The need for efficient computational screening of molecular candidates that possess desired properties frequently arises in various scientific and engineering problems, including drug discovery and materials design. However, the large size of the search space containing the candidates and the substantial computational cost of high-fidelity property prediction models makes screening practically challenging. In this work, we propose a general framework for constructing and optimizing a virtual screening (HTVS) pipeline that consists of multi-fidelity models. The central idea is to optimally allocate the computational resources to models with varying costs and accuracy to optimize the return-on-computational-investment (ROCI). Based on both simulated as well as real data, we demonstrate that the proposed optimal HTVS framework can significantly accelerate screening virtually without any degradation in terms of accuracy. Furthermore, it enables an adaptive operational strategy for HTVS, where one can trade accuracy for efficiency.
@article{arxiv.2109.11683,
title = {Optimal Decision Making in High-Throughput Virtual Screening Pipelines},
author = {Hyun-Myung Woo and Xiaoning Qian and Li Tan and Shantenu Jha and Francis J. Alexander and Edward R. Dougherty and Byung-Jun Yoon},
journal= {arXiv preprint arXiv:2109.11683},
year = {2023}
}