New spatial sequencing method maps RNA turnover kinetics across the mouse brain
Spatial NT-seq combines metabolic RNA labeling with in situ chemical recoding to co-map newly synthesized and pre-existing RNAs, revealing the ...
Tag: Machine Learning
AI Model Decodes Which Molecules Transporters Carry Across Cell Membranes
A new geometric deep learning framework called TraSPIN uses protein language models and graph learning to predict which small molecules ...
AI Reads the Hidden Rhythm of Cyberattacks to Reconstruct Multi-Stage Intrusions Automatically
A new provenance-graph framework called MotifTrace automatically discovers attack stages from temporal motifs and reconstructs complete multi-stage cyberattacks, outperforming state-of-the-art ...
Metabolic Aging Clocks Built From 18,000 People Predict Disease and Death Risk
A large Chinese clinical study of 18,476 people identified 56 age-linked metabolites and built metabolic aging clocks that predict fatty ...
Clustering Across Domains: New Method Sharpens Graph Transfer Learning
Researchers at Central South University have developed a cluster-based domain adaptation method that aligns only semantically similar portions of source ...
Glowing Molecules: How Fluorescence Spectroscopy Is Transforming Environmental Monitoring and Diagnostics
A new review in Discover Chemistry details how fluorescence spectroscopy of advanced materials is enabling ultrasensitive detection of heavy metal ...
AI That Watches You Dance: Graph Neural Network Learns to Coach Like a Master Teacher
A new graph neural network framework evaluates dance training in real time and automatically adapts practice plans, achieving record accuracy ...
Machine Learning Pinpoints Warning Signs of Compassion Fatigue in Psychiatric Nurses
A multicentre study of 607 Chinese psychiatric nurses used interpretable machine learning to identify perceived pressure, age, professional identity, depression ...
AI Model Predicts Breast Cancer Spread to Lymph Nodes Before Surgery
A leakage-controlled multimodal AI model combining PET/CT radiomics, deep-learning features, metabolic parameters and blood-based indices achieved moderate preoperative prediction of ...
Chemists Find a Faster Route to Accurate Quantum Models of Tricky Transition Metals
University of Pittsburgh researchers have developed a diagnostic-guided method that makes gold-standard coupled cluster calculations fast and accurate for strongly ...
Deep Learning Is Transforming How the World Spots Sick Plants, Landmark Review Finds
A sweeping review of 1,081 studies from 2014 to 2024 shows convolutional neural networks rapidly becoming the world's leading tool ...
Scientists Reverse Aging in Cells and Mice With a Single Gene
Harvard-led researchers developed a transcriptomic aging clock to screen rejuvenation genes and found that over-expressing the RNA splicing factor SRSF1 ...
AI-Powered CT Scan Model Distinguishes Pancreatic Tumors Before Surgery
A combined spectral CT and radiomics nomogram achieved over 0.9 area under the curve in distinguishing pancreatic neuroendocrine tumors from ...
AI Sets Sail to Design the Next Generation of Eco-Friendly Ship Coatings
A new review examines how artificial intelligence and machine learning could transform the design of sustainable, non-toxic marine antifouling coatings ...
AI Model Predicts Chemotherapy Response in Metastatic Colorectal Cancer, With Caveats
Turkish researchers tested fifteen machine learning models to predict chemotherapy response in metastatic colorectal cancer, finding that a tuned LightGBM ...
Fuzzy Logic System Flags Struggling Students Early — and Explains Why
Researchers have built an interpretable fuzzy logic system that detects at-risk students with high recall and translates risk scores into ...
AI Reads Brain Scans to Predict Tumor Aggressiveness Before Surgery
A five-center study shows deep learning models, especially nnU-Net, predict aggressive meningioma grades from MRI more reliably across hospitals than ...
Machine Learning Meets Ballistics: Predicting How PEEK Plates Deflect High-Speed Impacts
Researchers combined ballistic experiments, finite element modeling, and a neural network to predict how PEEK plates fail under oblique high-speed ...
Hospitals Are Drowning in Patient Data While Missing the Warning Signs That Matter
A new viewpoint in the Journal of General Internal Medicine argues that hospitals already collect the data needed to prevent ...
Geometry Meets the Spreadsheet: Flow Matching Reshapes Synthetic Tabular Data
A new flow matching framework assigns each tabular variable type its natural geometric space, improving synthetic data quality and resisting ...
POPULAR NEWS
-
TLR8 Inhibition Targets Liver Fibrosis in Biliary Atresia
-
Tenecteplase After Thrombectomy Shows No Functional Benefit in Basilar Stroke Trial
-
Inhibiting Glucosylceramide Synthase Destroys Cancer Cells by Disrupting Lysosomal Function
-
Turkish adaptation of nursing mentor cultural competence scale validated