Patents by Inventor Imran Haque
Imran Haque 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: 11847532Abstract: Systems and methods that analyze blood-based cancer diagnostic tests using multiple classes of molecules are described. The system uses machine learning (ML) to analyze multiple analytes, for example cell-free DNA, cell-free microRNA, and circulating proteins, from a biological sample. The system can use multiple assays, e.g., whole-genome sequencing, whole-genome bisulfite sequencing or EM-seq, small-RNA sequencing, and quantitative immunoassay. This can increase the sensitivity and specificity of diagnostics by exploiting independent information between signals. During operation, the system receives a biological sample, and separates a plurality of molecule classes from the sample. For a plurality of assays, the system identifies feature sets to input to a machine learning model. The system performs an assay on each molecule class and forms a feature vector from the measured values.Type: GrantFiled: February 11, 2021Date of Patent: December 19, 2023Assignee: Freenome Holdings, Inc.Inventors: Adam Drake, Daniel Delubac, Katherine Niehaus, Eric Ariazi, Imran Haque, Tzu-Yu Liu, Nathan Wan, Ajay Kannan, Brandon White
-
Patent number: 11681953Abstract: Systems and methods that analyze blood-based cancer diagnostic tests using multiple classes of molecules are described. The system uses machine learning (ML) to analyze multiple analytes, for example cell-free DNA, cell-free microRNA, and circulating proteins, from a biological sample. The system can use multiple assays, e.g., whole-genome sequencing, whole-genome bisulfite sequencing or EM-seq, small-RNA sequencing, and quantitative immunoassay. This can increase the sensitivity and specificity of diagnostics by exploiting independent information between signals. During operation, the system receives a biological sample, and separates a plurality of molecule classes from the sample. For a plurality of assays, the system identifies feature sets to input to a machine learning model. The system performs an assay on each molecule class and forms a feature vector from the measured values.Type: GrantFiled: April 15, 2019Date of Patent: June 20, 2023Assignee: Freenome Holdings, Inc.Inventors: Adam Drake, Daniel Delubac, Katherine Niehaus, Eric Ariazi, Imran Haque, Tzu-Yu Liu, Nathan Wan, Ajay Kannan, Brandon White
-
Publication number: 20220238181Abstract: A system for selecting CRISPR guides for knocking out one or more target genes in a target cell from a multiplicity of candidate guides comprises a memory and a processor. The processor determines whether the candidate guide meets a plurality of thresholds. The thresholds are associated with: a transcript support level; targeting a consensus sequence of a target gene; which exon of the target gene is targeted; targeting of a primary transcript, targeting of a common isoform; a precomputed prediction of editing outcomes; mapping to an expressed sequence; fraction of gene expression attributable to targeted transcripts; a common SNP overlap threshold; which exon of the target gene is targeted; overlap of a selected guide; predicted frameshift percentage; maximum and minimum GC content; off target score; where a coding sequence is targeted. In response to meeting the thresholds, the processor selects the candidate guide as a selected CRISPR guide.Type: ApplicationFiled: January 27, 2022Publication date: July 28, 2022Applicant: Recursion Pharmaceuticals, Inc.Inventors: James JENSEN, Timothy DAHLEM, Sarah HUGO, Jacob COOPER, Spencer SCHREIER, Ian QUIGLEY, Imran HAQUE, Nathan LAZAR, Alison GARDNER, Ben BANOWSKY, August ALLEN
-
Patent number: 11361438Abstract: In various embodiments, an experiment analysis application detects executional artifacts in experiments involving microwell plates. The experiment analysis application computes one or more sets of spatial features based on one or more heat maps associated with a microwell plate. The experiment analysis application then aggregates the set(s) of spatial features to generate a feature vector. The experiment analysis application inputs the feature vector into a trained classifier. In response, the trained classifier generates a label indicating that the microwell plate is associated with a first executional artifact.Type: GrantFiled: July 27, 2020Date of Patent: June 14, 2022Assignee: RECURSION PHARMACEUTICALS, INC.Inventors: Benjamin Marc Feder Fogelson, Peter McLean, Imran Haque, Marissa Saunders, Eric Fish, Charles Baker, Juan Sebastián Rodríguez Vera
-
Publication number: 20220028061Abstract: In various embodiments, an experiment analysis application detects executional artifacts in experiments involving microwell plates. The experiment analysis application computes one or more sets of spatial features based on one or more heat maps associated with a microwell plate. The experiment analysis application then aggregates the set(s) of spatial features to generate a feature vector. The experiment analysis application inputs the feature vector into a trained classifier. In response, the trained classifier generates a label indicating that the microwell plate is associated with a first executional artifact.Type: ApplicationFiled: July 27, 2020Publication date: January 27, 2022Inventors: Benjamin Marc Feder FOGELSON, Peter MCLEAN, Imran HAQUE, Marissa SAUNDERS, Eric FISH, Charles BAKER, Juan Sebastián Rodríguez VERA
