International Business Machines Corporation

Nuance Communications, Inc.

Merative US L.p.

Vanessa V Michelini

James Robert Lewis

Fang Wang

Anthony Edward Martinez

Brent L Davis

Ciprian Agapi

Cheryl L Eifert

Jia Xu

Kirk Alan Beaty

Melanie D Polkosky

Claudia S Huettner

Reza Ghasemi

Margarita Zabolotskaya

Vishwa Persaud

Kimberlee A Kemble

Marta Sanchez-Martin

Wallace J Sadowski

Felipe Gomez

Bhuvan Sharma

Sibyl C Sullivan

John R Lauria

Thomas Edward Creamer

Pengwei Yang

Elinor Dehan

Tracy Kong

Mengdi Zhu

Clifford J Strohofer

Baiju Dhirajlal Mandalia

Li Long Chen

William V Da Palma

Jeff Jianfei Li

Joel C Dubbels

Lan Luo

Vicki L Colson

Chon N Lei

Yan Du

Daniel F D'Elena

Thomas Alan Keahey

Jeffrey Bernard Nowicki

Shang Xue

Robert Maher

Phillip Luiz Viana

J Scott Gee

Robert E Coon

James M Donnelly

Michael S Matthews

Susan M Hill

Diane Britton

Stephen W Hanley

Computer based methods, systems, and computer readable media are provided for intelligently sorting cells using machine learning. A biological cell analysis sorting machine, wherein the biological cell analysis sorting machine comprises a flow cytometry system and a cell analytics sorting system, may be configured to detect configuration issues by analyzing results of a sorting experiment performed by the biological cell analysis sorting machine. An analysis of a history of prior sorting experiments and associated configuration settings may be performed and a corpus of documents pertaining to the sorting experiment based on the detected configuration issues may be analyzed. Updated configuration settings for the biological cell analysis sorting machine based on the performed analysis may be determined, and the biological cell analysis sorting machine may be configured with the updated configuration settings to conduct a desired sorting experiment.

Automated configuration of flow cytometry machines

Computer based methods, systems, and computer readable media for intelligently accessing various types of pharmaceutical information in a content repository and ranking drugs at the variant level, gene level, and pathway level. In some cases, drugs that target the same gene, gene variant, or biological pathway may be ranked based upon in vitro, pre-clinical, clinical, or post-clinical evidence. To determine ranking of a plurality of drugs, information pertaining to drug administration is analyzed for the drugs. For a plurality of drugs, attributes corresponding to the drug are determined, wherein the attributes include a variant or a gene targeted by the drug, and a biological pathway comprising the targeted variant or gene. The plurality of drugs are ranked according to a drug effectiveness score based on one or more of a determined efficacy, potency, or toxicity.

Determining drug effectiveness ranking for a patient using machine learning

A computer system updates a knowledge graph. A model corresponding to a set of documents is received, wherein the model comprises a plurality of entities, a plurality of entity associations, and a plurality of confidence scores corresponding to the plurality of entity associations. A relevance value is calculated for each entity of the plurality of entities that are present in the set of documents and for each entity of the plurality of entities that are present in a new document. One or more entity associations that are supported by specific portions of the new document are identified. The confidence scores for each of the identified one or more entity associations are updated based on a level of support in the new document. Embodiments of the present invention further include a method and program product for updating a knowledge graph in substantially the same manner described above.

Self-evolving knowledge graph

Computer based methods, systems, and computer readable media for classifying documents within a content repository or documents within the document subsets are provided. Documents may be pre-processed to render document sections visible to machine readers. Document subsets may be generated based on user-defined terms. The machine readable documents may be classified within the content repository into one of a group of categories, based-upon the number of times classification terms appear in a specific document section of the document. Documents may be ranked based upon the frequency of classification terms in the specific section. Documents may be associated with specific diseases such as cancer, genes, gene variants, and drugs or synonyms thereof by comparing relevant search terms to specific sections of the documents.

Automated document filtration and prioritization for document searching and access

Computer-based methods, systems, and computer readable media for managing documents within a content repository or documents within the document subsets are provided. Documents within the content repository may be classified into one of a functional category and a clinical category. Documents are applied to a machine learning annotation and analysis module to automatically annotate the documents to indicate relationships between entities. A request is processed for the documents including one or more search terms, wherein the search terms pertain to one or more entities from a group of gene, gene variant, drug, cancer and a biomedical/clinical term. Documents satisfying the request are identified by comparing the one or more search terms to the annotations and specific sections of the documents, and determining a relevance of a document based on the comparison and a frequency of the one or more search terms in each of the specific sections. The identified documents are ranked according to custom techniques.

