Mining Genotype-Phenotype Associations from Electronic Health Records
and Biorepositories using Semantic Web Technologies
Jyotishman Pathak, PhD Richard C. Kiefer, Robert R. Freimuth, PhD Suzette J. Bielinski, PhD Christopher G. Chute, MD, DrPH
Division of Biomedical Statistics and Informatics, Department of Health Sciences Research
Mayo Clinic, Rochester, MN
Background and Aims
From Relational Data Model to RDF Mapping to Querying via SPARQL
@prefix rr: <http://www.w3.org/ns/r2rml#>.
@prefix mayogc: <http://mayogc/>.
@prefix snomedct: <http://purl.bioontology.org/ontology/SNOMEDCT#>.
@prefix so: <http://purl.org/obo/owl/SO#>.
mayogc:PatientsMap a rr:TriplesMapClass;
rr:tableName "patients_hypothyroidism";
rr:subjectMap [ rr:template "http://patients/{clinicId}" ];
rr:predicateObjectMap [ rr:predicateMap [ rr:predicate snomedct:3982250];
rr:objectMap [ rr:column "clinicId" ] ];
rr:predicateObjectMap [ rr:predicateMap [ rr:predicate mayogc:mayogid ];
rr:objectMap [ rr:column "mayogid" ] ].
The Linked Clinical Data (LCD) project at aims
to develop a semantics-driven framework for
high-throughput phenotype representation,
extraction, integration, and querying from
electronic medical records using emerging
Semantic Web technologies, such as the W3C’s
Linking Open Data project .
The main goals of the LCD project are to:
Investigate ontology-based techniques for
representing and encoding phenotype data
derived from EHRs;
Develop a framework for publishing and
integrating ontology-encoded structured
phenotype data for federated querying using
Linked Data principles and technologies, and
Propose and validate semantic reasoning
techniques to support rapid cohort identification
in chronic diseases.
mayogc:GenesMap a rr:TriplesMapClass;
rr:tableName "patient_genotypes";
rr:subjectMap [ rr:template "http://genes/{patientId}" ];
rr:predicateObjectMap [ rr:predicateMap [ rr:predicate snomedct:3982250];
rr:objectMap [ rr:column "patientId" ] ];
rr:predicateObjectMap [ rr:predicateMap [ rr:predicate so:SO_0000694 ];
rr:objectMap [ rr:column "rsId" ] ];
rr:predicateObjectMap [ rr:predicateMap [ rr:predicate so:SO_0001027 ];
rr:objectMap [ rr:column "genotype" ] ].
 Use an ontology to describe the
columns of the relational database
 Map the model to express the
relationship between nodes/edges
Architecture
Linked Data refers to a set of best practices for
publishing and linking pieces of data,
information and knowledge in the Web.
W3C Linked Open Data project
2007 - 2 billion RDF triples, 2 million links
2011 - 31 billion RDF triples, 504 million links
 Write a SPARQL query
based on the mapping
rsID
rs5219
genotype
T:T
 Client applications send query requests
 Using the Linked Data API, the request is translated into a
federated SPARQL 1.1 query
 Patient data stored in RDBMS are surfaced as an endpoint
 SPARQL queries are automatically translated into SQL
statements using applications, such as Spyder
 Results are returned in XML, RDF or JSON formats
patient_genotypes
patientId
18299403
For more information –
http://informatics.mayo.edu/LCD
patient_demographics
clinicId
18299403
MayogcId
17297
wh_demographics
ClinicNumber
17297
table1Key
RK4748
wh_diagnosis
diagnosis
Type2 diabetes
table2Key
RK4748
 Workflow diagram of how the
data is traversed
Methods
The work proposed in this study is an attempt to use
Semantic Web technologies for integrating patient
clinical data derived from Electronic Health Records
(EHRs) with large-scale genomics data to study
genotype-phenotype associations. This aim is
achieved via:
Linked Data
Core technologies supporting Linked Data:
URIs for identifying entities or concepts,
RDF data model and RDFS/OWL ontologies
for representing, structuring and linking
descriptions of entities as resources,
An endpoint providing access to the resources
through SPARQL queries and
HTTP for retrieving resources or descriptions
of the resources.
SELECT ?ClinicNumber ?Diagnosis
WHERE {
SERVICE <http://edison.mayo.edu:8890/sparql> {
?s1 snomedct:3982250 ?clinicId .
?s1 gc:mayogcid ?mayogcId .
?s2 snomedct:3982250 ?patientId .
?s2 so:SO_0000694 ?rsId .
?s2 so:SO_0001027 ?genotype .
FILTER (?patientId =?clinicId )
}
SERVICE <http://hsrdev02:8890/sparql> {
?s3 mclss: internalKey ?table1Key .
?s3 tmo:TMO_0031 ?Diagnosis .
?s4 mclss: internalKey ?table2Key .
?s4 snomedct:3982250 ?ClinicNumber.
FILTER (?table1Key = ?table2Key ) .
}
FILTER(?ClinicNumber = ?mayogcid) .
FILTER(regex(str(?rsId), "rs5219", "i")) .
FILTER(regex(str(?genotype), “T:T", "i")) .
}
 RDF-based representation of clinical data from
Mayo Clinic EHR systems exposed via multiple
SPARQL endpoints
 Patient demographics, diagnoses, procedures
and medications
 Coded with Meaningful Use terminologies
 RDF-based representation of genetic data from
Mayo Clinic biobank repository exposed via a
SPARQL endpoint
 Patient single nucleotide polymorphism (SNP)
genotype data
 Coded with gene and sequence ontologies
 Federated SPARQL 1.1 queries integrating
genotype data with patient clinical data
 Perform a Phenome-Wide Association Study
(PheWAS) that allows a systematic study of
associations between a number of common
genetic variations and variety of large number
of clinical phenotypes
ClinicNumber
Diagnosis
17297
Rheumatoid arthritis
17297
Type 2 diabetes
7324383
Type 1 diabetes
4115
Celiac disease
4115
Type 2 diabetes
2503570
Type 1 diabetes
 Sample query results
Results: Type 2 Diabetes Mellitus
SNP-disease associations for T2DM
SNP rs5219 within the gene KCNJ11
 A query determines all the individuals having
a SNP associated with Type 2 Diabetes
Mellitus and retrieves the clinical diagnoses
(represented as ICD-9-CM codes) for each
eligible subject
 Using AHRQ’s Clinical Classification
Software, clustering is done for creating a
manageable number of clinically meaningful
categories