Abstract: A computer implemented method and system for identifying and visualizing features correlated with cancer subtypes, includes the steps of receiving a set of medical images representing an area including a patient's lesion, applying a classification model trained on lesions with known pathology by mathematically combining the model's learned weights with said medical images to produce a score indicating the likelihood of the lesion being of each particular cancer subtype, extracting importance maps from said classification model indicating features correlated with each cancer subtype by tracing the output of the model through the learned weights to identify regions of the input with a strong influence on the classification score for each cancer subtype, and displaying said importance maps visually on a computing device.

Abstract: A computer-implemented system within a computational cluster for aggregating data from a plurality of heterogeneous data sets into a homogeneous representation within a distributed, fault tolerant data source for the subsequent high-throughput retrieval, integration, and analysis of constituent data regardless of original data source location, data source format, and data encoding is configured for reading an input data set, generating a source data model based on the input data set, generating a vocabulary annotation and a profile of said source data model, executing semantic processing on said source data model so as to produce a normalized model based on standard ontology axioms and expanding the normalized model to identify and make explicit all implicit ontology axioms, and executing semantic querying on said data model using parallelized ontology reasoning based on an Enhance Most-Specific-Concept (MSC) algorithm.

Abstract: The present invention relates to computer implemented methods and system for creating and executing an query plan for SPARQL Protocol And Query Language (SPARQL) queries. The methods and systems are designed to accept as input a query in SPARQL syntax, convert this query to semQA2 and generate a parse tree, perform filter pushdown, generate an efficient query plan potentially using a cost function, and execute this query plan against data sources complying to or modeled as Resource Description Framework (RDF). The result of these methods and of the systems implementing these methods is a set of triples contained in the data sources that comprise a solution of the SPARQL query provided.

Abstract: A method on a computer for determining whether a hypothesis is verified by one or more ontologies. The method includes reading an address for a hypothesis comprised of one or more hypothesis axioms, wherein an axiom is represented in description logic form, reading an address for an ontology comprised of one or more ontology axioms and accessing the hypothesis and the ontology using the addresses that were read. The method further includes determining whether the ontology either corroborates or contradicts the hypothesis, identifying a first set of ontology axioms that corroborate the hypothesis and identifying a second set of ontology axioms that contradict the hypothesis, displaying a graphic indicating either corroboration or contradiction of the hypothesis, displaying the first set of ontology axioms together with a graphic indicating corroboration of the hypothesis and displaying the second set of ontology axioms together with a graphic indicating contradiction of the hypothesis.

Abstract: The present invention relates to computer implemented methods and system for determining relevance measures for computational resources based on their relatedness to a user's interests. The methods and systems are designed to accept as inputs a collection of unstructured textual data related to resources, and a structured graph of the relationships between resources, to calculate probability distributions of resources over latent communities discovered from the unstructured textual data, to activate the structured graph with these probability distributions, and to spread this activation throughout the graph in a fixed number of iterations. The result of these methods and of the systems implementing these methods is a set of relevance measures attached to the resources in the structured graph.

Abstract: The present invention relates to computer implemented methods and system for creating and executing an query plan for SPARQL Protocol And Query Language (SPARQL) queries. The methods and systems are designed to accept as input a query in SPARQL syntax, convert this query to semQA2 and generate a parse tree, perform filter pushdown, generate an efficient query plan potentially using a cost function, and execute this query plan against data sources complying to or modeled as Resource Description Framework (RDF). The result of these methods and of the systems implementing these methods is a set of triples contained in the data sources that comprise a solution of the SPARQL query provided.

Abstract: The present invention relates to computer implemented methods and system for determining relevance measures for computational resources based on their relatedness to a user's interests. The methods and systems are designed to accept as inputs a collection of unstructured textual data related to resources, and a structured graph of the relationships between resources, to calculate probability distributions of resources over latent communities discovered from the unstructured textual data, to activate the structured graph with these probability distributions, and to spread this activation throughout the graph in a fixed number of iterations. The result of these methods and of the systems implementing these methods is a set of relevance measures attached to the resources in the structured graph.

Abstract: The present invention relates to computer implemented methods and system for verifying hypotheses against ontologies. The methods and systems are designed to accept as inputs a set of axioms and/or assertions constituting a hypothesis, and a set of ontology axioms and/or assertions assumed to be true; determine whether the axioms and assertions constituting the hypothesis are either supported or contradicted by the axioms and assertions in the ontology, and extract the specific ontology axioms and/or assertions that either support or contradict the hypothesis. The result of these methods and of the systems implementing these methods is an indication on whether the hypothesis is supported by the ontology, contradicted by it, or neither supported nor contradicted by it, and if either supported or contradicted, the set of axioms and/or assertions from the ontology that cause the support or contradiction of the hypothesis.