Generative models for molecular discovery: Recent advances and challenges
Abstract Development of new products often relies on the discovery of novel molecules.
While conventional molecular design involves using human expertise to propose …
While conventional molecular design involves using human expertise to propose …
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 …
Score-based generative modeling in latent space
Score-based generative models (SGMs) have recently demonstrated impressive results in
terms of both sample quality and distribution coverage. However, they are usually applied …
terms of both sample quality and distribution coverage. However, they are usually applied …
Machine learning of reaction properties via learned representations of the condensed graph of reaction
The estimation of chemical reaction properties such as activation energies, rates, or yields is
a central topic of computational chemistry. In contrast to molecular properties, where …
a central topic of computational chemistry. In contrast to molecular properties, where …
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 …
[HTML][HTML] CLOOME: contrastive learning unlocks bioimaging databases for queries with chemical structures
A Sanchez-Fernandez, E Rumetshofer… - Nature …, 2023 - nature.com
The field of bioimage analysis is currently impacted by a profound transformation, driven by
the advancements in imaging technologies and artificial intelligence. The emergence of …
the advancements in imaging technologies and artificial intelligence. The emergence of …
High-dimensional Bayesian optimisation with variational autoencoders and deep metric learning
We introduce a method combining variational autoencoders (VAEs) and deep metric
learning to perform Bayesian optimisation (BO) over high-dimensional and structured input …
learning to perform Bayesian optimisation (BO) over high-dimensional and structured input …
Context-enriched molecule representations improve few-shot drug discovery
A central task in computational drug discovery is to construct models from known active
molecules to find further promising molecules for subsequent screening. However, typically …
molecules to find further promising molecules for subsequent screening. However, typically …
FPT: fine-grained detection of driver distraction based on the feature pyramid vision transformer
According to the surveys of the World Health Organization, distracted driving is one of main
causes of road traffic accidents. To improve road traffic safety, real-time detection of drivers' …
causes of road traffic accidents. To improve road traffic safety, real-time detection of drivers' …
Design of organic electronic materials with a goal-directed generative model powered by deep neural networks and high-throughput molecular simulations
In recent years, generative machine learning approaches have attracted significant attention
as an enabling approach for designing novel molecular materials with minimal design bias …
as an enabling approach for designing novel molecular materials with minimal design bias …