Timezone: »

TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search
Tarun Gogineni · Ziping Xu · Exequiel Punzalan · Runxuan Jiang · Joshua Kammeraad · Ambuj Tewari · Paul Zimmerman

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #718

Molecular geometry prediction of flexible molecules, or conformer search, is a long-standing challenge in computational chemistry. This task is of great importance for predicting structure-activity relationships for a wide variety of substances ranging from biomolecules to ubiquitous materials. Substantial computational resources are invested in Monte Carlo and Molecular Dynamics methods to generate diverse and representative conformer sets for medium to large molecules, which are yet intractable to chemoinformatic conformer search methods. We present TorsionNet, an efficient sequential conformer search technique based on reinforcement learning under the rigid rotor approximation. The model is trained via curriculum learning, whose theoretical benefit is explored in detail, to maximize a novel metric grounded in thermodynamics called the Gibbs Score. Our experimental results show that TorsionNet outperforms the highest-scoring chemoinformatics method by 4x on large branched alkanes, and by several orders of magnitude on the previously unexplored biopolymer lignin, with applications in renewable energy. TorsionNet also outperforms the far more exhaustive but computationally intensive Self-Guided Molecular Dynamics sampling method.

Author Information

Tarun Gogineni (University of Michigan)
Ziping Xu (University of Michigan)

My name is Ziping Xu. I am a second-year Ph.D. student in Statistics at the University of Michigan. My research interests are on sample efficient reinforcement learning and transfer learning for reinforcement learning. I am looking for a research-based internship in Summer 2020.

Exequiel Punzalan (University of Michigan)
Runxuan Jiang (University of Michigan)
Joshua Kammeraad (University of Michigan)
Ambuj Tewari (University of Michigan)
Paul Zimmerman (University of Michigan)

More from the Same Authors