Results 171 to 180 of about 549,786 (309)
Multi‐Site Transfer Classification of Major Depressive Disorder: An fMRI Study in 3335 Subjects
Advanced Science, EarlyView.The study proposes graph convolution network with sparse pooling to learn the hierarchical features of brain graph for MDD classification. Experiment is done on multi‐site fMRI samples (3335 subjects, the largest functional dataset of MDD to date) and transfer learning is applied, achieving an average accuracy of 70.14%.
Jianpo Su +14 more
wiley +1 more source
Advanced Science, EarlyView.This research deciphers the m6A transcriptome by profiling its sites and functional readout effects: from mRNA stability, translation to alternative splicing, across five different cell types. Machine learning model identifies novel m6A‐binding proteins DDX6 and FXR2 and novel m6A reader proteins FUBP3 and L1TD1.
Zhou Huang +11 more
wiley +1 more source
Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences [PDF]
, 2023 Christopher Lang +4 more
openalex +1 more source
Advanced Science, EarlyView.FLARE, a multimodal AI framework, combines pathology slides, radiology scans, and clinical reports to predict colorectal cancer outcomes, even when some tests are missing. Evaluated retrospectively in 1679 patients from four medical centers, it consistently achieved the best prognostic accuracy and clearly separated high‐ and low‐risk groups.
Linhao Qu +6 more
wiley +1 more source
Suppressing label noise in medical image classification using mixup attention and self-supervised learning [PDF]
Mengdi Gao +5 more
openalex +1 more source
The Disordered Region of ASXL1 Acts as an Auto‐Regulator Through Condensation
Advanced Science, EarlyView.ASXL1's long IDR encodes an electrostatic “basic platform + acidic brake” that autoregulates condensation. Truncation at a clinical hotspot lifts this brake, forming condensates that retarget BRD2, remodel local chromatin accessibility, and impair neutrophil maturation.
Xiao Fang, Qiwei Li, Wenqing Zhang
wiley +1 more source
MGM as a Large‐Scale Pretrained Foundation Model for Microbiome Analyses in Diverse Contexts
Advanced Science, EarlyView.We present the Microbial General Model (MGM), a transformer‐based foundation model pretrained on over 260,000 microbiome samples. MGM learns contextualized microbial representations via self‐supervised language modeling, enabling robust transfer learning, cross‐regional generalization, keystone taxa discovery, and prompt‐guided generation of realistic,
Haohong Zhang +5 more
wiley +1 more source
Learned Conformational Space and Pharmacophore Into Molecular Foundational Model
Advanced Science, EarlyView.The Ouroboros model introduces two orthogonal modules within a unified framework that independently learn molecular representations and generate chemical structures. This design enables flexible optimization strategies for each module and faithful structure reconstruction without prompts or noise.
Lin Wang +8 more
wiley +1 more source
Advanced Science, EarlyView.This study, through multi‐omics approaches and animal models, revealed that air pollutant PM10 exacerbates the progression of rheumatoid arthritis (RA) by suppressing FNBP1 expression and impairing the cytotoxic function of CD56dim NK cells. The “PM10–FNBP1–NK cells” axis provided novel insights into the environmental pathogenesis of RA and suggested ...
Runhan Zhao +11 more
wiley +1 more source
Advanced Science, EarlyView.Single‐cell profiling across bone marrow, spleen, mesenteric lymph, and blood in rhesus monkeys reveals organ Immunosenescence. GZMB rises with age, particularly in cytotoxic and terminally exhausted CD8+ T cells, and BHLHE40 emerges as a key transcription factor enriched across multiple CD8+ subsets, regulating pro‐inflammatory and exhaustion‐related ...
Shengnan Wang +10 more
wiley +1 more source