semantic web technologies for translational medicine
DESCRIPTION
Semantic Web Technologies for Translational Medicine. Vipul Kashyap, PhD [email protected] Senior Medical Informatician, Clinical Knowledge Management and Decision Support Clinical Informatics R&D, Partners Healthcare System Panel on “Towards a Semantic Web for the Life Sciences?” - PowerPoint PPT PresentationTRANSCRIPT
Semantic Web Technologies for Translational Medicine
Vipul Kashyap, [email protected]
Senior Medical Informatician, Clinical Knowledge Management and Decision Support
Clinical Informatics R&D, Partners Healthcare SystemPanel on “Towards a Semantic Web for the Life Sciences?”
October 24, 2005
Outline• Translational Medicine Use Case
— Translation of Genomic Research Insights into Clinical Care
• Key Functionalities— Data Integration— Actionable Decision Support— Knowledge Update and Propagation
• Semantic Web Technologies— RDF: Resource Description Framework— OWL: Web Ontology Language— SWRL: Semantic Web Rules Language
• Conclusions
Translational Medicine Use Case*:Dr. Genomus Meets Basketball Player Who fainted at Practice
• Clinical exam reveals abnormal heart sounds
• Family History: Father with sudden death at 40,
• 2 younger brothers apparently normal
• Ultrasound ordered based on clinical exam reveals cardiomyopathy
Structured Physical Exam
Structured Family History
Structured Imaging StudyReports
* Use Case provided by Dr. Tonya Hongsermeier
Actionable Decision Support inthe Workflow Context
Echo triggers guidance to screen for possible mutations:- MYH7, MYBPC3, TNN2, TNNI3, TPM1, ACTC, MYL2, MYL3
Knowledge-based Decision Support
Connecting Dx, Rx, Outcomes andPrognosis Data to Genotypic Data for Cardiomyopathy
statisticsapplication
server
statisticsapplication
server
Gene expression in HCM Test Results
MyectomyAtrial Arrhythymi
ER visitsClinic visits
Outcomes calculated every weekSyncopeER visit
microarray (encrypted)
ownershipmanager
encryption
Palpitations
Gene-Chips
populationregistry
databasedatabase
microarray (encrypted)
Ventricular ArrhyICD
Cong. Heart Failure
ER Visit
EKGCardiac Arr
Thalamus
person concept date
Gene-ChipsEchocardio
CardiomyopAtrial Fib.Echocardio
Z5937XZ5937XZ5937XZ5937X
Z5956XZ5956XZ5956XZ5956X
Z5956XZ5956XZ5956XZ5956X
Z5937X
raw value
3/43/43/43/4
3/93/93/93/9
5/25/25/25/2
4/6
A one slide Introduction to RDF/OWLWhat is RDF?
• Resource Description Framework – description of any resource
• Triples <resource, property, value>, e.g., <URI1, “name”, “Mr. X”>
— Nodes: “URI1”, “Mr. X”— Edge: “name”
• Graph based Data Model
• RDF graphs are instances of ontological elements
What is OWL?
• Web Ontology Language – description of knowledge and ontologies of a given domain
• Axioms/constraints capture knowledge about a given domain, e.g.,
— class(Patient), class(Person)— Patient Person
• Lattice Organization
• Axioms/constraints are imposed on underlying RDF Graph instances
• URIs (URLs) are used as identifiers for:• Resources, Properties, Values, Namespaces and Ontological Elements
• Namespaces contain:• Tags for RDF and OWL languages• Ontological elements (classes, properties) that are instantiated by these RDF Graphs• Ontological elements or XML Schema datatypes that are dimensions of identifiers such as LSIDs
Clinical Knowledge
Genomic KnowledgeFigure reprinted withpermission from Cerebra, Inc.
A Strawman Ontology for Translational Medicine
OWL ontologies that blend knowledgefrom the Clinical and Genomic Domains
Data IntegrationDomain Ontologiesfor Translational Medicine
LIMS Data EMR Data
RDF Wrapper RDF Wrapper
RDF Graph 1 RDF Graph 2
Merged RDF Graph
Instantiation
Use of RDF graphs that instantiate these ontologies:-- Rules/semantics-based integration independent of location, method of access or underlying data structures!- Highly configurable, minimize
software coding
Bridging Clinical and Genomic Information“Paternal” 1
type degree
Patient(id = URI1)
“Mr. X”
name
Person(id = URI2)
related_to
FamilyHistory(id = URI3)
has_family_history
“Sudden Death”problem
associated_relative
EMR Data
Patient(id = URI1)
MolecularDiagnosticTestResult(id = URI4)
has_structured_test_result
MYH7 missense Ser532Pro(id = URI5)
identifies_mutation
DialatedCardiomyopathy(id = URI6)
indicates_disease
LIMS Data
Rule/Semantics-based Integration:- Match Nodes with same Ids- Create new links: IF a patient’s structured test result indicates a disease THEN add a “suffers from link” to that disease
90%
evidence
Bridging Clinical and Genomic Information
Patient(id = URI1)
“Mr. X”
name
Person(id = URI2)
related_to
FamilyHistory(id = URI3)
has_family_history
“Sudden Death”problem
“Paternal” 1
type degree
associated_relative
StructuredTestResult(id = URI4)
MYH7 missense Ser532Pro(id = URI5)
identifies_mutation
DialatedCardiomyopathy(id = URI6)
indicates_disease
has_structured_test_result
suffers_from
has_gene
RDF Graphs provide a semantics-rich substrate for decision support. Can be exploited by SWRL Rules
90%
evidence
Actionable Decision Support:using SWRLIF the Patient’s structured test result identifies the mutation MYH7
missense:Ser532Pro with confidence ≥ 90%AND the structured test result is indicative of Dialated CardiomyopathyTHEN Patient suffers from Dialated CardioMyopathy Patient has gene MYH7missense:Ser532Pro Perform DCM monitoring and management protocol on the Patient.
