Patents by Inventor Gengxin Chen

Gengxin Chen 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).

  • Publication number: 20240013861
    Abstract: This disclosure provides an improved filtering techniques that can provide higher sequencing accuracy for processing high-throughput sequencing data. The filtering structure uses a hierarchical network structure comprising one or more network blocks for obtaining high quality sequences. Each network block comprises a base network module (or simply a base network) and a sequence filter. The base network generates one or more sequencing quality indicators. The sequencing quality indicators can represent qualities of accuracy of the basecalling of individual bases in a sequence, the quality of one or more sequences individually, or the quality of a group of sequences as a whole. The sequence filter generates the filtered results based on the various filtering strategies based on the one or more sequencing quality indicators.
    Type: Application
    Filed: November 28, 2022
    Publication date: January 11, 2024
    Applicant: GeneSense Technology Inc.
    Inventors: Shaobo Luo, Zhiyuan Xie, Gengxin Chen, Tianzhen Ao, Mei Yan
  • Patent number: 11580641
    Abstract: Methods and systems for determining a plurality of sequences of nucleic acid (e.g., DNA) molecules in a sequencing-by-synthesis process are provided. In one embodiment, the method comprises obtaining images of fluorescent signals obtained in a plurality of synthesis cycles. The images of fluorescent signals are associated with a plurality of different fluorescence channels. The method further comprises preprocessing the images of fluorescent signals to obtain processed images. Based on a set of the processed images, the method further comprises detecting center positions of clusters of the fluorescent signals using a trained convolutional neural network (CNN) and extracting, based on the center positions of the clusters of fluorescent signals, features from the set of the processed images to generate feature embedding vectors. The method further comprises determining, in parallel, the plurality of sequences of DNA molecules using the extracted features based on a trained attention-based neural network.
    Type: Grant
    Filed: February 25, 2022
    Date of Patent: February 14, 2023
    Assignee: GeneSense Technology Inc.
    Inventors: Gengxin Chen, Shaobo Luo, Shuwei Li, Jichao Yan, Tianzhen Ao, Yuan Lu, Mei Yan
  • Publication number: 20230044849
    Abstract: Disclosed are methods for determining copy number variation (CNV) known or suspected to be associated with a variety of medical conditions. In some embodiments, methods are provided for determining copy number variation of fetuses using maternal samples comprising maternal and fetal cell free DNA. In some embodiments, methods are provided for determining CNVs known or suspected to be associated with a variety of medical conditions. Some embodiments disclosed herein provide methods to improve the sensitivity and/or specificity of sequence data analysis by deriving a fragment size parameter. In some implementations, information from fragments of different sizes are used to evaluate copy number variations. In some implementations, one or more t-statistics obtained from coverage information of the sequence of interest is used to evaluate copy number variations. In some implementations, one or more fetal fraction estimates are combined with one or more t-statistics to determine copy number variations.
    Type: Application
    Filed: July 22, 2022
    Publication date: February 9, 2023
    Inventors: Sven Duenwald, David A. Comstock, Catalin Barbacioru, Darya I. Chudova, Richard P. Rava, Keith W. Jones, Gengxin Chen, Dimitri Skvortsov
  • Patent number: 11430541
    Abstract: Disclosed are methods for determining copy number variation (CNV) known or suspected to be associated with a variety of medical conditions. In some embodiments, methods are provided for determining copy number variation of fetuses using maternal samples comprising maternal and fetal cell free DNA. In some embodiments, methods are provided for determining CNVs known or suspected to be associated with a variety of medical conditions. Some embodiments disclosed herein provide methods to improve the sensitivity and/or specificity of sequence data analysis by deriving a fragment size parameter. In some implementations, information from fragments of different sizes are used to evaluate copy number variations. In some implementations, one or more t-statistics obtained from coverage information of the sequence of interest is used to evaluate copy number variations. In some implementations, one or more fetal fraction estimates are combined with one or more t-statistics to determine copy number variations.
    Type: Grant
    Filed: August 31, 2018
    Date of Patent: August 30, 2022
    Assignee: Verinata Health, Inc.
    Inventors: Sven Duenwald, David A. Comstock, Catalin Barbacioru, Darya I. Chudova, Richard P. Rava, Keith W. Jones, Gengxin Chen, Dimitri Skvortsov
  • Publication number: 20190065676
    Abstract: Disclosed are methods for determining copy number variation (CNV) known or suspected to be associated with a variety of medical conditions. In some embodiments, methods are provided for determining copy number variation of fetuses using maternal samples comprising maternal and fetal cell free DNA. In some embodiments, methods are provided for determining CNVs known or suspected to be associated with a variety of medical conditions. Some embodiments disclosed herein provide methods to improve the sensitivity and/or specificity of sequence data analysis by deriving a fragment size parameter. In some implementations, information from fragments of different sizes are used to evaluate copy number variations. In some implementations, one or more t-statistics obtained from coverage information of the sequence of interest is used to evaluate copy number variations. In some implementations, one or more fetal fraction estimates are combined with one or more t-statistics to determine copy number variations.
