公开(公告)号：US11742076B2

公开(公告)日：2023-08-29

申请号：US17960755

申请日：2022-10-05

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Matthew Edward Kollada

IPC: G16H40/20 ,  G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G16H30/40 ,  G06V10/77 ,  G06V10/82 ,  G06V10/774 ,  G06T7/00 ,  G06N20/00

CPC classification number: G16H40/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0016 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G06N20/00 ,  G06T2207/10088 ,  G06T2207/10104 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30016 ,  G06T2207/30104 ,  G06V2201/03

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating multi-modal data archetypes. In one aspect, a method comprises obtaining a plurality of training examples, wherein each training example corresponds to a respective patient and includes multi-modal data, having a plurality of feature dimensions, that characterizes the patient; jointly training an encoder neural network and a decoder neural network on the plurality of training examples; and generating a plurality of multi-modal data archetypes that each correspond to a respective dimension of a latent space, comprising, for each multi-modal data archetype: processing a predefined embedding that represents the corresponding dimension of the latent space using the decoder neural network to generate multi-modal data, having the plurality of feature dimensions, that defines the multi-modal data archetype.

公开(公告)号：US20230260634A1

公开(公告)日：2023-08-17

申请号：US18136832

申请日：2023-04-19

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Matthew Edward Kollada

IPC: G16H40/20 ,  G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G16H30/40 ,  G06V10/77 ,  G06V10/82 ,  G06V10/774 ,  G06T7/00

CPC classification number: G16H40/20 ,  G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G16H30/40 ,  G06V10/7715 ,  G06V10/82 ,  G06V10/774 ,  G06T7/0016 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying a patient. In one aspect, a method comprises: receiving multi-modal data characterizing a patient, wherein the multi-modal data comprises a respective feature representation for each of a plurality of modalities; processing the multi-modal data characterizing the patient using an encoder neural network to generate an embedding of the multi-modal data characterizing the patient; determining a respective classification score for each patient category in a set of patient categories based on the embedding of the multi-modal data characterizing the patient; and classifying the patient as being included in a corresponding patient category from the set of patient categories based on the classification scores.

公开(公告)号：US20240136058A1

公开(公告)日：2024-04-25

申请号：US18542321

申请日：2023-12-15

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Matthew Edward Kollada

IPC: G16H40/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G06T7/00 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70

CPC classification number: G16H40/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0016 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an encoder neural network and a decoder neural network. In one aspect, a method comprises, for each latent dimension in a proper subset of a plurality of latent dimensions of a latent space: processing a predefined embedding that represents the latent dimension using the decoder neural network to generate multi-modal data, having a plurality of feature dimensions, that defines a predicted multi-modal data archetype corresponding to the latent dimension; and updating the values of the set of decoder parameters using gradients of an archetype loss function that measures an error between: (i) a predicted multi-modal data archetype corresponding to the latent dimension, and (ii) a target multi-modal data archetype corresponding to the latent dimension.

公开(公告)号：US12087446B2

公开(公告)日：2024-09-10

申请号：US17740713

申请日：2022-05-10

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Matthew Kollada ,  Tathagata Banerjee

IPC: G16H50/20 ,  A61B5/00 ,  A61B5/0205 ,  A61B5/16 ,  G06N20/00 ,  G16H10/20

CPC classification number: G16H50/20 ,  A61B5/0205 ,  A61B5/165 ,  A61B5/7264 ,  G06N20/00 ,  G16H10/20

Abstract: Methods and systems are provided for diagnosing mental health conditions using multiple data modalities. In particular, a trained machine learning model is used for mental health diagnosis, wherein the trained model utilizes a dynamic fusion approach for capturing and preserving interactions as well as timing information between the multiple data modalities.

公开(公告)号：US20240021298A1

公开(公告)日：2024-01-18

申请号：US18370818

申请日：2023-09-20

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Matthew Edward Kollada

IPC: G16H40/20 ,  G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G16H30/40 ,  G06V10/77 ,  G06V10/82 ,  G06V10/774 ,  G06T7/00

CPC classification number: G16H40/20 ,  G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G16H30/40 ,  G06V10/7715 ,  G06V10/82 ,  G06V10/774 ,  G06T7/0016 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an encoder neural network and a decoder neural network. In one aspect, a method comprises: updating current values of a set of encoder parameters and current values of a set of decoder parameters using gradients of a reconstruction loss function that measures an error in a reconstruction of multi-modal data from a training example, wherein: the reconstruction loss function comprises a plurality of scaling factors that each scale a respective term in the reconstruction loss function that measures an error in the reconstruction of a corresponding proper subset of feature dimensions of the multi-modal data from the training example.

公开(公告)号：US20230343446A1

公开(公告)日：2023-10-26

申请号：US18212690

申请日：2023-06-21

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Peter Crocker

IPC: G16H30/40 ,  G06N3/02 ,  G06N3/08 ,  G06V10/82 ,  G16H50/70 ,  G06N3/045 ,  G06V10/77 ,  G06T7/00 ,  G16H40/20 ,  G16H50/20 ,  G06V10/774

CPC classification number: G16H40/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0016 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a respective response score for each of a plurality of patient categories. In one aspect, a method comprises: generating a drug signature for a drug; generating an embedding of the drug signature in a latent space; and processing: (i) the embedding of the drug signature in the latent space, and (ii) data defining a plurality of patient categories, to generate a plurality of response scores, wherein each response score corresponds to a respective patient category and characterizes a predicted response of patients included in the patient category to the drug.

公开(公告)号：US11670417B2

公开(公告)日：2023-06-06

申请号：US17960705

申请日：2022-10-05

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Matthew Edward Kollada

IPC: G16H50/30 ,  G06N3/08 ,  G16H20/60 ,  G16H40/20 ,  G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06N3/045 ,  G16H30/40 ,  G06V10/77 ,  G06V10/82 ,  G06V10/774 ,  G06T7/00 ,  G06N20/00

CPC classification number: G16H40/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0016 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G06N20/00 ,  G06T2207/10088 ,  G06T2207/10104 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30016 ,  G06T2207/30104 ,  G06V2201/03

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying a patient. In one aspect, a method comprises: receiving multi-modal data characterizing a patient, wherein the multi-modal data comprises a respective feature representation for each of a plurality of modalities; processing the multi-modal data characterizing the patient using an encoder neural network to generate an embedding of the multi-modal data characterizing the patient; determining a respective classification score for each patient category in a set of patient categories based on the embedding of the multi-modal data characterizing the patient; and classifying the patient as being included in a corresponding patient category from the set of patient categories based on the classification scores.

公开(公告)号：US11887724B2

公开(公告)日：2024-01-30

申请号：US17960759

申请日：2022-10-05

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Matthew Edward Kollada ,  Amirsina Torfi ,  Peter Crocker

IPC: G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06V10/82 ,  G06V10/774 ,  G06N3/08 ,  G16H30/40 ,  G16H40/20 ,  G06N3/045 ,  G06V10/77 ,  G06T7/00 ,  G06N20/00

CPC classification number: G16H40/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0016 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G06N20/00 ,  G06T2207/10088 ,  G06T2207/10104 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30016 ,  G06T2207/30104 ,  G06V2201/03

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a clinical recommendation for medical treatment of a patient. In one aspect a method comprises: receiving multi-modal data characterizing a patient, wherein the multi-modal data comprises a respective feature representation for each of a plurality of modalities; processing the multi-modal data characterizing the patient using a machine learning model, in accordance with values of a set of machine learning model parameters, to generate a patient classification that classifies the patient as being included in a patient category from a set of patient categories; determining an uncertainty measure that characterizes an uncertainty of the patient classification generated by the machine learning model; and generating a clinical recommendation for medical treatment of the patient based on: (i) the patient classification, and (ii) the uncertainty measure that characterizes the uncertainty of the patient classification.

公开(公告)号：US11798681B2

公开(公告)日：2023-10-24

申请号：US17960744

申请日：2022-10-05

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Tathagata Banerjee ,  Matthew Edward Kollada

IPC: G16H40/20 ,  G16H50/70 ,  G16H50/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G16H30/40 ,  G06V10/77 ,  G06V10/82 ,  G06V10/774 ,  G06T7/00 ,  G06N20/00

CPC classification number: G16H40/20 ,  G06N3/02 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0016 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G06N20/00 ,  G06T2207/10088 ,  G06T2207/10104 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30016 ,  G06T2207/30104 ,  G06V2201/03

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an encoder neural network and a decoder neural network. In one aspect, a method comprises: updating current values of a set of encoder parameters and current values of a set of decoder parameters using gradients of a reconstruction loss function that measures an error in a reconstruction of multi-modal data from a training example, wherein: the reconstruction loss function comprises a plurality of scaling factors that each scale a respective term in the reconstruction loss function that measures an error in the reconstruction of a corresponding proper subset of feature dimensions of the multi-modal data from the training example.

公开(公告)号：US20220392637A1

公开(公告)日：2022-12-08

申请号：US17740713

申请日：2022-05-10

Applicant: NEUMORA THERAPEUTICS, INC.

Inventor： Matthew Kollada ,  Tathagata Banerjee

IPC: G16H50/20 ,  G16H10/20

Abstract: Methods and systems are provided for diagnosing mental health conditions using multiple data modalities. In particular, a trained machine learning model is used for mental health diagnosis, wherein the trained model utilizes a dynamic fusion approach for capturing and preserving interactions as well as timing information between the multiple data modalities.