Granted Patent B2

US 12,683,008 · App. 18/319,212 · Granted Jul 14, 2026

Inventors: Hailey B. Lefkofsky (Chicago, IL); Christopher N. Vlangos (Chicago, IL)

Assignee: Tempus AI, Inc.

G16H20/70G16B20/00G16B30/10G16H10/60G16H15/00G16H20/10G16H70/40

Abstract

Claims (56)

1 . A method for generating treatment information for a patient diagnosed with at least one mental health disorder, the method comprising: at a computer system having one or more processors, and memory storing one or more programs for execution by the one or more processors:

a. obtaining molecular data from a multi-gene panel sequencing reaction performed upon a sample from the patient, the molecular data comprising a plurality of nucleic acid sequences, the nucleic acid sequences comprising sequence data from one or more introns, and sequence data from one or more promoter regions;

b. providing:

(1) a first set of clinical data associated with the patient, the first set of clinical data comprising a listing of prior medications and a listing of the one or more diagnoses; and

(2) a first cohort data set, wherein the first cohort data set comprises data from a first cohort of subjects which have been diagnosed with at least one mental health disorder in common with the patient;

c. generating a first report from a therapy engine based on the molecular data, the first set of clinical data, and the first cohort data set, the therapy engine comprising one or more machine learning algorithms (MLAs), and a knowledge database,

wherein the therapy engine uses the knowledge database to identify a target gene and determines an importance score of the target gene based on a plurality of metrics;

wherein the report provides:

(1) a listing of nucleic acid sequences that are associated with the diagnosed mental health disorder of the first cohort and that are identified in the molecular data from the patient;

(2) a list of one or more drugs that may be effective for the patient based on the listing of nucleic acids, and the data in the first cohort data set, and the identified target gene and importance score; and

d. causing the report to be presented to a user

wherein the therapy engine comprises a classifier to identify a drug resistance and wherein the drug resistance is listed on the report.

2 . The method of claim 1 , further comprising:

e. obtaining a second set of clinical data associated with the patient, wherein the second set of clinical data describes clinical activity of the patient subsequent to presentation of the report; and

f. updating the therapy engine with at least a portion of the second set of clinical data.

3 . The method of claim 1 , wherein the one or more introns and one or more promoters are associated with metabolic genes.

4 . The method of claim 1 , wherein the patient is diagnosed with more than one mental health disorder.

5 . The method of claim 1 , wherein the knowledge database comprises:

i. data related to interactions between a specific drug or drugs and one or more nucleic acid sequences associated with drug metabolism;

ii. primary drug metabolic pathway data;

iii. a first cohort data set derived at time 1 from a cohort of subjects, the first cohort data set comprising: drug or drugs used in a treatment, diagnosis before the treatment, treatment outcome; and

iv. drug information data collected from one or more of the following sources: scientific publications; scientific publications; a combination of external sources and/or other proprietary databases or information sources that are either public or available by subscription or upon request; literature sources or novel findings from analyzing a repository of clinical and genetic, genomic, or other-omic information.

6 . The method of claim 5 , wherein at least a portion of the subjects in the cohort were diagnosed with more than one mental health disorder.

7 . The method of claim 5 , wherein the knowledge database further comprises a second cohort data set derived at a time 2 , wherein the second cohort data set comprises information from at least one of the first cohort subjects.

8 . The method of claim 7 , wherein the knowledge database further comprises an Nth cohort data set derived at time N, wherein the Nth cohort data set comprises information from at least one of the previous cohort subjects.

9 . The method of claim 1 , wherein the report further provides supporting information for a drug classification, wherein the drug classification is selected from the list comprising: standard administrations, dosing considerations, additional risks to consider, and contraindications.

10 . The method of claim 1 , wherein the report further provides a listing of drugs associated with the patient diagnosis but which have no known nucleic acid sequence associations.

11 . The method of claim 1 , wherein the listing of prior medications comprises at least one medication dosage.

