# US 2016/0259847 A1 · Method of knowledge extraction through data mining

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0259847 A1
- Document ID: US20160259847A1
- Status: Published application
- Kind: A1
- Application number: 15/022,808
- Filed: 2014-08-08
- Published: 2016-09-08
- Earliest claimed: 2013-08-08
- Assignees: SystaMedic Inc.
- Applicants: SystaMedic Inc.
- Inventors: Anton F. FLIRI; William T. LOGING; Robert A. VOLKMANN
- Web page: https://patentgrep.com/patent/US20160259847A1

## CPC

- G06F 16/334: Query execution (filtering based on additional data G06F16/335)
- G06F 16/248: Presentation of query results
- G06F 16/358: Browsing; Visualisation therefor
- G06Q 10/063: Operations research, analysis or management
- G06Q 10/067: Enterprise or organisation modelling
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G16H 70/00: ICT specially adapted for the handling or processing of medical references
- G16H 70/40: relating to drugs, e.g. their side effects or intended usage
- G16Z 99/00: Subject matter not provided for in other main groups of this subclass
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16Z: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR

## Abstract

The disclosed embodiments relate to data mining methods for determining economically valuable cause effect relationships between objects and properties associated with objects using co-occurrence frequency measurements of semantic terms characterizing observations of properties, effects or behaviors of objects in different environments and using these measurements as object descriptors in calculations determining object similarities. Specifically, these methods may be used to identify new indications of medicines, identify biomarkers associated with disease, identify biomarkers associated with drug effects, quantify disease diagnosis, identify novel drug targets, identify pharmacologic equivalencies of medicines, identify pharmacologic equivalencies between medicines and traditional medicines, identify pharmacologic equivalencies between medicines and Natural products, identify equivalencies between alternate medical procedures, identify risk benefit profiles of medicine combinations, identify targets for antibodies, identify synergies between medicines, identify Side effects of medicines, identify risks of experimental medicines, identify functions of biological networks.

## Claims

### Claim 1

A data mining method comprising:
a first step comprising selecting, via a computer user interface, a list of objects and the synonyms for each of the selected objects,
a second step comprising selecting a set of semantic descriptors of observations of said objects
a third step comprising determining, using a computer processor, a co-occurrence frequency of said semantic descriptors identifying said selected objects and the said semantic descriptors identifying said observations in a data base,
a fourth step comprising summing up, using the computer processor, said co-occurrence frequency information for synonyms for said objects,
a fifth step comprising using the computer processor to construct co-occurrence frequency data bases wherein, the semantic terms identifying said objects are denoted either as rows or as columns in said databases providing either row or column identifiers in said database and wherein the semantic terms identifying said observations are either denoted as columns or as rows in said database providing either column or row identifiers in said data bases providing when objects are denoted as rows in said databases than said observations must be entered as columns in said data base or vice versa,
a sixth step comprising recording, using the computer processor, said co-occurrence frequency information at the intersections of said row identifiers with said columns identifiers in said data bases or each of the said selected objects and each of the said selected observations,
a seventh step comprising:
a step (7.1) comprising using the computer processor to select a first subset of co-occurrence frequency measurements associated with a first set of observations associated with a first set of selected objects,
a step (7.2) comprising using the computer processor to select a method for determining similarities between said co-occurrence frequency measurements associated with said objects and said observations,
a step (7.3) comprising using the computer processor to select a similarity measure for comparing said co-occurrence frequency measurements associated with said objects,
a step (7.4) comprising causing the computer processor to use the method selected in step (7.2) and the similarity measure selected in step (7.3) and the co-occurrence frequency measurements selected in step (7.1) to determine similarities between said objects,
an eighth step comprising:
a step (8.1) comprising using the computer processor to select co-occurrence frequency measurements associated with a second to nth set of observations associated with the first selected set of said objects and use of said other co-occurrence frequency measurements as second to nth descriptor sets of said selected objects,
a step (8.2) comprising causing the computer processor to use the method selected in step (7.2) and the similarity measure selected in step (7.3) and the co-occurrence frequency measurements selected in step (8.1) to determine similarities between said objects,
a ninth step comprising using the computer user interface to display similarity measures for said objects obtained with said sets of said descriptors,
a tenth step comprising using the computer processor to compare said similarity measures derived from co-occurrence frequency information associated with said set of observations associated with said selected objects.
an eleventh step comprising using the computer processor for determining correlations between similarity measures for said sets of selected observations associated with said selected objects, and
a twelfth step comprising:
a step (12.1) comprising using the computer processor to select observation groupings in said sets of said object associated observation for selected objects
a step (12.2) comprising using the computer processor to identify similarity measures associated with said object associated observation groupings
a step (12.3) comprising using the computer processor to determine correlations between said similarity measures for said groupings for said selected objects; and
a step (12.4) comprising using the computer user interface to display the correlations between said similarity measures for said groupings for said selected objects.

