Results 141 to 150 of about 46,859 (313)

Topology‐Aware Deep Learning on Higher‐Order Structures for Drug Response Prediction

open access: yesAdvanced Science, EarlyView.
We present TopDr, a topology‐aware deep learning framework that encodes both drugs and cell lines as multiscale simplicial complexes, capturing interactions at the 0‐, 1‐, and 2‐simplex levels. By jointly integrating local higher‐order neighborhoods and global topological structures, TopDr generates enriched representations for sensitivity prediction ...
Cong Shen   +3 more
wiley   +1 more source

Embryo Evaluation Based on ResNet with AdaptiveGA-optimized Hyperparameters

open access: bronze, 2022
Wenju Zhou Wenju Zhou   +4 more
openalex   +2 more sources

Artificial Intelligence‐Based Body Composition Analysis Reveals Sex‐Specific Prognostic Markers and Their Clinical Value in Gastric Cancer: A Multicenter Study

open access: yesAdvanced Science, EarlyView.
This study applied AI to quantify multidimensional body composition from CT images in gastric cancer and healthy controls. Distinct sex‐specific patterns and disease‐related alterations were identified and were associated with survival. Higher muscle and fat measures were linked to improved outcomes.
Tianxiang Li   +13 more
wiley   +1 more source

stMixer for Scalable Mosaic Integration and Label Transfer in Spatial Histology and Multi‐Omics

open access: yesAdvanced Science, EarlyView.
stMixer is an unsupervised framework for scalable integration and label transfer across spatial histology and multi‐slide multi‐omics data with incomplete modality overlap. It combines self‐looped cross‐attention, multimodal metric learning, and graph‐guided cluster voting to align heterogeneous sections, correct batch effects, and propagate ...
Qixing Yang   +3 more
wiley   +1 more source

De Novo Design of Membrane‐Targeting Antimicrobial Peptides Against Gram‐Negative Bacteria Using a Generative Artificial Intelligence Framework

open access: yesAdvanced Science, EarlyView.
Antimicrobial resistance caused by Gram‐negative bacteria remains difficult to overcome due to the protective outer membrane. To address this challenge, a multi‐condition constrained generative AI framework, GenMTAMP is proposed for de novo membrane‐targeting antimicrobial peptide design by integrating physicochemical and spatial structure descriptors.
Jingxiao Yu   +5 more
wiley   +1 more source

Hyperparameter optimization of hp-greedy reduced basis for gravitational wave surrogates [PDF]

open access: green, 2023
Franco Cerino   +4 more
openalex   +1 more source

ProSiteHunter: A Unified Framework for Sequence‐Based Prediction of Protein‐Nucleic Acid and Protein‐Protein Binding Sites

open access: yesAdvanced Science, EarlyView.
This study proposed a unified sequence‐based framework for protein binding site prediction, which adopted a tri‐track semantic multi‐source feature fusion strategy to effectively capture diverse macromolecular interaction sites and further improved the accuracy of antibody‐antigen interaction prediction.
Dongliang Hou   +8 more
wiley   +1 more source

An Efficient Neural Network for Segmenting Multiple Joint Tissues from Knee MRI with Hyperparameter Optimization: Data from the Osteoarthritis Initiative

open access: green, 2022
Pauline Shan Qing Yeoh   +5 more
openalex   +1 more source

Home - About - Disclaimer - Privacy