Results 201 to 210 of about 30,503 (277)
Genetic Diagnosis and Discovery Enabled by Large Language Models
We demonstrate that large language models (LLMs) can facilitate genetic diagnosis and discovery. LLMs were used to solve four types of genetic problems of sequentially increased complexity. An LLM‐based pipeline could analyze genetic variants in the genomic sequences of human hearing loss or rare genetic disease patients and assist in identifying ...
Tao Tu +25 more
wiley +1 more source
A Recommendation System for Trigger-Action Programming Rules via Graph Contrastive Learning. [PDF]
Kuang Z +5 more
europepmc +1 more source
The functionalized starch modifies the mitochondrial surface and encapsulates resveratrol into the cavity of helices, facilitating a novel mitochondrial transplantation platform (MLSR). Upon internalization in recipient cells, MLSR triggers mitophagy and maintains positive autophagic flux through RIP1/RIP3 pathway inhibition.
Nisha Wang +12 more
wiley +1 more source
NK Cell Activation by Platinum Boosts Immunotherapy in HR+/HER2− Breast Cancer
Multi‐omics and single‐cell analyses identify activated NK cells as key mediators of anti‐PD‐(L)1 response in HR+/HER2− breast cancer. Platinum chemotherapy enhances NK cell cytotoxicity through NF‐κB–associated signaling, synergizing with immunotherapy and providing a rationale for combination treatment.
Yi‐Yu Chen +8 more
wiley +1 more source
ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction. [PDF]
Dong Y +5 more
europepmc +1 more source
The results showed that the reduction of plasma 24‐hydroxycholesterol (24‐OHC) was related to the cognitive decline in elderly surgical patients. Neuroinflammation induced by anesthesia and surgery significantly downregulated SREBP2 in hippocampal reactive astrocytes, resulting in reduced cholesterol synthesis.
He Huang +13 more
wiley +1 more source
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
Graph contrastive learning as a versatile foundation for advanced scRNA-seq data analysis. [PDF]
Zhang Z +7 more
europepmc +1 more source
In hypoxic microenvironment, WNT5A is predominantly secreted by tumor‐associated macrophages. Hypoxia‐induced WTAP mediates ROR1 stability by m6A modifications in a HuR‐dependent manner in Glioma stem cells (GSCs). WNT5A activates the WNT pathway via ROR1 binding on GSCs, driving glioma‐derived endothelial cells (GDECs) differentiation.
Xiaoyong Chen +15 more
wiley +1 more source
TP-GCL: graph contrastive learning from the tensor perspective. [PDF]
Li M +6 more
europepmc +1 more source

