Machine learning methods for small data challenges in molecular science
B Dou, Z Zhu, E Merkurjev, L Ke, L Chen… - Chemical …, 2023 - ACS Publications
Small data are often used in scientific and engineering research due to the presence of
various constraints, such as time, cost, ethics, privacy, security, and technical limitations in …
various constraints, such as time, cost, ethics, privacy, security, and technical limitations in …
Hit and lead discovery with explorative rl and fragment-based molecule generation
Recently, utilizing reinforcement learning (RL) to generate molecules with desired properties
has been highlighted as a promising strategy for drug design. Molecular docking program--a …
has been highlighted as a promising strategy for drug design. Molecular docking program--a …
Characterizing uncertainty in machine learning for chemistry
Characterizing uncertainty in machine learning models has recently gained interest in the
context of machine learning reliability, robustness, safety, and active learning. Here, we …
context of machine learning reliability, robustness, safety, and active learning. Here, we …
HiGNN: A hierarchical informative graph neural network for molecular property prediction equipped with feature-wise attention
Elucidating and accurately predicting the druggability and bioactivities of molecules plays a
pivotal role in drug design and discovery and remains an open challenge. Recently, graph …
pivotal role in drug design and discovery and remains an open challenge. Recently, graph …
Augmentations in graph contrastive learning: Current methodological flaws & towards better practices
Graph classification has a wide range of applications in bioinformatics, social sciences,
automated fake news detection, web document classification, and more. In many practical …
automated fake news detection, web document classification, and more. In many practical …
[HTML][HTML] Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS
Deep learning models that leverage large datasets are often the state of the art for modelling
molecular properties. When the datasets are smaller (< 2000 molecules), it is not clear that …
molecular properties. When the datasets are smaller (< 2000 molecules), it is not clear that …
[HTML][HTML] Large-scale evaluation of k-fold cross-validation ensembles for uncertainty estimation
TM Dutschmann, L Kinzel, A Ter Laak… - Journal of …, 2023 - Springer
It is insightful to report an estimator that describes how certain a model is in a prediction,
additionally to the prediction alone. For regression tasks, most approaches implement a …
additionally to the prediction alone. For regression tasks, most approaches implement a …
Comprehensible artificial intelligence on knowledge graphs: A survey
Artificial Intelligence applications gradually move outside the safe walls of research labs and
invade our daily lives. This is also true for Machine Learning methods on Knowledge …
invade our daily lives. This is also true for Machine Learning methods on Knowledge …
[HTML][HTML] DeepReac+: deep active learning for quantitative modeling of organic chemical reactions
Y Gong, D Xue, G Chuai, J Yu, Q Liu - Chemical Science, 2021 - pubs.rsc.org
Various computational methods have been developed for quantitative modeling of organic
chemical reactions; however, the lack of universality as well as the requirement of large …
chemical reactions; however, the lack of universality as well as the requirement of large …
[HTML][HTML] Drug-likeness scoring based on unsupervised learning
Drug-likeness prediction is important for the virtual screening of drug candidates. It is
challenging because the drug-likeness is presumably associated with the whole set of …
challenging because the drug-likeness is presumably associated with the whole set of …