公开(公告)号：US12191000B2

公开(公告)日：2025-01-07

申请号：US18151197

申请日：2023-01-06

Applicant: Grail, LLC

Inventor： M. Cyrus Maher ,  Anton Valouev ,  Darya Filippova ,  Virgil Nicula ,  Karthik Jagadeesh ,  Oliver Claude Venn ,  Samuel S. Gross ,  John F. Beausang ,  Robert Abe Paine Calef

IPC: G16B30/00 ,  G06N5/04 ,  G06N20/00 ,  G16B20/20 ,  G16B40/00 ,  G16H10/40 ,  G16H10/60 ,  G16H50/20 ,  G16H50/70 ,  G16H70/60

Abstract: 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.

公开(公告)号：US20240321389A1

公开(公告)日：2024-09-26

申请号：US18605798

申请日：2024-03-14

Applicant: GRAIL, LLC

Inventor： Alexander W. Blocker ,  Earl Hubbell ,  Oliver Claude Venn ,  Qinwen Liu

IPC: G16B20/20 ,  C12Q1/6869 ,  G06F17/10 ,  G16B5/20 ,  G16B15/00 ,  G16B30/10 ,  G16B40/00

CPC classification number: G16B20/20 ,  C12Q1/6869 ,  G06F17/10 ,  G16B5/20 ,  G16B15/00 ,  G16B30/10 ,  G16B40/00

Abstract: A processing system uses a Bayesian inference based model for targeted sequencing or variant calling. In an embodiment, the processing system generates candidate variants of a cell free nucleic acid sample. The processing system determines likelihoods of true alternate frequencies for each of the candidate variants in the cell free nucleic acid sample and in a corresponding genomic nucleic acid sample. The processing system filters or scores the candidate variants by the model using at least the likelihoods of true alternate frequencies. The processing system outputs the filtered candidate variants, which may be used to generate features for a predictive cancer or disease model.

公开(公告)号：US20240271221A1

公开(公告)日：2024-08-15

申请号：US18417800

申请日：2024-01-19

Applicant: GRAIL, LLC

Inventor： Matthew Larson ,  Archana Shenoy ,  Sarah Stuart ,  Kelly McClintock ,  Siddhartha Bagaria

IPC: C12Q1/6886 ,  A61K45/06 ,  C12N15/10 ,  C12Q1/34 ,  C12Q1/6806 ,  C12Q1/6809 ,  C12Q1/6844 ,  C12Q1/6874 ,  G16H50/20

CPC classification number: C12Q1/6886 ,  A61K45/06 ,  C12N15/1006 ,  C12N15/1017 ,  C12Q1/34 ,  C12Q1/6806 ,  C12Q1/6809 ,  C12Q1/6844 ,  C12Q1/6874 ,  G16H50/20 ,  C12Q2600/112 ,  C12Q2600/154 ,  G01N2333/978

Abstract: In various aspects, the present disclosure provides methods, compositions, reactions mixtures, kits, and systems for analysis of cell-free nucleic acid molecules (e.g., cfRNA and/or cfDNA) from a urine sample. In some embodiments, the analysis is an analysis of methylation patterns in target genomic regions among cfDNA fragments in a urine sample. In some embodiments, compositions include a plurality of different bait oligonucleotides. Methods for the detection of cancer of various cancer types are also provided.

公开(公告)号：US20240212848A1

公开(公告)日：2024-06-27

申请号：US18523660

申请日：2023-11-29

Applicant: GRAIL, LLC

Inventor： M. Cyrus MAHER

IPC: G16H50/20 ,  C12Q1/6886 ,  G06F18/2115 ,  G16H50/30 ,  G16H50/70

CPC classification number: G16H50/20 ,  G06F18/2115 ,  G16H50/30 ,  G16H50/70 ,  C12Q1/6886

Abstract: Systems and methods for classifier training are provided. A first dataset is obtained that comprises, for each first subject, a corresponding plurality of bin values, each for a bin in a plurality of bins, and subject cancer condition. A feature extraction technique is applied to the first dataset thereby obtaining feature extraction functions, each of which is an independent linear or nonlinear function of bin values of the bins. A second dataset is obtained comprising, for each second subject, a corresponding plurality of bin values, each for a bin in the plurality of bins and subject cancer condition. The plurality of bin values of each corresponding subject in the second plurality are projected onto the respective feature extraction functions, thereby forming a transformed second dataset comprising feature values for each subject. The transformed second dataset and subject cancer condition serves to train a classifier on the cancer condition set.

公开(公告)号：US20240084396A1

公开(公告)日：2024-03-14

申请号：US18471025

申请日：2023-09-20

Applicant: GRAIL, LLC

Inventor： Samuel S. GROSS ,  Oliver Claude Venn ,  Seyedmehdi Shojaee ,  John Beausang ,  Arash Jamshidi

IPC: C12Q1/6886 ,  C12Q1/6869

CPC classification number: C12Q1/6886 ,  C12Q1/6869 ,  G16B30/10

Abstract: The present description provides a cancer assay panel for targeted detection of cancer-specific methylation patterns. Further provided herein are methods of designing, making, and using the cancer assay panel for the diagnosis of cancer.