### Claim 2 (depends on 1)

A method of claim 1 wherein the finite list of objects is selected from the group consisting of diseases, plants, proteins, genes, effects, microorganism, medicinal herbs, herbal extracts, remedies used in traditional medicine, GRAS substances, in vivo assays, members of social network groups, business enterprises, members of communities.

### Claim 3 (depends on 1)

A method of claim 1 wherein the finite list of objects comprises objects of composition of matter and the pertinent synonyms for each of the selected objects.

### Claim 4 (depends on 1)

A method of claim 1 wherein the finite list of objects is selected from the group consisting of pharmacologically active substances, natural products, prescription medicines, GRAS substances, proteins, genes, and RNA.

### Claim 5 (depends on 1)

A method of claim 1 wherein the finite list of object associated observations is selected from the group consisting of semantic descriptors of properties of matter, actions on composition of matter, activities of composition of matter, functions of composition of matter, physical properties of composition of matter, physicochemical properties of composition of matter, chemical structure features of composition of matter, utilities of composition of matter, economic value of composition of matter, method of manufacture, interactions with biological systems, effects on behavior of organism, modulation of behavior of organisms, interaction with cellular components of organisms, effects on cellular components of organisms, pharmacological effects in organisms, effects on physical activities of organisms, modulation of organism functions, toxicity in mammals, effects on ecological systems, effects on organ systems, effects on living organisms, effects on the environment, effects on disease, effects on social interactions, effects on information processing, effects on society, effects on commercial transactions, effects on information transmission, effects on machines, clinical utility, therapeutic indications, economic value of social transactions, costs, selling price, price of manufacture, origin of manufacture.

### Claim 6 (depends on 1)

A method of claim 1 wherein the finite list of observations is selected from the group consisting of disease symptoms, preclinical drug effect observations, effects in in vivo models of disease, clinical drug effects, modulation of protein interactions, modulation of protein functions, modulation of cellular function, modulation of gene expression profiles, modulation of RNA expression profiles, modulation of protein expression profiles, modulation of gene expression profiles, interactions with biological systems, effects on behavior of organism, modulation of behavior of organisms, interaction with cellular components of organisms, effects on cellular components of organisms, pharmacological effects in organisms, effects on physical activities of organisms, modulation of organism functions, toxicity in mammals, effects on organ systems.

### Claim 7 (depends on 1)

A method of claim 1 wherein the method for determining similarities between selected observations is an Unweighted Pair Group Method with Arithmetic Mean hierarchical clustering method PGA.

### Claim 8 (depends on 1)

A method of claim 1 wherein the similarity measure is cosine correlation.

### Claim at position 9

-21. (canceled)

### Claim 22 (depends on 1)

The use of the method of claim 1 for determining cause effect relationship of medicines.

### Claim 23 (depends on 1)

The use of the method of claim 1
for determining new indications of medicines.

### Claim 24 (depends on 1)

The use of the method of claim 1 for identifying biomarkers associated with disease.

### Claim 25 (depends on 1)

The use of the method of claim 1 for identifying biomarkers associated with drug effects.

### Claim 26 (depends on 1)

The use of the method of claim 1, for the diagnosis of disease.

### Claim 27 (depends on 1)

The use of the method of claim 1 for identifying novel drug targets.

### Claim 28 (depends on 1)

The use of the method of claim 1 for identifying pharmacologic equivalencies of medicines.

### Claim 29 (depends on 1)

The use of the method of claim 1
for identifying pharmacologic equivalencies of medicines and traditional medicines.

### Claim 30 (depends on 1)

The use of the method of claim 1 for identifying pharmacologic equivalencies of medicines and Natural products.

### Claim 31

(canceled)

### Claim 32 (depends on 1)

The use of the method of claim 1 for identifying risk benefit profiles of medicine combinations.

### Claim 33 (depends on 1)

The use of the method of claim 1 for identifying targets for antibodies.

### Claim 34 (depends on 1)

The use of the method of claim 1 for identifying synergies between medicines.

### Claim 35 (depends on 1)

The use of the method of claim 1 for identifying Side effects of medicines.

### Claim 36 (depends on 1)

The use of the method of claim 1 for identifying risks of experimental medicines.

### Claim at position 25

-61. (canceled)
