Given the rapid development of nanotechnology, it is crucial to understand the effects of
nanoparticles on living organisms. However, it is laborious to perform toxicological tests on a …

The problem of human trust is one of the most fundamental problems in applied artificial
intelligence in drug discovery. In silico models have been widely used to accelerate the …

The applicability domain of machine learning models trained on structural fingerprints for the
prediction of biological endpoints is often limited by the lack of diversity of chemical space of …

Determining which substances on the global market could be classified as persistent, mobile
and toxic (PMT) substances or very persistent, very mobile (vPvM) substances is essential to …

Reliable uncertainty quantification for statistical models is crucial in various downstream
applications, especially for drug design and discovery where mistakes may incur a large …

Immense effort has been exerted in the materials informatics community towards enhancing
the accuracy of machine learning (ML) models; however, the uncertainty quantification (UQ) …

A major research area in machine learning is the development of algorithms to compute the
reliability of individual predictions. Such reliability estimates are essential to increase the …

While the use of deep learning in drug discovery is gaining increasing attention, the lack of
methods to compute reliable errors in prediction for Neural Networks prevents their …

In the early stages of drug discovery, decisions regarding which experiments to pursue can
be influenced by computational models for quantitative structure–activity relationships …

The data acquired in civil engineering tasks often involve high acquisition costs, and the
available datasets tend to have a limited number of samples and are highly biased. To …