GPT-Neo Transformer Boosts Bacterial Promoter Prediction
A hybrid GPT-Neo transformer and Random Forest approach achieved 97 percent accuracy in detecting promoters in Agrobacterium tumefaciens.
A hybrid GPT-Neo transformer and Random Forest approach achieved 97 percent accuracy in detecting promoters in Agrobacterium tumefaciens.
Researchers trained an interpretable XGBoost model on biomechanical data from 204 male athletes to predict peak ACL force during side-cutting ...
A nine-year cohort study finds that a composite index combining triglyceride-glucose levels with frailty measures strongly predicts incident cardiovascular disease ...
A new risk–reward analysis of over 3.3 million football passes shows that higher-risk passes do not necessarily produce greater expected ...
A new framework for privacy-preserving healthcare analytics, published in Discover Artificial Intelligence, reports measurable gains in accuracy, latency, and communication ...
An explainable TabNet framework achieved an R² of 0.9880 when predicting employee performance from 100,000 workforce records, while its authors ...
A proof-of-concept study shows explainable AI can reconstruct dairy cow welfare-risk scores from routine milk records while revealing how, and ...
A machine learning study of 411,863 women across eleven Sub-Saharan African countries achieved 90.2 percent accuracy in predicting preterm birth ...
A multi-scale vision transformer analyzing UAV hyperspectral images identified pine wilt disease at the green attack and early stages with ...
A new review in Clinical and Experimental Medicine examines how molecular dynamics, docking, machine learning and AI platforms are being ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine