Machine learning-based prediction of hernia risk in peritoneal dialysis patients: a comparative study of models and SHAP-driven interpretability analysis. [PDF]
Cao Y, Hu X, Fang T, Guo J.
europepmc +1 more source
This work introduces a scalable, data‐driven strategy that turns the vast sequence diversity of phage receptor‐binding proteins into modular tools for engineering customizable phages. By clustering and experimentally validating diverse RBPs, the authors build an accurate map linking sequence to host specificity and create plug‐and‐play modules that ...
Shisong Jing +10 more
wiley +1 more source
XL-MSDigger: a deep learning-based, versatile solution for cross-linking mass spectrometry. [PDF]
Chen M +6 more
europepmc +1 more source
A new cerebrocortical organoid model using isogenic hiPSCs with familial Alzheimer's mutations recapitulates key AD features, including amyloid‐beta and phospho‐Tau aggregation, neuronal hyperexcitability, and synapse loss. Single‐cell RNA‐seq reveals aberrant pathways in excitatory and inhibitory neurons.
Sergio R. Labra +23 more
wiley +1 more source
Reliability of 3D quantitative displacement of femoral neck fracture site measured via CT and its correlation with femoral head avascular necrosis: a retrospective cohort study. [PDF]
Zhao K, Liu Y, Li H.
europepmc +1 more source
General schematic of the approach. Abstract Conventional Silver/Silver Chloride (Ag/AgCl) electrodes remain the clinical standard for electrophysiological monitoring but are hindered by poor skin conformity, mechanical rigidity, and signal degradation, particularly under motion or sweat.
Nazmi Alsaafeen +11 more
wiley +1 more source
X-intNMF: a cross- and intra-omics regularized NMF framework for multi-omics integration. [PDF]
Bui TT, Xie R, Zhang W.
europepmc +1 more source
De Novo Multi‐Mechanism Antimicrobial Peptide Design via Multimodal Deep Learning
Current AI‐driven peptide discovery often overlooks complex structural data. This study presents M3‐CAD, a generative pipeline that leverages 3D voxel coloring and a massive database of over 12 000 peptides to capture nuanced physicochemical contexts.
Xiaojuan Li +23 more
wiley +1 more source
Regarding: 'identification of risk factors and development of predictive models for chronic postsurgical pain after modified radical mastectomy'. [PDF]
Zhang Q, Jin H.
europepmc +1 more source
S3RL: Enhancing Spatial Single‐Cell Transcriptomics With Separable Representation Learning
Separable Spatial Representation Learning (S3RL) is introduced to enhance the reconstruction of spatial transcriptomic landscapes by disentangling spatial structure and gene expression semantics. By integrating multimodal inputs with graph‐based representation learning and hyperspherical prototype modeling, S3RL enables high‐fidelity spatial domain ...
Laiyi Fu +6 more
wiley +1 more source

