Molecular design with automated quantum computing-based deep learning and optimization

被引：0
作者：
Akshay Ajagekar
Fengqi You
机构：
[1] Cornell University,Systems Engineering
[2] Cornell University,Robert Frederick Smith School of Chemical and Biomolecular Engineering
来源：
npj Computational Materials | / 9卷
关键词：
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Computer-aided design of novel molecules and compounds is a challenging task that can be addressed with quantum computing (QC) owing to its notable advances in optimization and machine learning. Here, we use QC-assisted learning and optimization techniques implemented with near-term QC devices for molecular property prediction and generation tasks. The proposed probabilistic energy-based deep learning model trained in a generative manner facilitated by QC yields robust latent representations of molecules, while the proposed data-driven QC-based optimization framework performs guided navigation of the target chemical space by exploiting the structure–property relationships captured by the energy-based model. We demonstrate the viability of the proposed molecular design approach by generating several molecular candidates that satisfy specific property target requirements. The proposed QC-based methods exhibit an improved predictive performance while efficiently generating novel molecules that accurately fulfill target conditions and exemplify the potential of QC for automated molecular design, thus accentuating its utility.
引用
收藏
相关论文
共 149 条
  • [11] Chung PW(2012)From the computer to the laboratory: materials discovery and design using first-principles calculations J. Mater. Sci. 47 7317-2331
  • [12] Alshehri AS(2015)Machine learning predictions of molecular properties: accurate many-body potentials and nonlocality in chemical space J. Phys. Chem. Lett. 6 2326-1437
  • [13] You F(2013)Machine learning of molecular electronic properties in chemical compound space N. J. Phys. 15 095003-365
  • [14] Sliwoski G(2012)Machine learning methods for property prediction in chemoinformatics: quo vadis? J. Chem. Inf. Model. 52 1413-844
  • [15] Kothiwale S(2018)Inverse design in search of materials with target functionalities Nat. Rev. Chem. 2 0121-131
  • [16] Meiler J(2018)Inverse molecular design using machine learning: generative models for matter engineering Science 361 360-276
  • [17] Lowe EW(1994)Computer-aided molecular design using genetic algorithms Comput. Chem. Eng. 18 833-935
  • [18] Pyzer-Knapp EO(2020)Deep Learning and Knowledge-Based Methods for Computer-Aided Molecular Design - Toward a Unified Approach: State-of-the-Art and Future Directions Comput. Chem. Eng. 141 107005-52
  • [19] Suh C(2008)Exploring chemical space with discrete, gradient, and hybrid optimization methods J. Chem. Phys. 129 174105-6422
  • [20] Gómez-Bombarelli R(2018)Generative recurrent networks for de novo drug design Mol. Inf. 37 1700111-6
12345678910