Abstract: Embodiments of the present invention provide methods, computer program products, and systems for classification and identification of cancer genes while correcting for sample bias for tumor-derived genomic features as well as other biased features using machine learning techniques. Embodiments of the present invention can be used to receive a set of genes that include a first gene and a subset of synthetic genes that include similar features to the first gene and receive a set of gene labels associated with physiological characteristics. Embodiments of the present invention can estimate probabilities that genes in the set of genes are associated with gene labels in the set of gene labels using a machine learning classifier and estimate an effective probability range for the first gene and each gene label based, at least in part, on the first gene's estimated probabilities and the estimated probabilities of one or more of the synthetic genes.

Abstract: In an approach for constructing causal graphs, a processor receives data, a first set of constraints, and one or more graph parameters. A processor constructs a causal graph based on the data, first set of constraints, and one or more graph parameters. A processor generates an interactive display interface for the constructed causal graph. A processor refines the constructed causal graph using the interactive display interface.

Abstract: Embodiments of the present invention provide methods, computer program products, and systems for classification and identification of cancer genes while correcting for sample bias for tumor-derived genomic features as well as other biased features using machine learning techniques. Embodiments of the present invention can be used to receive a set of genes that include a first gene and a subset of synthetic genes that include similar features to the first gene and receive a set of gene labels associated with physiological characteristics. Embodiments of the present invention can estimate probabilities that genes in the set of genes are associated with gene labels in the set of gene labels using a machine learning classifier and estimate an effective probability range for the first gene and each gene label based, at least in part, on the first gene's estimated probabilities and the estimated probabilities of one or more of the synthetic genes.

Abstract: Embodiments of the present invention provide methods, computer program products, and systems for classification and identification of cancer genes while correcting for sample bias for tumor-derived genomic features as well as other biased features using machine learning techniques. Embodiments of the present invention can be used to receive a set of genes that include a first gene and a subset of synthetic genes that include similar features to the first gene and receive a set of gene labels associated with physiological characteristics. Embodiments of the present invention can estimate probabilities that genes in the set of genes are associated with gene labels in the set of gene labels using a machine learning classifier and estimate an effective probability range for the first gene and each gene label based, at least in part, on the first gene's estimated probabilities and the estimated probabilities of one or more of the synthetic genes.

Abstract: In an approach for constructing causal graphs, a processor receives data, a first set of constraints, and one or more graph parameters. A processor constructs a causal graph based on the data, first set of constraints, and one or more graph parameters. A processor generates an interactive display interface for the constructed causal graph. A processor refines the constructed causal graph using the interactive display interface.

Abstract: Embodiments of the present invention provide methods, computer program products, and systems for classification and identification of cancer genes while correcting for sample bias for tumor-derived genomic features as well as other biased features using machine learning techniques. Embodiments of the present invention can be used to receive a set of genes that include a first gene and a subset of synthetic genes that include similar features to the first gene and receive a set of gene labels associated with physiological characteristics. Embodiments of the present invention can estimate probabilities that genes in the set of genes are associated with gene labels in the set of gene labels using a machine learning classifier and estimate an effective probability range for the first gene and each gene label based, at least in part, on the first gene's estimated probabilities and the estimated probabilities of one or more of the synthetic genes.

Abstract: Modelling disease progression using non-clinical information proxies for clinical information, by accessing a computer-based Bayesian model of the progression of a disease, adapting the Bayesian model to include one or more clinical factors that are believed to influence progression of the disease, adapting the Bayesian model to include one or more non-clinical proxies for one or more clinical factors that are believed to influence progression of the disease, identifying interdependencies among variables of the Bayesian model based on a meta-analysis of literature associated with any of the disease, the clinical factors, and the non-clinical proxies, providing values for any of the variables of the Bayesian model, and presenting any portion of the Bayesian model via a computer-based output device.

Abstract: A method for identifying cancer driver genes is provided. The method includes receiving at least one patient input file containing information for a mutation variation and/or an expression of the gene, parsing the information from the input file into a data structure, annotating the information with cancer driving related annotation, extracting genetic features related to the patient from the information, and scoring the information with a first probability that the mutation variation drives cancer and/or a set of further probabilities that the expression of the gene drives cancer. The first probability and the set of further probabilities are calculated with a first and second Bayesian Network graphical model, respectively.

Abstract: A computer-executable algorithm that estimates parameters of a predictive model in computation time of less than O(n2k2) when k<=n, is described herein, wherein n is a number of data items considered when estimating the parameters of the predictive model and k is a number of features of each data item considered when estimating the parameters of the predictive model. The parameters are estimated to maximize the probability of observing target values in the training data given the features considered in the training data.

Abstract: Described herein are technologies pertaining to predicting whether a living being, such as a human being, an animal, or a plant, has a phenotype or set of phenotypes in real-time or near real-time. A filter set of genetic markers are determined heuristically, by first univariately computing scores for respective genetic markers that are indicative of their predictive ability with respect to the phenotype or the set of phenotypes. Thereafter, during training, the filter set is initially selected and thereafter expanded based upon the scores, until predictive accuracy for the phenotype or set of phenotypes reaches a threshold or is optimized. The filter set, which includes a relatively small number of genetic markers, is subsequently employed for real-time or near-real time phenotype prediction.