WibBondIndexData.zip

This dataset is released in conjunction with the paper “Bond Order Predictions Using Deep Neural Networks." The dataset consists of 436,938 ordinary organic molecules, their geometries, and bond orders assigned by the NBO and Gaussian software packages, both of which are licensed to Los Alamos National Laboratory. This dataset is useful for training neural networks, specifically HIPPYNN which has been released through the Feynman Center for Innovation. The trained neural network can make accurate predictions of bond orders on organic and biological molecules significantly faster than the quantum mechanical methods the neural networks are based on. These neural networks are of relevance to basic research into biological molecules, where bonding information is used to parameterize classical force fields for molecular dynamics simulations. <br>