A5060953325- Computational Drug Discovery Methods
- Lipid Membrane Structure and Behavior
- Molecular Sensors and Ion Detection
- Protein Structure and Dynamics
- Machine Learning in Materials Science
- Neuroscience and Neuropharmacology Research
- Biomedical Text Mining and Ontologies
- Bioinformatics and Genomic Networks
- Machine Learning in Bioinformatics
- Cell Image Analysis Techniques
Kobe University
2022-2025
Three-dimensional structures of protein-ligand complexes provide valuable insights into their interactions and are crucial for molecular biological studies drug design. However, high-dimensional multimodal nature hinders end-to-end modeling, earlier approaches depend inherently on existing protein structures. To overcome these limitations expand the range that can be accurately modeled, it is necessary to develop efficient methods.
The mechanisms underlying human odor recognition remain largely unclear, making it challenging to predict the scent of a novel molecule based solely on its molecular structure. Unlike taste, which is classified into limited number categories, perception highly complex and lacks universally defined labels, rendering absolute classification inherently ambiguous. To address this issue, we propose relative evaluation framework for prediction, focusing similarity rather than descriptors. In...
General anesthetics are indispensable in modern medicine because they induce a reversible loss of consciousness and sensation humans. On the other hand, their molecular mechanisms action have not yet been elucidated. Several studies identified main targets some general anesthetics. The structures γ-aminobutyric acid A (GABAA) receptors with intravenous such as propofol etomidate recently determined. Although these anesthetic binding provide essential insights into mechanism anesthetics,...
Abstract Three-dimensional structures of protein-ligand complexes provide valuable insights into their interactions and are crucial for molecular biological studies drug design. However, high-dimensional multimodal nature hinders end-to-end modeling, earlier approaches depend inherently on existing protein structures. To overcome these limitations expand the range that can be accurately modeled, it is necessary to develop efficient methods. We introduce an equivariant diffusion-based...
Ultra-large virtual chemical spaces have emerged as a valuable resource for drug discovery, providing access to billions of make-on-demand compounds with high synthetic success rates. Chemical language models can potentially accelerate the exploration these vast through direct compound generation. However, existing are not designed navigate specific and often overlook accessibility. To address this gap, we introduce product-of-experts (PoE) models, modular scalable approach navigating...
Ultralarge virtual chemical spaces have emerged as a valuable resource for drug discovery, providing access to billions of make-on-demand compounds with high synthetic success rates. Chemical language models can potentially accelerate the exploration these vast through direct compound generation. However, existing are not designed navigate specific and often overlook accessibility. To address this gap, we introduce product-of-experts (PoE) models, modular scalable approach navigating...
Abstract General anesthetics are indispensable in modern medicine because they induce a reversible loss of consciousness and sensation humans. On the other hand, their molecular mechanisms action have not yet been elucidated. Several studies identified main targets some general anesthetics. The structures γ-aminobutyric acid A (GABA ) receptors with intravenous such as propofol etomidate recently determined. Although these anesthetic-binding provide essential insights into mechanism...