Geometric deep learning on molecular representations
Geometric deep learning (GDL) is based on neural network architectures that incorporate
and process symmetry information. GDL bears promise for molecular modelling applications …
and process symmetry information. GDL bears promise for molecular modelling applications …
Deep learning methods for molecular representation and property prediction
Highlights•The deep learning method could effectively represent the molecular structure and
predict molecular property through diversified models.•One, two, and three-dimensional …
predict molecular property through diversified models.•One, two, and three-dimensional …
Machine learning enables interpretable discovery of innovative polymers for gas separation membranes
Polymer membranes perform innumerable separations with far-reaching environmental
implications. Despite decades of research, design of new membrane materials remains a …
implications. Despite decades of research, design of new membrane materials remains a …
Artificial intelligence for natural product drug discovery
Developments in computational omics technologies have provided new means to access
the hidden diversity of natural products, unearthing new potential for drug discovery. In …
the hidden diversity of natural products, unearthing new potential for drug discovery. In …
Accelerated rational PROTAC design via deep learning and molecular simulations
Proteolysis-targeting chimeras (PROTACs) have emerged as effective tools to selectively
degrade disease-related proteins by using the ubiquitin-proteasome system. Developing …
degrade disease-related proteins by using the ubiquitin-proteasome system. Developing …
Deep learning in virtual screening: recent applications and developments
TB Kimber, Y Chen, A Volkamer - International journal of molecular …, 2021 - mdpi.com
Drug discovery is a cost and time-intensive process that is often assisted by computational
methods, such as virtual screening, to speed up and guide the design of new compounds …
methods, such as virtual screening, to speed up and guide the design of new compounds …
Model agnostic generation of counterfactual explanations for molecules
GP Wellawatte, A Seshadri, AD White - Chemical science, 2022 - pubs.rsc.org
An outstanding challenge in deep learning in chemistry is its lack of interpretability. The
inability of explaining why a neural network makes a prediction is a major barrier to …
inability of explaining why a neural network makes a prediction is a major barrier to …
Scoring functions for protein-ligand binding affinity prediction using structure-based deep learning: a review
The rapid and accurate in silico prediction of protein-ligand binding free energies or binding
affinities has the potential to transform drug discovery. In recent years, there has been a …
affinities has the potential to transform drug discovery. In recent years, there has been a …
Explainable, domain-adaptive, and federated artificial intelligence in medicine
Artificial intelligence (AI) continues to transform data analysis in many domains. Progress in
each domain is driven by a growing body of annotated data, increased computational …
each domain is driven by a growing body of annotated data, increased computational …
Explainable machine learning for property predictions in compound optimization: miniperspective
R Rodríguez-Pérez, J Bajorath - Journal of medicinal chemistry, 2021 - ACS Publications
The prediction of compound properties from chemical structure is a main task for machine
learning (ML) in medicinal chemistry. ML is often applied to large data sets in applications …
learning (ML) in medicinal chemistry. ML is often applied to large data sets in applications …