Anton V Valouev

20230045925, Feb 16, 2023

Sep 29, 2022

17/936529

- Menlo Park CA, US
Anton Valouev - Palo Alto CA, US
Darya Filippova - Sunnyvale CA, US
Matthew H. Larson - San Francisco CA, US
M. Cyrus Maher - San Mateo CA, US
Monica Portela dos Santos Pimentel - San Jose CA, US
Robert Abe Paine Calef - Redwood City CA, US
Collin Melton - Menlo Park CA, US

GRAIL, LLC - Menlo Park CA

G16B 30/10
G06N 3/04
G16H 50/20
G16B 40/20
G16B 40/30
G06N 3/08

Classification of cancer condition, in a plurality of different cancer conditions, for a species, is provided in which, for each training subject in a plurality of training subjects, there is obtained a cancer condition and a genotypic data construct including genotypic information for the respective training subject. Genotypic constructs are formatted into corresponding vector sets comprising one or more vectors. Vector sets are provided to a network architecture including a convolutional neural network path comprising at least a first convolutional layer associated with a first filter that comprise a first set of filter weights and a scorer. Scores, corresponding to the input of vector sets into the network architecture, are obtained from the scorer. Comparison of respective scores to the corresponding cancer condition of the corresponding training subjects is used to adjust the filter weights thereby training the network architecture to classify cancer condition.

20210324477, Oct 21, 2021

Apr 19, 2021

17/233548

- Menlo Park CA, US
Anton Valouev - Palo Alto CA, US

C12Q 1/6886
G16B 40/00

A system generates a cancer detection panel. The system is configured to generate an assay having a minimized size and number of genomic regions while still detecting the presence of cancer at or above a specific performance threshold. To select the genomic regions for the panel, the system employs a classification model. The classification model receives a set of genomic regions that may be associated with disease presence. The model then determines a sensitivity score for each genomic region and ranks the regions according to their score. The sensitivity score is based on a likelihood that variations in the genomic region are indicative of cancer. The model then selects genomic regions for the panel based on their rank. The model only selects as many genomic indicators as are needed for desired detection performance. The genomic regions can be associated with solid or liquid cancers, viral regions, or cancer hotspots.

20210115520, Apr 22, 2021

Apr 24, 2019

17/050372

- Menlo Park CA, US
Anton Valouev - Palo Alto CA, US
Seyedmehdi Shojaee - San Francisco CA, US
Oliver Claude Venn - San Francisco CA, US

C12Q 1/6886
G16B 40/20
C12Q 1/70
G16B 20/20
G16B 20/10
G16B 30/10

Methods for screening for a cancer condition in a subject are provided. A biological sample from the subject is obtained. The sample comprises cell-free nucleic acid from the subject and potentially cell-free nucleic acid from a pathogen in a set of pathogens. The cell-free nucleic acid in the biological sample is sequenced to generate a plurality of sequence reads from the subject. A determination is made, for each respective pathogen in the set of pathogens, of a corresponding amount of the plurality of sequence reads that map to a sequence in a pathogen target reference for the respective pathogen, thereby obtaining a set of amounts of sequence reads, each respective amount of sequence reads in the set of amounts of sequence reads for a corresponding pathogen in the set of pathogens. The set of amounts of sequence reads is used to determine whether the subject has the cancer condition.

20200185059, Jun 11, 2020

Dec 10, 2019

16/709537

- Menlo Park CA, US
Anton Valouev - Palo Alto CA, US
Darya Filippova - Sunnyvale CA, US
Virgil Nicula - Cupertino CA, US
Karthik Jagadeesh - San Francisco CA, US
Oliver Claude Venn - San Francisco CA, US
Samuel S. Gross - Sunnyvale CA, US
John F. Beausang - Menlo Park CA, US
Robert Abe Paine Calef - Redwood City CA, US

