Assigning confidence to molecular property prediction.

ABSTRACT: Introduction: Computational modeling has rapidly advanced over the last decades. Recently, machine learning has emerged as a powerful and cost-effective strategy to learn from existing datasets and perform predictions on unseen molecules. Accordingly, the explosive rise of data-driven techniques raises an important question: What confidence can be assigned to molecular property predictions and what techniques can be used?Areas covered: The authors discuss popular strategies for predicting molecular properties, their corresponding uncertainty sources and methods to quantify uncertainty. First, the authors' considerations for assessing confidence begin with dataset bias and size, data-driven property prediction and feature design. Next, the authors discuss property simulation v

SUBMITTER: Nigam A 

PROVIDER: S-EPMC9449894 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature