Related Experiment Video
Updated: May 2, 2026
Identifying the Effects of BRCA1 Mutations on Homologous Recombination using Cells that Express Endogenous Wild-type BRCA1
Published on: February 17, 2011
Gene expression signature for predicting homologous recombination deficiency in triple-negative breast cancer
Jia-Wern Pan1, Zi-Ching Tan2, Pei-Sze Ng2
1Cancer Research Malaysia, Subang Jaya, Malaysia. jiawern.pan@cancerresearch.my.
Abstract:
Triple-negative breast cancers (TNBCs) are a subset of breast cancers that have remained difficult to treat. A proportion of TNBCs arising in non-carriers of BRCA pathogenic variants have genomic features that are similar to BRCA carriers and may also benefit from PARP inhibitor treatment. Using genomic data from 129 TNBC samples from the Malaysian Breast Cancer (MyBrCa) cohort, we developed a gene expression-based machine learning classifier for homologous recombination deficiency (HRD) in TNBCs. The classifier identified samples with HRD mutational signature at an AUROC of 0.93 in MyBrCa validation datasets and 0.84 in TCGA TNBCs. Additionally, the classifier strongly segregated HRD-associated genomic features in TNBCs from TCGA, METABRIC, and ICGC. Thus, our gene expression classifier may identify triple-negative breast cancer patients with homologous recombination deficiency, suggesting an alternative method to identify individuals who may benefit from treatment with PARP inhibitors or platinum chemotherapy.
Insights
Researchers developed a machine learning classifier to detect homologous recombination deficiency (HRD) in triple-negative breast cancer (TNBC). This tool may identify TNBC patients who could benefit from PARP inhibitors or platinum chemotherapy.
Area of Science:
- Oncology
- Genomics
- Bioinformatics
Background:
- Triple-negative breast cancer (TNBC) presents significant treatment challenges.
- Some TNBCs, even in non-BRCA mutation carriers, exhibit genomic similarities to BRCA-mutated cancers.
- These similarities suggest potential sensitivity to PARP inhibitors.
Purpose of the Study:
- To develop and validate a machine learning classifier for homologous recombination deficiency (HRD) in TNBC.
- To assess the classifier's ability to identify TNBC patients who might respond to PARP inhibitors or platinum chemotherapy.
Main Methods:
- Utilized genomic data from 129 TNBC samples in the Malaysian Breast Cancer (MyBrCa) cohort.
- Developed a gene expression-based machine learning classifier to predict HRD.
- Validated the classifier on independent datasets, including TCGA TNBCs.
Main Results:
- The classifier achieved an AUROC of 0.93 in MyBrCa validation datasets and 0.84 in TCGA TNBCs for identifying HRD mutational signatures.
- The classifier effectively segregated HRD-associated genomic features across multiple large TNBC datasets (TCGA, METABRIC, ICGC).
Conclusions:
- A novel gene expression classifier can identify homologous recombination deficiency in triple-negative breast cancer.
- This classifier offers a potential method to identify TNBC patients suitable for PARP inhibitor or platinum-based chemotherapy.
