Results 211 to 220 of about 47,079 (313)

CLRe: A Synergistic Dual‐Engine Framework for One‐Step Retrosynthesis Prediction

open access: yesAdvanced Science, EarlyView.
CLRe uses a contrastive difficulty score to order pretrained seq2seq fine‐tuning for retrosynthesis. Reaction embeddings define the ranking score, and a cumulative easy‐to‐hard schedule expands from the easiest subset to the full training set while earlier examples remain active.
Tianhao Su   +5 more
wiley   +1 more source

CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model

open access: yesAdvanced Science, EarlyView.
In this work, CoSP (contrastive multi‐state pretrain), an intelligent inverse design method for reconfigurable metamaterials based on a contrastive pretrained large language model, is proposed. Numerical experiments demonstrate that CoSP can design reconfigurable metamaterial structures for multi‐state, multi‐band optical responses, showing great ...
Shujie Yang   +4 more
wiley   +1 more source

A Hybrid ISSA-XGBoost Model for Predicting Wellbore Leakage. [PDF]

open access: yesSensors (Basel)
Bai K   +5 more
europepmc   +1 more source

Data‐Driven Design of Self‐Adhesive Epidermal Electrodes and Sensors

open access: yesAdvanced Science, EarlyView.
This work presents self‐adhesive, stretchable epidermal electrodes and sensors developed through a data‐driven design framework that integrates artificial neural networks with genetic algorithms. By tailoring optimization objectives, either maximizing electrical conductivity and adhesion or enhancing piezoresistive sensitivity, the study enables the ...
Xuan Li   +10 more
wiley   +1 more source

TSTScope Unifies Single‐Cell Multi‐Omics to Identify Functional T Cell States Predictive of Immunotherapy Response

open access: yesAdvanced Science, EarlyView.
TSTScope is an interpretable AI framework that integrates single‐cell transcriptomes with TCR information through curated gene‐program constraints. By linking receptor context to functional T cell states, it reveals response‐associated tumor‐specific T cell programs in lung cancer immunotherapy cohorts and defines an MPR score associated with ...
Shiwei Cao   +8 more
wiley   +1 more source

Biochemically Constrained Multi‐Omics Integration Reveals Protein–Metabolite Dependencies Across Diseases

open access: yesAdvanced Science, EarlyView.
ProMetNet introduces a biologically constrained deep learning framework for proteo‐metabolomic integration by embedding Reactome‐derived pathway topology into neural networks. It captures non‐linear molecular dependencies and pathway‐level metabolic reorganization, enabling interpretable discrimination.
Minghui Zhao   +6 more
wiley   +1 more source

Home - About - Disclaimer - Privacy