Patents by Inventor Michael Vella

Michael Vella 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).

  • Sequence variation detection using deep learning
    Patent number: 12387817
    Abstract: Methods, systems, and computer program products are disclosed that use embeddings of candidate variation information and deep learning models to accurately and efficiently detect variations in biopolymer sequencing data, particularly suboptimal sequencing data.
    Type: Grant
    Filed: May 13, 2019
    Date of Patent: August 12, 2025
    Assignee: NVIDIA Corporation
    Inventors: Nikolai Yakovenko, Johnny Israeli, Avantika Lal, Michael Vella, Zhen Hu
  • Genetic mutation detection using deep learning
    Patent number: 12094572
    Abstract: The present disclosure provides methods, systems, and computer program products that use deep learning models to classify candidate mutations detected in sequencing data, particularly suboptimal sequencing data. The methods, systems, and programs provide for increased efficiency, accuracy, and speed in identifying mutations from a wide range of sequencing data.
    Type: Grant
    Filed: August 5, 2022
    Date of Patent: September 17, 2024
    Assignee: NVIDIA Corporation
    Inventors: Johnny Israeli, Avantika Lal, Michael Vella, Nikolai Yakovenko, Zhen Hu
  • Genetic mutation detection using deep learning
    Patent number: 11443832
    Abstract: The present disclosure provides methods, systems, and computer program products that use deep learning models to classify candidate mutations detected in sequencing data, particularly suboptimal sequencing data. The methods, systems, and programs provide for increased efficiency, accuracy, and speed in identifying mutations from a wide range of sequencing data.
    Type: Grant
    Filed: March 7, 2019
    Date of Patent: September 13, 2022
    Assignee: NVIDIA Corporation
    Inventors: Johnny Israeli, Avantika Lal, Michael Vella, Nikolai Yakovenko, Zhen Hu
  • SEQUENCE VARIATION DETECTION USING DEEP LEARNING
    Publication number: 20200365234
    Abstract: The present disclosure provides methods, systems, and computer program products that use embeddings of candidate variation information and deep learning models to accurately and efficiently detect variations in biopolymer sequencing data, particularly suboptimal sequencing data.
    Type: Application
    Filed: May 13, 2019
    Publication date: November 19, 2020
    Applicant: NVIDIA Corporation
    Inventors: Nikolai YAKOVENKO, Johnny ISRAELI, Avantika LAL, Michael VELLA, Zhen HU
  • GENETIC MUTATION DETECTION USING DEEP LEARNING
    Publication number: 20200286587
    Abstract: The present disclosure provides methods, systems, and computer program products that use deep learning models to classify candidate mutations detected in sequencing data, particularly suboptimal sequencing data. The methods, systems, and programs provide for increased efficiency, accuracy, and speed in identifying mutations from a wide range of sequencing data.
    Type: Application
    Filed: March 7, 2019
    Publication date: September 10, 2020
    Applicant: NVIDIA Corporation
    Inventors: Johnny ISRAELI, Avantika LAL, Michael VELLA, Nikolai YAKOVENKO, Zhen HU
  • Device having preformed triple junctions to maintain electrode conductivity and a method for making and using the device
    Patent number: 9903016
    Abstract: In systems where insulating deposits form during normal operation, electrodes are configured with a preformed dielectric thereon, wherein the preformed dielectric is formed with a geometric feature that preforms a triple junction. These triple junctions enhance low level discharge activity to facilitate localized breakdown of the deposits and maintain electrode conductivity.
    Type: Grant
    Filed: December 23, 2016
    Date of Patent: February 27, 2018
    Assignee: E/G Electro-Graph, Inc.
    Inventor: Michael Vella
  • DEVICE HAVING PREFORMED TRIPLE JUNCTIONS TO MAINTAIN ELECTRODE CONDUCTIVITY AND A METHOD FOR MAKING AND USING THE DEVICE
    Publication number: 20170107608
    Abstract: In systems where insulating deposits form during normal operation, electrodes are configured with a preformed dielectric thereon, wherein the preformed dielectric is formed with a geometric feature that performing a triple junction. These triple junctions enhance low level discharge activity to facilitate localized breakdown of the deposits and maintain electrode conductivity.
    Type: Application
    Filed: December 23, 2016
    Publication date: April 20, 2017
    Inventor: MICHAEL VELLA
  • In-situ triple junction formation to maintain electrode conductivity
    Patent number: 9551061
    Abstract: In systems where insulating deposits form during normal operation, electrodes are configured so the deposits have the effect of creating in-situ triple junctions. These triple junctions enhance low level discharge activity to facilitate localized breakdown of the deposits and maintain electrode conductivity.
    Type: Grant
    Filed: October 23, 2015
    Date of Patent: January 24, 2017
    Assignee: E/G Electro-Graph Inc.
    Inventor: Michael Vella
  • IN-SITU TRIPLE JUNCTION FORMATION TO MAINTAIN ELECTRODE CONDUCTIVITY
    Publication number: 20160115581
    Abstract: In systems where insulating deposits form during normal operation, electrodes are configured so the deposits have the effect of creating in-situ triple junctions. These triple junctions enhance low level discharge activity to facilitate localized breakdown of the deposits and maintain electrode conductivity.
    Type: Application
    Filed: October 23, 2015
    Publication date: April 28, 2016
    Applicant: E/G ELECTRO-GRAPH, INC.
    Inventor: MICHAEL VELLA
  • GEOMETRIC FIELD ENHANCEMENT TO MAINTAIN ELECTRODE CONDUCTIVITY
    Publication number: 20160118220
    Abstract: Features that create localized electric field enhancement are deliberately introduced on conductors where deposits having insulating characteristics can form. The purpose of the introduced features is to enhance localized breakdown of the deposits in order to maintain electrode conductivity.
    Type: Application
    Filed: October 23, 2015
    Publication date: April 28, 2016
    Applicant: E/G ELECTRO-GRAPH, INC.
    Inventor: MICHAEL VELLA
  • Magnetic field reduction apparatus and magnetic plasma flood system for ion beam processing
    Patent number: 8686640
    Abstract: An ion beam processing system includes a plasma generator with a magnetic flood system. Magnets are provided for reducing the transverse magnetic field in the ion beam transport region of the plasma flood device so as to control charging damage or to neutralize beam space charge in ion beam processing and semiconductor ion implantation. The system is especially adapted for beam lines with ribbon beams.
    Type: Grant
    Filed: November 9, 2012
    Date of Patent: April 1, 2014
    Assignee: E/G Electro-Graph Inc.
    Inventor: Michael Vella