Representation of molecular structures with persistent homology for machine learning applications in chemistry

• Published in: Nature communications 2020-06, Vol.11 (1), p.3230-9, Article 3230
• Main Authors: Townsend, Jacob, Micucci, Cassie Putman, Hymel, John H., Maroulas, Vasileios, Vogiatzis, Konstantinos D.
• Format: Article
• Language: English
• Subjects: 639/638/563/606; 639/638/630; 639/705/1041; Carbon dioxide; Chemical fingerprinting; Computer applications; Density functional theory; Fingerprinting; First principles; Functional groups; Homology; Humanities and Social Sciences; Learning algorithms; Machine learning; Molecular structure; multidisciplinary; Organic chemistry; Representations; Science; Science (multidisciplinary); Screening; Target recognition
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-020-17035-5

Machine learning and high-throughput computational screening have been valuable tools in accelerated first-principles screening for the discovery of the next generation of functionalized molecules and materials. The application of machine learning for chemical applications requires the conversion of molecular structures to a machine-readable format known as a molecular representation. The choice of such representations impacts the performance and outcomes of chemical machine learning methods. Herein, we present a new concise molecular representation derived from persistent homology, an applied branch of mathematics. We have demonstrated its applicability in a high-throughput computational screening of a large molecular database (GDB-9) with more than 133,000 organic molecules. Our target is to identify novel molecules that selectively interact with CO 2 . The methodology and performance of the novel molecular fingerprinting method is presented and the new chemically-driven persistence image representation is used to screen the GDB-9 database to suggest molecules and/or functional groups with enhanced properties. The choice of molecular representations can severely impact the performances of machine-learning methods. Here the authors demonstrate a persistence homology based molecular representation through an active-learning approach for predicting CO 2 /N 2 interaction energies at the density functional theory (DFT) level.