This repository contais the data and files for the PiNet2 dipole-quadrupole (PiNet2-DQ) models.
PiNet2 is an equivariant graph convolutional neural network (GCNN) architecture, accessible from the pairwise interaction neural network (PiNN) library built by Y. Shao et al. [1-2]. PiNN can be installed by following the instructions in https://github.com/Teoroo-CMC/PiNN.
The data, as well as files for reading the dataset and trained models are provided. More information can be found in [3].
[1] Li, J.; Knijff, L.; Zhang, Z.-Y.; Andersson, L.; Zhang, C. PiNN: Equivariant Neural Network Suite for Modelling Electrochemical Systems. J. Chem. Theory Comput., 2025, 21: 1382.
[2] Shao, Y.; Hellström, M.; Mitev, P. D.; Knijff, L.; Zhang, C. PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials. J. Chem. Inf. Model., 2020, 60: 1184.
[3] Muuga, K.; Knijff, L; Zhang, C. Inference of molecular electrostatic potentials from machine learning models for dipole and quadrupole predictions. AI Sci., 2026, 2: 025002