Related Experiment Video
Updated: Dec 6, 2025
Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization
Published on: October 3, 2025
Pathway-Based Drug Response Prediction Using Similarity Identification in Gene Expression
Seyed Ali Madani Tonekaboni1,2, Gangesh Beri1, Benjamin Haibe-Kains1,2,3,4,5
1Princess Margaret Cancer Centre, Toronto, ON, Canada.
Abstract:
Lapatinib and trastuzumab (Herceptin) are targeted therapies designed for patients with HER2+ breast tumors. Although these therapies improved survival rates of patients with this tumor type, not all the patients harboring HER2 amplification respond to these drugs. The NeoALTTO clinical trial was designed to test whether a higher response rate can be achieved by combining lapatinib and trastuzumab. Although the combination therapy showed almost double the response rate compared to the monotherapies, 40% of the patients did not respond to the treatment. In this study, we sought to identify biomarkers of HER2+ breast cancer patients' response to drugs relying on gene expression profiles of tumors. We show that univariate gene expression-based biomarkers are significant but weak predictors of drug response. We further show that pathway activities, estimated from gene expression patterns quantified using the recent transcriptional similarity coefficient (TSC) between the tumor samples, yield high predictive value for therapy response (concordance index >0.8, p < 0.05). Moreover, machine learning models, built using multiple algorithms including logistic regression, naive Bayes, random forest, k-nearest neighbor, and support vector machine, for predicting drug response in the NeoALTTO clinical trial, resulted in lower performance compared to our pathway-based approach. Our results indicate that transcriptional similarity of biological pathways can be used to predict lapatinib and trastuzumab response in HER2+ breast cancer.
Insights
Identifying biomarkers for HER2+ breast cancer drug response is crucial. Pathway activity, not individual genes, accurately predicts response to lapatinib and trastuzumab therapies.
Area of Science:
- Oncology
- Genomics
- Bioinformatics
Background:
- Targeted therapies like lapatinib and trastuzumab improve outcomes for HER2+ breast cancer patients.
- However, a significant portion of patients do not respond to these treatments, necessitating better predictive biomarkers.
Purpose of the Study:
- To identify reliable biomarkers for predicting patient response to lapatinib and trastuzumab in HER2+ breast cancer.
- To compare the predictive power of gene expression profiles, pathway activities, and machine learning models.
Main Methods:
- Analyzed gene expression profiles from the NeoALTTO clinical trial.
- Assessed univariate gene expression biomarkers and pathway activities using the transcriptional similarity coefficient (TSC).
- Developed and evaluated machine learning models (logistic regression, naive Bayes, random forest, k-NN, SVM) for response prediction.
Main Results:
- Univariate gene expression biomarkers showed weak predictive value.
- Pathway activities estimated via TSC demonstrated high predictive accuracy for therapy response (concordance index >0.8, p < 0.05).
- Pathway-based approach outperformed various machine learning models in predicting drug response.
Conclusions:
- Transcriptional similarity of biological pathways is a robust predictor of response to lapatinib and trastuzumab in HER2+ breast cancer.
- This pathway-centric approach offers a more effective strategy for personalized therapy selection compared to individual gene biomarkers or standard machine learning models.
