Dataset Information

Gene signature-based prediction of triple-negative breast cancer patient response to Neoadjuvant chemotherapy.

ABSTRACT: Neoadjuvant chemotherapy is the current standard of care for large, advanced, and/or inoperable tumors, including triple-negative breast cancer. Although the clinical benefits of neoadjuvant chemotherapy have been illustrated through numerous clinical trials, more than half of the patients do not experience therapeutic benefit and needlessly suffer from side effects. Currently, no clinically applicable biomarkers are available for predicting neoadjuvant chemotherapy response in triple-negative breast cancer; the discovery of such a predictive biomarker or marker profile is an unmet need. In this study, we introduce a generic computational framework to calculate a response-probability score (RPS), based on patient transcriptomic profiles, to predict their response to neoadjuvant chemotherapy. We first validated this framework in ER-positive breast cancer patients and showed that it predicted neoadjuvant chemotherapy response with equal performance to several clinically used gene signatures, including Oncotype DX and MammaPrint. Then, we applied this framework to triple-negative breast cancer data and, for each patient, we calculated a response probability score (TNBC-RPS). Our results indicate that the TNBC-RPS achieved the highest accuracy for predicting neoadjuvant chemotherapy response compared to previously proposed 143 gene signatures. When combined with additional clinical factors, the TNBC-RPS achieved a high prediction accuracy for triple-negative breast cancer patients, which was comparable to the prediction accuracy of Oncotype DX and MammaPrint in ER-positive patients. In conclusion, the TNBC-RPS accurately predicts neoadjuvant chemotherapy response in triple-negative breast cancer patients and has the potential to be clinically used to aid physicians in stratifying patients for more effective neoadjuvant chemotherapy.

SUBMITTER: Zhao Y

PROVIDER: S-EPMC7476842 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Gene signature-based prediction of triple-negative breast cancer patient response to Neoadjuvant chemotherapy.

Zhao Yanding Y Schaafsma Evelien E Cheng Chao C

Cancer medicine 20200721 17

Neoadjuvant chemotherapy is the current standard of care for large, advanced, and/or inoperable tumors, including triple-negative breast cancer. Although the clinical benefits of neoadjuvant chemotherapy have been illustrated through numerous clinical trials, more than half of the patients do not experience therapeutic benefit and needlessly suffer from side effects. Currently, no clinically applicable biomarkers are available for predicting neoadjuvant chemotherapy response in triple-negative b ...[more]

PMID: 32692484

Similar Datasets

Project description:BackgroundPathological complete response (pCR) is associated with favorable prognosis in patients with triple-negative breast cancer (TNBC). However, only 30-40% of TNBC patients treated with neoadjuvant chemotherapy (NAC) show pCR, while the remaining 60-70% show residual disease (RD). The role of the tumor microenvironment in NAC response in patients with TNBC remains unclear. In this study, we developed a machine learning-based two-step pipeline to distinguish between various histological components in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of TNBC tissue biopsies and to identify histological features that can predict NAC response.MethodsH&E-stained WSIs of treatment-naïve biopsies from 85 patients (51 with pCR and 34 with RD) of the model development cohort and 79 patients (41 with pCR and 38 with RD) of the validation cohort were separated through a stratified eightfold cross-validation strategy for the first step and leave-one-out cross-validation strategy for the second step. A tile-level histology label prediction pipeline and four machine-learning classifiers were used to analyze 468,043 tiles of WSIs. The best-trained classifier used 55 texture features from each tile to produce a probability profile during testing. The predicted histology classes were used to generate a histology classification map of the spatial distributions of different tissue regions. A patient-level NAC response prediction pipeline was trained with features derived from paired histology classification maps. The top graph-based features capturing the relevant spatial information across the different histological classes were provided to the radial basis function kernel support vector machine (rbfSVM) classifier for NAC treatment response prediction.ResultsThe tile-level prediction pipeline achieved 86.72% accuracy for histology class classification, while the patient-level pipeline achieved 83.53% NAC response (pCR vs. RD) prediction accuracy of the model development cohort. The model was validated with an independent cohort with tile histology validation accuracy of 83.59% and NAC prediction accuracy of 81.01%. The histological class pairs with the strongest NAC response predictive ability were tumor and tumor tumor-infiltrating lymphocytes for pCR and microvessel density and polyploid giant cancer cells for RD.ConclusionOur machine learning pipeline can robustly identify clinically relevant histological classes that predict NAC response in TNBC patients and may help guide patient selection for NAC treatment.

Dataset Information

Gene signature-based prediction of triple-negative breast cancer patient response to Neoadjuvant chemotherapy.

Publications

Gene signature-based prediction of triple-negative breast cancer patient response to Neoadjuvant chemotherapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets