Eric%20Neumann%20Clinical%20Semantic%20Group

1
Tutorial Semantic Web Applications in Clinical
Data Management
Eric NeumannClinical Semantic Group W3C HCLS
chair, MIT Fellow
2
Tutorial Overview

• Bench-to-Bedside Vision
• Information Challenges
• Semantic Web What is it?
• RDF Recombinant Data (Aggregation)
• OWL Vocabularies (NCI, SNOMED)
• Rules
• Translational Medicine Needs
• Clinical Data Standards- CDISC
• Re-Using Clinical Knowledge
• Retrospective DBs JANUS
• Open Knowledge Benefits Tox Commons

3
Bench-to-Bedside

• Connecting pre-clinical and clinical studies
• Translational Medicine
• Patient Stratification Personalized medicine
  (not the same)
• Knowledge and Data Integration
• Better Disease Understanding
• Next Generation Therapies, New Applications
• More Predictive (earlier) Safety Signals

4
from Innovation or Stagnation, FDA Report March
2004
5
New Regulatory Issues Confronting Pharmaceuticals
from Innovation or Stagnation, FDA Report March
2004
6
Translational Medicine

• Enable physicians to more effectively translate
  relevant findings and hypotheses into therapies
  for human health
• Support the blending of huge volumes of clinical
  research and phenotypic data with genomic
  research data
• Apply that knowledge to patients and finally make
  individualized, preventative medicine a reality
  for diseases that have a genetic basis

7
Drug Discovery Development Knowledge
Qualified Targets
Molecular Mechanisms
Lead Generation
Toxicity Safety
Lead Optimization
Pharmacogenomics
Biomarkers
Clinical Trials
Launch
8
Ecosystem Goal State
Merging Biomed Research, Clinical Trials and
Clinical Practice
9
HCChoices
HCLS Ecosystem
Insurers
Grants
HMO,PPO
Biomed Research
Publications and Public Databases
BKB
Gov/Funding
Large Studies
Risks Benefits
Disease Areas
Drug RD
EHR
Mol Path Res
Clin Res
Chem Manuf
Drug Programs
Clin POC
Surveillance
BiomarkerTox
HCP
Public
Preclin
Marketing
Gov/Regulatory
VA System RD
CROs
Clin Safety
JANUS
SafetyCommons
10
Information Challenges

• No common way to bring data and docs together
• HTML links carries no meaning with them
• Todays integration approaches prevent data
  re-use
• No global way to annotate our experiments and
  experiences
• Most annotations cannot be found by context
• No sci-blog for data interpretation
• Enterprise Information access and discoverability
  are weak
• Making timely discoveries!
• Why we all like Google
• Cutting and pasting between docs promotes fact
  mutation and loss of provenance
• Address business operations and tracking, and
  reduce static data copying

11
A web of information
Courtesy ofR. Stevens
12
Distributed Nature of Biomedical Knowledge
Patents

• Silos of Data

Tox
HCS
Biomarkers
Targets
Libraries
Assays
DrugRegistry
Diseases
Genotypes
ClinicalTrials
13
The Big Picture In Drug RD
Hard to understand from just a few isolated
Points of View
14
What if Scientists could put it together for
themselves?
15
Complete view tells a very different Story
16
Whose Schema?
17
Why Searching ala Google is not enough

• Googles ability to rank and graph without using
  semantics is comparable to

a Drug RD Project that looks for
associations, but makes no attempt to find or
represent mechanisms of action
18
What is the Semantic Web?
19
The Layer Cake
20
The Current Web

• What the computer sees Dumb links
• No semantics - lta hrefgt treated just like ltboldgt
• Minimal machine-processable information

21
The Semantic Web

• Machine-processable semantic information
• Semantic context published making the data more
  informative to both humans and machines

22
Needed to realize the SW vision

• A standard way of identifying things
• A standard way of describing things
• A standard way of linking things
• Standard vocabularies for talking about things

23
The Semantic WebBasic Standards for Describing
Things

• Richer structure for basic resources (XML)
• Describe Data by Semantics and Not Syntax RDF
• Define Semantics using RDFS or OWL
• Reference and Relate All Resources using URIs
• SPARQL is super model of SQL
• Rules for higher level reasoning

24
The Technologies RDF

• Resource Description Framework (RDF)
• W3C standard for making statements or hypotheses
  about data and concepts
• Descriptive statements are expressed as triples
  (Subject, Verb, Object)

Property
Subject
Object
ltCompound HB-2182gt ltbinds_togt
ltTarget P38_alphagt
25
Facts as triples
has_associated_disease
PARK1
Parkinson disease
subject
predicate
object
26
From triples to a graph
MAPT
Parkinson disease
MAPT
Pick disease
PARK1
Parkinson disease
TBP
Parkinson disease
TBP
Spinocerebellar ataxia
has_associated_disease
27
Connecting graphs

• Integrate graphs from multiple resources
• Query across resources

28
Semantic Web Technologies

• Richer structure for resources
• eXtensible Markup Language (XML)
• Exposed semantics
• Resource Description Framework (RDF)
• Explicit semantics
• Ontologies
• Web Ontology Language (OWL)

29
The URI - global identification

• URI serves as a universal and uniform identifier
  for all web based resources.

30
A Family of Identifiers
URI
URL
URN
URI Uniform Resource Identifier URL Uniform
Resource Locator URN Uniform Resource
Name LSID Life Science Identifier
LSID
URI Uniform Resource Identifier URL Uniform
Resource Locator URN Uniform Resource Name LSID
Life Science Identifier
http//www.w3.org/Addressing/
31
Uniform Resource Locator

• A type or resource identifier
• Identifies the location of a resource (or part
  thereof)
• Specifies a protocol to access the resource
• http, ftp, mailto
• E.g.,
• http//www.nlm.nih.gov/

URI
URL
URN
LSID
32
Uniform Resource Name

• A type or resource identifier
• Identifies the name of a resource
• Location independent
• Defines a namespace
• E.g.,
• urnisbn0-262-02591-4
• urnumlsC0001403

URI
URL
URN
LSID
33
Life Science Identifier

• A type or resource identifier
• A type of URN
• For biological entities
• Specific properties
• Versioned
• Resolvable
• Immutable
• E.g.,

URI
URL
URN
LSID
http//lsid.sourceforge.net/
34
RDF Examples

• as RDF-XML
• ltcdiscSubject http//clinic.com/study/T2271/subje
  ct/4183542663506gt
• ltncisex_code rdfresourcenciFemale /gt
• ltcdisctreatment rdfresourcehttp//clinic.com
  /study/T2271/subject/4183542663506/observation/O22
  41 /gt ltcdiscvitalSigns
  rdfresourcehttp//clinic.com/study/T2271/subjec
  t/4183542663506/observation/O6561 /gt
  ltcdiscadverseEvent rdfresourcehttp//
  clinic.com/study/T2271/subject/4183542663506/obser
  vation/O6622 /gt
• lt/cdiscSubjectgt
• as N3
• lthttp//clinic.com/study/T2271/subject/41835426635
  06gt
• a cdiscSubject
• ncisex_code nciFemale
• cdisctreatment lthttp//clinic.com/study/T2
  271/subject/4183542663506/observation/O2241gt
  cdiscvitalSigns lthttp//clinic.com/stu
  dy/T2271/subject/4183542663506/observation/O6561gt
  cdiscadverseEvent
  lthttp//clinic.com/study/T2271/subject/41835426635
  06/observation/O6622gt .

35
Semantic Data Integration Incremental Roadmap

• Data assets remain as they are!They do not need
  to be modified
• The wrapper abstracts out details related to
  location, access and data structure
• Integration happens at the information level
• Highly configurable and incremental process
• Ability to specify declarative rules and mappings
  for further hypothesis generation

36
RDBM gt RDF
lthasDiseasegt ltinteractsWithgt ltcanCausegt
ltURIgt
ltURIgt
primary keys
primary keys
ltURIgt
ltURIgt
ltURIgt
ltURIgt
Virtualized RDF
37
Semantic Data IntegrationBridging Clinical and
Genomic Information
Paternal
1
90
type
degree
evidence1

• Rule/Semantics-based Integration
• Match Nodes with same Ids
• Create new links IF a patients structured test
  result indicates a disease
• THEN add a
  suffers from link to that disease

38
Semantic Data IntegrationBridging Clinical and
Genomic Information
RDF Graphs provide a semantics-rich substrate for
decision support. Can be exploited by SWRL Rules
39
Semantic Data Integration and VisualizationDrug
Discovery
Drug Discovery Dashboard http//www.w3.org/2005/04
/swls/BioDash
40
Semantic Data IntegrationBridging Chemistry and
Molecular Biology
Semantic Lenses Different Views of the same data
BioPax Components
Target Model
urnlsiduniprot.orguniprotP49841
Apply Correspondence Ruleif ?target.xref.lsid
?bpxprot.xref.lsidthen ?target.correspondsTo.
?bpxprot
41
Semantic Data IntegrationBridging Chemistry and
Molecular Biology

• Lenses can aggregate, accentuate, or even analyze
  new result sets
• Behind the lens, the data can be persistently
  stored as RDF-OWL

• Correspondence does not need to mean same
  descriptive object, but may mean objects with
  identical references

42
Semantic Data IntegrationPathway Polymorphisms

• Merge directly onto pathway graph
• Identify targets with lowest chance of genetic
  variance
• Predict parts of pathways with highest functional
  variability
• Map genetic influence to potential pathway
  elements
• Select mechanisms of action that are minimally
  impacted by polymorphisms

43
Scenario Biomarker Qualification

• Semantics which Define
• Biomarker Roles
• Disease
• Toxicity
• Efficacy
• Molecular and cytological markers
• Tissue-specific
• High content screening derived information
• Different sets associated with different
  predictive tools
• Statistical discrimination based on selected
  samples
• Predictive power
• Alternative cluster prediction algorithms
• Support qualifications from multiple studies
  (comparisons)
• Causal mechanisms
• Pathways
• Population variation

44
Semantic Data Integration Advantages

• RDF Graph based data model
• More expressive than the tree based XML Schema
  Model
• RDF Reification
• Same piece of information can be given different
  values of belief by different clinical genomic
  researchers
• Potential for Schema-less Data Integration
• Hypothesis driven approach to defining mapping
  rules
• Can define mapping rules on the fly
• Incremental approach for Data Integration
• Ability to introduce new data sources into the
  mix incrementally at low cost
• Use of Ontology to disallow meaningless mapping
  rules?
• For e.g., mapping a gene to a protein

45
Semantic Data IntegrationSchema-free data
integration

• Low cost approach for data integration
• No need for maintenance of costly schema mappings
• Ability to merge RDF graphs based on simple
  declarative rules that specify
• Equality of URIs
• Connecting nodes of same type
• Connecting two nodes associated by a path
• Disadvantage Potential for specifying spurious
  non-sensical rules

46
Semantic Data IntegrationUse of Reification

• Level of accuracy of test result.
• Sensitivity and Specificity of lab result
• Level of confidence in genotyping or gene
  sequencing
• Probabilistic relationships
• Likelihood that a particular test result or
  condition is indicative of a disease or other
  medical condition
• Level of trust in a resource
• Results from a lab may be trusted more than
  result from another
• Results from well known health sites (NLM) may be
  trusted more than others
• Belief attribution
• Scientific hypotheses may be attributed to
  appropriate researchers

47
The Available Data Space

• Separate RDF documents are merged automatically
  into one aggregate graph.

48

• Recombination in Molecular Genetics works due to
  proper alignment of genetic regions, thereby
  preventing gene loss, mangling, or duplication.

49
Recombinant Data

• Graphs can be filtered and pivoted, without
  losing meaning

50
Recombinant Data

• Mash-ups that dont lose perspective
• Dynamic mixing of data
• Provide Different Views for Different Roles and
  Functions
• Dashboards
• Direct output of a SPARQL query

51
Key Functionality offered by Semantic Web

• Ubiquity
• Same identifiers for anything from anywhere
• Discoverability
• Global search on any entity
• Interoperability
• gt Recombinant Data is Application Independence
  

52
Data Vision

• Aggregating data and statements using the Web
• Defined aggregation by need and role
• Recombinant Data
• Common system of referencing things (no copying)
• even is they exits in one of many databases
• Indexing things by types and with tags
• Common and ad hoc vocabularies
• Supporting the collective knowledge of an RD
  Community
• A Wiki that has awareness about types and things
• New Generation Discovery Tools

53
Ontologies andWeb Ontology Language (OWL)
54
OWL Introduction

• History DAML OIL OWL (2001)
• DAML DARPA Agent Markup Language (1999)
• OIL Ontology Inference Layer (1997)
• Based on RDF(S)
• Added features, mostly related to identity
• Restrictions
• Three flavors of increasing expressiveness, but
  decreasing tractability
• OWL Lite
• OWL DL (used for most applications)
• OWL Full

55
The Knowledge Semantics Continuum
Medication Lists DDI Lists
KEGG
Thesauri BT/NT, Parent/Child, Informal Is-A
Formal is-a Frames (Properties)
Disjointness, Inverse
DB Schema
CYC
Catalog
RDF(S)
Ontylog
Terms/ glossary
IEEE SUO
OWL
Value Restriction
Formal instances
General Logical constraints
MeSH, Gene Ontology, UMLS Meta
Snomed
Ontology Dimensions based on McGuinness and Finin
56
OWL DL Example

• Class Benign intracranial meningiomain the NCI
  Thesaurus

http//cancer.gov/cancerinfo/terminologyresources/
ltowlClass rdfID"Benign_Intracranial_Meningioma"
gt ltrdfslabelgtBenign Intracranial
Meningiomalt/rdfslabelgt ltcodegtC5133lt/codegt
ltowlequivalentClassgt ltowlClassgt
ltowlintersectionOf rdfparseType"Collection"gt
ltowlClass rdfabout"Benign_Intracranial_Neopl
asm"/gt ltowlClass rdfabout"Benign_Meningiom
a"/gt ltowlClass rdfabout"Intracranial_Menin
gioma"/gt lt/owlintersectionOfgt lt/owlClassgt
lt/owlequivalentClassgt ltPreferred_NamegtBenign
Intracranial Meningiomalt/Preferred_Namegt
ltSemantic_TypegtNeoplastic Processlt/Semantic_Typegt
ltdSynonymgtBenign Intracranial Meningiomalt/dSynony
mgt ltNCI_META_CUIgtCL006955lt/NCI_META_CUIgt lt/o
wlClassgt
57
OWL Class Constructors
Borrowed from Tutorial on OWL by Bechhofer,
Horrocks and Patel-Schneider http//www.cs.man.ac.
uk/horrocks/ISWC2003/Tutorial/
58
OWL Axioms

• Axioms (mostly) reducible to inclusion (v)
• C D iff both C v D and D v C

Borrowed from Tutorial on OWL by Bechhofer,
Horrocks and Patel-Schneider http//www.cs.man.ac.
uk/horrocks/ISWC2003/Tutorial/
59
Existential vs. Universal Quantification

• Existential quantification
• owlsomeValuesFrom
• Necessary condition
• E.g., migraine headache has_symptom throbbing
  pain only if one-sided
• Universal quantification
• owlallValuesFrom
• Necessary and sufficient condition
• E.g., heart disease disease located_to heart

60
OWL reasoners

• For OWL DL, not OWL Full
• Reasoners
• Fact
• Pellet
• RacerPro
• Functions
• Consistency checking
• Automatic classification

http//owl.man.ac.uk/factplusplus/
http//www.mindswap.org/2003/pellet/
http//www.racer-systems.com/
61
OWL Reasoners Details

• CEL
• Polynomial time classifier for the description
  logic EL
• EL is specially geared towards biomedical
  ontologies
• Cerebra
• Commerical C reasoner, Support for OWL-API
• Tableaux based reasoning for TBoxes and ABoxes
• Fact
• Free open source reasoner for DL reasoning
• Support for Lisp API and OWL API
• KAON2
• Free Java based DL reasoner with support for SWRL
  fragment
• Support for DIG API
• MSPASS
• A generalized theorem prover for numerous logics,
  also works for DLs
• Pellet
• Free open source Java based reasoner for DLs
• Support for OWL, DIG APIs and Jena Interface
• RacerPro
• Commercial lisp based reasoner for DLs

62
Editing OWL ontologies
http//protege.stanford.edu/
63
Resources available in OWL

• Many resources currently available in OWL
• Gene Ontology
• NCI Thesaurus
• Many projects using OWL
• e.g., BioPax
• NCBO - Mark Musen, Director

http//www.geneontology.org/
http//cancer.gov/cancerinfo/terminologyresources/
http//www.biopax.org/
64
OBO format
http//www.godatabase.org/dev/doc/obo_format_spec.
html

• Used to represent many ontologies in the OBO
  family (Open Biological Ontologies)
• Essentially a subset of OWL DL

http//obo.sourceforge.net/
Term id GO0019563 name glycerol
catabolism namespace biological_process def
"The chemical reactions and pathways resulting in
the breakdown of glycerol subset
gosubset_prok exact_synonym "glycerol breakdown"
exact_synonym "glycerol degradation"
xref_analog MetaCycPWY0-381 is_a GO0006071
! glycerol metabolism is_a GO0046174 ! polyol
catabolism
65
Domain Semantics in Clinical Trials

• Clinical Semantics
• Patient/Subject ? Disease/Health state
• Diagnostics ? Findings
• Findings ? Inferred (proposed) Disease state
• Disease state ? Patient Classification /
  Segmentation
• Design ? Trial arms / treatments
• Observation ? POC, safety, mechanisms

66
Linking Clinical Ontologies with the Semantic Web
SNOMED
CDISC
ICD10
Clinical Trials ontology
RCRIM (HL7)
Disease Models
Pathways(BioPAX)
Tox
Genomics
Extant ontologies
Under development
Bridge concept
67
Ontology Referencing

• ltrdfRDF
• xmlns owlhttp//www.w3.org/owl
• xmlns snomedhttp// snomed.org
• xmlns cdischttp//cdisc.org/cdisc
• xmlns icd10http//www.ich.org/icd10
• xmlns ncihttp//www.nci.nih.gov/thesaurus
• xmlns rcrimhttp//www.hl7.org/rcrim
• xmlns biopaxhttp//biopax.org/biopax
• xmlns biopaxhttp//biopax.org/biopax
• ltsnomeddisease snomedDiabetesType2gt
• ltbiopaxinvolvesgt ltnciInsulinSignalingPathwaygt
  

68
Rules and Policies
69
Imagine this CDS RuleIf Renal Disease and DM
and no contraindication, should be on ACE
inhibitor or ARB

• Renal disease
• Chronic Renal Failure
• Nephropathy, chronic renal failure, end-stage
  renal disease, renal insufficiency, hemodialysis,
  peritoneal dialysis on Problem List (SNOMED)
• Creatinine gt 2
• Calculated GFR lt 50
• Malb/creat ratio test gt 30
• Diabetes
• Many variants on the problem list
• On Insulin or oral hypoglycemic drug
• Contraindication to ACE inhibitor
• Allergy, Cough on ACE on adverse reaction list,
  or Hyperkalemia on problem list, Pregnant (20
  sub rules to define this state)
• K test result gt 5

70
Translational Medicine
71
Translational Medicine in Drug RD
Early
Middle
Late
Cellular
Systems
Human
In Vitro Studies
Animal Studies
Clinical Studies
Disease Models (Therapeutic Relevance)
Toxicities
Target/System Efficacy



72
Case Study Drug Safety Safety Lenses

• Lenses can focus data in specific ways
• Hepatoxicity, genotoxicity, hERG, metabolites
• Can be wrapped around statistical tools
• Aggregate other papers and findings (knowledge)
  in context with a particular project
• Align animal studies with clinical results
• Support special Alert-channels by regulators
  for each different toxicity issue
• Integrate JIT information on newly published
  mechanisms of actions

73
ClinDash Clinical Trials Browser
Subjects

• Values can be normalized across all measurables
  (rows)

• Samples can be aligned to their subjects using
  RDF rules
• Clustering can now be done over all measureables
  (rows)

74
GeneLogic GeneExpress Data

• Additional relations and aspects can be defined
  additionally

75
ClinDash Clinical Trials Browser
Subjects

• Values can be normalized across all measurables
  (rows)

• Samples can be aligned to their subjects using
  RDF rules
• Clustering can now be done over all measureables
  (rows)

76
EDC and EHR

• Should they be merged?
• Differences in goals and implementations
• Reduce data redundancy
• The Semantic Web solution
• Use EHR RDF to generate part of EDC frame
• Use same URIs for patient, clinic entities

77
AE Channels

• ltitem rdfabout" http//www.cdc.gov/MMWR/48e905bd
  b66310af85ad2e8503628e01 "gt
• lttitlegtFemale service members reported higher
  rates of reactions to the previous dose of
  vaccine during anthrax vaccination of all U.S.
  military personnel.lt/titlegt
• ltlinkgthttp//www.cdc.gov/MMWR/48e905bdb66310af85a
  d2e8503628e01lt/linkgt
• ltdescriptiongtPosted by alan_zimmers to
  health.mil/adverse_eventsx26Processes on Thu
  Jan 19 2006lt/descriptiongt
• ltdccreatorgt alan_zimmers lt/dccreatorgt
• ltdcdategt2006-01-19T112403Zlt/dcdategt
• ltrdftypegtAdverseEventlt/dcsubjectgt
• ltdcsubjectgtAnthrax Vaccinationx26Treatmentlt/d
  csubjectgt
• ltnihurigt
• ltdctitlegt Female service members reported
  higher rates of reactions to the previous dose of
  vaccine during anthrax vaccination of all U.S.
  military personnel.lt/dctitlegt
• ltdccreatorgtA Sainz-Perezlt/dccreatorgt
• ltdccreatorgtH Gary-Gouylt/dccreatorgt
• ltdcidentifiergt
• lt nihPubMedIDgt
• lt nihidValuegt16408101lt/connoteaidV
  aluegt
• ltrdfvaluegtPMID 16408101lt/rdfvalue
  gt
• lt/ nihPubMedIDgt
• lt/dcidentifiergt
• ltdcdategt2006-01-12lt/dcdategt

78
AE Channels

• ltitem rdfabout" http//www.cdc.gov/MMWR/48e905bd
  b66310af85ad2e8503628e01 "gt
• lttitlegtFemale service members reported higher
  rates of reactions to the previous dose of
  vaccine during anthrax vaccination of all U.S.
  military personnel.lt/titlegt
• ltlinkgthttp//www.cdc.gov/MMWR/48e905bdb66310af85a
  d2e8503628e01lt/linkgt
• ltdescriptiongtPosted by alan_zimmers to
  health.mil/adverse_eventsx26Processes on Thu
  Jan 19 2006lt/descriptiongt
• ltdccreatorgt alan_zimmers lt/dccreatorgt
• ltdcdategt2006-01-19T112403Zlt/dcdategt
• ltrdftypegtAdverseEventlt/dcsubjectgt
• ltdcsubjectgtAnthrax Vaccinationx26Treatmentlt/d
  csubjectgt
• ltknnugget rdfresourceN251gt
• lttnexpertgtAlan R lt/tnexpertgt
• lttntopicgtnsAnthraxTreatmentlt/tntopicgt
• lttnkChannelgtnsHomelandSeccuritylt/tnkChannel
  gt
• lttncommentgtThis research suggests a lower
  limit of adverse responseslt/tncomment gt
• lt/knnugget gt
• ltnihurigt
• ltdctitlegt Female service members reported
  higher rates of reactions to the previous dose of
  vaccine during anthrax vaccination of all U.S.
  military personnel.lt/dctitlegt
• ltdccreatorgtA Sainz-Perezlt/dccreatorgt
• ltdccreatorgtH Gary-Gouylt/dccreatorgt
• ltdcidentifiergt

79
Knowledge Channels

• ltitem rdfabout"http//www.connotea.org/user/hann
  ahr/uri/48e905bdb66310af85ad2e8503628e01"gt
• lttitlegtHigh Mda-7 expression promotes malignant
  cell survival and p38 MAP kinase activation in
  chronic lymphocytic leukemia.lt/titlegt
• ltlinkgthttp//www.connotea.org/user/hannahr/uri/48
  e905bdb66310af85ad2e8503628e01lt/linkgt
• ltdescriptiongtPosted by hannahr to
  CLLSignallingx26Processes on Thu Jan 19
  2006lt/descriptiongt
• ltdccreatorgthannahrlt/dccreatorgt
• ltdcdategt2006-01-19T112403Zlt/dcdategt
• ltdcsubjectgtCLLSignallingx26Processeslt/dcsubj
  ectgt
• ltconnoteaurigt
• ltdctitlegtHigh Mda-7 expression promotes
  malignant cell survival and p38 MAP kinase
  activation in chronic lymphocytic
  leukemia.lt/dctitlegt
• ltdccreatorgtA Sainz-Perezlt/dccreatorgt
• ltdccreatorgtH Gary-Gouylt/dccreatorgt
• ltdcidentifiergt
• ltconnoteaPubMedIDgt
• ltconnoteaidValuegt16408101lt/connotea
  idValuegt
• ltrdfvaluegtPMID 16408101lt/rdfvalue
  gt
• lt/connoteaPubMedIDgt
• lt/dcidentifiergt
• ltdcdategt2006-01-12lt/dcdategt
• ltprismpublicationNamegtLeukemialt/prismpublicat
  ionNamegt

80
Knowledge Channels

• ltitem rdfabout"http//www.connotea.org/user/hann
  ahr/uri/48e905bdb66310af85ad2e8503628e01"gt
• lttitlegtHigh Mda-7 expression promotes malignant
  cell survival and p38 MAP kinase activation in
  chronic lymphocytic leukemia.lt/titlegt
• ltlinkgthttp//www.connotea.org/user/hannahr/uri/48
  e905bdb66310af85ad2e8503628e01lt/linkgt
• ltdescriptiongtPosted by hannahr to
  CLLSignallingx26Processes on Thu Jan 19
  2006lt/descriptiongt
• ltdccreatorgthannahrlt/dccreatorgt
• ltdcdategt2006-01-19T112403Zlt/dcdategt
• ltdcsubjectgtCLLSignallingx26Processeslt/dcsubj
  ectgt
• ltknnugget rdfresourceN251gt
• lttnexpertgtAlan R lt/tnexpertgt
• lttntopicgtnsP38lt/tntopicgt
• lttnkChannelgtnsKinaseslt/tnkChannel gt
• lttncommentgtThis paper suggests a mechanism
  for P38 protection of CLL B-cellslt/tncomment gt
• lt/knnugget gt
• ltconnoteaurigt
• ltdctitlegtHigh Mda-7 expression promotes
  malignant cell survival and p38 MAP kinase
  activation in chronic lymphocytic
  leukemia.lt/dctitlegt
• ltdccreatorgtA Sainz-Perezlt/dccreatorgt
• ltdccreatorgtH Gary-Gouylt/dccreatorgt
• ltdcidentifiergt
• ltconnoteaPubMedIDgt

81
Surveillance using RSS/RDF(CDC)
82
Clinical Data Standards (CDISC)
83
Protocol and the Semiotic TriangleDoug Fridsma
(U Pittsburg)
Symbol Protocol
Source John Speakman/Charlie Mead
84
CDISC and the Semantic Web?

• Reduce the need to write data parsers to any
  CDISC XML Schema
• Make use of ontologies and terminologies directly
  using RDF
• Easier inclusion of Genomic data
• Use Semantic Lenses for Reviewers
• Easier acceptance by industry with their current
  technologies

85
During 2006-2007
SDTM variables asCommon DataElementsControlle
dTerminologies
NCI Thesaurus
In OWL format
CDISCClinical Data Interchange Standards
Consortium
UMLS
RCRIM Regulated Clinical Research and
Information Management,technical committee
Relationship HL7/CDISC
BRIDGBiomedical Research Integrated Domain Group
Model
HL7 Health Level Seven
86
Ongoing work at FDA
Announcement of CDISC/SDTMas a standard format
CDISCClinical Data Interchange Standards
Consortium
RCRIM Regulated Clinical Research and
Information Management,technical committee
Relationship HL7/CDISC
Janus Model and Data Warehouse
HL7 Health Level Seven
populate a cross-study database and do more
comprehensive analyses for the benefit of
patients.
87
Retrospective DBs JANUS

• Accessing and analyzing CT data without changing
  any schema
• Interpretive Annotations without impacting CDB
• Analyses and Insights by Future Projects
• Collective Knowledge on Targets, Diseases, and
  Toxicities

88
Tox Commons

• Proposed Open Re-use of Failed Compounds
• Common Effort by Pharmaceuticals
• Puzzle Analogy
• No real IP in Failed Clinical Data
• Part of Science Commons Initiative
• Is a Drug Safety Commons Possible?, Bio-ITWorld

