Post on 26-Jan-2015
description
The Translational Medicine Ontology and Knowledge Base: Using Semantic Web Technology in Personalized Medicine for Data Integration
Joanne S. Luciano Research Associate Professor Tetherless World Constellation Rensselaer Polytechnic Institute, Troy, NY USA
Translational Medicine
“...the process by which the results of research done in the laboratory are directly used to develop new ways to treat patients and research done outside the laboratory is used to inform laboratory research”
World Wide Web
• World Wide Web (WWW) - a system of extensively interlinked hypertext documents
• HTML Hype-Text Markup Language - the standard protocol for formatting and displaying documents on the world Wide web.
• Hyper-Text Transfer Protocol (HTTP) - a protocol to transfer hypertext requests and information between servers and browsers.
http://dictionary.reference.com/
Semantic Web
• Giant Global Graph (GGG) the content plus pointers transitioning to content plus pointers plus relationships plus descriptions.
• Starting with RDF, OWL and SPARQL.
• Not magic bullets, but the tools which allow us to break free of the document layer.
http://dictionary.reference.com/browse/www http://dig.csail.mit.edu/breadcrumbs/node/215
Personalized Medicine
• We are moving towards a system of personalized medicine.
• This requires more data availability and smarter systems on all sides.
• NOW IMAGINE – if data were as easily accessible as web pages
Assembly of Knowledge
• Identify it • Access it • Get it • Assemble it • Make sense
out of it DataQueries
AD patient scenario
(timeline)
TMOOntology
Existing Ontologies
(OBO, RO, BFO)
Existing DataAdditional Data needed for Use Case
Semantic Extensions
described with
provides focus for
InitialQuery
Sketches
motivated by
FinalExecutableQueries
applied to
Top down
Bottom-up
Medical Experts
(serving a Role)
identify relevant concepts
Personalized Medicine Questions are Complex
• Understand disease heterogeneity • Comprehend disease progression • Determine genetic and environmental contributors • Create treatments against relevant targets
– Drugs against relevant targets (molecular structures) – Yoga against stress – Exercise against obesity – Elimination diet against food intolerance or allergy
• Develop markers to predict response • Identify concrete endpoints to measure response
Personalized Medicine Data are Complex
Need an integrative data environment to answer scientific questions
– Patient data • Genetics, epigenetics, expression,
environment, phenotype, demographic – Treatment data
• Existing drugs, mechanisms of action – Disease data
• Human and animal models – Standard of care
• Diagnostic guidelines
Data split up in many different places (bug or feature?)
W3C’s HCLS Interest Group
Mission: …use of Semantic Web technologies for health care and life science, with focus on … translational medicine. These domains stand to gain tremendous benefit …as they depend on the interoperability of information from many domains and processes for efficient decision support.
Participants
Bosse Andersson, AstraZeneca Colin Batchelor, RSC Olivier Bodenreider, NIH Tim Clark, HMS Christi Denney, Eli Lilly Christopher Domarew, Albany Medical
Center Michel Dumontier, Carleton University Thomas Gambet, W3C Lee Harland, Pfizer Anja Jentzsch, Free University Berlin Vipul Kashyap, Cigna Peter Kos, HMS Julia Kozlovsky, AstraZeneca Timothy Lebo, RPI Joanne Luciano, RPI
Scott Marshall, Leiden University Medical Center
Jim McCusker, RPI Deborah McGuiness, RPI Jim McGurk, Daiichi Sankyo Chimezie Ogbuji, Cleveland Clinic Elgar Pichler, AstraZeneca Bob Powers, Predictive Medicine Eric Prud'hommeaux, W3C Matthias Samwald, DERI Lynn Schriml, University of Maryland Susie Stephens, Johnson & Johnson
Pharmaceutical R&D Peter Tonellato, HMS Trish Whetzel, Stanford Jun Zhao, Oxford University
Alzheimer’s Disease Scenario 1
• Patient visits clinician who enters symptoms into EHR.
• Physician does a differential diagnosis with working diagnosis of AD.
• Physician arranges for a battery of tests, all entered into EHR.
Mapping Terms to Existing Ontologies
Identify key terms and look for standard ontology that contains that term
In Patient Scenario Step 1, map the word “patient" to the “patient role” in the Ontology for Biomedical Investigation (OBI) ontology [OBI:0000093] “Physician” to the NCI Thesaurus term “Physician”
Translational Medicine Knowledge Base
Terms (ontologies)
Translation (linking)
Data
Discovery Questions and Answers
What genes are associated with or implicated in AD?
Diseasome and PharmGKB indicate at least 97 genes have some association with AD.
Which SNPs may be potential AD biomarkers?
PharmGKB reveals 63 SNPs.
Which market drugs might potentially be repurposed for AD because they modulate AD implicated genes?
57 compounds or classes of compounds are used to treat 45 diseases, including AD, diabetes, obesity, and hyper/hypotension
Questions Answers
Clinical Trials Questions and Answers
Since my patient is suffering from drug-induced side effects for AD treatment, can an AD clinical trial with a different mechanism of action be identified?
Of the 438 drugs linked to AD trials, only 58 are in active trials and only 2 (Doxorubicin and IL-2) have a documented mechanism of action. 78 AD-associated drugs have an established MOA.
Find AD patients without the APOE4 allele as these would be good candidates for the clinical trial involving Bapineuzumab?
Of the 4 patients with AD, only one does not carry the APOE4 allele, and may be a good candidate for the clinical trial.
What active trials are ongoing that would be a good fit for Patient 2?
58 Alzheimer trials, 2 mild cognitive impairment trials, 1 hypercholesterolaemia trial, 66 myocardial infarction trials, 46 anxiety trials, and 126 depression trials.
Questions Answers
Physician Questions and Answers
What are the diagnostic criteria for AD?
There are 12 diagnostic inclusion criteria and 9 exclusion criteria
Does Medicare D cover Dopenezil?
Medicare D covers two brand name formulations of Donepezil: Aricept and Aricept ODT.
Have any AD patients been treated for other neurological conditions?
Patient 2 was found to suffer from AD and depression.
Questions Answers
Summary The data landscape for personalized medicine is
highly fragmented Many domain specific terminologies and ontologies
exist Enabled connection of domain specific ontologies
through a high level BFO compliant ontology A TMKB has been created that demonstrates the
proof of concept Make your data as accessible as web pages.
See the CSHALS or Data.Gov
Thank you! • Paper: TMO/TMKB (in press): http://bit.ly/fjPV5g
http://www.w3.org/wiki/HCLSIG/PharmaOntology/Publications • Ontology: http://bit.ly/hJ7r4W
http://code.google.com/p/translationalmedicineontology/ • Use Cases: (Scenarios) http://bit.ly/evVtmt
http://www.w3.org/wiki/HCLSIG/PharmaOntology/UseCases • Knowledge Base: http://bit.ly/ef2WLJ
http://www.w3.org/wiki/HCLSIG/PharmaOntology/TMKB • Wiki: http://www.w3.org/wiki/HCLSIG/PharmaOntology • Conference on Semantics in Health Care and Life Science
(CSHALS): http://www.iscb.org/cshals2011 • Semantic Health Care and Life Science Tutorial:
http://sparql.tw.rpi.edu/
Backup Slides
• Physician performs cognitive tests and confirms AD diagnosis.
• Physician selects appropriate drug, aided by the ontology.
• Physician prescribes a drug.
• Physician has follow-up visit.
Alzheimer’s Disease Scenario 2
• Physician may investigate various clinical trials for the patient.
• Physician may enroll patient in trial.
• Patient record updated.
Alzheimer’s Disease Scenario 3
TMO Query
How many patients experienced side effects while taking Donepezil?
This is a graphic representation of the question
TM Ontology Overview
Data Sources
• Disparate data sources – clinicaltrials.gov, DailyMed, Diseaseome,
DrugBank, LinkedCT, Medicare, SIDER • Constructed AD diagnostic criteria. • Seven synthetic patient records.
– Demographic, contact, family, life style, allergies, etc.
– Typical of a patient record
Future Directions
• Expand patient record representation • Develop the representation of genetic
variation and pharmacogenetics • Investigate animal models for disease
and capture treatment outcomes • Explore integration with i2b2/
tranSMART
Data Challenges • Patient data split across eHRs, clinical trial systems,
genetic testing vendors, and longitudinal studies • Drug information split across systems such as the
Orange Book, DrugBank, ClinicalTrials.gov, DailyMed, SIDER, PharmGKB, formulary lists
• Disease information split across OMIM, GEO, commercial databases
• Different data representation approaches used by different communities
• No unifying schema to pull data together