Semantic annotation of biomedical data
Download as PPTX, PDF3 likes1,803 views
The document discusses the challenges and importance of semantic annotation in the biomedical domain, highlighting the need for ontology-based annotations to improve data integration and facilitate translational discoveries. It outlines a workflow for automatic annotation services utilizing recognized ontologies and tools like the NCBO Annotator Web Service. The presentation emphasizes the need for enhanced concept recognition and semantic expansion techniques to keep pace with the evolving landscape of biomedical data.
Semantic annotation of biomedical data
- 1. Semantic annotation of biomedical dataClement [email protected] - EXMO seminar - March 24th, 2010
- 2. Speech overviewIntroduction: semantic annotation, semantic web, biomedical context, the challenge
- 3. Ontology-based annotation workflow: concept recognition, semantic expansion, why it’s hard?
- 4. Annotation services: the NCBO Annotator web service, the NCBO biomedical resources index
- 5. Users & use cases
- 6. Conclusion and future work2INRIA - EXMO seminar - March 24th, 2010
- 7. Annotation & semantic webPart of the vision for the semantic web
- 8. Web content must be semantically described using ontologies
- 9. Semantic annotations help to structure the web
- 10. Annotation is not an easy task
- 12. Lack of annotation tools (convenient, simple to use and easily integrated into automatic processes)
- 13. Today’s web content (& public data available through the web) mainly composed of unstructured textINRIA - EXMO seminar - March 24th, 20103
- 14. Annotation is not a common practiceHigh number of ontologies
- 15. Getting access to all is hard: formats, locations, APIs
- 16. Lack of tools that easily access all ontologies (domain)
- 17. Users do not always know the structure of an ontology’s content or how to use it in order to do the annotations themselves
- 18. Lack of tools to do the annotations automatically
- 19. Boring additional task without immediate reward for the userINRIA - EXMO seminar - March 24th, 20104
- 20. Biomedical contextExplosion of publicly available biomedical data
- 21. Very diverse, grow very fast
- 22. Most of the data are unstructured and rarely described with ontology concepts available in the domains
- 23. Hard for biomedical researchers to find the data they need
- 25. Translational discoveries are prevented
- 26. Good example of use of ontologies and terminologies for annotations
- 28. PubMed (biomedical literature) indexed with Mesh headings
- 29. Limitations
- 30. UMLS only, almost nothing for OBO & OWL ontologies
- 31. Manual approaches, curators (scalability?)
- 32. Automatic approaches (usability & accuracy?) INRIA - EXMO seminar - March 24th, 20105
- 33. The challengeAutomatically process a piece of raw text to annotate it with relevant ontologies
- 34. Large scale – to scale up for many resources and ontologies
- 35. Automatic – to keep precision and accuracy
- 36. Easy to use and to access – to prevent the biomedical community from getting lost
- 37. Customizable – to fit very specific needs
- 38. Smart – to leverage the knowledge contained in ontologiesINRIA - EXMO seminar - March 24th, 20106
- 39. VocabularyElement = a collection of observations resulting from a biomedical experiment or study
- 40. a dataset, clinical-trial description, research article, imaging study
- 41. Text metadata = the set of free text that describe or ‘annotate’ an element
- 42. Resource = a collection of elements
- 43. GEO, PubMed, ClinicalTrial.gov, Guideline.gov, ArrayExpress
- 44. Concept = a unique entity (class) in an specific ontology (has an URI)
- 45. UMLS CUI or NCBO URI e.g., C0025202, DOID:1909
- 46. Term = a string that identifies a given concept (name, synonyms)
- 47. Melanoma, Melanomas, Malignant melanoma
- 48. Annotation = meta-information on a data: this data deals with this concept
- 49. PMID17984116 deals with C0025202INRIA - EXMO seminar - March 24th, 20107
- 50. Why using ontologies?They structure the knowledge from a domainThey specify terms that can be used by natural language processing algorithms to process textThey uniquely identify concept (URI)They specify relations between concepts that can be used for computing concept similarityThey define hierarchies allowing abstraction of typeThey play the role of common denominator for various data from a domainINRIA - EXMO seminar - March 24th, 20108
- 51. Why using ontologies?9INRIA - EXMO seminar - March 24th, 2010
- 52. Why is it a hard problem? (1/2)Identify concept from text is a hard task
- 53. May involve NLP, stemming, spell-checking, or recognition of morphological variants
- 56. We want to deal with millions of concepts (~4M)
- 57. 200+ ontologies in several format, spread out
- 58. Huge biomedical resources e.g., PubMed 17M citations
- 59. What to do with annotations when the ontologies and the resources evolve over time
- 60. e.g., elements in resources are added
- 61. e.g., concepts in ontologies are removed INRIA - EXMO seminar - March 24th, 201010
- 62. Why is it a hard problem? (2/2)How to leverage the knowledge contained in ontologies?Process the transitive closure for relations (not trivial for ontologies with 300k concepts)Execute semantic distance algorithms to determine similarityCompute mappings between ontologies to connect ontologies one anotherKeep all of this up to date when ontologies evolvee.g., new GO version everydayINRIA - EXMO seminar - March 24th, 201011
- 63. Ontology-based annotation workflowINRIA - EXMO seminar - March 24th, 2010`12First, direct annotations are created by recognizing concepts in raw text,Second, annotations are semantically expanded using knowledge of the ontologies,Third, all annotations are scored according to the context in which they have been created.
