scholarly journals Evaluation of Thermochemical Machine Learning for Potential Energy Curves and Geometry Optimization

2021 ◽  
Author(s):  
Dakota Folmsbee ◽  
David R. Koes ◽  
Geoffrey Hutchison
Keyword(s):  
Machine Learning ◽  
Potential Energy ◽  
Density Functional ◽  
Single Point ◽  
Geometry Optimization ◽  
Potential Energy Curves ◽  
Semiempirical Methods ◽  
Neural Net ◽  
Quantitative Accuracy ◽  
The Moment

While many machine learning methods, particularly deep neural networks have been trained for density functional and quantum chemical energies and properties, the vast majority of these methods focus on single-point energies. In principle, such ML methods, once trained, offer thermochemical accuracy on par with density functional and wave function methods but at speeds comparable to traditional force fields or approximate semiempirical methods. So far, most efforts have focused on optimized equilibrium single-point energies and properties. In this work, we evaluate the accuracy of several leading ML methods across a range of bond potential energy curves and torsional potentials. Methods were trained on the existing ANI-1 training set, calculated using the ωB97X / 6-31G(d) single points at non-equilibrium geometries. We find that across a range of small molecules, several methods offer both qualitative accuracy (e.g., correct minima, both repulsive and attractive bond regions, anharmonic shape, and single minima) and quantitative accuracy in terms of the mean absolute percent error near the minima. At the moment, ANI-2x, FCHL, and our new grid-based convolutional neural net show good performance.

scholarly journals Evaluation of Thermochemical Machine Learning for Potential Energy Curves and Geometry Optimization

2020 ◽  
Author(s):  
Dakota Folmsbee ◽  
David R. Koes ◽  
Geoffrey Hutchison
Keyword(s):  
Machine Learning ◽  
Potential Energy ◽  
Density Functional ◽  
Single Point ◽  
Geometry Optimization ◽  
Potential Energy Curves ◽  
Semiempirical Methods ◽  
Neural Net ◽  
Quantitative Accuracy ◽  
The Moment

While many machine learning methods, particularly deep neural networks have been trained for density functional and quantum chemical energies and properties, the vast majority of these methods focus on single-point energies. In principle, such ML methods, once trained, offer thermochemical accuracy on par with density functional and wave function methods but at speeds comparable to traditional force fields or approximate semiempirical methods. So far, most efforts have focused on optimized equilibrium single-point energies and properties. In this work, we evaluate the accuracy of several leading ML methods across a range of bond potential energy curves and torsional potentials. Methods were trained on the existing ANI-1 training set, calculated using the ωB97X / 6-31G(d) single points at non-equilibrium geometries. We find that across a range of small molecules, several methods offer both qualitative accuracy (e.g., correct minima, both repulsive and attractive bond regions, anharmonic shape, and single minima) and quantitative accuracy in terms of the mean absolute percent error near the minima. At the moment, ANI-2x, FCHL, and our new grid-based convolutional neural net show good performance.

scholarly journals Evaluation of Thermochemical Machine Learning for Potential Energy Curves and Geometry Optimization

2020 ◽  
Author(s):  
Dakota Folmsbee ◽  
David R. Koes ◽  
Geoffrey Hutchison
Keyword(s):  
Machine Learning ◽  
Potential Energy ◽  
Density Functional ◽  
Single Point ◽  
Geometry Optimization ◽  
Potential Energy Curves ◽  
Semiempirical Methods ◽  
Neural Net ◽  
Quantitative Accuracy ◽  
The Moment

While many machine learning methods, particularly deep neural networks have been trained for density functional and quantum chemical energies and properties, the vast majority of these methods focus on single-point energies. In principle, such ML methods, once trained, offer thermochemical accuracy on par with density functional and wave function methods but at speeds comparable to traditional force fields or approximate semiempirical methods. So far, most efforts have focused on optimized equilibrium single-point energies and properties. In this work, we evaluate the accuracy of several leading ML methods across a range of bond potential energy curves and torsional potentials. Methods were trained on the existing ANI-1 training set, calculated using the ωB97X / 6-31G(d) single points at non-equilibrium geometries. We find that across a range of small molecules, several methods offer both qualitative accuracy (e.g., correct minima, both repulsive and attractive bond regions, anharmonic shape, and single minima) and quantitative accuracy in terms of the mean absolute percent error near the minima. At the moment, ANI-2x, FCHL, and our new grid-based convolutional neural net show good performance.