    Type: Application
    Filed: August 31, 2018
    Publication date: February 28, 2019
    Inventors: Sven Duenwald, David A. Comstock, Catalin Barbacioru, Darya I. Chudova, Richard P. Rava, Keith W. Jones, Gengxin Chen, Dimitri Skvortsov
  • Publication number: 20180289764
    Abstract: The present invention discloses a traditional Chinese medicine composition for treating psoriasis, the traditional Chinese medicine composition is prepared from materials in the following parts by weight: 5-15 parts of paeoniae radix rubra (red peony root), 3-9 parts of curcumae rhizoma (rhizoma zedoariae), 10-20 parts of sarcandrae herba (sarcandra glabra), 10-20 parts of smilacis glabrae rhizoma (glabrous greenbrier rhizome), 5-15 parts of mume fructus (black plum). The invention has the beneficial effects that the therapeutic effect can be achieved at a small dosage, the toxicity is significantly reduced, the onset is rapid, and the recurrence can be delayed. The effect is more prominent for psoriasis vulgaris (PASI50 up to 60%), especially for early onset patients.
    Type: Application
    Filed: August 19, 2016
    Publication date: October 11, 2018
    Applicant: Guangdong Provincial Hospital of Chinese Medicine
    Inventors: Chuanjian LU, Ruizhi Zhao, Guowei Xuan, Ling Han, Gengxin Chen, Yuhong Yan, Lijuan Li
  • Patent number: 10095831
    Abstract: Disclosed are methods for determining copy number variation (CNV) known or suspected to be associated with a variety of medical conditions. In some embodiments, methods are provided for determining copy number variation of fetuses using maternal samples comprising maternal and fetal cell free DNA. In some embodiments, methods are provided for determining CNVs known or suspected to be associated with a variety of medical conditions. Some embodiments disclosed herein provide methods to improve the sensitivity and/or specificity of sequence data analysis by deriving a fragment size parameter. In some implementations, information from fragments of different sizes are used to evaluate copy number variations. In some implementations, one or more t-statistics obtained from coverage information of the sequence of interest is used to evaluate copy number variations. In some implementations, one or more fetal fraction estimates are combined with one or more t-statistics to determine copy number variations.
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: October 9, 2018
    Assignee: Verinata Health, Inc.
    Inventors: Sven Duenwald, David A. Comstock, Catalin Barbacioru, Darya I. Chudova, Richard P. Rava, Keith W. Jones, Gengxin Chen, Dimitri Skvortsov
  • Patent number: 9804156
    Abstract: The disclosure provides SLE biomarkers. The disclosure further provides kits and methods of diagnosing, prognosing, and stratifying subjects with the disease by utilizing SLE biomarkers.
    Type: Grant
    Filed: March 6, 2013
    Date of Patent: October 31, 2017
    Assignee: LIFE TECHNOLOGIES CORPORATION
    Inventors: Niroshan Ramachandran, Lihao Meng, Gengxin Chen, David Bourdon, Suzy Van Le
  • Publication number: 20170220735
    Abstract: Disclosed are methods for determining copy number variation (CNV) known or suspected to be associated with a variety of medical conditions. In some embodiments, methods are provided for determining copy number variation of fetuses using maternal samples comprising maternal and fetal cell free DNA. In some embodiments, methods are provided for determining CNVs known or suspected to be associated with a variety of medical conditions. Some embodiments disclosed herein provide methods to improve the sensitivity and/or specificity of sequence data analysis by deriving a fragment size parameter. In some implementations, information from fragments of different sizes are used to evaluate copy number variations. In some implementations, one or more t-statistics obtained from coverage information of the sequence of interest is used to evaluate copy number variations. In some implementations, one or more fetal fraction estimates are combined with one or more t-statistics to determine copy number variations.
    Type: Application
    Filed: December 16, 2016
    Publication date: August 3, 2017
    Inventors: Sven Duenwald, David A. Comstock, Catalin Barbacioru, Darya I. Chudova, Richard P. Rava, Keith W. Jones, Gengxin Chen, Dimitri Skvortsov
  • Publication number: 20120094861
    Abstract: The present invention provides compositions and methods for identifying molecules in samples that bind to molecules associated with pathogenic agents (e.g., infectious agents). In certain aspects, the invention may be used to identify individuals that have been exposed to one or more pathogenic agent or have generated antibodies in response to one or more pathogenic agent. In other aspects, the invention is directed to the identification of molecules of one or more pathogenic agent that may be used to generate immune responses in other individuals.
    Type: Application
    Filed: October 26, 2011
    Publication date: April 19, 2012
    Applicants: U. S. Army Medical Research and Materiel Command, Invitrogen Incorporated
    Inventors: James Meegan, Alex Tikhonov, Barry Schweitzer, Gengxin Chen, Robert G. Ulrich
  • Publication number: 20090305899
    Abstract: The present invention provides compositions and methods for identifying molecules in samples that bind to molecules associated with pathogenic agents (e.g., infectious agents). In certain aspects, the invention may be used to identify individuals that have been exposed to one or more pathogenic agent or have generated antibodies in response to one or more pathogenic agent. In other aspects, the invention is directed to the identification of molecules of one or more pathogenic agent that may be used to generate immune responses in other individuals.
    Type: Application
    Filed: November 17, 2008
    Publication date: December 10, 2009
    Applicants: Invitrogen Incorporated, U.S. Army Medical Research and Material Command
    Inventors: James Meegan, Alex Tikhonov, Barry Schweitzer, Gengxin Chen, Robert G. Ulrich