- 64. Concept recognition (step 1)Uses a dictionary: a list of strings that identifies ontology concepts
- 65. 220 ontologies, ~4.2M concepts & ~7.9M termsUses NCIBI Mgrep, a syntactic concept recognizerHigh degree of accuracy Fast, scalable,Domain independent13INRIA - EXMO seminar - March 24th, 2010`
- 66. Semantic expansion (step 2)Uses is_a hierarchies defined by original ontologies
- 67. Uses mapping in UMLS Metathesaurus and NCBO BioPortal
- 68. Uses semantic- similarity algorithms based on the is_a graph (ongoing work)
- 69. Components available as web services14INRIA - EXMO seminar - March 24th, 2010`
- 70. An example“Melanoma is a malignant tumor of melanocytes which are found predominantly in skin but also in the bowel and the eye”.
- 71. NCI/C0025201, Melanocyte in NCI Thesaurus
- 72. 39228/DOID:1909, Melanoma in Human Disease
- 74. 39228/DOID:191, Melanocytic neoplasm, direct parent of Melanoma in Human Disease
- 75. 39228/DOID:0000818, cell proliferation disease, grand parent of Melanoma in Human Disease
- 77. FMA/C0025201, Melanocyte in Foundational Model of Anatomy, concept mapped to NCI/C0025201 in UMLS.INRIA - EXMO seminar - March 24th, 2010`15“Melanoma is a malignant tumor of melanocytes whichare found predominantly in skin but also in the bowel and the eye”.Annotations servicesNCBO Annotator web service
- 78. The annotation workflow available as a service
- 79. Automatically process a piece of raw text to annotate it with relevant ontology concepts and return the annotations to the user
- 80. NCBO Biomedical resources index
- 81. We have used the annotation workflow to annotate some common resources (gene expression data, clinical trials, articles) and index then by concepts
- 83. http://bioportal.bioontology.org/INRIA - EXMO seminar - March 24th, 201016
- 84. NCBO Annotator web servicehttp://bioportal.bioontology.org/annotatorSemantic web vision
- 87. OWL ontology that formalizes the service model
- 88. Higher expressivity (e.g., SWRL rules)
- 89. Annotations returned to the users in OWL as instances
- 90. Software agents and semantic web technology stack (e.g., SPARQL)
- 91. What distinguish the service?
- 92. Can be integrated in current workflow (service-oriented approach)
- 94. Creates annotations for both all UMLS and NCBO ontologiesINRIA - EXMO seminar - March 24th, 201017[AMIA STB 09][BMC BioInformatics 09]
- 95. NCBO Annotator in BioPortalINRIA - EXMO seminar - March 24th, 201018
- 96. NCBO Biomedical Resources indexhttp://bioportal.bioontology.org/resourcesWe have used the workflow to index several important biomedical resources with ontology concepts (22+)
- 97. The index can be used to enhance search & data integrationINRIA - EXMO seminar - March 24th, 201019[DILS 08][BMC BioInfo09][IC 10]
- 98. Ex: annotation of a GEO element20
- 99. Ex: search of a GEO element21
- 100. OBR results available in NCBO BioPortalINRIA - EXMO seminar - March 24th, 201022Example of resource available (name and description)Number of annotations in the OBR indexOntology concept/term browsedTitle and URL link to the original elementContext in which an element has been annotatedID of an element
- 101. Good use of the semantics (1/2)Simple keywords based search miss resultsINRIA - EXMO seminar - March 24th, 201023
- 102. 24Good use of the semantics (2/2)INRIA - EXMO seminar - March 24th, 2010
- 103. First evaluationMgrep vs. MetaMap evaluation
- 104. Higher precision & faster
- 105. Not limited to UMLS terminologies
- 106. 22 resources the annotation index
- 107. Between 99% and 100% of the processed elements are annotated
- 108. The number of annotating concepts ranges from 359 to 769
- 109. Functional comparative evaluation with online queries
- 110. Superior average number of results (i.e., resource elements)
- 111. Higher number of terms for which we return results. Significant improve in the case of AE or GEO.INRIA - EXMO seminar - March 24th, 201025[BMC BioInformatics 09]
- 112. Technical detailsWorkflow and pre-computation of the data Java, JDBC & MySQL (prototypes)Java, Spring/Hibernate & MySQL (production)Services deployed as REST web servicesTomcat & RestLetINRIA - EXMO seminar - March 24th, 201026
- 113. 27Users…INRIA - EXMO seminar - March 24th, 2010Ontology-based services (OBS)NCBO Biomedical Resources index service NCBO Annotator web serviceBioPortal servicesUMLS servicesUCSFLaboratreeCollabRxUCHSCPharmGKB, JAXHGMDBioPortal UIPDB/PLoSI2B2NextBioIO informatics“Resources” tab`KnewcoIO informaticsCaNanoLab
- 114. …and uses casesFor concept recognition from text
