Neumora Therapeutics, Inc.

Yale University

Blackthorn Therapeutics, Inc.

Theravance Biopharma R&d IP, LLC

William J Martin

Parvez Ahammad

Humberto Andres Gonzalez Cabezas

Yuelu Liu

Monika Sharma Mellem

Pablo Christian Gersberg

John D Murray

Alan Anticevic

Fei Shen

Jacqueline AM Smith

Systems and methods for utilizing machine learning to generate a trans-diagnostic classifier that is operative to concurrently diagnose a plurality of different mental health disorders using a single trans-diagnostic questionnaire that includes a plurality of questions (e.g., 17 questions). Machine learning techniques are used to process labeled training data to build statistical models that include trans-diagnostic item-level questions as features to create a screen to classify groups of subjects as either healthy or as possibly having a mental health disorder. A subset of questions is selected from the multiple self-administered mental health questionnaires and used to autonomously screen subjects across multiple mental health disorders without physician involvement, optionally remotely and repeatedly, in a short amount of time.

Machine learning-based diagnostic classifier

The present tools and methods for detecting, diagnosing, predicting, prognosticating, or treating a neurobehavioral phenotype in a subject. These tools and methods relates to a genotype and neurophenotype topography-based approach for analyzing brain neuroimaging and gene expression maps to identify drug targets associated with neurobehavioral phenotypes and, conversely, neurobehavioral phenotypes associated with potential drug targets, to develop rational design and application of pharmacological therapeutics for brain disorders, and to provide methods and tools for treatment of subjects in need of neurological therapy.

Methods and tools for detecting, diagnosing, predicting, prognosticating, or treating a neurobehavioral phenotype in a subject

The present disclosure relates to computer generated topographies from computer correlations of neurobehavioral phenotype mapping data and gene expression mapping data. Neurobehavioral phenotype mapping data is obtained for a selected phenotype and correlated with gene expression mapping data for one or more genes to define a phenotype-gene pair topography for each phenotype-gene pair. A score for each phenotype-gene pair is determined based on the correlation. The scores are used to identify genes, or drug targets, associated with the respective gene of the respective phenotype-gene pair. Conversely, gene expression mapping data is obtained for a selected gene and correlated with neurobehavioral phenotype mapping data for one or more phenotypes to define a gene-phenotype topography for each gene-phenotype pair. A score for each gene-phenotype pair is determined based on the correlation. The scores are used to identify a phenotype associated with the respective phenotype-gene pair.

Methods and systems for computer-generated predictive application of neuroimaging and gene expression mapping data

Systems and methods for utilizing machine learning to generate a trans-diagnostic classifier that is operative to concurrently diagnose a plurality of different mental health disorders using a single trans-diagnostic questionnaire that includes a plurality of questions (e.g., 17 questions). Machine learning techniques are used to process labeled training data to build statistical models that include trans-diagnostic item-level questions as features to create a screen to classify groups of subjects as either healthy or as possibly having a mental health disorder. A subset of questions are selected from the multiple self-administered mental health questionnaires and used to autonomously screen subjects across multiple mental health disorders without physician involvement, optionally remotely and repeatedly, in a short amount of time.

Growing community of inventors

San Francisco, CA, United States of America

William J Martin