Results 231 to 240 of about 1,488,905 (295)

Composition‐Aware Cross‐Sectional Integration for Spatial Transcriptomics

open access: yesAdvanced Intelligent Discovery, EarlyView.
Multi‐section spatial transcriptomics demands coherent cell‐type deconvolution, domain detection, and batch correction, yet existing pipelines treat these tasks separately. FUSION unifies them within a composition‐aware latent framework, modeling reads as cell‐type–specific topics and clustering in embedding space.
Qishi Dong   +5 more
wiley   +1 more source

Harnessing Machine Learning to Understand and Design Disordered Solids

open access: yesAdvanced Intelligent Discovery, EarlyView.
This review maps the dynamic evolution of machine learning in disordered solids, from structural representations to generative modeling. It explores how deep learning and model explainability transform property prediction into profound physical insight.
Muchen Wang, Yue Fan
wiley   +1 more source

DeepMapper: Attention‐Based AutoEncoder for System Identification in Wound Healing and Stage Prediction

open access: yesAdvanced Intelligent Discovery, EarlyView.
The authors develop a deep learning model for real‐time tracking of wound progression. The deep learning framework maps the nonlinear evolution of a time series of images to a latent space, where they learn a linear representation of the dynamics. The linear model is interpretable and suitable for applications in feedback control.
Fan Lu   +11 more
wiley   +1 more source

Multi‐Property Machine Learning Models to Accelerate the Transition Toward Bio‐Based Emulsion Polymers

open access: yesAdvanced Intelligent Discovery, EarlyView.
A machine learning framework simultaneously predicts four critical properties of monomers for emulsion polymerization: propagation rate constant, reactivity ratios, glass transition temperature, and water solubility. These tools can be used to systematically identify viable bio‐based monomer pairs as replacements for conventional formulations, with ...
Kiarash Farajzadehahary   +1 more
wiley   +1 more source

AS‐pHopt: An Optimal pH Prediction Model Enhanced by Active Site of Enzymes

open access: yesAdvanced Intelligent Discovery, EarlyView.
To address the low accuracy of enzyme optimal pH (pHopt) prediction, this study develops active site‐based pHopt (AS‐pHopt), a prediction model enhanced by active site information and pseudo‐label prediction. Integrating key structural and physicochemical features affecting enzyme pHopt, AS‐pHopt uses Evolutionary Scale Modeling (ESM)‐2 with active ...
Wenxiang Song   +6 more
wiley   +1 more source

Home - About - Disclaimer - Privacy