MOTIVATION: Building calibrated and discriminating predictive models can be developed through the direct optimization of model performance metrics with combinatorial search algorithms. Often, predictive algorithms are desired in clinical settings to identify patients that may be high and low risk. However, due to the large combinatorial search space, these algorithms are slow and do not guarantee the global optimality of their selection. RESULTS: Here, we present a novel and quick maximum likelihood-based feature selection algorithm, named GameRank. The method is implemented into an R package composed of additional functions to build calibrated and discriminative predictive models. AVAILABILITY AND IMPLEMENTATION: GameRank is available at https://github.com/Genentech/GameRank and released under the MIT License.

BACKGROUND: Bioinformatics data analysis often deals with additive mixtures of signals for which only class labels are known. Then, the overall goal is to estimate class related signals for data mining purposes. A convenient application is metabolic monitoring of patients using infrared spectroscopy. Within an infrared spectrum each single compound contributes quantitatively to the measurement. RESULTS: In this work, we propose a novel factorization technique for additive signal factorization that allows learning from classified samples. We define a composed loss function for this task and analytically derive a closed form equation such that training a model reduces to searching for an optimal threshold vector. Our experiments, carried out on synthetic and clinical data, show a sensitivity of up to 0.958 and specificity of up to 0.841 for a 15-class problem of disease classification. Using class and regression information in parallel, our algorithm outperforms linear SVM for training cases having many classes and few data. CONCLUSIONS: The presented factorization method provides a simple and generative model and, therefore, represents a first step towards predictive factorization methods.

One key principle of natural immune systems is the extracellular presentation of peptides bound to MHC-II complexes on the cell surface to represent the internal state. The prediction of those peptides that are presented became a current research topic in machine learning, as they may be used as potential vaccines for immunization. In addition the biological immune system (IS) is a learning system in its own right. In this work, we design an artificial immune system (AIS) that is based on observations of the natural immune system to predict MHC-II binding peptides. Our strategy simulates the mutable receptors of T lymphocytes as well as their selection during life time. We model the receptor specificity and binding mode as well as the lymphocyte's influence during an inflammatory response. Finally, our implementation uses the pathogen specificity of T cells to model the prediction problem.