patient(?p) & molecular_diagnostic_test(?t) & has_structured_test_result(?p, ?t) & identifies_mutation(?t, “MYH7 missense:Ser532Pro”) & indicates_disease(?t, “Dialated Cardiomyopathy”) suffers_from(?p, “Dialated Cardiomyopathy”)
has_gene(?p, “MYH7 missense:Ser532Pro)recommended_intervention(“DCM Monitoring and Management”)
Semantic Web Rules Language (SWRL)
• References to ontological concepts and relationships— Describe clinical and genomic information
• Can be used to infer patient state:— Patient has a particular gene/mutation— Patient suffers from a particular disease
• Can be used to recommend clinical care:— Order Monitoring and Management Protocol
patient(?p) & molecular_diagnostic_test(?t) & mutation(?m) & disease(?d)has_structured_test_result(?p, ?t) & identifies_mutation(?t, ?m) & indicates_disease(?t, ?d) & suggested_protocol(?d, ?pro) suffers_from(?p, ?d)
has_gene(?p, ?m)order_protocol(?pro)
Knowledge Update and PropagationIF Molecular Diagnostic reveals MYH7 missense: Ser532Pro or Phe764LeuAND No Structural Heart Disease on EchocardiogramTHEN perform DCM monitoring and management protocol
IF Molecular Diagnostic reveals MYH7 missense: Ser532ProAND No Structural Heart Disease on EchocardiogramTHEN perform late onset of DCM monitoring protocol
If Molecular Diagnostic reveals MYH7 missense Phe764LEUAND No Structural Heart Disease on EchocardiogramTHEN perform early onset of DCM monitoring protocol
• Discovery of New Genotypes• Invention of New Monitoring Protocols• Discovery of Associations between Genotype, Disease and Monitoring Protocols• Modification of Decision Support Rules to Reflect This Modifies resultant RDF graphs generated!
KnowledgeUpdate(Hypothetical)
Knowledge Update and Propagation
• Discovery of New Genotypes• Invention of New Monitoring Protocols• Discovery of Associations between Genotype, Disease and Monitoring Protocols• Modification of Decision Support Rules to Reflect This Modifies resultant RDF graphs generated!
IF Molecular Diagnostic reveals MYH7 missense: Ser532Pro or Phe764LeuAND No Structural Heart Disease on EchocardiogramTHEN perform DCM monitoring and management protocol
IF Molecular Diagnostic reveals MYH7 missense: Ser532ProAND No Structural Heart Disease on EchocardiogramTHEN perform late onset of DCM monitoring protocol
IF Molecular Diagnostic reveals MYH7 missense Phe764LEUAND No Structural Heart Disease on EchocardiogramTHEN perform early onset of DCM monitoring protocol
KnowledgeUpdate(Hypothetical)
Knowledge Update and PropagationGenotype Disease
indicates
MonitoringProtocol
indicatesrecommended_intervention
Rule- genotype_condition- indicates_disease- recommended_intervention
Genotype1 Disease
MonitoringProtocol1
indicates recommended_intervention
Genotype2
indicates
MonitoringProtocol2
indicates
Rule1- genotype_condition- indicates_disease- recommended_interventionRule2- genotype_condition- indicates_disease- recommended_intervention
KnowledgeUpdate
UpdatePropagation
Decision SupportLogic Update
Use of OWL Inferences for:- Keeping knowledge internally consistent- Propagating changes to Dependent Knowledge Artifacts
Updated RDF Graphsare generated fromthis point on!
Conclusions
• Translational Medicine is a knowledge intensive field. The ability to capture semantics of this knowledge is crucial for implementation.
• Personalized Medicine cannot be implemented in an scalable, efficient and extensible manner without Semantic Web technologies
• The rate of Knowledge Updates will change drastically as Genomic knowledge explodes
• Automated Semantics-based Knowledge Update and Propagation will be key in keeping the knowledge updated and current