Premenopausal breast cancer: potential clinical utility of a multi-omics based machine learning approach for patient stratification

Abstract

Background: The breast cancer (BC) epidemic is a multifactorial disease attributed to the early twenty-first century: about two million of new cases and half a million deaths are registered annually worldwide. New trends are emerging now: on the one hand, with respect to the geographical BC prevalence and, on the other hand, with respect to the age distribution. Recent statistics demonstrate that young populations are getting more and more affected by BC in both Eastern and Western countries. Therefore, the old rule "the older the age, the higher the BC risk" is getting relativised now. Accumulated evidence shows that young premenopausal women deal with particularly unpredictable subtypes of BC such as triple-negative BC, have lower survival rates and respond less to conventional chemotherapy compared to the majority of postmenopausal BC.

Working hypothesis: Here we hypothesised that a multi-level diagnostic approach may lead to the identification of a molecular signature highly specific for the premenopausal BC. A multi-omic approach using machine learning was considered as a potent tool for stratifying patients with benign breast alterations into well-defined risk groups, namely individuals at high versus low risk for breast cancer development.

Results and conclusions: The study resulted in identifying multi-omic signature specific for the premenopausal BC that can be used for stratifying patients with benign breast alterations. Our predictive model is capable of discriminating individually between high and low BC-risk with high confidence (>90%) and considered of potential clinical utility. Novel risk assessment approaches and advanced screening programmes-as the long-term target of this project-are of particular importance for predictive, preventive and personalised medicine as the medicine of the future, due to the expected health benefits for young subpopulations and the healthcare system as a whole.

Keywords: Bioinformatics; Biomarker panel; Breast cancer; Laboratory medicine; Machine learning; Menopause; Multi-level diagnostics; Patient stratification; Predictive preventive personalised medicine.

Fig. 1

Western blot imaging of the expression rates for a actin and b catalase as demonstrated for the samples/patients numbered 1–7 which correspond to the patients 1 and 2 diagnosed with benign breast alterations, 3–7 breast cancer patients, whereby 3–6 are premenopausal BC and 7 is postmenopausal BC

Fig. 2

Cophenetic correlation (left) and silhouette index (right) as a function of the number of NMF clusters. Both plots clearly favour a solution with two patient groups. The solution of a consensus clustering over 100 NMF runs (purple) is contrasted with the silhouette indices for clustering the markers (red) and the patients (green)

Fig. 3

Left: silhouette plot of two patient subgroups with 37 and 24 patients, respectively. The x-axis shows the cluster silhouette for each patient on the y-axis. The cluster silhouette is a measure of how similar each patient is compared to patients in its own cluster and the closest patient from other clusters. The silhouette measure ranges from 0 to 1, where 1 indicates a perfect agreement of the assumed cluster assignment with patient distances. The average cluster silhouette for all patients in cluster 1 and 2 is shown. The overall average silhouette index was 1. Right: consensus matrix with super-imposed dendrogram of hierarchical clustering. The consensus matrix depicts the relative frequency of two patients falling into the same cluster across repeated NMF runs. A clear separation of two patient subgroups (red blocks) can be seen. Patients in these groups frequently fall into the same cluster.

Fig. 4

Prediction of correct patient cluster assignment: The boxplot shows the distribution of 10 AUC values resulting from 10 repeats of a tenfold cross-validation procedure. Within each cross-validation loop, a GBM classifier was trained on 9/10 of the available patient data and tested on the hold out rest. A 50% AUC indicates chance level and a AUC of 100% a perfect prediction performance

Fig. 5

Principal component plot depicting both identified patient subgroup and 14 breast cancer patients. Shown is the projection of patients (indicated by numbers) on the first two principal components of the biomarker signature space. The first two principal components explain 19.6 and 9.2% of the total variance

Fig. 6

Boxplots depicting the distribution of individual variables in low risk (cluster 1) and high risk (cluster 2) patient subgroups. All markers show a statistically significant difference between high- and low-risk groups after multiple testing corrections

Fig. 7

Heat map of patients—the x-axis displays individualised patient profiles (patients involved are listed on the y-axis); characteristic patterns of following biomarker are presented: CA IV, CA IV/I + II + III, CA II, CA III, actin expression, catalase expression, CA I, and hybridome Hcy/CA(I–IV). The colour code displays the row-wise normalised magnitude (e.g. expression levels for proteins) of each marker (z-score): green = high, red = low. Example: indicated with the red arrow patient is at high BC risk; in this case, low levels of CA IV, CA IV/I + II + III, CA II and CA III, but high levels of actin, catalase, CA I, and Hcy / CA (I–IV) have been demonstrated that is characteristic for the profile of the “high risk” cluster. The patient at low risk for BC indicated with the green arrow shows exactly opposite patterns