公开(公告)号：US11929148B2

公开(公告)日：2024-03-12

申请号：US16816918

申请日：2020-03-12

Applicant: GRAIL, LLC

Inventor： Darya Filippova ,  Matthew H. Larson ,  M. Cyrus Maher ,  Monica Portela dos Santos Pimentel ,  Robert Abe Paine Calef

IPC: G16B30/00 ,  C12Q1/6886 ,  G06N20/00 ,  G16B20/10 ,  G16H10/40 ,  G16H10/60 ,  G16H50/20 ,  G16H50/50 ,  G16H50/70

CPC classification number: G16B30/00 ,  C12Q1/6886 ,  G06N20/00 ,  G16B20/10 ,  G16H10/40 ,  G16H10/60 ,  G16H50/20 ,  G16H50/50 ,  G16H50/70 ,  C12Q2600/112

Abstract: Systems and methods for determining a cancer class of a subject are provided in which a plurality of sequence reads, in electronic form, are obtained from a biological sample of the subject. The sample comprises a plurality of cell-free DNA molecules including respective DNA molecules longer than a threshold length of less than 160 nucleotides. The plurality of sequence reads excludes sequence reads of cell-free DNA molecules in the plurality of cell-free DNA molecules longer than the threshold length. The plurality of sequence reads is used to identify a relative copy number at each respective genomic location in a plurality of genomic locations in the genome of the subject. The genetic information about the subject obtained from the sample and the genetic information consisting of the identification of the relative copy number at each respective genomic location, is applied to a classifier that determines the cancer class of the subject.

公开(公告)号：US11884966B2

公开(公告)日：2024-01-30

申请号：US16354799

申请日：2019-03-15

Applicant: GRAIL, LLC

Inventor： Yuk-Ming Dennis Lo ,  Rossa Wai Kwun Chiu ,  Kwan Chee Chan ,  Wanxia Gai ,  Lu Ji

IPC: C12Q1/68 ,  C12Q1/6823 ,  C12Q1/6886

CPC classification number: C12Q1/6823 ,  C12Q1/6886 ,  C12Q2600/112 ,  C12Q2600/118 ,  C12Q2600/154 ,  C12Q2600/156 ,  C12Q2600/158 ,  C12Q2600/172

Abstract: Provided herein are compositions comprising tissue-specific markers for identifying a tissue of origin of a cell-free nucleic acid, e.g., a cell-free DNA molecule. Also provided herein are methods, compositions, and systems for identifying a tissue of origin of a cell-free nucleic acid by determining an absolute amount of cell-free nucleic acids comprising the tissue-specific marker. Also provided herein are methods, compositions, and systems for detecting a cancer in a tissue of an organism by analyzing tissue-specific markers.

公开(公告)号：US11869661B2

公开(公告)日：2024-01-09

申请号：US16881928

申请日：2020-05-22

Applicant: GRAIL, LLC

Inventor： M. Cyrus Maher

IPC: G16H50/20 ,  G16H50/70 ,  G16H50/30 ,  G06F18/2115 ,  C12Q1/6886

CPC classification number: G16H50/20 ,  G06F18/2115 ,  G16H50/30 ,  G16H50/70 ,  C12Q1/6886

Abstract: Systems and methods for classifier training are provided. A first dataset is obtained that comprises, for each first subject, a corresponding plurality of bin values, each for a bin in a plurality of bins, and subject cancer condition. A feature extraction technique is applied to the first dataset thereby obtaining feature extraction functions, each of which is an independent linear or nonlinear function of bin values of the bins. A second dataset is obtained comprising, for each second subject, a corresponding plurality of bin values, each for a bin in the plurality of bins and subject cancer condition. The plurality of bin values of each corresponding subject in the second plurality are projected onto the respective feature extraction functions, thereby forming a transformed second dataset comprising feature values for each subject. The transformed second dataset and subject cancer condition serves to train a classifier on the cancer condition set.

公开(公告)号：US11795513B2

公开(公告)日：2023-10-24

申请号：US17832375

申请日：2022-06-03

Applicant: GRAIL, LLC

Inventor： Samuel S. Gross ,  Oliver Claude Venn ,  Seyedmehdi Shojaee ,  John Beausang ,  Arash Jamshidi

IPC: C12Q1/6886 ,  C12Q1/6869 ,  G16B30/10 ,  G16B5/00 ,  G16B40/00 ,  G16B25/20 ,  G16B20/00 ,  G16B40/20

CPC classification number: C12Q1/6886 ,  C12Q1/6869 ,  C12Q2600/154 ,  G16B5/00 ,  G16B20/00 ,  G16B25/20 ,  G16B30/10 ,  G16B40/00 ,  G16B40/20

Abstract: The present description provides a cancer assay panel for targeted detection of cancer-specific methylation patterns. Further provided herein are methods of designing, making, and using the cancer assay panel for the diagnosis of cancer.

公开(公告)号：US20230170048A1

公开(公告)日：2023-06-01

申请号：US18151197

申请日：2023-01-06

Applicant: Grail, LLC

Inventor： M. Cyrus MAHER ,  Anton VALOUEV ,  Darya FILIPPOVA ,  Virgil NICULA ,  Karthik JAGADEESH ,  Oliver Claude VENN ,  Samuel S. GROSS ,  John F. BEAUSANG ,  Robert Abe Paine CALEF

IPC: G16B30/00 ,  G16B20/20 ,  G16B40/00 ,  G16H70/60 ,  G06N5/04 ,  G16H10/60 ,  G16H50/70 ,  G16H50/20 ,  G06N20/00 ,  G16H10/40

CPC classification number: G16B30/00 ,  G06N5/04 ,  G06N20/00 ,  G16B20/20 ,  G16B40/00 ,  G16H10/40 ,  G16H10/60 ,  G16H50/20 ,  G16H50/70 ,  G16H70/60

Abstract: 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.