environmental Engineering
Oregon State University

Abstract

Porous organic cage molecules harbor nanosized cavities that selectively adsorb gas molecules, lending them applications in separations and sensing. For comparing cages and predicting their adsorption properties, we embed/encode a set of 74 porous organic cage molecules into a low-dimensional, latent “cage space” on the basis of their intrinsic porosity. We first computationally scan each cage to generate a three-dimensional (3D) image of its porosity. Leveraging the singular value decomposition, in an unsupervised manner, we then learn across all cages an approximate, lower-dimensional subspace in which the 3D porosity images congregate. The “eigencages” are the set of orthogonal, characteristic 3D porosity images that span this lower-dimensional subspace, ordered in terms of importance. The learned latent representations of the cages encode the salient features of their cavities and are predictive of their adsorption properties.

Bio

Cory Simon is an Assistant Professor at Oregon State University. His research group employs molecular models and simulations, machine learning, and statistical mechanics to discover nanoporous materials for sensing, separations, and gas storage. He received his Chemical Engineering PhD in 2016 from the University of California, Berkeley. Cory has conducted research at Virginia Tech, École Polytechnique Fédérale de Lausanne, Lawrence Berkeley National Laboratory, Okinawa Institute of Science and Technology and Altius Institute.

Wednesday, October 30, 2019 at 1:00pm to 2:00pm

Gleeson Hall (Chem Engr), 200
2115 SW Campus Way, Corvallis, OR 97331

Event Type

Lecture or Presentation

Event Topic

Research

Organization
Electrical Engineering and Computer Science
Contact Name

Michael Slater

Contact Email

slater@eecs.oregonstate.edu

Subscribe
Google Calendar iCal Outlook

Recent Activity