-
Publication number: 20220027795Abstract: In various embodiments, a training application trains a classifier to detect executional artifacts in experiments involving microwell plates. The training application computes spatial information based on a heat map associated with a microwell plate. The training application then computes a set of features based on the spatial information. Subsequently, the training application executes one or more machine learning operations based, at least in part, on the set of features to generate a trained classifier. The trained classifier classifies sets of features associated with different microwell plates with respect to labels associated with executional artifacts. Advantageously, the trained classier can be used to accurately and consistently detect executional artifacts across different experiments and over time.Type: ApplicationFiled: July 27, 2020Publication date: January 27, 2022Inventors: Benjamin Marc Feder FOGELSON, Peter MCLEAN, Imran HAQUE, Marissa SAUNDERS, Eric FISH, Charles BAKER, Juan Sebastián Rodríguez VERA
-
Publication number: 20210210205Abstract: Systems and methods that analyze blood-based cancer diagnostic tests using multiple classes of molecules are described. The system uses machine learning (ML) to analyze multiple analytes, for example cell-free DNA, cell-free microRNA, and circulating proteins, from a biological sample. The system can use multiple assays, e.g., whole-genome sequencing, whole-genome bisulfite sequencing or EM-seq, small-RNA sequencing, and quantitative immunoassay. This can increase the sensitivity and specificity of diagnostics by exploiting independent information between signals. During operation, the system receives a biological sample, and separates a plurality of molecule classes from the sample. For a plurality of assays, the system identifies feature sets to input to a machine learning model. The system performs an assay on each molecule class and forms a feature vector from the measured values.Type: ApplicationFiled: February 11, 2021Publication date: July 8, 2021Inventors: Adam Drake, Daniel Delubac, Katherine Niehaus, Eric Ariazi, Imran Haque, Tzu-Yu Liu, Nathan Wan, Ajay Kannan, Brandon White
-
Publication number: 20210174958Abstract: Systems and methods that analyze blood-based cancer diagnostic tests using multiple classes of molecules are described. The system uses machine learning (ML) to analyze multiple analytes, for example cell-free DNA, cell-free microRNA, and circulating proteins, from a biological sample. The system can use multiple assays, e.g., whole-genome sequencing, whole-genome bisulfite sequencing or EM-seq, small-RNA sequencing, and quantitative immunoassay. This can increase the sensitivity and specificity of diagnostics by exploiting independent information between signals. During operation, the system receives a biological sample, and separates a plurality of molecule classes from the sample. For a plurality of assays, the system identifies feature sets to input to a machine learning model. The system performs an assay on each molecule class and forms a feature vector from the measured values.Type: ApplicationFiled: April 15, 2019Publication date: June 10, 2021Inventors: Adam Drake, Daniel Delubac, Katherine Niehaus, Eric Ariazi, Imran Haque, Tzu-Yu Liu, Nathan Wan, Ajay Kannan, Brandon White
-
Patent number: 8706427Abstract: Methods and algorithms are presented that implement linear algebraic techniques for rapidly estimating chemical similarities for several popular measures. The methods of the present invention reflect source similarity measures for both Tanimoto calculation and rank ordering. After a precalculation step on a database, the methods of the present invention afford several orders of magnitude of speedup in database screening. The present invention also provides an asymptotic speedup for large similarity matrix construction problems, reducing the number of conventional slow similarity evaluations required from quadratic to linear scaling.Type: GrantFiled: February 26, 2011Date of Patent: April 22, 2014Assignee: The Board of Trustees of the Leland Stanford Junior UniversityInventors: Imran Haque, Vijay Pande
-
Publication number: 20110213567Abstract: Methods and algorithms are presented that implement linear algebraic techniques for rapidly estimating chemical similarities for several popular measures. The methods of the present invention reflect source similarity measures for both Tanimoto calculation and rank ordering. After a precalculation step on a database, the methods of the present invention afford several orders of magnitude of speedup in database screening. The present invention also provides an asymptotic speedup for large similarity matrix construction problems, reducing the number of conventional slow similarity evaluations required from quadratic to linear scaling.Type: ApplicationFiled: February 26, 2011Publication date: September 1, 2011Applicant: The Board of Trustees of the Leland Stanford Junior UniversityInventors: Imran Haque, Vijay Pande