Related Experiment Video
Updated: Jul 12, 2026
Systems Biology of Metabolic Regulation by Estrogen Receptor Signaling in Breast Cancer
Published on: March 17, 2016
Integrative systematic review and transcriptomic -machine learning analysis of molecular signatures in metaplastic
Joshua Agilinko1,2, Sonam Patel2, Jogitha Selvarajah2
1The Elm Breast Unit, King George Hospital, Barking, Havering and Redbridge University Hospitals NHS Trust, Ilford, Essex IG3 8YB, UK.
Background:
Metaplastic breast cancer (MpBC) is a rare and aggressive breast cancer subtype characterised by marked histological heterogeneity, therapeutic resistance and poor clinical outcomes. Despite increasing molecular research, existing evidence remains fragmented, heterogeneous and poorly integrated, limiting clinical translation and biomarker validation.
Methods:
We developed an integrative analytical framework combining systematic review, quantitative meta-analysis, transcriptomic profiling and interpretable machine learning to identify and prioritise molecular markers in MpBC. A Preferred Reporting Items for Systematic Reviews and Meta Analyses-guided systematic review was conducted across PubMed, arXiv and Semantic Scholar. Effect sizes were standardised to Cohen's d and synthesised using a random-effects model. Transcriptomic analysis was performed on the GSE165407 dataset using DESeq2 in R (RStudio version 1.1.463), with differentially expressed genes cross-referenced against literature-derived biomarkers. Supervised models including a multi-layer perceptron and boosted random forest were applied, with performance evaluated using receiver operating characteristic analysis. Model interpretability was assessed using SHapley Additive exPlanations.
Results:
Eleven studies met inclusion criteria. Meta-analysis demonstrated low heterogeneity and a pooled effect size of d = 0.74 (95% CI 0.59-0.88), indicating a consistent moderate-to-large biomarker signal across studies. Pathway enrichment revealed convergence on PI3K/AKT/mTOR signalling, immune modulation and epithelial -mesenchymal transition. Transcriptomic profiling demonstrated concordance with literature-derived markers. The random forest model achieved strong classification performance (AUC = 0.91), with high specificity and minimal misclassification. SHapley Additive exPlanations analysis identified both canonical (PI3KCA, RPL39, EXO1) and non-canonical (CD55, LARGE2) contributors to model prediction.
Conclusion:
This study provides an integrated synthesis linking systematic evidence, transcriptomic validation and interpretable machine learning in MpBC. By reconciling fragmented literature with data-driven modelling, we identify a biologically coherent and clinically tractable molecular signature, offering a foundation for biomarker-driven stratification and translational validation.
Insights
This study integrates diverse data to identify key molecular markers for metaplastic breast cancer (MpBC), a rare and aggressive subtype. Findings offer a foundation for improved biomarker-driven stratification and clinical translation.
Area of Science:
- Oncology
- Genomics
- Bioinformatics
Background:
- Metaplastic breast cancer (MpBC) is a rare, aggressive subtype with poor outcomes.
- Existing MpBC research is fragmented, hindering clinical application and biomarker validation.
Purpose of the Study:
- To develop an integrative framework for identifying and prioritizing molecular markers in MpBC.
- To overcome limitations of fragmented evidence in MpBC research.
Main Methods:
- Systematic review, meta-analysis, transcriptomic profiling, and interpretable machine learning were combined.
- A PRISMA-guided systematic review and meta-analysis synthesized existing evidence.
- Transcriptomic data (GSE165407) and machine learning (Random Forest, MLP) identified key biomarkers.
Main Results:
- Meta-analysis showed a consistent moderate-to-large biomarker signal (d = 0.74).
- Pathway analysis highlighted PI3K/AKT/mTOR signaling, immune modulation, and EMT.
- Machine learning identified canonical (PI3KCA, RPL39, EXO1) and non-canonical (CD55, LARGE2) markers with high accuracy (AUC = 0.91).
Conclusions:
- An integrated approach reconciled fragmented literature with data-driven insights in MpBC.
- A coherent, clinically relevant molecular signature for MpBC was identified.
- This provides a foundation for biomarker-based stratification and translational research in MpBC.