Automated document filtration with machine learning of annotations for document searching and access

Computer-based methods, systems, and computer readable media for managing documents within a content repository or documents within the document subsets are provided. Documents may be pre-processed to be machine readable and classified within the content repository into one or more categories, based upon a number of times classification terms appear in a specific section of the document or based on an article type tag. Document subsets may be generated based on user-defined terms. Documents may be associated with specific cancer-types, genes, gene variants and drugs by comparing relevant search terms to specific sections of the documents. A request for processing the documents may include one or more of the search terms, pertaining to one or more from a group of gene, gene variant, drug, and cancer terms. A priority score may be determined for documents based on a frequency of one or more of the search terms in each of the specific sections, and the documents may be ranked from highest total priority score to lowest total priority score.

Automated document filtration and priority scoring for document searching and access

A computer system processes documents in a content repository. Each document of a plurality of documents is classified into one of a functional category and a clinical category. Each document is annotated using one or more corpora to generate document annotations. Documents satisfying one or more query terms are identified by comparing each query term to the document annotations. The identified documents are ranked based on a determined relevance. Guidelines are produced based on the ranking of the identified documents. Embodiments of the present invention further include a method and program product for processing documents in a content repository in substantially the same manner described above.

Processing documents in content repositories to generate personalized treatment guidelines

The computer receives customer registration information and encryption parameters from a customer, then transmits them to the server of an entity such as a pharmacy or bank. After the entity utilizes the transmitted encryption parameters to encrypt confidential portions of a message to the customer, the computer captures the message by way of receiving, photographing, scanning, or otherwise obtaining a copy of the message. The computer identifies glyphs in the message indicative of the corresponding encryption parameters as well as where the encrypted portions of the message start/end. Using the identified glyphs and corresponding encryption parameters, the computer decrypts the confidential portions of the message and displays the message in entirety on the computer.

Message encryption

A method, system, and computer program product are provided for generating a container providing a computing environment. At least one processing device combines a base image of a first type of container, including at least one application and an operating system, with a base image of a second type of container including middleware and configuration information to produce a base image of a target container including, from the first type of container, the at least one application and the operating system, and the middleware and the configuration information from the second type of container. The base image of the target container is executed on a computer to provide the computing environment configured in accordance with the configuration information.

Generating target configuration containers providing computer environments based on a configuration container

An application performs a regression test by the application processing a use case. Actual output data generated by the application processing the use case can be compared to expected output data and whether the actual output data matches the expected output data can be determined. Responsive to determining that the actual output data does not match the expected output data, the actual output data can be compared to refreshed source data and whether the actual output data matches the refreshed source data can be determined. Responsive to determining that the actual output data matches the refreshed source data, an automated remedy action can be automatically selected, and the expected output data can be updated with the refreshed source data by implementing the automated remedy action.

Regression testing of an application that uses big data as a source of data

In an approach for protecting a resource, a processor receives a resource and a parameter, wherein the parameter indicates a condition upon which the resource will be made accessible. A processor encrypts the resource. A processor associates the parameter with decryption information for the encrypted resource. A processor sends the encrypted resource to a computing device. A processor determines that the condition of the parameter has been met based on external information regarding the parameter. A processor sends the decryption information to the computing device.

Smart resource access for decrypted information

A method, system, and computer program product for performing cognitive-based dynamic tuning of a software-based system include monitoring live operation of the system, and determining whether tuning is needed based on the monitoring. Analyzing information and suggesting a change in one or more parameters is based on the determining, the information including an output of a learning algorithm that learns an effect of changes in one or more of the one or more parameters on performance of the system.

Cognitive-based dynamic tuning

Mechanisms are provided to implement a relation network visualization and interaction engine that is configured to generate an extended adjacency matrix representation of a relation network. The mechanisms create a relation network data structure, and generate an adjacency matrix graphical representation of the relation network based on analysis of the relation network data structure. The mechanisms extend the adjacency matrix graphical representation by adding an interactive indirect relation glyph, for an indirect relation in the relation network, to the adjacency matrix graphical representation in association with representations of a source entity and a target entity that correspond to the indirect relation, to thereby generate an extended adjacency matrix graphical representation. The mechanisms output the extended adjacency matrix graphical representation in a visual manner on a computing device.

Multi-attribute relation network visualization and interaction interface

Systems and methods for dynamic image content overlaying are disclosed. In embodiments, a computer-implemented method comprises analyzing one or more digital image frames for the presence of a placeholder, wherein the placeholder overlays a dynamic image space on a display object and includes a content identifier and a contour mesh; determining the content identifier; retrieving select image content based on the content identifier; determining an orientation of the dynamic image space; transforming the select image content to produce transformed image content that matches the contour mesh and the orientation of the dynamic image space; and replacing the placeholder with the transformed image content to produce a set of one or more embedded image frames.

Dynamic image content overlaying

Growing community of inventors

Coconut Creek, FL, United States of America

Vanessa V Michelini