Abstract: A method for feature selection is provided. The method includes the steps of selecting a predictor set of features, adding at least one complementary feature to the predictor set based on a quality of prediction, checking to see if all of the features of the predictor set are repeated, and if not, removing at least one feature from the predictor set. The algorithm and method repeats the steps of adding complements, checking the predictor set and removing features until the features of the predictor set are repeated. Once the features of. the predictor set are repeated the proper number of times, the algorithm and method terminate.

Abstract: A method for feature selection is provided. The method includes the steps of selecting a predictor set of features, adding at least one complementary feature to the predictor set based on a quality of prediction, checking to see if all of the features of the predictor set are repeated, and if not, removing at least one feature from the predictor set. The algorithm and method repeats the steps of adding complements, checking the predictor set and removing features until the features of the predictor set are repeated. Once the features of. the predictor set are repeated the proper number of times, the algorithm and method terminate.

Abstract: Methods, systems and computer readable media for network-based identification of significant molecules, for which at least one biological network is provided to include significant molecules to be identified. A node in the network is identified. A member-specific sub-network containing nodes connected to the identified node is identified for L levels of nearest neighbors, wherein L is a positive integer, and a connectivity score is calculated for the molecule represented by the identified node based on significance scores of each node contained in the member-specific sub-network. These steps are repeated for other nodes in the network.

Abstract: Systems, tools, methods and recordable media for text mining textual documents and extracting and associating entities and interactions mined with other data formats, such as diagrammatic displays and experimental data, using a local format. Additionally, information may be overlaid and compared with existing biological diagrams.

Abstract: System, tools and methods for extracting the contents from a graphical image, such as the representation of a biological process, and converting the contents into a standardized, machine readable format. The standard format can be used to create editable graphical representations of images, such as biological models.

Abstract: A user's context can be captured in terms of experimental results and other locally collected data. The use of extracted links between imported scientific text, biological models or experimental data, and proprietary or public data to provide relevance ranking, filtering, and categorization of imported scientific text or biological models, based upon their linking with the local data is described.

Abstract: Systems, methods and computer readable media for performing a domain-specific metasearch, and obtaining search results therefrom. A metasearch engine capable of accessing generic, web-based search engines and domain-relevant search engines is provided to receive one or more queries inputted by a user, and to search for documents on at least one the generic, web-based search engines and domain-relevant search engines which are relevant to the queries. Raw data search results are fetched in the form of text documents. Relevant data including semantic information are extracted from the raw data search results, and converted to a local format. The relevant data having been converted to the local format may be visualized as a network visualization. Additionally or alternatively, the raw data search results may be ranked and/or filtered based on the linking of the relevant data.

Abstract: Methods, systems and computer readable media for correlating data from data sets to higher level categories of characterization of the data. Data from a first set of data is analyzed to determine where members of the first set map to an ontology. Data from a second set of data is analyzed to determine where members of the second set map to the ontology. From such analysis a subset of the first set of data is identified and a subset of the second set of data is identified. The subset of the first set of data is statistically analyzed with regard to its mapping to the ontology, and a first set of ontology terms are identified that are statistically differentiated by members of the subset of the first set of data. The subset of the second set of data is statistically analyzed with regard to its mapping to the ontology, and a second set of ontology terms is identified that are statistically differentiated by members of the subset of the second set of data.

Abstract: A method for performing network reconstruction is provided. The method includes the steps of selecting a predictor set of features, adding a complement to the predictor set based on a quality of prediction, checking to see if all of the features of the predictor set are repeated, and then removing one feature from the predictor set. The algorithm and method repeat the steps of adding a complement, checking the predictor set and removing a feature until the features of the predictor set are repeated. If the features of the predictor set are repeated, the algorithm and method terminate.

Abstract: Systems, methods and recordable media for facilitating user-guidance of computational analysis and knowledge extraction tools for use with biological data for disambiguation and determination of causation in representations of the data. Systems, methods, tools and computer readable media for user-guided expansion of biological networks and manipulations of the same. Tools for qualitative simulation of network models, for identifying interactions between multiple networks and form maintaining knowledge about multiple alternative biological networks. Combinations of portions of networks may be constructed to provide optimal networks. Networks may be evaluated against experimental data and networks of interest may be identified based on experimental data.

Abstract: Systems, methods and recordable media for facilitating user-guidance of statistical analysis of large datasets based upon word-based textual annotations associated with the large datasets. Particular applications to large biological datasets are described.

Abstract: Systems, tools, methods and recordable media for providing a visual grammar to be associated with a local format for creating interactive biological diagrams. Stencils are provided to represent higher level representations of associated entities and interactions are descriptively and unambiguously displayed. Additionally, information may be overlaid and compared with existing biological diagrams.

Abstract: A system and method for performing domain-specific knowledge based metasearches. A metasearch engine is provided for accessing a searching text-based documents using generic search engines while simultaneously being able to access publication based databases and sequence databases as well as in-house proprietary databases and any database capable of being interfaced with a web interface so as to produce search results in text format. A data mining module is also provided for organizing raw data obtained by unsupervised clustering, simple relevance ranking, and categorization, all of which are done independently of one another. The system is capable of storing previous search data for use in query refinement or subsequent searches based upon the stored data. A search results collection browser may be provided for analyzing current browsing patterns of the user for developing weighting factors to be used in ordering the results of future searches.

Abstract: A method for performing network reconstruction is provided. The method includes the steps of selecting a predictor set of features, adding a complement to the predictor set based on a quality of prediction, checking to see if all of the features of the predictor set are repeated, and then removing one feature from the predictor set. The Algorithm and method repeats the steps of adding a complement, checking the predictor set and removing a feature until the features of the predictor set are repeated. If the features of the predictor set are repeated, the algorithm and method terminate.

Abstract: Systems, tools, methods and recordable media for text mining textual documents and extracting and associating entities and interactions mined with other data formats, such as diagrammatic displays and experimental data, using a local format. Additionally, information may be overlaid and compared with existing biological diagrams.

Abstract: Systems, methods and recordable media for interactively importing, creating, and manipulating biological diagrams. Such diagrams may be used for linking and navigating to other sources of biological information.

Abstract: Systems and methods for database searching and data analysis with simultaneous, unified access to multiple heterogeneous data sources with effective reuse of user search session information for data analysis. The systems comprise a data source containing at least a partial copy of at least two public databases, at least one search program module operatively coupled to the data source and configured to carry out a search of the databases in the data source according to a user query, a data mining module operatively coupled to the data source and configured to provide for clustering of search results or documents from the user query and a user interface program module operatively coupled to the search program module and the data mining module, the user interface program module configured provide a visual interface for creating the user query and viewing the search results.

Abstract: Software systems and methods for organizing and manipulating diverse data sets to facilitate identification, trends, correlations and other useful relationships among the data. Extremely large data set such as microarray data and other biological data are graphically displayed and sorted in an effort to develop visual similarities, correlations or trends that can be seen by a user of the present invention. Various schemes for graphical representations of the data, as well as sorting schemes are provided. Additionally, non-experimental or other data can be displayed and tracked along with the data upon which the sorting schemes are processed.

Abstract: An extensible, generalized architecture, an application programming interface, software and methods for building data overlays, as well as software, a system, methods and interface for building specific data overlays, with particular relevance to biological data.

Abstract: System, tools and methods for extracting the contents from a graphical image, such as the representation of a biological process, and converting the contents into a standardized, machine readable format. The standard format can be used to create editable graphical representations of images, such as biological models.