Strengths and limitations of microarray-based phenotype prediction: lessons learned from the IMPROVER Diagnostic Signature Challenge.

MOTIVATION: After more than a decade since microarrays were used to predict phenotype of biological samples, real-life applications for disease screening and identification of patients who would best benefit from treatment are still emerging. The interest of the scientific community in identifying best approaches to develop such prediction models was reaffirmed in a competition style international collaboration called IMPROVER Diagnostic Signature Challenge whose results we describe herein. RESULTS: Fifty-four teams used public data to develop prediction models in four disease areas including multiple sclerosis, lung cancer, psoriasis and chronic obstructive pulmonary disease, and made predictions on blinded new data that we generated. Teams were scored using three metrics that captured various aspects of the quality of predictions, and best performers were awarded. This article presents the challenge results and introduces to the community the approaches of the best overall three performers, as well as an R package that implements the approach of the best overall team. The analyses of model performance data submitted in the challenge as well as additional simulations that we have performed revealed that (i) the quality of predictions depends more on the disease endpoint than on the particular approaches used in the challenge; (ii) the most important modeling factor (e.g. data preprocessing, feature selection and classifier type) is problem dependent; and (iii) for optimal results datasets and methods have to be carefully matched. Biomedical factors such as the disease severity and confidence in diagnostic were found to be associated with the misclassification rates across the different teams. AVAILABILITY: The lung cancer dataset is available from Gene Expression Omnibus (accession, GSE43580). The maPredictDSC R package implementing the approach of the best overall team is available at www.bioconductor.org or http://bioinformaticsprb.med.wayne.edu/.

Glass microneedles for force measurements: a finite-element analysis model.

Changes in developed force (0.1-3.0 microN) observed during contraction of single myofibrils in response to rapidly changing calcium concentrations can be measured using glass microneedles. These microneedles are calibrated for stiffness and deflect on response to developed myofibril force. The precision and accuracy of kinetic measurements are highly dependent on the structural and mechanical characteristics of the microneedles, which are generally assumed to have a linear force-deflection relationship. We present a finite-element analysis (FEA) model used to simulate the effects of measurable geometry on stiffness as a function of applied force and validate our model with actual measured needle properties. In addition, we developed a simple heuristic constitutive equation that best describes the stiffness of our range of microneedles used and define limits of geometry parameters within which our predictions hold true. Our model also maps a relation between the geometry parameters and natural frequencies in air, enabling optimum parametric combinations for microneedle fabrication that would reflect more reliable force measurement in fluids and physiological environments. We propose a use for this model to aid in the design of microneedles to improve calibration time, reproducibility, and precision for measuring myofibrillar, cellular, and supramolecular kinetic forces.