PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials

Abstract

Atomic neural networks (ANNs) constitute a class of machine learning methods for predicting potential energy surfaces and physico-chemical properties of molecules and materials. Despite many successes, developing interpretable ANN architectures and implementing existing ones efficiently are still challenging. This calls for reliable, general-purpose and open-source codes. Here, we present a python library named PiNN as a solution toward this goal. In PiNN, we designed a new interpretable and high-performing graph convolutional neural network variant, PiNet, as well as implemented the established Behler-Parrinello high-dimensional neural network. These implementations were tested using datasets of isolated small molecules, crystalline materials, liquid water and an aqueous alkaline electrolyte. PiNN comes with a visualizer called PiNNBoard to extract chemical insight "learned" by ANNs, provides analytical stress tensor calculations and interfaces to both the Atomic Simulation Environment and a development version of the Amsterdam Modeling Suite. Moreover, PiNN is highly modularized which makes it useful not only as a standalone package but also as a chain of tools to develop and to implement novel ANNs. The code is distributed under a permissive BSD license and is freely accessible at https://github.com/Teoroo-CMC/PiNN/ with full documentation and tutorials.

References in corpus (27)

• The NumPy array: a structure for efficient numerical computation
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• How van der Waals interactions determine the unique properties of water
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• i-PI 2.0: A Universal Force Engine for Advanced Molecular Simulations
• Nucleation mechanism for the direct graphite-to-diamond phase transition
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Alchemical and structural distribution based representation for improved QML
• Hierarchical modeling of molecular energies using a deep neural network
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Atom-Density Representations for Machine Learning
• Efficient nonparametric $n$-body force fields from machine learning
• Coupling of surface chemistry and electric double layer at TiO${}_2$ electrochemical interfaces
• Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks
• High-dimensional neural network potentials for solvation: The case of protonated water clusters in helium

Cited by in corpus (16)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science
• Committee neural network potentials control generalization errors and enable active learning
• Improving the accuracy of the neuroevolution machine learning potential for multi-component systems
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• Short-range order and its impacts on the BCC NbMoTaW multi-principal element alloy by the machine-learning potential
• Predicting tensorial molecular properties with equivariant machine-learning models
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• PyXtal FF: a Python Library for Automated Force Field Generation
• Transferability of machine learning potentials: Protonated water neural network potential applied to the protonated water hexamer
• ParAMS: Parameter Optimization for Atomistic and Molecular Simulations
• PiNNwall: Heterogeneous Electrode Models from Integrating Machine Learning and Atomistic Simulation
• Training Algorithm Matters for the Performance of Neural Network Potential: A Case Study of Adam and the Kalman Filter Optimizers
• Machine Learning Inference of Molecular Dipole Moment in Liquid Water
• Molecular electrostatic potentials from machine learning models for dipole and quadrupole predictions