Identification of VWA5A as a novel biomarker for inhibiting metastasis in breast cancer by machine-learning based protein prioritization

Abstract

Distant metastasis is the leading cause of death in breast cancer (BC). The timing of distant metastasis differs according to subtypes of BCs and there is a need for identification of biomarkers for the prediction of early and late metastasis. To identify biomarker candidates whose abundance level can discriminate metastasis types, we performed a high-throughput proteomics assay using tissue samples from BCs with no metastasis, late metastasis, and early metastasis, processed data with machine learning-based feature selection, and found that low VWA5A could be responsible for shorter duration of metastasis-free interval. Low expression of VWA5A gene in METABRIC cohort was associated with poor survival in BCs, especially in hormone receptor (HR)-positive BCs. In-vitro experiments confirmed tumor suppressive effect of VWA5A on BCs in HR+ and triple-negative BC cell lines. We found that expression of VWA5A can be assessed by immunohistochemistry (IHC) on archival tissue samples. Decreasing nuclear expression of VWA5A was significantly associated with advanced T stage and lymphatic invasion in consecutive BCs of all subtypes. We discovered lower expression of VWA5A as the potential biomarker for metastasis-prone BCs, and our results support the clinical utility of VWA5A IHC, as an adjunctive tools for prognostication of BCs.

Figure 1

VWA5A is prioritized as a biomarker candidate for metastasis type discrimination. (A) The t-SNE plots of the patient embeddings with the nine features selected by our method (left) and with randomly selected features. (B) Scatter plots of the nine candidates in terms of mutual information ranks and NP score ranks. Candidate biomarkers selected by our method are marked as red dots.

Figure 2

Prognostic relevance of VWA5A gene expression on disease free survivals of patients in METABRIC cohort. Higher VWA5A expression was significantly associated with favorable disease free survivals in METABRIC cohort.

Figure 3

Biological role of VWA5A assessed by in vitro functional assay. (A) Knock-out VWA5A using siRNA transfection resulted in marked decrease in the expression levels of VWA5A. (B) siRNA transfected cell lines T47D, BT20 and HCC70 showed more aggressive behaviors including increased cellular invasion and migration.

Figure 4

Expression of VWA5A in the validation set. (A) VWA5A expression was assessed by immunohistochemistry and histoscore of 50 was used to discriminate VWA5A-low and VWA5A-high groups. (B) Lower VWA5A expression of breast cancer cells were associated with advance pT stage of the patients in the validation set.

Figure 5

Schematic overview of biomarker candidate selection. (A) Leave-one-out cross-validation (LOOCV) scheme for biomarker candidate selection. For each CV fold, a sample was used as a held-out test set, while the other samples were used for feature selection. After feature selection, SVM classifier was trained with the selected features and tested with the test set. (B) Within each LOOCV training set, we prioritized proteins by mutual information (MI) network propagation (NP). Proteins were ranked in terms of the discriminative power of metastasis type measured by MI. After feature prioritization, features were added to the classification model via recursive feature selection, until the accuracy reached the maximum.