Patents by Inventor Richard D. Hull

Richard D. Hull 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: 7219020
    Abstract: A novel extension of the vector space model for computing chemical similarity is described. In one embodiment, a method calculates similarity between molecules and molecular descriptors using the singular value composition (SVD) of a molecule/descriptor matrix and, for example, an identity matrix, to create a low dimensional representation of the original descriptor space. Probe or query molecules then can be projected into the low dimensional representation and compared to the molecules from the original matrix.
    Type: Grant
    Filed: April 10, 2000
    Date of Patent: May 15, 2007
    Assignee: Axontologic, Inc.
    Inventors: Richard D. Hull, Eugene M. Fluder, Jr., Suresh B. Singh, Robert P. Sheridan, Robert B. Nachbar, Simon K. Kearsley
  • Patent number: 6542903
    Abstract: An extension of the vector space model for computing chemical similarity using textual and chemical descriptors is described. The method uses a chemical and/or textual description of a molecule/chemical and a decomposes a molecule/chemical descriptor matrix by a suitable technique such as singular value decomposition to create a low dimensional representation of the original descriptor space. Similarities between a user probe and the textual and/or chemical descriptors are then computed and ranked.
    Type: Grant
    Filed: August 10, 2001
    Date of Patent: April 1, 2003
    Assignee: Merck & Co., Inc.
    Inventors: Richard D. Hull, Eugene M. Fluder, Jr., Suresh B. Singh
  • Publication number: 20020087508
    Abstract: An extension of the vector space model for computing chemical similarity using textual and chemical descriptors is described. The method uses a chemical and/or textual description of a molecule/chemical and a decomposes a molecule/chemical descriptor matrix by a suitable technique such as singular value decomposition to create a low dimensional representation of the original descriptor space. Similarities between a user probe and the textual and/or chemical descriptors are then computed and ranked.
    Type: Application
    Filed: August 10, 2001
    Publication date: July 4, 2002
    Applicant: Merck & Co., Inc.
    Inventors: Richard D. Hull, Eugene M. Fluder, Suresh B. Singh
  • Patent number: 6332138
    Abstract: An extension of the vector space model for computing chemical similarity using textual and chemical descriptors is described. The method uses a chemical and/or textual description of a molecule/chemical and a decomposes a molecule/chemical descriptor matrix by a suitable technique such as singular value decomposition to create a low dimensional representation of the original descriptor space. Similarities between a user probe and the textual and/or chemical descriptors are then computed and ranked.
    Type: Grant
    Filed: July 24, 2000
    Date of Patent: December 18, 2001
    Assignee: Merck & Co., Inc.
    Inventors: Richard D. Hull, Eugene M. Fluder, Jr., Suresh B. Singh