A Bayesian Approach to Calibrating High-Throughput Virtual Screening Results and Application to Organic Photovoltaic Materials

TL;DR

This paper introduces a Bayesian calibration method for high-throughput virtual screening of organic photovoltaic materials, improving the accuracy of quantum-chemical property predictions and providing uncertainty estimates.

Contribution

It presents a novel Bayesian approach using Gaussian processes and molecular graph information to calibrate quantum-chemical and device properties in virtual screening.

Findings

Enhanced calibration accuracy for electronic and device properties.

Provides uncertainty estimates for each calibrated prediction.

Applicable to high-throughput screening of organic photovoltaic materials.

Abstract

A novel approach for calibrating quantum-chemical properties determined as part of a high-throughput virtual screen to experimental analogs is presented. Information on the molecular graph is extracted through the use of extended connectivity fingerprints, and exploited using a Gaussian process to calibrate both electronic properties such as frontier orbital energies, and optical gaps and device properties such as short circuit current density, open circuit voltage and power conversion efficiency. The Bayesian nature of this process affords a value for uncertainty in addition to each calibrated value. This allows the researcher to gain intuition about the model as well as the ability to respect its bounds.