Three-Gene Expression Signature for Predicting Lymph Node Metastasis in Cervical Cancer

Yachen Duan developed a three-gene expression signature to predict lymph node metastasis in cervical squamous cell carcinoma. The signature was discovered using transcriptomic data from 116 TCGA samples and validated on an independent clinical cohort of 202 patients from Fudan University Shanghai Cancer Center. The dataset was last updated on 2026-05-13.

Use Cases

• Training machine learning models for cancer prognosis based on gene expression data.
• Validating biomarker signatures for lymph node metastasis prediction in independent clinical cohorts.
• Developing integrated clinical-molecular risk assessment models using features like tumor size and lymphovascular invasion.

Strengths

• The signature was validated on an independent clinical cohort of 202 patients (101 LNM-positive and 101 LNM-negative).
• Model performance metrics are reported, including an AUC of 0.745 and bootstrap-validated robustness.
• The combined model integrating the signature with clinical features achieved an AUC of 0.789.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 49.4 KB, indicating limited scope.

Provenance

Source

The Cancer Genome Atlas (TCGA) and Fudan University Shanghai Cancer Center clinical cohort.

Collection Method

Retrospective biomarker discovery using transcriptomic data analysis and LASSO regression, validated via qRT-PCR.

Freshness

Last updated 2026-05-13 05:56:58; freshness should be verified.