Construction of a long non-coding RNA panel for breast cancer diagnosis using RNA sequencing data
Main Article Content
Abstract
This study aims to construct a robust lncRNA-based diagnostic panel for Breast Invasive Carcinoma (BRCA) using next-generation sequencing data. RNA-seq data of 184 tumor and 16 normal tissue samples were retrieved from The Cancer Genome Atlas (TCGA). Differentially expressed lncRNAs (DE-lncRNAs) were identified using DESeq2. To mitigate overfitting and select optimal features, the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression model was applied with 5-fold cross-validation (λ1se). Model stability was validated via 50-times repeated stratified subsampling. From 3,293 significant DE-lncRNAs, a diagnostic panel comprising six lncRNAs (LINC01614, LINC02202, LINC01537, AC134312.5, LINC02185, and AC106897.1) was established. The panel demonstrated superior diagnostic performance with an Area Under the Curve (AUC) of 0.9997, significantly outperforming individual genes. At the optimal Youden index cut-off (J = 0.9375), the model achieved 100% sensitivity and 93.75% specificity. Validation via repeated subsampling confirmed high stability with a mean AUC of 0.9976. We successfully constructed a highly accurate and stable 6-lncRNA diagnostic panel for BRCA using LASSO. This panel may serve as a potential candidate for further evaluation in breast cancer diagnostic research.
Article Details
Keywords
Breast Cancer, lncRNA, LASSO, Diagnosis, TCGA, molecular biomarker
References
2. Kim J, et al. Global patterns and trends in breast cancer incidence and mortality across 185 countries. Nat Med. 2025; 31(4): 1154-1162.
3. Boyd NF, et al. Mammographic density and the risk and detection of breast cancer. N Engl J Med. 2007; 356(3): 227-236.
4. Wang S, et al. Over-detection and over-surveillance in breast screening: current status and the potential for artificial intelligence optimisation. Insights Imaging. 2025; 16(1): 276.
5. Polyak K. Heterogeneity in breast cancer. J Clin Invest. 2011; 121(10): 3786-3788.
6. Xu S, et al. Oncogenic long noncoding RNA landscape in breast cancer. Mol Cancer. 2017; 16(1): 129.
7. El-Helkan B, et al. Long non-coding RNAs as novel prognostic biomarkers for breast cancer in Egyptian women. Sci Rep. 2022; 12(1): 19498.
8. Wang Y, Song B, Zhu L, et al. Long non-coding RNA LINC01614 as a potential biomarker for prognostic prediction in breast cancer. PeerJ. 2019; 7:e7976.
9. Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. J Stat Softw. 2010;33(1):1-22.Shaath H, Elango R, Alajez NM. Molecular classification of breast cancer utilizing long non-coding RNA transcriptomes identifies novel diagnostic lncRNA panel for triple-negative breast cancer. Cancers (Basel). 2021; 13(21).
10. Fan CN, Ma L, Liu N. Comprehensive analysis of novel three-long noncoding RNA signatures as diagnostic and prognostic biomarkers of human triple-negative breast cancer. J Cell Biochem. 2019; 120(3): 3185-3196.
11. Wu J, Cai Y, Zhao G, et al. A ten N6-methyladenosine-related long non-coding RNAs signature predicts prognosis of triple-negative breast cancer. J Clin Lab Anal. 2021; 35(6): e23779.
12. Xu M, et al. A seven-lncRNA signature for predicting prognosis in breast carcinoma. Transl Cancer Res. 2021;10(9):4033-4046.
13. Chen T, Shi K, Sun S. LINC01614 activated by SP1 promoted malignant behavior of triple-negative breast cancer cells via the WNT/β-catenin signaling pathway. Rev Invest Clin. 2024; 76(4): 185-198.