A knowledge graph-guided transcriptomic framework identifies a 20-gene prognostic signature for cervical cancer
- 1State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Xinjiang Medical University, Urumqi, 830017 China
- 2College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, 830017 China
Abstract
Background: Current cervical cancer risk stratification relies on FIGO stage and lymph node status, which fail to capture molecular heterogeneity and leave patients over- or under-treated. Conventional transcriptomic biomarker discovery relies solely on differential expression, yielding thousands of candidates that often lack disease specificity. To address these limitations, we developed a computational framework that integrates knowledge graph (KG) embeddings with transcriptomic differential expression to identify cervical cancer-specific prognostic biomarkers.
Results: Among ten embedding models for prediction of gene-disease associations, ComplEx showed the highest cervical cancer specificity (Top 100 mean Z-score = 4.19, range 3.54–6.71). Intersection of KG-predicted candidates (Z ≥ 1.645, P < 0.05) with DESeq2 differentially expressed genes (adjusted P < 0.05, |log2FoldChange|> 1) identified 468 high-confidence candidate genes. Using a nested cross-validated Top-K weighted risk score approach, a 20-gene prognostic signature was finalized. The signature demonstrated an unbiased nested cross-validated C-index of 0.638 ± 0.057 for Top-K selection, while the apparent full-data C-index was 0.760 (bootstrap 95% CI 0.697–0.812) and the mean time-dependent AUC was 0.795. Multivariable Cox regression confirmed the signature as an independent prognostic factor after adjusting for age and FIGO stage (HR = 1.89 per SD, P < 0.001, C-index = 0.803), with the strongest discrimination in Stage I disease (C-index = 0.796). Also, external validation in GSE52903 showed a consistent but non-significant trend toward survival discrimination (log-rank P = 0.055; HR = 1.30).
Conclusions: This study introduces a Z-score-based specificity framework that integrates knowledge-graph embedding with transcriptomic analysis for cervical cancer biomarker discovery. Unlike conventional KG evaluations that rely solely on link-prediction metrics, the disease-specificity Z-score calibrates each gene against ten control solid tumors to filter pan-cancer noise, thereby enhancing the disease specificity of the transcriptomic analysis. These results support the signature’s hypothesis-generating potential for personalized risk stratification, though prospective validation in independent cohorts with survival endpoints remains essential before clinical application.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12859-026-06577-y.
Related
- An Oxidative Stress-Associated Seven-Gene Prognostic Signature in Lung Adenocarcinoma: Integrative Transcriptomic Analysis Across Public Cohorts
- Longitudinal Transcriptomic Analysis Identifies Persistent Immune-Related Signature Associated With Restrictive Left Ventricular Filling Patterns After Heart Transplantation
- Integrated single-cell and machine learning analysis identifies an autophagy- and immune-related prognostic signature in adrenocortical carcinoma
- Integrated Transcriptomic Analysis Identifies a Ferroptosis-Related Gene Signature Underlying Macrophage Heterogeneity and Immune Dysregulation in Rheumatoid Arthritis Synovium
- A kbhb-associated prognostic signature identifies TTLL12 as a promoter of lung adenocarcinoma progression associated with M2 macrophage infiltration.
BibTeX
@article{deng2026knowledge,
title = {{A knowledge graph-guided transcriptomic framework identifies a 20-gene prognostic signature for cervical cancer}},
author = {Ziyi Deng and Xuehua Bi and Hanyuan Zhang},
journal = {BMC Bioinformatics},
year = {2026},
month = jul,
doi = {10.1186/s12859-026-06577-y},
url = {https://doi.org/10.1186/s12859-026-06577-y},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - A knowledge graph-guided transcriptomic framework identifies a 20-gene prognostic signature for cervical cancer
AU - Ziyi Deng
AU - Xuehua Bi
AU - Hanyuan Zhang
PY - 2026
DA - 2026/07/30
JO - BMC Bioinformatics
DO - 10.1186/s12859-026-06577-y
UR - https://doi.org/10.1186/s12859-026-06577-y
AB - Background: Current cervical cancer risk stratification relies on FIGO stage and lymph node status, which fail to capture molecular heterogeneity and leave patients over- or under-treated. Conventional transcriptomic biomarker discovery relies solely on differential expression, yielding thousands of candidates that often lack disease specificity. To address these limitations, we developed a computational framework that integrates knowledge graph (KG) embeddings with transcriptomic differential expression to identify cervical cancer-specific prognostic biomarkers. Results: Among ten embedding models for prediction of gene-disease associations, ComplEx showed the highest cervical cancer specificity (Top 100 mean Z-score = 4.19, range 3.54–6.71). Intersection of KG-predicted candidates (Z ≥ 1.645, P < 0.05) with DESeq2 differentially expressed genes (adjusted P < 0.05, |log2FoldChange|> 1) identified 468 high-confidence candidate genes. Using a nested cross-validated Top-K weighted risk score approach, a 20-gene prognostic signature was finalized. The signature demonstrated an unbiased nested cross-validated C-index of 0.638 ± 0.057 for Top-K selection, while the apparent full-data C-index was 0.760 (bootstrap 95% CI 0.697–0.812) and the mean time-dependent AUC was 0.795. Multivariable Cox regression confirmed the signature as an independent prognostic factor after adjusting for age and FIGO stage (HR = 1.89 per SD, P < 0.001, C-index = 0.803), with the strongest discrimination in Stage I disease (C-index = 0.796). Also, external validation in GSE52903 showed a consistent but non-significant trend toward survival discrimination (log-rank P = 0.055; HR = 1.30). Conclusions: This study introduces a Z-score-based specificity framework that integrates knowledge-graph embedding with transcriptomic analysis for cervical cancer biomarker discovery. Unlike conventional KG evaluations that rely solely on link-prediction metrics, the disease-specificity Z-score calibrates each gene against ten control solid tumors to filter pan-cancer noise, thereby enhancing the disease specificity of the transcriptomic analysis. These results support the signature’s hypothesis-generating potential for personalized risk stratification, though prospective validation in independent cohorts with survival endpoints remains essential before clinical application. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12859-026-06577-y.
SN - 1471-2105
ER -