Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImproving Molecular Force Fields Across Configurational Space by Combining Supervised and Unsupervised Machine Learning
135
0
0.0
(
0
)
Added by
Gr\\'egory Cordeiro Fonseca
Publication date
2021
fields
Physics
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
The training set of atomic configurations is key to the performance of any Machine Learning Force Field (MLFF) and, as such, the training set selection determines the applicability of the MLFF model for predictive molecular simulations. However, most atomistic reference datasets are inhomogeneously distributed across configurational space (CS), thus choosing the training set randomly or according to the probability distribution of the data leads to models whose accuracy is mainly defined by the most common close-to-equilibrium configurations in the reference data. In this work, we combine unsupervised and supervised ML methods to bypass the inherent bias of the data for common configurations, effectively widening the applicability range of MLFF to the fullest capabilities of the dataset. To achieve this goal, we first cluster the CS into subregions similar in terms of geometry and energetics. We iteratively test a given MLFF performance on each subregion and fill the training set of the model with the representatives of the most inaccurate parts of the CS. The proposed approach has been applied to a set of small organic molecules and alanine tetrapeptide, demonstrating an up to two-fold decrease in the root mean squared errors for force predictions of these molecules. This result holds for both kernel-based methods (sGDML and GAP/SOAP models) and deep neural networks (SchNet model). For the latter, the developed approach simultaneously improves both energy and forces, bypassing the compromise to be made when employing mixed energy/force loss functions.
rate research
Read More
Atomistic or ab-initio molecular dynamics simulations are widely used to predict thermodynamics and kinetics and relate them to molecular structure. A common approach to go beyond the time- and length-scales accessible with such computationally expensive simulations is the definition of coarse-grained molecular models. Existing coarse-graining approaches define an effective interaction potential to match defined properties of high-resolution models or experimental data. In this paper, we reformulate coarse-graining as a supervised machine learning problem. We use statistical learning theory to decompose the coarse-graining error and cross-validation to select and compare the performance of different models. We introduce CGnets, a deep learning approach, that learns coarse-grained free energy functions and can be trained by a force matching scheme. CGnets maintain all physically relevant invariances and allow one to incorporate prior physics knowledge to avoid sampling of unphysical structures. We show that CGnets can capture all-atom explicit-solvent free energy surfaces with models using only a few coarse-grained beads and no solvent, while classical coarse-graining methods fail to capture crucial features of the free energy surface. Thus, CGnets are able to capture multi-body terms that emerge from the dimensionality reduction.
We assess Gaussian process (GP) regression as a technique to model interatomic forces in metal nanoclusters by analysing the performance of 2-body, 3-body and many-body kernel functions on a set of 19-atom Ni cluster structures. We find that 2-body GP kernels fail to provide faithful force estimates, despite succeeding in bulk Ni systems. However, both 3- and many-body kernels predict forces within a $sim$0.1 eV/$text{AA}$ average error even for small training datasets, and achieve high accuracy even on out-of-sample, high temperature, structures. While training and testing on the same structure always provides satisfactory accuracy, cross-testing on dissimilar structures leads to higher prediction errors, posing an extrapolation problem. This can be cured using heterogeneous training on databases that contain more than one structure, which results in a good trade-off between versatility and overall accuracy. Starting from a 3-body kernel trained this way, we build an efficient non-parametric 3-body force field that allows accurate prediction of structural properties at finite temperatures, following a newly developed scheme [Glielmo et al. PRB 97, 184307 (2018)]. We use this to assess the thermal stability of Ni$_{19}$ nanoclusters at a fractional cost of full ab initio calculations.
Dynamics of flexible molecules are often determined by an interplay between local chemical bond fluctuations and conformational changes driven by long-range electrostatics and van der Waals interactions. This interplay between interactions yields complex potential-energy surfaces (PES) with multiple minima and transition paths between them. In this work, we assess the performance of state-of-the-art Machine Learning (ML) models, namely sGDML, SchNet, GAP/SOAP, and BPNN for reproducing such PES, while using limited amounts of reference data. As a benchmark, we use the cis to trans thermal relaxation in an azobenzene molecule, where at least three different transition mechanisms should be considered. Although GAP/SOAP, SchNet, and sGDML models can globally achieve chemical accuracy of 1 kcal mol-1 with fewer than 1000 training points, predictions greatly depend on the ML method used as well as the local region of the PES being sampled. Within a given ML method, large differences can be found between predictions of close-to-equilibrium and transition regions, as well as for different transition mechanisms. We identify key challenges that the ML models face in learning long-range interactions and the intrinsic limitations of commonly used atom-based descriptors. All in all, our results suggest switching from learning the entire PES within a single model to using multiple local models with optimized descriptors, training sets, and architectures for different parts of complex PES.
In software reverse engineering, decompilation is the process of recovering source code from binary files. Decompilers are used when it is necessary to understand or analyze software for which the source code is not available. Although existing decompilers commonly obtain source code with the same behavior as the binaries, that source code is usually hard to interpret and certainly differs from the original code written by the programmer. Massive codebases could be used to build supervised machine learning models aimed at improving existing decompilers. In this article, we build different classification models capable of inferring the high-level type returned by functions, with significantly higher accuracy than existing decompilers. We automatically instrument C source code to allow the association of binary patterns with their corresponding high-level constructs. A dataset is created with a collection of real open-source applications plus a huge number of synthetic programs. Our system is able to predict function return types with a 79.1% F1-measure, whereas the best decompiler obtains a 30% F1-measure. Moreover, we document the binary patterns used by our classifier to allow their addition in the implementation of existing decompilers.
We address the degree to which machine learning can be used to accurately and transferably predict post-Hartree-Fock correlation energies. Refined strategies for feature design and selection are presented, and the molecular-orbital-based machine learning (MOB-ML) method is applied to several test systems. Strikingly, for the MP2, CCSD, and CCSD(T) levels of theory, it is shown that the thermally accessible (350 K) potential energy surface for a single water molecule can be described to within 1 millihartree using a model that is trained from only a single reference calculation at a randomized geometry. To explore the breadth of chemical diversity that can be described, MOB-ML is also applied to a new dataset of thermalized (350 K) geometries of 7211 organic models with up to seven heavy atoms. In comparison with the previously reported $Delta$-ML method, MOB-ML is shown to reach chemical accuracy with three-fold fewer training geometries. Finally, a transferability test in which models trained for seven-heavy-atom systems are used to predict energies for thirteen-heavy-atom systems reveals that MOB-ML reaches chemical accuracy with 36-fold fewer training calculations than $Delta$-ML (140 versus 5000 training calculations).
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
