Multimodal Cross‐Attentive Graph‐Based Framework for Predicting In Vivo Endocrine Disruptors
A multimodal cross‐attentive graph neural network integrates molecular graphs with androgen and estrogen adverse outcome pathway (AOP)–anchored in vitro assay signals to predict in vivo endocrine disruption. By fusing information on Tier‐1 AOP logits with chemical structures, the framework achieves high accuracy and provides assay‐traceable ...
Eder Soares de Almeida Santos +6 more
wiley +1 more source
MACFIV: a novel framework for nonlinear causal inference in the body mass index-hypertension relationship with many weak and pleiotropic genetic instruments. [PDF]
Chen D, Wang Y, Shi D, Cao Y, Hu YQ.
europepmc +1 more source
The formation of insulating Li2S during discharge in solid‐state lithium–sulfur batteries passivate reaction sites and limits sulfur utilization. In this work, a microstructure‐resolved modeling framework coupling transport and reaction kinetics is developed to predict charge–discharge behavior and reveal particle‐scale species evolution and incomplete
Arpan K. Sharma +4 more
wiley +1 more source
Variable Selection via Fused Sparse-Group Lasso Penalized Multi-state Models Incorporating Molecular Data. [PDF]
Miah K +4 more
europepmc +1 more source
Revolutionizing Lithium Metal Anodes With 3D‐Printed Topology‐Optimized Hosts for Enhanced Stability
This study presents a topology‐optimized lithium metal anode host fabricated via digital light processing (DLP) 3D printing. The reinforced microstructure provides mechanical stability, suppresses dendrite growth, and accommodates volume changes.
Xin Hu +5 more
wiley +1 more source
Socio-ecological factors of health literacy and physical activity among middle-aged and older Chinese adults. [PDF]
Huang L +8 more
europepmc +1 more source
BiSCALE: A pathology‐driven deep learning framework for multi‐scale gene expression prediction from whole‐slide images. It accurately infers bulk and near‐cellular spot‐level expression, links predictions to clinical phenotypes, identifies disease‐associated niches, and enables applications in risk stratification and cell‐identity annotation, providing
Hailong Zheng +8 more
wiley +1 more source
GenCPM: a toolbox for generalized connectome-based predictive modeling. [PDF]
Xu B +4 more
europepmc +1 more source
Leveraging Artificial Intelligence and Large Language Models for Cancer Immunotherapy
Cancer immunotherapy faces challenges in predicting treatment responses and understanding resistance mechanisms. Artificial intelligence (AI) and machine learning (ML) offer powerful solutions for cancer immunotherapy in patient stratification, biomarker discovery, treatment strategy optimization, and foundation model development.
Xinchao Wu +4 more
wiley +1 more source
Partial Effects in Environmental Mixtures: Evidence and Guidance on Methods and Implications. [PDF]
Kamenetsky ME +9 more
europepmc +1 more source

