Systems and methods for predicting therapy efficacy from normalized biomarker scores
Inventors
Bagaev, Alexander • Frenkel, Feliks • Ataullakhanov, Ravshan
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11842797-B2
Publication Date
2023-12-12
Expiration Date
Abstract
Techniques for determining therapy scores for at least two of an anti-PD1 therapy, an anti-CTLA4 therapy, an IL-2 therapy, an IFN alpha therapy, an anti-cancer vaccine therapy, an anti-angiogenic therapy, and an anti-CD20 therapy. The techniques include determining, using sequencing data for the subject and information indicating distribution of biomarker values across one or more reference populations, a first set of normalized biomarker scores for a first set of biomarkers associated with a first therapy; and a second set of normalized biomarker scores for a second set of biomarkers associated with a second therapy; providing the first set of normalized biomarker scores as input to a statistical model to obtain a first therapy score for the first therapy; and providing the second set of normalized biomarker scores as input to the statistical model to obtain a second therapy score for the second therapy.
Core Innovation
The invention provides a system and method for computing therapy scores for therapies in a plurality of therapies for a subject based on sequencing data and biomarker information from at least one database. Sequencing data about at least one biological sample of the subject is obtained, and biomarker information indicating a distribution of values for each biomarker in a reference subset of a plurality of biomarkers is accessed. Each biomarker in the reference subset is associated with at least one therapy.
Using both the sequencing data and the biomarker information, the system determines therapy scores by determining un-normalized biomarker scores and then determining normalized biomarker scores by adjusting the un-normalized biomarker scores to a common scale using the biomarker distributions. The first therapy score is determined using the normalized biomarker scores, and the therapy score indicates the subject's response to administration of the first therapy.
The invention recommends, for the subject, at least one therapy based on the determined therapy scores. The first therapy is selected from the group consisting of an anti-PD1 therapy, an anti-CTLA4 therapy, an IL-2 therapy, an IFN alpha therapy, an anti-cancer vaccine therapy, an anti-angiogenic therapy, and an anti-CD20 therapy, and the first set of biomarkers comprises at least three biomarkers selected from the group of biomarkers associated with the first therapy in Table 2.
Claims Coverage
Independent claim coverage includes the same core computerized scoring and therapy recommendation workflow across the provided claims. The inventive features center on database biomarker distributions linked to therapies, normalization of biomarker scores to a common scale, therapy score computation from normalized biomarker scores, and recommendation of at least one therapy based on the determined therapy scores.
Therapy scoring from sequencing data and database biomarker distributions
Obtaining sequencing data about at least one biological sample of a subject; accessing, in at least one database, biomarker information indicating a distribution of values for each biomarker in a reference subset, with each biomarker associated with at least one therapy; determining therapy scores for at least some therapies using both the sequencing data and the biomarker information.
Normalize biomarker scores to a common scale using biomarker value distributions
Determining normalized biomarker scores by adjusting un-normalized biomarker scores to a common scale using the distributions of values for the biomarkers, and determining a first therapy score for the first therapy using the normalized biomarker scores.
Recommend therapies based on determined therapy scores and therapy-to-biomarker mapping in Table 2
Recommending, for the subject, at least one therapy based on the determined therapy scores, where the first therapy is selected from the group consisting of an anti-PD1 therapy, an anti-CTLA4 therapy, an IL-2 therapy, an IFN alpha therapy, an anti-cancer vaccine therapy, an anti-angiogenic therapy, and an anti-CD20 therapy, and where the first set of biomarkers comprises at least three biomarkers selected from the group of biomarkers associated with the first therapy in Table 2.
Indicate therapy score as indicative of response
The first therapy score indicates the subject's response to administration of the first therapy.
Across the independent claims, the inventive core is computing normalized biomarker scores from sequencing data using database-provided biomarker value distributions, using those normalized biomarker scores to compute therapy scores for therapies such as anti-PD1 and anti-CTLA4, and recommending therapies to the subject based on the computed therapy scores, with biomarker sets constrained by Table 2 mappings.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?