公开(公告)号：US12008752B2

公开(公告)日：2024-06-11

申请号：US17362018

申请日：2021-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Layne Christopher Price

IPC: G06N3/08 ,  G06T7/00 ,  G06T7/73 ,  G16H30/40 ,  G16H40/67 ,  H04W4/02

CPC classification number: G06T7/0012 ,  G06N3/08 ,  G06T7/74 ,  G16H30/40 ,  G16H40/67 ,  H04W4/026 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Techniques for automated alignment of image capture of physical ailments are described. A method of automated alignment of image capture of physical ailments includes determining an alignment class of a first image of an object using an alignment classifier executing on a user device, providing alignment instructions based on the alignment class and a reference image associated with the object using at least one machine learning model executing on the user device, obtaining an aligned image of the object after the user device has been repositioned relative to the object based on the alignment instructions, and sending the aligned image to an agent device via a telemedicine service of a provider network.

公开(公告)号：US12057196B1

公开(公告)日：2024-08-06

申请号：US17209486

申请日：2021-03-23

Applicant: Amazon Technologies, Inc.

Inventor： Layne Christopher Price ,  David Heckerman

IPC: G16B30/10 ,  G06N3/08 ,  G16B40/00 ,  G16B50/30

CPC classification number: G16B30/10 ,  G06N3/08 ,  G16B40/00 ,  G16B50/30

Abstract: Techniques are described and relate to anisotropic pooling for contextual embedding of a protein sequence. In an example, a system receives a first biological sequence and determines a sequence arrangement that comprises a component of the first biological sequence and a second biological sequence of components. By using an artificial intelligence (AI) model, the system determines a third sequence that comprises a contextual embedding vector corresponding to the component of the first biological sequence. The AI model generates the third sequence based at least in part on the sequence arrangement and by at least using a convolution and anisotropic pooling.

公开(公告)号：US20250064908A1

公开(公告)日：2025-02-27

申请号：US18924824

申请日：2024-10-23

Applicant: AMAZON TECHNOLOGIES, INC

Inventor： Frank Wilhelm Schmitz ,  David Heckerman ,  Layne Christopher Price ,  Antje Heit

IPC: A61K39/00 ,  A61K39/39 ,  A61K45/06

Abstract: Provided herein are immunogenic compositions comprising tumor-specific neoantigen long peptides, tumor-specific neoantigen short peptides, and adjuvant, optionally a helper peptide, and optionally a tumor-specific peptide. The disclosure also provides methods of using these immunogenic compositions for treating cancer.

公开(公告)号：US11923044B1

公开(公告)日：2024-03-05

申请号：US16896907

申请日：2020-06-09

Applicant: Amazon Technologies, Inc.

Inventor： Alexander Sewall Ford ,  Vanessa Nguyen ,  Layne Christopher Price ,  Franziska Seeger ,  Yen Ling Adelene Sim

IPC: G16B15/00 ,  G16B30/20 ,  G16B40/00

CPC classification number: G16B15/00 ,  G16B30/20 ,  G16B40/00

Abstract: Techniques for predicting a protein sequence are described. An exemplary method includes receiving a request to predict a missing area of a protein's primary sequence and a corresponding three-dimensional position of the missing area; applying a machine learning model to backbone Cartesian coordinates of the protein's primary sequence and a protein vector of a representation of the protein's primary sequence including the missing area to predict a missing area of the protein primary sequence and a corresponding three-dimensional position for the missing area, wherein the machine learning model is selected from the group consisting of: an attention-based machine learning model, a bidirectional long short term memory-based model, and a convolutional neural network-based model; and outputting a result of the machine learning model.

公开(公告)号：US20250003004A1

公开(公告)日：2025-01-02

申请号：US18271540

申请日：2023-07-06

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Haibao Tang ,  David Heckerman ,  Layne Christopher Price ,  Frank Wilhelm Schmitz ,  Alena Harley ,  Antje Heit ,  Samuel Anthony Danziger

IPC: C12Q1/6886 ,  A61K39/00

Abstract: Disclosed herein is a method, comprising administering to a subject in need thereof an initial immunogenic composition comprising a plurality of tumor-specific neoantigens, each corresponding to a member of a first set of tumor-associated mutations in a subject, and none corresponding to a member of a second set of tumor-associated mutations in the subject; and quantifying each member of the first set of tumor-associated mutations and each member of the second set of tumor-associated mutations in circulating material comprising tumor-associated mutations isolated from the subject at each of multiple time points.

公开(公告)号：US11929152B1

公开(公告)日：2024-03-12

申请号：US16896877

申请日：2020-06-09

Applicant: Amazon Technologies, Inc.

Inventor： Alexander Sewall Ford ,  Zachary Wu ,  Layne Christopher Price ,  Franziska Seeger ,  Yen Ling Adelene Sim

IPC: G01N33/48 ,  G06N3/044 ,  G16B5/20 ,  G16B15/00 ,  G16B40/00

CPC classification number: G16B40/00 ,  G06N3/044 ,  G16B5/20 ,  G16B15/00

Abstract: Techniques for predicting a pair of an enzyme primary sequence and a substrate, and interaction probability for the pair are described. An exemplary method includes receiving a request to predict a pair of an enzyme primary sequence and a substrate, and interaction probability for the pair; combining an enzyme vector, a substrate vector, and an interaction indication for the enzyme and substrate to form a machine learning model input; applying a machine learning model to the machine learning model input to predict the pair of an enzyme primary sequence and a substrate, and interaction probability for the pair; and outputting a result of the application of the machine learning model including the predicted pair of an enzyme primary sequence and a substrate, and interaction probability for the pair.

公开(公告)号：US20220383996A1

公开(公告)日：2022-12-01

申请号：US17332719

申请日：2021-05-27

Applicant: Amazon Technologies, Inc.

Inventor： Layne Christopher Price ,  David Heckerman ,  Frank Wilhelm Schmitz

IPC: G16H10/60 ,  A61K39/00 ,  G16B15/20 ,  G16H50/20

Abstract: Techniques are described and relate to assigning peptides to peptide groups for vaccine development. In an example, a peptide property of a peptide is determined, where this peptide is from different peptides that are to be assigned to different groups of vaccine. A determination is also made that the peptide is to be assigned to a first group from the different groups based at least in part on the peptide property. The first group has a first group property that is based at least in part on peptide properties of first peptides to be assigned to the first group. The first group property is within a similarity range relative to a second group property of a second group from the different groups. Information is generated and indicates that the peptide is assigned to the first group.

公开(公告)号：US11218666B1

公开(公告)日：2022-01-04

申请号：US17119074

申请日：2020-12-11

Applicant: Amazon Technologies, Inc.

Inventor： Bertrand Haas ,  Layne Christopher Price

IPC: H04N7/14 ,  G06K9/00 ,  G10L15/183 ,  G06T13/20 ,  H04N7/15 ,  G10L15/00 ,  G06T13/40

Abstract: Devices, systems, and methods are provided for audio and video capture and presentation. A method may include receiving, by a first device, images of a user, identifying, in a first image of the images, a first expression of the user, and identifying, in a second image of the images, a second expression of the user. The method may include determining that the first expression is associated with a first phoneme and that the second expression is associated with a second phoneme. The method may include generating audio including the first phoneme and the second phoneme, and sending the audio to a second device for presentation.