Back to results
US 12,755,820 B2Granted
Systems and methods for predicting hematological conditions using methylation data
AssigneeH. Lee Moffitt Cancer Center and Research Institute, Inc.
InventorsRyan Schenck, Alexander Anderson
Life of this patent
Estimating the term…
Abstract
Systems and methods for predicting hematological conditions using methylation data are described herein. An example computer-implemented method includes: receiving patient data associated with a blood specimen from a subject, the patient data including fluctuating methylation clock (FMC) data; inputting the FMC data into a trained machine learning model; and predicting, using the trained machine learning model, a hematological condition in the subject.
Claims19
A computer-implemented method comprising:
- receiving patient data associated with a blood specimen from a subject, the patient data comprising fluctuating methylation clock (FMC) data including DNA methylation fluctuation data for a plurality of fluctuating CpG (fCpG) sites;
- generating a hematopoiesis model that describes a clonal expansion of a plurality of cells from the blood specimen using the DNA methylation fluctuation data as clocks in the cells to model repeated cycling between methylated and unmethylated states;
- determining, based on a plurality of parameters for normal hematopoiesis, an fCpG variance measure and an fCpG distribution measure for the hematopoiesis model;
- inputting at least a portion of the FMC data into a trained machine learning model, wherein the trained machine learning model is trained using sub-sampled fCpG site data;
- and
- predicting, using the trained machine learning model and based at least in part on the determined fCpG variance measure and fCpG distribution measure, a hematological condition in the subject.
3 more elements
A method comprising:
- receiving a blood specimen from a subject;
- obtaining, using a microarray, fluctuating methylation clock (FMC) data associated with the blood specimen, wherein the FMC data includes DNA methylation fluctuation data for a plurality of fluctuating CpG (fCpG) sites;
- generating a hematopoiesis model that describes a clonal expansion of a plurality of cells from the blood specimen using the DNA methylation fluctuation data as clocks in the cells to model repeated cycling between methylated and unmethylated states;
- determining, based on a plurality of parameters for normal hematopoiesis, an fCpG variance measure and an fCpG distribution measure for the hematopoiesis model;
- inputting, using a computing device, at least a portion of the FMC data into a trained machine learning model, wherein the trained machine learning model is trained using sub-sampled fCpG site data;
- and
- predicting, using the trained machine learning model and based at least in part on the determined fCpG variance measure and fCpG distribution measure, a hematological condition in the subject.
4 more elements
A system comprising:
- at least one processor and a memory operably coupled to the at least one processor, the memory having computer-executable instructions stored thereon that, when executed by the at least one processor, cause the processor to:
- receive patient data associated with a blood specimen from a subject, the patient data comprising fluctuating methylation clock (FMC) data, wherein the FMC data includes DNA methylation fluctuation data for a plurality of fluctuating CpG (fCpG) sites;
- generate a hematopoiesis model that describes a clonal expansion of a plurality of cells from the blood specimen using the DNA methylation fluctuation data as clocks in the cells to model repeated cycling between methylated and unmethylated states;
- determine, based on a plurality of parameters for normal hematopoiesis, an fCpG variance measure and an fCpG distribution measure for the hematopoiesis model;
- input at least a portion of the FMC data into a trained machine learning model, wherein the trained machine learning model is trained using sub-sampled fCpG site data;
- and
- receive, from the trained machine learning model and based at least in part on the determined fCpG variance measure and fCpG distribution measure, a predicted hematological condition in the subject.
4 more elements
Dependencies are inferred from the claim text.