- 115. Decide which clinical trials are relevant for a particular patient. Use the annotator service to map clinical-trial eligibility criteria to concepts from UMLS
- 117. Use concepts recognized in the abstracts of publications to triage papers for curation
- 118. For structuring Web data
- 119. Ensure that any textual annotation created in Laboratree also has corresponding ontology-based annotations
- 120. For mining gene expression data
- 121. http://gminer.mcw.edu/INRIA - EXMO seminar - March 24th, 201028
- 122. ConclusionEnabling data integration and translational discoveries requires scalable data annotation using ontologies
- 123. Semantic annotations can bridge the gap between resources and ontologies
- 124. Ontology-based annotations are essential for new semantic services on the Web
- 125. Our annotation workflow offers high-throughput, semantic annotation
- 126. Offers an automated, service-oriented vision
- 127. Leverages the knowledge contained in ontologies
- 128. Please try it and join us!INRIA - EXMO seminar - March 24th, 201029
- 129. Future workEnhanced concept recognition
- 130. NLP and text mining techniques
- 131. to enhance the recognition of concepts
- 132. to avoid noise
- 135. Extracting a similarity measure from the annotation index
- 136. Composing semantic expansion components on demand
- 137. Methods for annotation evolution
- 138. Allowing users to update the annotations previously done by the service
- 139. Updating the annotations in the index as metadata change
- 140. Parameterization of the scoring algorithm on demandINRIA - EXMO seminar - March 24th, 201030
- 141. Credits and collaborators@ NCBO, Stanford University
- 142. Dr. Nigam H. Shah M.D., PhD initiator of the project & biomedical expert
- 143. Pr. Mark A. Musen NCBO PI
- 144. Dr. Adrien Coulet postdoc, new resources within resource index & extraction
- 145. Cherie Youn Software developer & production releases
- 146. Nipun Bhatia CS student Mgrep evaluation
- 147. @ Univ. of Victoria
- 148. Chris Callendar Software developer (UI)
- 149. @ NCIBI, Univ. of Michigan
- 150. Manhong Dai Mgrep designers & developers
- 151. Dr. Fan Meng 31INRIA - EXMO seminar - March 24th, 2010
- 152. Thank youNational Center for BioMedical Ontologyhttp://www.bioontology.orgBioPortal, biomedical ontology repositoryhttp://bioportal.bioontology.orgContact [email protected]
Editor's Notes
- #2: Let’s try to understand the context of this work and what we mean by semantic annotation.
- #5: Ontology based annotation is not wide-spread; possibly because of:Lack of a one stop shop for bio-ontologiesLack of tools to annotate datasetsManual will not scaleAutomatic can it be ‘good enough’?Lack of a sustainable mechanism to create ontology based annotations
- #10: They structure the knowledge from a domainThey specify terms that can be used by natural language processing algorithms to process textThey uniquely identify concept (URI)They specify relations between concepts that can be used for computing concept similarityThey define hierarchies allowing abstraction of typeThey play the role of common denominator for various data from a domain
- #14: Uses a dictionary (or lexicon): a list of strings that identifies ontology conceptsConstructed by accessing ontologies and pooling all concept names or other string forms (synonyms, labels) that syntactically identify conceptsWe use Mgrep, a syntactic concept recognizerDeveloped by University of Michigan – NCIBIHas a very high degree of accuracy (over 95% in recognizing disease names)Fast, scalable, domain independentAnother AMIA STB 2009 presentation (tomorrow, 1:50pm)Mgrep vs. MetaMap evaluation Higher precision & faster Not limited to UMLS terminologies
- #22: Performing a search of GEO using OBR. A user searching for “melanoma” in Bioportal is able to view the set of online data resources that have been annotated with the ontology terms related to this query. The GEO element “melanoma progression” is returned as a pertinent element for this search. (Note: In the current version, we have dealt only with element titles and descriptions to validate the notion of context awareness. Later, we will process the more of the metadata structure to enable a finer grained level of detail.) The display within BioPortal allows the user to view the original data set with a single click.
- #29: Specific evaluation with external users on progressCenter for Clinical and Translational InformaticsJackson LabUniv. of Indiana (research management system)
- #33: Let’s try to understand the context of this work and what we mean by semantic annotation.