Search

Background: Single sample predictors (SSPs) and Subtype classification models (SCMs) are gene expression-based classifiers used to identify the four primary molecular subtypes of breast cancer (basal-like, HER2-enriched, luminal A, and luminal B). SSPs use hierarchical clustering, followed by nearest centroid classification, based on large sets of tumor-intrinsic genes. SCMs use a mixture of Gaussian distributions based on sets of genes with expression specifically correlated with three key breast cancer genes (estrogen receptor [ER], HER2, and aurora kinase A [AURKA]). The aim of this study was to compare the robustness, classification concordance, and prognostic value of these classifiers with those of a simplified three-gene SCM in a large compendium of microarray datasets.Methods: Thirty-six publicly available breast cancer datasets (n = 5715) were subjected to molecular subtyping using five published classifiers (three SSPs and two SCMs) and SCMGENE, the new three-gene (ER, HER2, and AURKA) SCM. We used the prediction strength statistic to estimate robustness of the classification models, defined as the capacity of a classifier to assign the same tumors to the same subtypes independently of the dataset used to fit it. We used Cohen κ and Cramer V coefficients to assess concordance between the subtype classifiers and association with clinical variables, respectively. We used Kaplan-Meier survival curves and cross-validated partial likelihood to compare prognostic value of the resulting classifications. All statistical tests were two-sided.Results: SCMs were statistically significantly more robust than SSPs, with SCMGENE being the most robust because of its simplicity. SCMGENE was statistically significantly concordant with published SCMs (κ = 0.65-0.70) and SSPs (κ = 0.34-0.59), statistically significantly associated with ER (V = 0.64), HER2 (V = 0.52) status, and histological grade (V = 0.55), and yielded similar strong prognostic value.Conclusion: Our results suggest that adequate classification of the major and clinically relevant molecular subtypes of breast cancer can be robustly achieved with quantitative measurements of three key genes. [ABSTRACT FROM AUTHOR]

The paper presents an original filter approach for effective feature selection in microarray data characterized by a large number of input variables and a few samples. The approach is based on the use of a new information-theoretic selection, the double input symmetrical relevance (DISR), which relies on a measure of variable complementarity. This measure evaluates the additional information that a set of variables provides about the output with respect to the sum of each single variable contribution. We show that a variable selection approach based on DISR can be formulated as a quadratic optimization problem: the dispersion sum problem (DSP). To solve this problem, we use a strategy based on backward elimination and sequential replacement (BESR). The combination of BESR and the DISR criterion is compared in theoretical and experimental terms to recently proposed information-theoretic criteria. Experimental results on a synthetic dataset as well as on a set of eleven microarray classification tasks show that the proposed technique is competitive with existing filter selection methods. [ABSTRACT FROM PUBLISHER]

Because of high dimensionality, machine learning algorithms typically rely on feature selection techniques in order to perform effective classification in microarray gene expression data sets. However, the large number of features compared to the number of samples makes the task of feature selection computationally hard and prone to errors. This paper interprets feature selection as a task of stochastic optimization, where the goal is to select among an exponential number of alternative gene subsets the one expected to return the highest generalization in classification. Blocking is an experimental design strategy which produces similar experimental conditions to compare alternative stochastic configurations in order to be confident that observed differences in accuracy are due to actual differences rather than to fluctuations and noise effects. We propose an original blocking strategy for improving feature selection which aggregates in a paired way the validation outcomes of several learning algorithms to assess a gene subset and compare it to others. This is a novelty with respect to conventional wrappers, which commonly adopt a sole learning algorithm to evaluate the relevance of a given set of variables. The rationale of the approach is that, by increasing the amount of experimental conditions under which we validate a feature subset, we can lessen the problems related to the scarcity of samples and consequently come up with a better selection. The paper shows that the blocking strategy significantly improves the performance of a conventional forward selection for a set of 16 publicly available cancer expression data sets. The experiments involve six different classifiers and show that improvements take place independent of the classification algorithm used after the selection step. Two further validations based on available biological annotation support the claim that blocking strategies in feature selection may improve the accuracy and the quality of the solut- - ion. The first validation is based on retrieving PubMEd abstracts associated to the selected genes and matching them to regular expressions describing the biological phenomenon underlying the expression data sets. The biological validation that follows is based on the use of the Bioconductor package GoStats in order to perform gene ontology statistical analysis [ABSTRACT FROM PUBLISHER]

The embedding of advanced simulation techniques in power cables enables improved thermal protection because of higher accuracy, adaptiveness and flexibility. In particular, they make possible (i) the accurate solution of differential equations describing the cables thermal dynamics and (ii) the adoption of the resulting solution in the accomplishment of dedicated protective functions. However, the use of model-based protective systems is exposed to the uncertainty affecting some model components (e.g. weather along the line route, thermophysical properties of the soil, cable parameters). When uncertainty can be described in terms of probability distribution, well-known techniques, such as Monte Carlo, are used to simulate the system behaviour. On the other hand, when the description of uncertainty in probabilistic terms is unfeasible or problematic, nonprobabilistic alternatives should be taken into consideration. This paper will discuss and compare three interval-based techniques as alternatives to probabilistic methods in the simulation of power cable dynamics. The experimental session will assess the interval-based approaches by simulating the thermal behaviour of medium voltage power cables. [ABSTRACT FROM AUTHOR]

Dynamic loading of power components in a deregulated electricity market requires reliable models that are able to predict the thermal behaviour when the load exceeds a particular value. The thermal stress of the components is known to be the most critical factor to the assessment of network load capability. Predicting the evolution of the thermal stress during overload conditions is essential to estimate the loss of insulation life and to evaluate the consequent risks of both technical and economical nature. The paper discusses an innovative grey-box architecture for integrating physical knowledge modelling (also know as white-box) with machine learning techniques (also known as black-box) in dynamic load capability assessment of power components. To evaluate the effectiveness of the proposed solution, a specific case study concerning a system of medium-voltage power cables is presented. [ABSTRACT FROM AUTHOR]