12 . The method of claim 1 , wherein the listing of prior medications comprises at least one patient response to a medication.

13 . The method of claim 1 , wherein the therapy engine identifies a likely side effect of the drug(s) listed and provides that side effect information on the report.

14 . The method of claim 1 , wherein the therapy engine identifies a recommended dosage of each drug included in the listing of one or more drugs, and provides that dosage information on the report.

15 . The method of claim 1 , wherein the therapy engine identifies a next potential drug recommendation by excluding from the report at least one medication included in the listing of prior medications.

16 . The method of claim 1 , wherein the therapy engine comprises a classifier to identify a sub-type of depression and the mental health disorder the patient is diagnosed with is depression, wherein the sub-type of depression is listed on the report.

17 . The method of claim 1 , wherein the plurality of metrics comprises at least one of a gene/therapy metric, a gene/drug metric, or a correlation strength metric.

18 . A system for generating information about treatment for a patient diagnosed with a mental health disorder, the system comprising:

a. at least one memory; and

b. at least one processor coupled to the at least one memory,

the system configured to cause the at least en one processor to execute instructions stored in the at least one memory to:

i. obtain molecular data from a multi-gene panel sequencing reaction performed upon a sample from the patient, the molecular data comprising a plurality of nucleic acid sequences, the nucleic acid sequences comprising sequence data from one or more introns, and sequence data from one or more promoter regions;

ii. provide;

(1) a first set of clinical data associated with the patient, the first set of clinical data comprising a listing of prior medications and a listing of the one or more diagnoses; and

(2) a first cohort data set, wherein the first cohort data set comprises data from a first cohort of subjects which have been diagnosed with at least one mental health disorder in common with the patient;

iii. generate a first report from a therapy engine based on the molecular data, the therapy engine comprising one or more machine learning algorithms (MLAs), the first set of clinical data, and the first cohort data set, and a knowledge database,

wherein the therapy engine uses the knowledge database to identify a target gene and determines an importance score of the target gene based on a plurality of metrics, and

wherein the report provides: (1) a listing of nucleic acid sequences that are associated with the diagnosed mental health disorder of the first cohort; (2) a list of one or more drugs that may be effective for the patient based on the listing of nucleic acids and the data in the first cohort data set, and the identified target gene and importance score;

iv. cause the report to be presented to a user

wherein the therapy engine comprises a classifier to identify a drug resistance and wherein the drug resistance is listed on the report.

19 . A non-transitory computer readable medium having stored thereon program code instructions that, when executed by a processor, cause the processor to:

i. obtain molecular data from a multi-gene panel sequencing reaction performed upon a sample from the patient, the molecular data comprising a plurality of nucleic acid sequences, the nucleic acid sequences comprising sequence data from one or more introns, and sequence data from one or more promoter regions;

ii. provide (1) a first set of clinical data associated with the patient, the first set of clinical data comprising a listing of prior medications and a listing of the one or more diagnoses; and

(2) a first cohort data set, wherein the first cohort data set comprises data from a first cohort of subjects which have been diagnosed with at least one mental health disorder in common with the patient;

iii. generate a first report from a therapy engine based on the molecular data, the first set of clinical data, and the first cohort data set, the therapy engine comprising one or more machine learning algorithms (MLAs) and a knowledge database,

wherein the therapy ending uses the knowledge database to identify a target gene and determines an importance score of the target gene based on a plurality of metrics, and

wherein the report provides: (1) a listing of nucleic acid sequences that are associated with the diagnosed mental health disorder of the first cohort; (2) a list of one or more drugs that may be effective for the patient based on the listing of nucleic acids, the data in the first cohort data set, and the identified target gene and importance score;

iv. cause the report to be presented to a user

wherein the therapy engine comprises a classifier to identify a drug resistance and wherein the drug resistance is listed on the report.

Assignments (4)

Continuity (6)

References Cited (147)