Decipher Biosciences, Inc.

Mayo Foundation for Medical Education and Research

University of Michigan

The University of British Columbia

Veracyte Sd, Inc.

Nicholas Erho

Elai Davicioni

Hussam Al-Deen Ashab

Ismael A Vergara Correa

Robert B Jenkins

Shuang Zhao

Felix Y Feng

Anamaria Crisan

Mercedeh Ghadessi

Christine Buerki

Peter Black

Mohammed Alshalalfa

S Laura Chang

Sei-Won Laura Chang

Shuang G Zhao

In some embodiments, a machine learning model may be accessed and used to generate a likelihood score related to a condition. In some embodiments, pre-computed vectors may be derived from a training dataset used to build the machine learning model, and the pre-computed vectors may be used to generate processed data from target data derived from a target sample. The machine learning model may then be used on the processed data to generate the likelihood score related to the condition. As an example, subsets of the training dataset may be randomly selected, and the pre-computed vectors may be derived from the randomly-selected subsets of the training dataset. The pre-computed vectors may be applied to the target data to generate the processed data. In one use case, for example, the target data may be normalized using the pre-computed vectors.

Systems and methods for preprocessing target data and generating predictions using a machine learning model

The present invention relates to methods, systems and kits for the diagnosis, prognosis and the determination of progression of cancer in a subject. The invention also provides biomarkers that define subgroups of prostate cancer, clinically useful classifiers for distinguishing prostate cancer subtypes, bioinformatic methods for determining clinically useful classifiers, and methods of use of each of the foregoing. The methods, systems and kits can provide expression-based analysis of biomarkers for purposes of subtyping prostate cancer in a subject. Further disclosed herein, in certain instances, are probe sets for use in subtyping prostate cancer in a subject. Classifiers for subtyping a prostate cancer are provided. Methods of treating cancer based on molecular subtyping are also provided.

Subtyping prostate cancer to predict response to hormone therapy

Methods, compositions, and kits for identifying individuals who will be responsive to post-operative radiation therapy for treatment of prostate cancer are disclosed. In particular, the invention relates to a genomic signature based on expression levels of DNA Damage Repair genes that can be used to identify individuals likely to benefit from post-operative radiation therapy after a prostatectomy.

Use of genomic signatures to predict responsiveness of patients with prostate cancer to post-operative radiation therapy

The present invention relates to methods, systems and kits for the diagnosis, prognosis, and treatment of bladder cancer in a subject. The invention also provides biomarkers that define subgroups of bladder cancer, clinically useful classifiers for distinguishing bladder cancer subtypes, bioinformatic methods for determining clinically useful classifiers, and methods of use of each of the foregoing. The methods, systems and kits can provide expression-based analysis of biomarkers for purposes of subtyping bladder cancer in a subject. Further disclosed herein, in certain instances, are probe sets for use in subtyping bladder cancer in a subject. Classifiers for subtyping a bladder cancer are provided. Methods of treating bladder cancer based on molecular subtyping are also provided.

Molecular subtyping, prognosis, and treatment of bladder cancer

The present invention relates to methods, systems and kits for the diagnosis, prognosis and the determination of cancer progression of prostate cancer in a subject. The invention also provides clinically useful genomic classifiers for predicting prostate cancer metastasis and identifying tumor aggressiveness. The methods, systems and kits can provide expression-based analysis of biomarkers for purposes of predicting metastatic disease and lethal prostate cancer in a subject. Further disclosed herein, in certain instances, are probe sets for use in predicting prostate cancer metastasis in a subject. Classifiers for predicting prostate cancer metastasis are provided. Methods of treating cancer based on tumor aggressiveness are also provided. The methods and classifiers of the present invention are also useful for predicting early prostate cancer metastasis.

Genetic signatures to predict prostate cancer metastasis and identify tumor aggressiveness

Disclosed herein, in certain instances, are methods, systems and kits for the diagnosis, prognosis and determination of cancer progression of a cancer in a subject. Further disclosed herein, in certain instances, are methods, systems and kits for determining the treatment modality of a cancer in a subject. The methods, systems and kits comprise expression-based analysis of biomarkers. Further disclosed herein, in certain instances, are probe sets for use in assessing a cancer status in a subject.

Cancer diagnostics using biomarkers

Disclosed herein, in certain instances, are methods for the diagnosis, prognosis and determination of cancer progression of a cancer in a subject. Further disclosed herein, in certain instances, are methods for determining the treatment modality of a cancer in a subject. The methods comprise expression-based analysis of non-coding targets and coding targets. Further disclosed herein, in certain instances, are probe sets for use in assessing a cancer status in a subject.

Growing community of inventors

Vancouver, Canada

Nicholas Erho