Multi-fidelity prediction of molecular optical peaks with deep learning

10/18/2021
by   kevinpgreenman, et al.
0

Optical properties are central to molecular design for many applications, including solar cells and biomedical imaging. A variety of ab initio and statistical methods have been developed for their prediction, each with a trade-off between accuracy, generality, and cost. Existing theoretical methods such as time-dependent density functional theory (TD-DFT) are generalizable across chemical space because of their robust physics-based foundations but still exhibit random and systematic errors with respect to experiment despite their high computational cost. Statistical methods can achieve high accuracy at a lower cost, but data sparsity and unoptimized molecule and solvent representations often limit their ability to generalize. Here, we utilize directed message passing neural networks (D-MPNNs) to represent both dye molecules and solvents for predictions of molecular absorption peaks in solution. Additionally, we demonstrate a multi-fidelity approach based on an auxiliary model trained on over 28,000 TD-DFT calculations that further improves accuracy and generalizability, as shown through rigorous splitting strategies. Combining several openly-available experimental datasets, we benchmark these methods against a state-of-the-art regression tree algorithm and compare the D-MPNN solvent representation to several alternatives. Finally, we explore the interpretability of the learned representations using dimensionality reduction and evaluate the use of ensemble variance as an estimator of the epistemic uncertainty in our predictions of molecular peak absorption in solution. The prediction methods proposed herein can be integrated with active learning, generative modeling, and experimental workflows to enable the more rapid design of molecules with targeted optical properties.

READ FULL TEXT

page 34

page 35

research
05/18/2023

Multi-Fidelity Machine Learning for Excited State Energies of Molecules

The accurate but fast calculation of molecular excited states is still a...
research
06/07/2019

Machine Learning Prediction of Accurate Atomization Energies of Organic Molecules from Low-Fidelity Quantum Chemical Calculations

Recent studies illustrate how machine learning (ML) can be used to bypas...
research
03/07/2019

Transfer Learning Using Ensemble Neural Nets for Organic Solar Cell Screening

Organic Solar Cells are a promising technology for solving the clean ene...
research
07/13/2021

Calibrated Uncertainty for Molecular Property Prediction using Ensembles of Message Passing Neural Networks

Data-driven methods based on machine learning have the potential to acce...
research
06/02/2021

A Hypergraph Convolutional Neural Network for Molecular Properties Prediction using Functional Group

We propose a Molecular Hypergraph Convolutional Network (MolHGCN) that p...
research
10/16/2018

Prediction of Atomization Energy Using Graph Kernel and Active Learning

Data-driven prediction of molecular properties presents unique challenge...
research
06/04/2021

SE(3)-equivariant prediction of molecular wavefunctions and electronic densities

Machine learning has enabled the prediction of quantum chemical properti...

Please sign up or login with your details

Forgot password? Click here to reset