Dataset Information

Construction and validation of a gene expression classifier to predict immunotherapy response in primary triple-negative breast cancer.

ABSTRACT:

Background

Immune checkpoint inhibitors (ICI) improve clinical outcomes in triple-negative breast cancer (TNBC) patients. However, a subset of patients does not respond to treatment. Biomarkers that show ICI predictive potential in other solid tumors, such as levels of PD-L1 and the tumor mutational burden, among others, show a modest predictive performance in patients with TNBC.

Methods

We built machine learning models based on pre-ICI treatment gene expression profiles to construct gene expression classifiers to identify primary TNBC ICI-responder patients. This study involved 188 ICI-naïve and 721 specimens treated with ICI plus chemotherapy, including TNBC tumors, HR+/HER2- breast tumors, and other solid non-breast tumors.

Results

The 37-gene TNBC ICI predictive (TNBC-ICI) classifier performs well in predicting pathological complete response (pCR) to ICI plus chemotherapy on an independent TNBC validation cohort (AUC = 0.86). The TNBC-ICI classifier shows better performance than other molecular signatures, including PD-1 (PDCD1) and PD-L1 (CD274) gene expression (AUC = 0.67). Integrating TNBC-ICI with molecular signatures does not improve the efficiency of the classifier (AUC = 0.75). TNBC-ICI displays a modest accuracy in predicting ICI response in two different cohorts of patients with HR + /HER2- breast cancer (AUC = 0.72 to pembrolizumab and AUC = 0.75 to durvalumab). Evaluation of six cohorts of patients with non-breast solid tumors treated with ICI plus chemotherapy shows overall poor performance (median AUC = 0.67).

Conclusion

TNBC-ICI predicts pCR to ICI plus chemotherapy in patients with primary TNBC. The study provides a guide to implementing the TNBC-ICI classifier in clinical studies. Further validations will consolidate a novel predictive panel to improve the treatment decision-making for patients with TNBC.

SUBMITTER: Ensenyat-Mendez M

PROVIDER: S-EPMC10333210 | biostudies-literature | 2023 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Construction and validation of a gene expression classifier to predict immunotherapy response in primary triple-negative breast cancer.

Ensenyat-Mendez Miquel M Orozco Javier I J JIJ Llinàs-Arias Pere P Íñiguez-Muñoz Sandra S Baker Jennifer L JL Salomon Matthew P MP Martí Mercè M DiNome Maggie L ML Cortés Javier J Marzese Diego M DM

Communications medicine 20230710 1

<h4>Background</h4>Immune checkpoint inhibitors (ICI) improve clinical outcomes in triple-negative breast cancer (TNBC) patients. However, a subset of patients does not respond to treatment. Biomarkers that show ICI predictive potential in other solid tumors, such as levels of PD-L1 and the tumor mutational burden, among others, show a modest predictive performance in patients with TNBC.<h4>Methods</h4>We built machine learning models based on pre-ICI treatment gene expression profiles to constr ...[more]

PMID: 37430006

Similar Datasets

Project description:BackgroundRapid advances in transcriptomic profiles have resulted in recognizing IRLs (immune-related long noncoding RNAs), as modulators of the expression of genes related to immune cells that mediate immune inhibition as well as immune stimulatory, indicating LncRNAs play fundamental roles in immune modulation. Hence, we establish an IRL classifier to precisely predict prognosis and immunotherapeutic efficiency in laryngeal squamous cell carcinoma (LSCC).MethodsLSCC RNA-seq (RNA sequencing) datasets, somatic mutation data, and corresponding clinicopathologic information were acquired from TCGA (the Cancer Genome Atlas) and Gene Expression Omnibus (GEO) databases. Spearman correlation analysis identified LncRNAs associated with immune-related genes (IRG). Based on Lasso penalized regression and random forest (RF), we constructed an IRL classifier associated with prognosis. GEO database was utilized to validate the IRL classifier. The predictive precision and clinical application of the IRL classifier were assessed and compared to clinicopathologic features. The immune cell infiltration of LSCC was calculated via CIBERSORTx tools and ssGSEA (single-sample gene set enrichment analysis). Then, we systematically correlated the IRL classifier with immunological characteristics from multiple perspectives, such as immune-related cells infiltrating, tumor microenvironment (TME) scoring, microsatellite instability (MSI), tumor mutation burden (TMB), and chemokines. Finally, the TIDE (tumor immune dysfunction and exclusion) algorithm was used to predict response to immunotherapy.ResultsBased on machine learning approach, three prognosis-related IRLs (BARX1-DT, KLHL7-DT, and LINC02154) were selected to build an IRL classifier. The IRL classifier could availably classify patients into the low-risk and high-risk groups based on the different endpoints, including recurrence-free survival (RFS) and overall survival (OS). In terms of predictive ability and clinical utility, the IRL classifier was superior to other clinical characteristics. Encouragingly, similar results were observed in the GEO databases. Immune infiltration analysis displayed immune cells that are significantly richer in low-risk group, CD8 T cells and activated NK cells via CIBERSORTx algorithm as well as activated CD8 T cell via ssGSEA. Additionally, compared with the high-risk group, immune score, CD8 T effector was higher in the low-risk group, yet stromal score, score of p53 signaling pathway and TGFher in the Tx algorithm, was lower in the low-risk group. Corresponding results were confirmed in GEO dataset. Finally, TIDE analysis uncovered that the IRL classifier may be effectually predict the clinical response of immunotherapy in LSCC.ConclusionBased on BARX1-DT, KLHL7-DT, and LINC02154, the IRL classifier was established, which can be used to predict the prognosis, immune infiltration status, and immunotherapy response in LSCC patients and might facilitate personalized counseling for immunotherapy.

Dataset Information

Construction and validation of a gene expression classifier to predict immunotherapy response in primary triple-negative breast cancer.

Background

Methods

Results

Conclusion

Publications

Construction and validation of a gene expression classifier to predict immunotherapy response in primary triple-negative breast cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets