Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Formalizing knowledge and
evidence about potential
drug-drug interactions
Jodi Schneider1, Mathias Brochhausen2,
Samuel Ro...
Potential Drug-Drug Interaction
(PDDI)
• Co-prescription or co-administration of two
drugs known to interact.
• Preventabl...
There is substantial disagreement
in PDDI evidence sources
• 4 clinically oriented drug information compendia agreed
on on...
Goal: Make disagreements and
discrepancies visible
• Did compendium A and compendium B
consider the same evidence?
• Cite ...
Overall project goals
• Support drug information compendia editors
who review PDDI evidence.
• More easily integrate and c...
Update an existing knowledge base
• The old knowledge base, DIKB-old, has:
– PDDI claims & evidence collected in prior wor...
Requirements
1. Distinguish between:
– a drug drug interaction
(an actual occurrence in a patient)
– a potential drug drug...
Main idea
• Formalize claims
• Use new ontologies
– Nanopublications
– Micropublications
– Updated OBO Foundry ontologies,...
Process
• Collaborate with an evidence workgroup
– includes 4 pharmacology experts:
Carol Collins, Amy Grizzle, Lisa Hines...
USING NEW METHODS TO
FORMALIZE PDDI CLAIMS AND
EVIDENCE
1. Respect clinically-relevant
distinctions
• Observed
– PDDI evidence derived from an in vivo study
• Inferred
– PDDI Cla...
2. Pull in external knowledge
• Compatible with OBO Foundry
• Reuse identifiers:
– ChEBI - Chemical Entities of Biological...
3. Use nanopublications (NP)
13
assertion
provenance
publication info
nanopublication
Based on http://nanopub.org/wordpres...
assertion
prov:generatedAtTime
prov:hadMember
prov:wasAttributedTo
prov:wasDerivedFrom
DIKB nanopublication
prov:generated...
15
4. What about the EVIDENCE?
DATA?
Kantola, T., Kivistö, K. T., & Neuvonen, P. J. (1998). Erythromycin and verapamil
con...
Model the evidence with the
Micropublications Ontology
A claim is supported by methods, materials, and
data:
– MP:Claim
– ...
MP is complementary to NP
MP NP
• Publishable
• Citable
• Use provenance
17
• Publishable
• Citable
• Use provenance
MP is complementary to NP
MP NP
• Publishable
• Citable
• Use provenance
• Logical structure
18
• Publishable
• Citable
• ...
We link MP and NP
• We extended the MP ontology to add two
new properties:
– MP:formalizedAs
– MP:formalizes
• NP <formal ...
ddi:ddi-spl-annotation-np-assertion-314 a np:assertion,
owl:Class ;
rdfs:label "erythromycin - simvastatin potential drug-...
MP:Claim
Building up an MP graph
Building up an MP graph
Building up an MP graph
Building up an MP graph
Building up an MP graph
Building up an MP graph
Building up an MP graph
Building up an MP graph
Building up an MP graph
OUTLOOK
Future Work
• Can clinicians quickly identify the rationale for any
given knowledge claim, using the DIKB?
• Are MP’s easy...
Thanks!
• Carol Collins, Amy Grizzle, Lisa Hines, Harry
Hochheiser, and John R Horn
• ERCIM “Alain Bensoussan” Fellowship
...
Data is publicly available
• Nanopublication and Micropublication graphs
http://purl.org/net/drug-interaction-knowledge-
b...
Silos of PDDI knowledge claims
Scientific literatureProduct labeling Clinical experience
Evidence of PDDI knowledge claims is
distributed across multiple sources
Pre-market studies Post-market studies
Product la...
Efficiency and scalability from
structured publication
Claim
Support
Reference
• Drug4X4interacts4with4drug4Y
• Drug4X4inh...
Facts in the evidence base are used
for reasonable extrapolation…
erythromycin
obo:CHEBI_48923
CYP3A4
obo:PR_000006130
sim...
Making an inference
Evidence(Base
"erythromycin,inhibits,CYP3A4."
"CYP3A4,catalyzes,a,Phase,I,or,
Phase,II,enzymatic,react...
Micropublication Ontology (MP)
Clark, T., Ciccarese, P., Goble, C.: Micropublications: a semantic model for claims, eviden...
DIKB micropublication graph for
the erythromycin - simvastatin
interaction
Claim
1
erythromycin increases the AUC of simva...
ddi:ddi-spl-annotation-np-assertion-314 a np:assertion,
owl:Class ;
rdfs:label "erythromycin - simvastatin potential drug-...
ddi:ddi-spl-annotation-np-assertion-314
prov:generatedAtTime
"2015-08-13T15:46:38.746060"^^xsd:dateTime ;
prov:hadMember d...
ddi:ddi-spl-annotation-nanopub-314
prov:generatedAtTime
"2015-08-13T15:46:38.745973"^^xsd:dateTime ;
prov:wasAttributedTo
...
46
Scalability
47
48
4. What about the EVIDENCE?
Formalizing knowledge and evidence about potential drug drug interactions, BDM2I at ISWC2015, 2015-10-11
Upcoming SlideShare
Loading in …5
×

Formalizing knowledge and evidence about potential drug drug interactions, BDM2I at ISWC2015, 2015-10-11

1,324 views

Published on

Workshop paper presentation for BDM2I at ISWC 2015.
Paper at http://ceur-ws.org/Vol-1428/BDM2I_2015_paper_10.pdf
And
http://jodischneider.com/pubs/bdm2i2015.pdf

Abstract:
Potential drug-drug interactions (PDDI) are a significant source of preventable drug-related harm. One contributing factor is that there is no standard way to represent PDDI knowledge claims and associated evidence in a computable form. The research we present in this paper addresses this problem by creating a new version of the Drug Interaction Knowledge Base, with scalable, interlinkable repositories for PDDI evidence and PDDI knowledge claims.

Jodi Schneider, Mathias Brochhausen, Samuel Rosko, Paolo Ciccarese, William R. Hogan, Daniel Malone, Yifan Ning, Tim Clark and Richard D. Boyce. “Formalizing knowledge and evidence about potential drug-drug interactions.” International Workshop on Biomedical Data Mining, Modeling, and Semantic Integration: A Promising Approach to Solving Unmet Medical Needs (BDM2I 2015) at ISWC 2015 Bethlehem, Pennsylvania, USA, October 11

Published in: Technology
  • Be the first to comment

Formalizing knowledge and evidence about potential drug drug interactions, BDM2I at ISWC2015, 2015-10-11

  1. 1. Formalizing knowledge and evidence about potential drug-drug interactions Jodi Schneider1, Mathias Brochhausen2, Samuel Rosko1, Paolo Ciccarese3,6, William R. Hogan4, Daniel Malone5, Yifan Ning1, Tim Clark6, Richard D. Boyce1 1 – University of Pittsburgh 2 – University of Arkansas for Medical Sciences 3 – PerkinElmer Innovation Lab 4 – University of Florida 5 – The University of Arizona 6 – Massachusetts General Hospital and Harvard Medical School
  2. 2. Potential Drug-Drug Interaction (PDDI) • Co-prescription or co-administration of two drugs known to interact. • Preventable and have large impact: – 5-14% of hospital inpatients (Magro et al 2012) – .02-.17% of emergency room visits each year (CDC) 2
  3. 3. There is substantial disagreement in PDDI evidence sources • 4 clinically oriented drug information compendia agreed on only 2.2% of 406 PDDIs considered to be “major” by at least one source. (Abarca et al 2003) • Only 1/4th of 59 contraindicated drug pairs were listed in 3 PDDI information sources. (Wang et al 2010) • Only 18 (28%) of 64 pharmacy information and clinical decisions support systems correctly identified 13 PDDIs considered clinically significant by a team of drug interaction experts. (Saverno et al 2011) 3
  4. 4. Goal: Make disagreements and discrepancies visible • Did compendium A and compendium B consider the same evidence? • Cite a particular statement, indicating a disagreement with it. • Mark some evidence as more or less credible. 4
  5. 5. Overall project goals • Support drug information compendia editors who review PDDI evidence. • More easily integrate and cross-check info. • Update and maintain an existing knowledge base, the Drug Interaction Knowledge Base (DIKB). 5
  6. 6. Update an existing knowledge base • The old knowledge base, DIKB-old, has: – PDDI claims & evidence collected in prior work – 36 competency questions – A taxonomy of PDDI evidence • Limitations – Not used clinically – No computable, standard representation of PDDI knowledge claims and evidence 6
  7. 7. Requirements 1. Distinguish between: – a drug drug interaction (an actual occurrence in a patient) – a potential drug drug interaction (an information content entity that may exist because of an observation or inference). 2. Link to biological processes 3. Computability 4. Maintainability 7
  8. 8. Main idea • Formalize claims • Use new ontologies – Nanopublications – Micropublications – Updated OBO Foundry ontologies, including a bespoke ontology for Potential Drug-Drug Interactions (DIDEO) 8
  9. 9. Process • Collaborate with an evidence workgroup – includes 4 pharmacology experts: Carol Collins, Amy Grizzle, Lisa Hines, John R Horn • Investigate how to formalize PDDI claims and evidence, focusing on clinically relevant info. • Transform data into the new DIKB. – 410 knowledge claims about 88 drugs (October 2015) 9
  10. 10. USING NEW METHODS TO FORMALIZE PDDI CLAIMS AND EVIDENCE
  11. 11. 1. Respect clinically-relevant distinctions • Observed – PDDI evidence derived from an in vivo study • Inferred – PDDI Claim inferred from metabolic mechanistic knowledge of how drugs interact 11
  12. 12. 2. Pull in external knowledge • Compatible with OBO Foundry • Reuse identifiers: – ChEBI - Chemical Entities of Biological Interest – PRO - PRotein Ontology • Flexible, query-based infrastructure 12
  13. 13. 3. Use nanopublications (NP) 13 assertion provenance publication info nanopublication Based on http://nanopub.org/wordpress/?page_id=65
  14. 14. assertion prov:generatedAtTime prov:hadMember prov:wasAttributedTo prov:wasDerivedFrom DIKB nanopublication prov:generatedAtTime prov:wasAttributedTo
  15. 15. 15 4. What about the EVIDENCE? DATA? Kantola, T., Kivistö, K. T., & Neuvonen, P. J. (1998). Erythromycin and verapamil considerably increase serum simvastatin and simvastatin acid concentrations*. Clinical Pharmacology & Therapeutics, 64(2), 177-182. http://dx.doi.org/10.1016/S0009-9236(98)90151-5
  16. 16. Model the evidence with the Micropublications Ontology A claim is supported by methods, materials, and data: – MP:Claim – MP:Method – MP:Materials – MP:Data 16 Clark, T., Ciccarese, P., Goble, C.: Micropublications: a semantic model for claims, evidence, arguments and annotations in biomedical communications. Journal of Biomedical Semantics 5(1), 28 (2014). Ontology at http://purl.org/mp 16
  17. 17. MP is complementary to NP MP NP • Publishable • Citable • Use provenance 17 • Publishable • Citable • Use provenance
  18. 18. MP is complementary to NP MP NP • Publishable • Citable • Use provenance • Logical structure 18 • Publishable • Citable • Use provenance • Natural language • Supports claim conflict. • Makes evidence structure explicit.
  19. 19. We link MP and NP • We extended the MP ontology to add two new properties: – MP:formalizedAs – MP:formalizes • NP <formal representation> MP:formalizes MP:Claim <natural language representation> 19
  20. 20. ddi:ddi-spl-annotation-np-assertion-314 a np:assertion, owl:Class ; rdfs:label "erythromycin - simvastatin potential drug-drug interaction" ; rdfs:subClassOf [ a owl:Restriction ; owl:onProperty obo:IAO_0000136 ; owl:someValuesFrom [ a owl:Class ; owl:intersectionOf ( obo:DIDEO_00000012 [ a owl:Restriction ; owl:hasValue obo:CHEBI_48923 ; owl:onProperty obo:BFO_0000052 ] ) ] ], [ a owl:Restriction ; owl:onProperty obo:IAO_0000136 ; owl:someValuesFrom [ a owl:Class ; owl:intersectionOf ( obo:DIDEO_00000013 [ a owl:Restriction ; owl:hasValue obo:CHEBI_9150 ; owl:onProperty obo:BFO_0000052 ] ) ] ], obo:DIDEO_00000000 . NP: Assertion
  21. 21. MP:Claim
  22. 22. Building up an MP graph
  23. 23. Building up an MP graph
  24. 24. Building up an MP graph
  25. 25. Building up an MP graph
  26. 26. Building up an MP graph
  27. 27. Building up an MP graph
  28. 28. Building up an MP graph
  29. 29. Building up an MP graph
  30. 30. Building up an MP graph
  31. 31. OUTLOOK
  32. 32. Future Work • Can clinicians quickly identify the rationale for any given knowledge claim, using the DIKB? • Are MP’s easy to create with appropriate tools? • Can drug experts retrieve more complete information with search tools derived from the DIKB? 32
  33. 33. Thanks! • Carol Collins, Amy Grizzle, Lisa Hines, Harry Hochheiser, and John R Horn • ERCIM “Alain Bensoussan” Fellowship Programme (FP7/2007-2013) no 246016 • National Library of Medicine 1R01LM011838-01 • National Library of Medicine & National Institute of Dental and Craniofacial Research 5T15LM007059-29 33
  34. 34. Data is publicly available • Nanopublication and Micropublication graphs http://purl.org/net/drug-interaction-knowledge- base/published-NP-and-MP-graphs • Queries http://purl.org/net/drug-interaction-knowledge- base/micropublication-queries • DIDEO: Drug-drug Interaction and Drug-drug Interaction Evidence Ontology (Brochhausen et al 2014) http://www.obofoundry.org/ontology/dideo.html 34
  35. 35. Silos of PDDI knowledge claims Scientific literatureProduct labeling Clinical experience
  36. 36. Evidence of PDDI knowledge claims is distributed across multiple sources Pre-market studies Post-market studies Product labeling Reported in Clinical experience Scientific literature Rarely reported in Rarely reported in Reported in Rarely reported in Drug Compendia synthesize PDDI evidence into knowledge claims but • May fail to include important evidence • Disagree if specific evidence items can support or refute PDDI knowledge claims Source for Source for
  37. 37. Efficiency and scalability from structured publication Claim Support Reference • Drug4X4interacts4with4drug4Y • Drug4X4inhibits4enzyme4Q • Data • Materials • Methods • Scientific4literature • Product4label • Other… • Scientific4literature • Product4label • Other… Micropublication evidence4item Argument4graphs Primary4data Annotating4 while4publishing Argument4graphs Evidence4board4annotates while4creating4a4new4drug4information4sources Primary4data Annotating4 published4 documents Authors4annotate44 during4the4publication4process4444 38
  38. 38. Facts in the evidence base are used for reasonable extrapolation… erythromycin obo:CHEBI_48923 CYP3A4 obo:PR_000006130 simvastatin obo:CHEBI_9150 molecularly6 decreases6activity obo:RO_0002449 catalyzes6a6Phase6I6or6 Phase6II6enzymatic6 reaction6involving obo:DIDEO_00000096 inhibits<catalyzes6metabolism6of obo:DIDEO_00000090 39
  39. 39. Making an inference Evidence(Base "erythromycin,inhibits,CYP3A4." "CYP3A4,catalyzes,a,Phase,I,or, Phase,II,enzymatic,reaction, involving,simvastatin." OWL inference "erythromycin, ‘inhibits=catalyzes,metabolism,of’, simvastatin." Knowledge(Base } Statement,A "Statement,A,is,about, {erythromycin}." "Statement,A,is,about,{simvastatin}." "Statement,A,is,about,{CYP3A4}." "Statement,A,is,a,PDDI,statement." transformation 40
  40. 40. Micropublication Ontology (MP) Clark, T., Ciccarese, P., Goble, C.: Micropublications: a semantic model for claims, evidence, arguments and annotations in biomedical communications. Journal of Biomedical Semantics 5(1), 28 (2014). Ontology at http://purl.org/mp 41
  41. 41. DIKB micropublication graph for the erythromycin - simvastatin interaction Claim 1 erythromycin increases the AUC of simvastatin Data 1 MP 1 mp:argues Method 1 mp:qualifiedBy obo:CHEBI_48923 mp:qualifiedBy obo:CHEBI_9150 mp:qualifiedBy obo:DIDEO_00000000 Materials 1 mp:supports mp:supports mp:supports mp:supports http://dx.doi.org/ 10.1016/ S0009-9236(98)90151-5 42
  42. 42. ddi:ddi-spl-annotation-np-assertion-314 a np:assertion, owl:Class ; rdfs:label "erythromycin - simvastatin potential drug-drug interaction" ; rdfs:subClassOf [ a owl:Restriction ; owl:onProperty obo:IAO_0000136 ; owl:someValuesFrom [ a owl:Class ; owl:intersectionOf ( obo:DIDEO_00000012 [ a owl:Restriction ; owl:hasValue obo:CHEBI_48923 ; owl:onProperty obo:BFO_0000052 ] ) ] ], [ a owl:Restriction ; owl:onProperty obo:IAO_0000136 ; owl:someValuesFrom [ a owl:Class ; owl:intersectionOf ( obo:DIDEO_00000013 [ a owl:Restriction ; owl:hasValue obo:CHEBI_9150 ; owl:onProperty obo:BFO_0000052 ] ) ] ], obo:DIDEO_00000000 . NP: Assertion
  43. 43. ddi:ddi-spl-annotation-np-assertion-314 prov:generatedAtTime "2015-08-13T15:46:38.746060"^^xsd:dateTime ; prov:hadMember dikbEvidence:EV_PK_DDI_NR, dikbEvidence:EV_PK_DDI_Par_Grps, dikbEvidence:EV_PK_DDI_RCT ; prov:wasAttributedTo <http://orcid.org/0000-0002-2993-2085> ; prov:wasDerivedFrom "Derived from the DIKB's evidence base using the listed belief criteria" . NP:Provenance
  44. 44. ddi:ddi-spl-annotation-nanopub-314 prov:generatedAtTime "2015-08-13T15:46:38.745973"^^xsd:dateTime ; prov:wasAttributedTo <http://orcid.org/0000-0002-2993-2085> . NP:Publication Info
  45. 45. 46
  46. 46. Scalability 47
  47. 47. 48 4. What about the EVIDENCE?

×