Patents by Inventor Christopher W. Szeto
Christopher W. Szeto has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11948687Abstract: A method of determining a region of interest in an image of tissue of an individual by an apparatus including processing circuitry may include executing, by the processing circuitry, instructions that cause the apparatus to partition an image of tissue of an individual into a set of areas, identify a tissue type of each area of the image, and apply a classifier to the image to determine a region of interest, the classifier being configured to determine regions of interest based on the tissue types of the set of areas of the image.Type: GrantFiled: July 21, 2021Date of Patent: April 2, 2024Assignees: NantCell, Inc., NantHealth, Inc., NantOmics, LLCInventors: Mustafa I. Jaber, Liudmila A. Beziaeva, Bing Song, Christopher W. Szeto, Stephen Charles Benz, Shahrooz Rabizadeh
-
Publication number: 20230267375Abstract: A distributed, online machine learning system is presented. Contemplated systems include many private data servers, each having local private data. Researchers can request that relevant private data servers train implementations of machine learning algorithms on their local private data without requiring de-identification of the private data or without exposing the private data to unauthorized computing systems. The private data servers also generate synthetic or proxy data according to the data distributions of the actual data. The servers then use the proxy data to train proxy models. When the proxy models are sufficiently similar to the trained actual models, the proxy data, proxy model parameters, or other learned knowledge can be transmitted to one or more non-private computing devices. The learned knowledge from many private data servers can then be aggregated into one or more trained global models without exposing private data.Type: ApplicationFiled: April 21, 2023Publication date: August 24, 2023Inventors: Christopher W. SZETO, Stephen Charles BENZ, Nicholas J. WITCHEY
-
Publication number: 20230260628Abstract: A method at a computing device for classifying elements within an input, the method including breaking the input into a plurality of patches; for each patch: creating a vector output; applying a characterization map to select a classification bin from a plurality of classification bins; and utilizing the selected classification bin to classify the vector output to create a classified output; and compiling the classified output from each patch.Type: ApplicationFiled: April 26, 2023Publication date: August 17, 2023Applicants: NantOmics, LLC, NantHealth, Inc.Inventors: Mustafa Jaber, Liudmila A Beziaeva, Christopher W Szeto, Bing Song
-
Patent number: 11694122Abstract: A distributed, online machine learning system is presented. Contemplated systems include many private data servers, each having local private data. Researchers can request that relevant private data servers train implementations of machine learning algorithms on their local private data without requiring de-identification of the private data or without exposing the private data to unauthorized computing systems. The private data servers also generate synthetic or proxy data according to the data distributions of the actual data. The servers then use the proxy data to train proxy models. When the proxy models are sufficiently similar to the trained actual models, the proxy data, proxy model parameters, or other learned knowledge can be transmitted to one or more non-private computing devices. The learned knowledge from many private data servers can then be aggregated into one or more trained global models without exposing private data.Type: GrantFiled: August 18, 2022Date of Patent: July 4, 2023Assignees: NANTOMICS, LLC, NANT HOLDINGS IP, LLCInventors: Christopher W. Szeto, Stephen Charles Benz, Nicholas J. Witchey
-
Patent number: 11676707Abstract: A method at a computing device for classifying elements within an input, the method including breaking the input into a plurality of patches; for each patch: creating a vector output; applying a characterization map to select a classification bin from a plurality of classification bins; and utilizing the selected classification bin to classify the vector output to create a classified output; and compiling the classified output from each patch.Type: GrantFiled: December 1, 2021Date of Patent: June 13, 2023Assignees: NantOmics, LLC, Nant Health, Inc.Inventors: Mustafa Jaber, Liudmila A Beziaeva, Christopher W Szeto, Bing Song
-
Publication number: 20230030506Abstract: A method of determining a clinical value for an individual based on a tumor in an image by an apparatus including processing circuitry may include executing, by the processing circuitry, instructions that cause the apparatus to determine a lymphocyte distribution of lymphocytes in the tumor based on the image; apply a classifier to the lymphocyte distribution to classify the tumor, the classifier having been trained to classify tumors into a class selected from at least two classes respectively associated with lymphocyte distributions; and determine the clinical value for the individual based on prognoses of individuals with tumors in the class into which the classifier classified the tumor.Type: ApplicationFiled: January 11, 2021Publication date: February 2, 2023Inventors: Mustafa I. JABER, Christopher W. SZETO, Liudmila A. BEZIAEVA, Stephen Charles BENZ
-
Publication number: 20220405644Abstract: A distributed, online machine learning system is presented. Contemplated systems include many private data servers, each having local private data. Researchers can request that relevant private data servers train implementations of machine learning algorithms on their local private data without requiring de-identification of the private data or without exposing the private data to unauthorized computing systems. The private data servers also generate synthetic or proxy data according to the data distributions of the actual data. The servers then use the proxy data to train proxy models. When the proxy models are sufficiently similar to the trained actual models, the proxy data, proxy model parameters, or other learned knowledge can be transmitted to one or more non-private computing devices. The learned knowledge from many private data servers can then be aggregated into one or more trained global models without exposing private data.Type: ApplicationFiled: August 18, 2022Publication date: December 22, 2022Inventors: Christopher W. SZETO, Stephen Charles BENZ, Nicholas J. WITCHEY
-