89
FDAs JANUS Full Modelone visual representation
90
FDAs JANUS basic elements diagramanother visual
representation
General classes of Clinical observations
91
SDTM ala RDF

• lthttp//clinic.com/study/T2271/subject/41835426635
  06gt
• a cdiscSubject
• ncisex_code nciFemale
• cdisctreatment lthttp//clinic.com/study/T2271
  /subject/4183542663506/observation/O2241gt
  cdiscvitalSigns lthttp//clinic.com/study/T22
  71/subject/4183542663506/observation/O6561gt
  cdiscadverseEvent lthttp//clinic.com/study
  /T2271/subject/4183542663506/observation/O6622gt
• // ROUTE DRGGROUP DOSE pid
  treatment tpfday tptday
• // IV B 7 MG 4183542663506 7mg then
  14mg SEMWEB 6/11/84 7/11/84
• lthttp//clinic.com/study/T2271/subject/S83221/obse
  rvation/O2241 gt
• a cdiscTreatment // cdiscTreatment is a
  subclass of cdiscObservation
  cdiscdesign_arm lthttp//clinic.com/study/T2271/t
  reated_B/double_dosegt cdiscroute
  cdiscIV_route
• cdiscdrug_group "B
• cdiscdose "7"
• cdiscdose_units nistmg
• cdisctreatment "7mg then 14mg SEMWEB"
• cdiscfirst_date "6/11/84"
• cdiscterm_date "7/11/84" .

92
SDTM ala RDF

• lthttp//clinic.com/study/T2271/subject/S83221/obse
  rvation/O2241 gt
• a cdiscBiomarker_Measure // a subclass of
  cdiscObservation cdiscbiomarker_proc
  lthttp//clinic.com/study/T2271/treated_B/biomarker
  _samplegt cdiscmol_analyses
  nihgene_expression
• cdiscbiomarker_set lthttp//nci.nih.gov/biomar
  kers/colon_cancer/B324gt
• cdiscbiomarker_values 2.343, 1.211, 0531,
  23.34, 83.12, 4.323, 9.543
• cdiscunits nistnorm_ratio
• cdiscdate "6/11/84"

93
HCLS Drug Safety and Efficacy Focus Areas

• Translational Science Perspective
• Subject State Thinking (biomarkers)
• Safety dimensions
• Efficacy (disease models)
• Animal ? Human (CDISCs SEND, SDTM/ODM)
• Clinical Observations and their relation to
  biomarkers ( mechanisms) and pharmacogenomics
• Connecting back to Discovery
• Targets
• Biomarkers
• Therapeutic Knowledge
• Leads, Candidates selection
• Mechanisms of Action
• BioPAX

94
Proposed Notes and Activities

• http//www.w3.org/2001/sw/hcls/
• Notes planned
• SDTM and JANUS from a SW perspective
• Semantic enriched evolvable recombinant clinical
  observations
• DEMO Table and XML models ala RDF
• Retrospective DBs (JANUS) and SW power of
  annotations and links
• DEMO using URI code and RDBM
• Provenance and trust (non-reputability)
• ACL?

95
Reasons for SW

• Exponential Growth and Distribution of Medical
  Knowledge and Complex Data - needs to scale with
  the Web!
• Reduce innovation adoption curve from discovery
  into accepted standards of practice (currently 17
  years)
• Reduce the cost/duration/risk of clinical trial
  management
• Patient identification and recruitment
• Trial Design (Learn/Confirm, adaptive trials)
• Improved data quality and clinical outcomes
  measurement
• Post-market surveillance (knowledge channels)
• Reduce preventable, anticipatable adverse events
  (5-10)
• The market is balking at healthcare inflation,
  new technologies and therapeutics will find
  increasing resistance for reimbursement
• SW could prove many time less expensive than
  traditional IT solutions
• Less code creation and maintenance if Rules are
  SW based
• SW content is more manageable to achieve business
  goals

96
Key Semantic Web Principles

• Plan for change
• Free data from the application that created it
• Lower reliance on overly complex Middleware
• The value in "as needed" data integration
• Big wins come from many little ones
• The power of links - network effect
• Open-world, open solutions are cost effective
• Importance of "Partial Understanding"

97
Thank You

• More info at http//www.w3.org/2001/sw/hcls/