Yixing People's Hospital

Multimodal Transformer Integrating CT and Pathology for Postoperative Risk Stratification in Stage I Non–Small Cell Lung Cancer

A biologically interpretable multimodal artificial intelligence framework outperformed guideline-based postoperative risk stratification for stage I non–small cell lung cancer and identified patients who would benefit from adjuvant therapy.

Effectiveness and Safety of Fixed‐Dose Combination Metformin and Empagliflozin in Type 2 Diabetes: A Prospective, Multicenter, Real‐World Study From China

BACKGROUND: This study assessed the real-world effectiveness and safety of a fixed-dose combination (FDC) of metformin and empagliflozin in Chinese patients with type 2 diabetes mellitus (T2DM). METHODS: This prospective, multicenter, real-world study enrolled consecutive patient...

Sodium L-lactate alleviates DSS-induced colitis through gut microbiota remodeling and Akkermansia enrichment

L-lactate, a byproduct of glycolysis and hypoxia, accumulates in the gut during disease progression and may affect host responses and microbial metabolism. Here, we investigated the protective effect of sodium L-lactate on dextran sulfate sodium (DSS)-induced colitis in mice and...

Mechanistic investigation and optimization of a cellulase-additive compounding system for bio-polishing of cotton fabric

Purpose This study aimed to develop an efficient and low-damage bio-polishing process for cotton fabric by optimizing a cellulase-additive compounding strategy. Design/methodology/approach Acidic and neutral cellulases were compared using orthogonal and single-factor experiments....

Recent Advances in CRISPR/Cas Systems for Respiratory Pathogen Diagnostics

Early, rapid, and accurate detection is essential for clinical management and epidemiological control of acute respiratory infections caused by pathogens. Traditional testing methods such as microbial culture, serological testing, and PCR are restrictive in terms of operation and...

Enzyme discovery and catalytic mechanism insights for mitigating inhibitory effects in tobacco lignocellulose biodegradation: advances, challenges, and perspectives

Tobacco biomass constitutes a substantial yet underexploited lignocellulosic resource with considerable potential for bioconversion. However, its efficient enzymatic utilization is constrained by pronounced structural heterogeneity and the presence of diverse non-structural inhib...

A Multi-Modal Pre-training Framework-Driven Active Learning System for Enhanced Protein Evolution of Cs CE

Abstract Protein language models have shown strong potential in modeling fitness landscapes for directed evolution; however, their predictive accuracy and generalization to unexplored sequence space remain limited under few-shot learning conditions. Here, we present MmALS (Multi-...