Publication number: 20220403413Abstract: Systems and methods are presented that allow for determination and prediction of payload toxicity in therapeutic viruses. Disclosed herein are methods of determining payload toxicity of an expressed polypeptide in a cell, comprising: generating or procuring a plurality of expression vectors, each containing a different recombinant nucleic acid sequence that encodes a corresponding recombinant polypeptide; expressing the recombinant nucleic acid sequence in a plurality of host cells while culturing the host cells; sequencing the plurality of expression vectors after culturing the host cells; and correlating at least portions of the recombinant nucleic acid sequence with a toxicity measure.Type: ApplicationFiled: July 24, 2020Publication date: December 22, 2022Applicants: Nantomics, LLC, NantBio, Inc.Inventors: Kamil Wnuk, Lise Geissert, Jeremi Sudol, Charles Vaske, Stephen Charles Benz, Connie Tsai, Kayvan Niazi, Christopher W. Szeto
-
Publication number: 20220375602Abstract: A method of determining a region of interest in an image of tissue of an individual by an apparatus including processing circuitry may include executing, by the processing circuitry, instructions that cause the apparatus to partition an image of tissue of an individual into a set of areas, identify a tissue type of each area of the image, and apply a classifier to the image to determine a region of interest, the classifier being configured to determine regions of interest based on the tissue types of the set of areas of the image.Type: ApplicationFiled: July 21, 2021Publication date: November 24, 2022Inventors: Mustafa I. JABER, Liudmila A. BEZIAEVA, Bing SONG, Christopher W. SZETO, Stephen Charles BENZ, Shahrooz RABIZADEH
-
Publication number: 20220290250Abstract: The present disclosure provides methods and systems of identifying a tumor patient for treatment with a combination of targeted therapy and immune oncology based on differential checkpoint expression patterns, and their association with mutation status, irrespective of the tumor tissue type. Also provided herein are methods of treatment for a tumor with a combination of targeted therapy and immune-oncology (IO) therapy.Type: ApplicationFiled: July 23, 2020Publication date: September 15, 2022Applicant: Nantomics LLCInventor: Christopher W. Szeto
-
Publication number: 20220092340Abstract: A method at a computing device for classifying elements within an input, the method including breaking the input into a plurality of patches; for each patch: creating a vector output; applying a characterization map to select a classification bin from a plurality of classification bins; and utilizing the selected classification bin to classify the vector output to create a classified output; and compiling the classified output from each patch.Type: ApplicationFiled: December 1, 2021Publication date: March 24, 2022Applicants: NantOmics, LLC, NantHealth, Inc.Inventors: Mustafa Jaber, Liudmila A. Beziaeva, Christopher W. Szeto, Bing Song
-
Publication number: 20210381058Abstract: An immune gene expression signature and immune cell distribution in the tumor, in combination, can be used to infer an immune phenotype of the tumor, which further can be used to characterize the tumor, selecting an optimal immune therapy to the tumor, and predicting the treatment outcome of an immune therapy.Type: ApplicationFiled: September 23, 2019Publication date: December 9, 2021Inventors: Christopher W. Szeto, Stephen Charles Benz
-
Patent number: 11195062Abstract: A method at a computing device for classifying elements within an input, the method including breaking the input into a plurality of patches; for each patch: creating a vector output; applying a characterization map to select a classification bin from a plurality of classification bins; and utilizing the selected classification bin to classify the vector output to create a classified output; and compiling the classified output from each patch.Type: GrantFiled: November 15, 2019Date of Patent: December 7, 2021Assignees: NantOmics, LLC, NantHealth, Inc.Inventors: Mustafa Jaber, Liudmila A Beziaeva, Christopher W Szeto, Bing Song
-
Publication number: 20200294622Abstract: TBNC expression data are analyzed and subtyped into four distinct groups by expression level. Recursive feature elimination allowed for identification of about 80 genes that defined four clusters. So obtained cluster information can be used to associate the clusters with specific drug sensitivity, survival time, and other relevant parameters.Type: ApplicationFiled: December 3, 2018Publication date: September 17, 2020Inventor: Christopher W. Szeto
-
Publication number: 20200160097Abstract: A method at a computing device for classifying elements within an input, the method including breaking the input into a plurality of patches; for each patch: creating a vector output; applying a characterization map to select a classification bin from a plurality of classification bins; and utilizing the selected classification bin to classify the vector output to create a classified output; and compiling the classified output from each patch.Type: ApplicationFiled: November 15, 2019Publication date: May 21, 2020Inventors: Mustafa Jaber, Liudmila A Beziaeva, Christopher W Szeto, Bing Song
-
Publication number: 20190292606Abstract: An immune gene expression signature is associated with clinical features in tumor samples and can be used to predict the immunological state of a tumor and/or sensitivity of the tumor to immune therapy.Type: ApplicationFiled: May 23, 2019Publication date: September 26, 2019Inventors: Christopher W. SZETO, Sandeep K. REDDY
-
Publication number: 20190295720Abstract: An immune gene expression signature is associated with clinical features in tumor samples and can be used to predict the immunological state of a tumor and/or sensitivity of the tumor to immune therapy.Type: ApplicationFiled: March 19, 2019Publication date: September 26, 2019Inventor: Christopher W. SZETO
-
Publication number: 20180039732Abstract: Contemplated systems and methods employ a priori known cell line genomics and drug response data to build a library of response predictors across multiple and distinct cell types and drugs. Statistical analysis of selected response predictors is then employed to identify a drug with a response predictor that has significant gain in prediction power relative to other drugs. Entity coefficients of the so identified response predictor are then applied to the output of a pathway model that was based on an actual patient's omic signature.Type: ApplicationFiled: August 3, 2017Publication date: February 8, 2018Inventors: Christopher W. Szeto, Stephen Charles Benz, Charles Joseph Vaske