MLatom: A program package for quantum chemical research assisted by machine learning

• Published in: Journal of computational chemistry Vol. 40; no. 26; pp. 2339 - 2347
• Main Author: Dral, Pavlo O.
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 05.10.2019; Wiley Subscription Services, Inc
• Subjects: Algorithms; Artificial intelligence; Computer memory; Computer simulation; Fortran; kernel ridge regression; Kernels; Linear algebra; Machine learning; Mathematical analysis; molecular descriptor; Organic chemistry; Python; Quantum chemistry; sampling; Vectors (mathematics); sampling; quantum chemistry; molecular descriptor; machine learning; Fortran; Python; kernel ridge regression
• ISSN: 0192-8651; 1096-987X; 1096-987X
• DOI: 10.1002/jcc.26004

MLatom is a program package designed for computationally efficient simulations of atomistic systems with machine‐learning (ML) algorithms. It can be used out‐of‐the‐box as a stand‐alone program with a user‐friendly online manual. The use of MLatom does not require extensive knowledge of machine learning, programming, or scripting. The user need only prepare input files and choose appropriate options. The program implements kernel ridge regression and supports Gaussian, Laplacian, and Matérn kernels. It can use arbitrary, user‐provided input vectors and can convert molecular geometries into input vectors corresponding to several types of built‐in molecular descriptors. MLatom saves and re‐uses trained ML models as needed, in addition to estimating the generalization error of ML setups. Various sampling procedures are supported and the gradients of output properties can be calculated. The core part of MLatom is written in Fortran, uses standard libraries for linear algebra, and is optimized for shared‐memory parallel computations. © 2019 Wiley Periodicals, Inc. An out‐of‐the‐box, stand‐alone program package MLatom with a user‐friendly online manual is presented for computationally efficient atomistic simulations with machine learning. MLatom supports kernel ridge regression, various sampling procedures including structure‐based sampling, model selection and evaluation, and conversion of molecular coordinates to several built‐in molecular descriptors. The program can be used for solving generic machine‐learning tasks, constructing molecular potential energy surfaces and calculating energy gradients, and exploring chemical space.