Graduate Seminar Series

September 08, 2023

12:00 p.m. ET

Scaife Hall 105

Accelerating design of organic materials with machine learning and AI

Deep learning is revolutionizing many areas of science and technology, particularly in natural language processing, speech recognition, and computer vision. In this talk, we will provide an overview of the latest developments of machine learning and AI methods and their application to the problem of drug discovery and development at Isayev’s Lab at CMU. We identify several areas where existing methods have the potential to accelerate materials research and disrupt more traditional approaches. First, we proposed a novel ML-guided materials discovery platform that combines synergistic innovations in automated flow synthesis and automated machine learning (AutoML) method development. A software-controlled, continuous polymer synthesis platform enables rapid iterative experimental–computational cycles that result in the synthesis of hundreds of unique copolymer compositions within a multi-variable compositional space. The non-intuitive design criteria identified by ML, accomplished by exploring less than 0.9% of overall compositional space, upended conventional wisdom in designing 19F MRI agents and led to identifying >10 copolymer compositions that outperformed state-of-the-art materials. Our platform is now being integrated with CMU Cloud Lab.

Second, we will present a deep learning model that approximates the solution of the Schrodinger equation. We introduce the AIMNet-NSE (Neural Spin Equilibration) architecture, which can predict molecular energies for an arbitrary combination of molecular charge and spin multiplicity. The AIMNet-NSE model allows us to bypass QM calculations fully and derive the ionization potential, electron affinity, and conceptual Density Functional Theory quantities like electronegativity, hardness, and condensed Fukui functions. We show that these descriptors, along with learned atomic representations, could be used to model chemical reactivity through an example of regioselectivity in electrophilic aromatic substitution reactions.

05-31-isayev.jpg

Olexandr Isayev, Carnegie Mellon University

Olexandr Isayev is an Associate Professor in the Department of Chemistry at Carnegie Mellon University. In 2008, Olexandr received his Ph.D. in computational chemistry. He was a Postdoctoral Research Fellow at the Case Western Reserve University and a scientist at the government research lab. During 2016-2019 he was a faculty at UNC Eshelman School of Pharmacy, the University of North Carolina at Chapel Hill. Olexandr received the “Emerging Technology Award” from the American Chemical Society (ACS) and the GPU computing award from NVIDIA. The research in his lab focuses on connecting artificial intelligence (AI) with chemical sciences.

Upcoming Events

  • December 6 2023

    3:00 PM ET

    Materials Science and Engineering

    Ph.D. Thesis Defense

    Chemo-Mechanical Interactions to Improve Intestinal Retention of Ingestible Medical Devices, presented by Durva Naik

    2327 Wean Hall

  • December 8 2023

    12:00 PM ET

    Materials Science and Engineering

    Graduate Student Seminar

    Unraveling the governing factors for cholesteric liquid crystal self-assembly of polysaccharides presented by CĂ©cile A. C. Chazot, Northwestern University

    Scaife Hall 105

  • December 8 2023

    1:00 PM ET

    Materials Science and Engineering

    Ph.D. Thesis Defense

    Cylindrical Grain Boundary Motion in the Isoconfigurational Ensemble, presented by Anqi Qiu

    2327 Wean Hall

  • December 12 2023

    9:00 AM ET

    Materials Science and Engineering

    Ph.D. Program Information Session

    Join us for a virtual discussion about becoming part of the Materials Science and Engineering graduate student community.

    Zoom link to be shared upon registration

  • December 12 2023

    2:00 PM ET

    Materials Science and Engineering

    Ph.D. Thesis Defense

    Ingestible Electronics for Diagnostics and Therapy, presented by Gaurav Balakrishnan

    Scott Hall 6142

  • December 13 2023

    9:00 AM ET

    Materials Science and Engineering

    Masters Program Information Session

    Join us for a virtual discussion about becoming part of the Materials Science and Engineering graduate student community.

    Zoom link to be shared upon registration