Automation of (Macro)molecular Properties Using a Bootstrapping Swarm Artificial Neural Network Method: Databases for Machine Learning

Abstract

In this study, we employed a novel method for prediction of (macro)molecular properties using a swarm artificial neural network method as a machine learning approach. In this method, a (macro)molecular structure is represented by a so-called description vector, which then is the input in a so-called bootstrapping swarm artificial neural network (BSANN) for training the neural network. In this study, we aim to develop an efficient approach for performing the training of an artificial neural network using either experimental or quantum mechanics data. In particular, we aim to create different user-friendly online accessible databases of well-selected experimental (or quantum mechanics) results that can be used as proof of the concepts. Furthermore, with the optimized artificial neural network using the training data served as input for BSANN, we can predict properties and their statistical errors of new molecules using the plugins provided from that web-service. There are four databases accessible using the web-based service. That includes a database of 642 small organic molecules with known experimental hydration free energies, the database of 1475 experimental pKa values of ionizable groups in 192 proteins, the database of 2693 mutants in 14 proteins with given values of experimental values of changes in the Gibbs free energy, and a database of 7101 quantum mechanics heat of formation calculations. All the data are prepared and optimized in advance using the AMBER force field in CHARMM macromolecular computer simulation program. The BSANN is code for performing the optimization and prediction written in Python computer programming language. The descriptor vectors of the small molecules are based on the Coulomb matrix and sum over bonds properties, and for the macromolecular systems, they take into account the chemical-physical fingerprints of the region in the vicinity of each amino acid.Recently, neural network method has seen a broad range of applications in molecular modeling. 1 In Ref., 2 a hierarchical interacting particle neural network approach is introduced using quantum models to predict molecular properties. In this approach, different hierarchical regularization terms have been introduced to improve the convergence of the optimized parameters. While in Ref., 3 the machine learning like-potentials are used to predict molecular properties, such as enthalpies or potential energies. The degree to which the general features included in characterizing the chemical space of molecules to improve the predictions of these models is also discussed in Refs. 4,5 Tuckerman and co-workers 6 used a stochastic neural network technique to fit high-dimensional free energy surfaces characterized by reduced subspace of collective coordinates. While very recently 7 a comparison study has been