G16B 30/00
G16B 20/20
G16B 40/00
G16H 70/60
G16H 10/40
G16H 10/60
G16H 50/70
G16H 50/20
G06N 20/00
G06N 5/04

Technical solutions for classifying patients with respect to multiple cancer classes are provided. The classification can be done using cell-free whole genome sequencing information from subjects. A reference set of subjects is used to train classifiers to recognize genomic markers that distinguish such cancer classes. The classifier training includes dividing the reference genome into a set of non-overlapping bins, applying a dimensionality reduction method to obtain a feature set, and using the feature set to train classifiers. For subjects with unknown cancer class, the trained classifiers provide probabilities or likelihoods that the subject has a respective cancer class for each cancer in a set of cancer classes. The present disclosure thus describes methods to improve the screening and detection of cancer class from among several cancer classes. This serves to facilitate early and appropriate treatment for subjects afflicted with cancer.

20200005899, Jan 2, 2020

May 31, 2019

16/428575

- Menlo Park CA, US
Anton Valouev - Palo Alto CA, US
Darya Filippova - Sunnyvale CA, US
Matthew H. Larson - San Francisco CA, US
M. Cyrus Maher - San Mateo CA, US
Monica Portela dos Santos Pimentel - San Jose CA, US
Robert Abe Paine Calef - Redwood City CA, US
Collin Melton - Menlo Park CA, US

G16B 30/10
G16B 40/20
G16B 40/30
G06N 3/04
G06N 3/08
G16H 50/20

Classification of cancer condition, in a plurality of different cancer conditions, for a species, is provided in which, for each training subject in a plurality of training subjects, there is obtained a cancer condition and a genotypic data construct including genotypic information for the respective training subject. Genotypic constructs are formatted into corresponding vector sets comprising one or more vectors. Vector sets are provided to a network architecture including a convolutional neural network path comprising at least a first convolutional layer associated with a first filter that comprise a first set of filter weights and a scorer. Scores, corresponding to the input of vector sets into the network architecture, are obtained from the scorer. Comparison of respective scores to the corresponding cancer condition of the corresponding training subjects is used to adjust the filter weights thereby training the network architecture to classify cancer condition.

20190316209, Oct 17, 2019

Apr 15, 2019

16/384784

- Menlo Park CA, US
Samuel S. Gross - Sunnyvale CA, US
Darya Filippova - Sunnyvale CA, US
Ling Shen - Redwood City CA, US
Oliver Claude Venn - San Francisco CA, US
Alexander Weaver Blocker - Mountain View CA, US
Nan Zhang - Fremont CA, US
Tara Maddala - Sunnyvale CA, US
Alex Aravanis - San Mateo CA, US
Qinwen Liu - Fremont CA, US
Anton Valouev - Palo Alto CA, US
Virgil Nicula - Cupertino CA, US

C12Q 1/6886
G16H 50/30
G16H 50/20
C12Q 1/6806
C40B 40/06
C12Q 1/6869

A predictive cancer model generates a cancer prediction for an individual of interest by analyzing values of one or more types of features that are derived from cfDNA obtained from the individual. Specifically, cfDNA from the individual is sequenced to generate sequence reads using one or more physical assays, examples of which include a small variant sequencing assay, whole genome sequencing assay, and methylation sequencing assay. The sequence reads of the physical assays are processed through corresponding computational analyses to generate each of small variant features, whole genome features, and methylation features. The values of features can be provided to a predictive cancer model that generates a cancer prediction. In some embodiments, the values of different types of features can be separately provided into different predictive models. Each separate predictive model can output a score that can serve as input into an overall model that outputs the cancer prediction.

20190287649, Sep 19, 2019

Mar 13, 2019

16/352739

- Menlo Park CA, US
Anton Valouev - La Canada CA, US
Virgil Nicula - Cupertino CA, US
Karthik Jagadeesh - San Francisco CA, US
M. Cyrus Maher - San Mateo CA, US
Matthew H. Larson - San Francisco CA, US
Monica Portela dos Santos Pimentel - San Jose CA, US
Robert Abe Paine Calef - Redwood City CA, US

G16B 30/10

A system, method and computer program product for analyzing data of high dimensionality (e.g., sequence reads of nucleic acid samples in connection with a disease condition) are provided.