Biomarker dynamics affecting neoadjuvant therapy response and outcome of HER2-positive breast cancer subtype.

HER2+ breast cancer (BC) is an aggressive subtype genetically and biologically heterogeneous. We evaluate the predictive and prognostic role of HER2 protein/gene expression levels combined with clinico-pathologic features in 154 HER2+ BCs patients who received trastuzumab-based neoadjuvant chemotherapy (NACT). The tumoral pathological complete response (pCR) rate was 40.9%. High tumoral pCR show a scarce mortality rate vs subjects with a lower response. 93.7% of ypT0 were HER2 IHC3+ BC, 6.3% were HER2 IHC 2+/SISH+ and 86.7% of ypN0 were HER2 IHC3+, the remaining were HER2 IHC2+/SISH+. Better pCR rate correlate with a high percentage of infiltrating immune cells and right-sided tumors, that reduce distant metastasis and improve survival, but no incidence difference. HER2 IHC score and laterality emerge as strong predictors of tumoral pCR after NACT from machine learning analysis. HER2 IHC3+ and G3 are poor prognostic factors for HER2+ BC patients, and could be considered in the application of neoadjuvant therapy. Increasing TILs concentrations, lower lymph node ratio and lower residual tumor cellularity are associated with a better outcome. The immune microenvironment and scarce lymph node involvement have crucial role in clinical outcomes. The combination of all predictors might offer new options for NACT effectiveness prediction and stratification of HER2+ BC during clinical decision-making.

Cost-sensitive learning strategies for high-dimensional and imbalanced data: a comparative study.

High dimensionality and class imbalance have been largely recognized as important issues in machine learning. A vast amount of literature has indeed investigated suitable approaches to address the multiple challenges that arise when dealing with high-dimensional feature spaces (where each problem instance is described by a large number of features). As well, several learning strategies have been devised to cope with the adverse effects of imbalanced class distributions, which may severely impact on the generalization ability of the induced models. Nevertheless, although both the issues have been largely studied for several years, they have mostly been addressed separately, and their combined effects are yet to be fully understood. Indeed, little research has been so far conducted to investigate which approaches might be best suited to deal with datasets that are, at the same time, high-dimensional and class-imbalanced. To make a contribution in this direction, our work presents a comparative study among different learning strategies that leverage both feature selection, to cope with high dimensionality, as well as cost-sensitive learning methods, to cope with class imbalance. Specifically, different ways of incorporating misclassification costs into the learning process have been explored. Also different feature selection heuristics have been considered, both univariate and multivariate, to comparatively evaluate their effectiveness on imbalanced data. The experiments have been conducted on three challenging benchmarks from the genomic domain, gaining interesting insight into the beneficial impact of combining feature selection and cost-sensitive learning, especially in the presence of highly skewed data distributions.

A comparative analysis of biomarker selection techniques.

Feature selection has become the essential step in biomarker discovery from high-dimensional genomics data. It is recognized that different feature selection techniques may result in different set of biomarkers, that is, different groups of genes highly correlated to a given pathological condition, but few direct comparisons exist which quantify these differences in a systematic way. In this paper, we propose a general methodology for comparing the outcomes of different selection techniques in the context of biomarker discovery. The comparison is carried out along two dimensions: (i) measuring the similarity/dissimilarity of selected gene sets; (ii) evaluating the implications of these differences in terms of both predictive performance and stability of selected gene sets. As a case study, we considered three benchmarks deriving from DNA microarray experiments and conducted a comparative analysis among eight selection methods, representatives of different classes of feature selection techniques. Our results show that the proposed approach can provide useful insight about the pattern of agreement of biomarker discovery techniques.