BAND NN: A Deep Learning Framework For Energy Prediction and Geometry Optimization of Organic Small Molecules

2019 ◽  
Author(s):  
Siddhartha Laghuvarapu ◽  
Yashaswi Pathak ◽  
U. Deva Priyakumar
Keyword(s):  
Machine Learning ◽  
Density Functional ◽  
Computational Cost ◽  
Geometry Optimization ◽  
Dft Methods ◽  
Energy Prediction ◽  
Machine Learning Model ◽  
Equilibrium Structures ◽  
High Level ◽  
Non Equilibrium

Recent advances in artificial intelligence along with development of large datasets of energies calculated using quantum mechanical (QM)/density functional theory (DFT) methods have enabled prediction of accurate molecular energies at reasonably low computational cost. However, machine learning models that have been reported so far requires the atomic positions obtained from geometry optimizations using high level QM/DFT methods as input in order to predict the energies, and do not allow for geometry optimization. In this paper, a transferable and molecule-size independent machine learning model (BAND NN) based on a chemically intuitive representation inspired by molecular mechanics force fields is presented. The model predicts the atomization energies of equilibrium and non-equilibrium structures as sum of energy contributions from bonds (B), angles (A), nonbonds (N) and dihedrals (D) at remarkable accuracy. The robustness of the proposed model is further validated by calculations that span over the conformational, configurational and reaction space. The transferability of this model on systems larger than the ones in the dataset is demonstrated by performing calculations on select large molecules. Importantly, employing the BAND NN model, it is possible to perform geometry optimizations starting from non-equilibrium structures along with predicting their energies.

scholarly journals Assessing Conformer Energies using Electronic Structure and Machine Learning Methods

2020 ◽  
Author(s):  
Dakota Folmsbee ◽  
Geoffrey Hutchison
Keyword(s):  
Machine Learning ◽  
Electronic Structure ◽  
Density Functional ◽  
Large Scale ◽  
Single Point ◽  
Semiempirical Method ◽  
Coupled Cluster ◽  
Scale Evaluation ◽  
Machine Learning Methods ◽  
Electronic Structure Methods

We have performed a large-scale evaluation of current computational methods, including conventional small-molecule force fields, semiempirical, density functional, ab initio electronic structure methods, and current machine learning (ML) techniques to evaluate relative single-point energies. Using up to 10 local minima geometries across ~700 molecules, each optimized by B3LYP-D3BJ with single-point DLPNO-CCSD(T) triple-zeta energies, we consider over 6,500 single points to compare the correlation between different methods for both relative energies and ordered rankings of minima. We find promise from current ML methods and recommend methods at each tier of the accuracy-time tradeoff, particularly the recent GFN2 semiempirical method, the B97-3c density functional approximation, and RI-MP2 for accurate conformer energies. The ANI family of ML methods shows promise, particularly the ANI-1ccx variant trained in part on coupled-cluster energies. Multiple methods suggest continued improvements should be expected in both performance and accuracy.

scholarly journals Assessing Conformer Energies using Electronic Structure and Machine Learning Methods

2020 ◽  
Author(s):  
Dakota Folmsbee ◽  
Geoffrey Hutchison
Keyword(s):  
Machine Learning ◽  
Electronic Structure ◽  
Density Functional ◽  
Large Scale ◽  
Single Point ◽  
Semiempirical Method ◽  
Coupled Cluster ◽  
Scale Evaluation ◽  
Machine Learning Methods ◽  
Electronic Structure Methods

We have performed a large-scale evaluation of current computational methods, including conventional small-molecule force fields, semiempirical, density functional, ab initio electronic structure methods, and current machine learning (ML) techniques to evaluate relative single-point energies. Using up to 10 local minima geometries across ~700 molecules, each optimized by B3LYP-D3BJ with single-point DLPNO-CCSD(T) triple-zeta energies, we consider over 6,500 single points to compare the correlation between different methods for both relative energies and ordered rankings of minima. We find promise from current ML methods and recommend methods at each tier of the accuracy-time tradeoff, particularly the recent GFN2 semiempirical method, the B97-3c density functional approximation, and RI-MP2 for accurate conformer energies. The ANI family of ML methods shows promise, particularly the ANI-1ccx variant trained in part on coupled-cluster energies. Multiple methods suggest continued improvements should be expected in both performance and accuracy.

scholarly journals Potential Energy Surface (PES) Scan of Gas-Phase L-Proline

2014 ◽  
Vol 38 ◽  
pp. 26-34
Author(s):  
Anouar el Guerdaoui ◽  
Yassine el Kahoui ◽  
Malika Bourjila ◽  
Rachida Tijar ◽  
Abderrahman el Gridani
Keyword(s):  
Potential Energy ◽  
Potential Energy Surface ◽  
Gas Phase ◽  
Density Functional ◽  
Energy Surface ◽  
Conformational Stability ◽  
Geometry Optimization ◽  
Basis Set ◽  
Absolute Minimum ◽  
Pes Scan

We performed here a systematic ab initio calculations on neutral gas-phase L-proline. A total of 8 local minima were located by geometry optimization of the trial structures using density functional theory (DFT) with B3LYP three parameter hybrid potential coupled with the 6-31G)d( basis set. The absolute minimum obtained will be subject to a rigid potential energy surface (PES) scan by rotating its carboxylic group using the same method with more accurate basis set B3LYP/6-311++G(d,p), to get a deeper idea about its conformational stability. The main aim of the present work was the study of the rigidity of the L-proline structure and the puckering of its pyrrolidine ring.

Sign in / Sign up

Export Citation Format

Share Document