Keynote de Clement Jonquet a l'atelier RISE (Atelier Recherche d’Information Sémantique) le 30 juin 2015

1. Atelier Recherche d’Information Sémantique, RISE’15
30 juin 2015 – Rennes
Clement Jonquet – jonquet@lirmm.fr
A few contributions of
the SIFR
(Semantic Indexing of French
biomedical Resources project)
and how we reuse NCBO
technology

2. How is this relevant to RISE?
 Modèles de Recherche d'Information Sémantique
 Extraction d'Information
 Annotation Sémantique
 Indexation Sémantique
 Alignement d'ontologies et correspondances pour la Recherche
d'Information
 Langages de Représentation des connaissances pour la Recherche
d'Information
 Utilisation des distances Sémantiques pour la Recherche
d'Information
Atelier RISE 2015
30 juin 2015, Rennes

3. A few introduction words
Atelier RISE 2015
30 juin 2015, Rennes

4. Biologist have adopted
ontologies
 To provide canonical representation of scientific
knowledge
 To annotate experimental data to enable
interpretation, comparison, and discovery across
databases
 To facilitate knowledge-based applications for
 Decision support
 Natural language-processing
 Data integration
 But ontologies are: spread out, in different formats, of
different size, with different structures
Atelier RISE 2015
30 juin 2015, Rennes

5. Working with terminologies &
ontologies – a portal please!
 You’ve built an ontology, how do you let the world know?
 You need an ontology, where do you go o get it?
 How do you know whether an ontology is any good?
 How do you find resources that are relevant to the
domain of the ontology (or to specific terms)?
 How could you leverage your ontology to enable new
science?
 How could you use ontologies without managing them ?
Atelier RISE 2015
30 juin 2015, Rennes

6. Atelier RISE 2015
30 juin 2015, Rennes
 Comparison of the
approaches
[IWBBIO'14]

7. Annotation challenge
 Explosion of biomedical data: diverse,
distributed, unstructured… not linked to
ontologies
 Hard for biomedical researchers to find the
data they need
 Data integration problem
 Translational discoveries are prevented
 Good examples
 GO annotations
 PubMed (biomedical literature) indexed with
Mesh headings
 Annotate data with ontology concepts
 Horizontal approach
ONTOLOGIES
RESOURCES
Atelier RISE 2015
30 juin 2015, Rennes

8. Good use of the semantics (1/2)
 Simple keywords based search miss results
Atelier RISE 2015
30 juin 2015, Rennes

9. Good use of the semantics (2/2)
Atelier RISE 2015
30 juin 2015, Rennes

10. A few words about SIFR
project
Atelier RISE 2015
30 juin 2015, Rennes

11. Semantic Indexing of
French Biomedical Data
Resources project
… in collaboration with…

12. People
 Young researchers
 Clement Jonquet
 Mathieu Roche
 Sandra Bringay
 Advisors
 Stefano A. Cerri
 Maguelonne Teisseire
 Pascal Poncelet
 Staff
 Vincent Emonet
 Students
 Juan Antonio Lossio Ventura
 Guillaume Surroca
 ~3 MSc students / year
 Close collaborators
 Philippe Lemoisson (TETIS)
 Pierre Larmande (IRD / IBC)
 Mark Musen (BMIR)
 Stefan Darmoni (CISMEF)
 Sebastien Harispe (LGI2P)
Atelier RISE 2015
30 juin 2015, Rennes

13. Increasing number of biomedical
data + multilingualism
 Limits of keyword-based indexing
 Biomedical community has turned to ontologies to describe their
data and turn them into structured and formalized knowledge
 Using ontologies is by means of creating semantic annotations
 Crucial need for tools & services for French biomedical data
 Biomedical data integration challenge
 New potential sceintific discoveries hidden in data
 Translational research
Atelier RISE 2015
30 juin 2015, Rennes

14. Use ontologies for indexing, mining
and searching (French) biomedical
data
 Obj1: Design, development and deployment
of the French Annotator.
 Obj2: Obtain new research results to exploit
and enhance ontology-based indexing
services.
 semantic distances
 ontology alignment
 ontology enrichment and disambiguation
 Obj3: Valorization of indexing services
Atelier RISE 2015
30 juin 2015, Rennes

15. Atelier RISE 2015
30 juin 2015, Rennes
A French biomedical Annotator

16. Atelier RISE 2015
30 juin 2015, Rennes
Use biomedical ontologies-based
annotations end-user applications

17. Reuse of the NCBO
technology
Atelier RISE 2015
30 juin 2015, Rennes

18. Bioportal : A “one stop shop”
for Biomedical Ontologies
 Web repository for biomedical ontologies
 Make ontologies accessible and usable – abstraction on
format, locations, structure, etc.
 Users can publish, download, browse, search, comment,
align ontologies and use them for annotations both online
and via a web services API.
 Online support for ontology
 Peer review
 Notes (comments and discussion)
 Versioning
 Mapping
 Search
 Resources
Atelier RISE 2015
30 juin 2015, Rennes

19. http://bioportal.bioontology.org
BioPortal Ontology Repository

20. http://data.bioontology.org
Ontology
Services
• Search
• Traverse
• Comment
• Download
Widgets
• Tree-view
• Auto-complete
• Graph-view
Annotation
Data Access
Mapping
Services
• Create
• Upload
• Download
Term recognition
Search “data”
annotated with a
given term
http://bioportal.bioontology.org Atelier RISE 2015
30 juin 2015, Rennes

21. Current axes of research
Atelier RISE 2015
30 juin 2015, Rennes

22. SIFR axes of research (1/8):
Design of the SIFR (French)
Annotator service
 Deployment of a local instance of BioPortal at LIRMM
 16 French terminologies imported from UMLS, EHTOP & BioPortal
 UTF8 compliant Mgrep concept recognizer (Univ. of Michigan)
 http://bioportal.lirmm.fr/annotator
 New improvement to the annotation workflow
 Automatic term extraction measures (C-value, LIDF-value, etc.)
 Scoring of annotations & representation in RDF using the AO
[SWAT4LS 2014]
Atelier RISE 2015
30 juin 2015, Rennes

23. Improving the Annotator(s) –
example with scoring
 Objective : To improve the Annotator(s) results by ranking
the annotations according to their relevance
 While not changing the service implementation
 Take into account their frequencies (as originally proposed in
2009 and removed)
 Add a term extraction measure, called C-Value, used to
positively discriminate annotations generated from matches
with multi-word terms.
 2 new scoring methods allowing to score and rank
annotations by their importance in the given input data
 Interesting results validated against PubMed manual
annotations
 [SWAT4LS 2014]
Atelier RISE 2015
30 juin 2015, Rennes

24. SIFR axes of research (2/8):
Dealing with multilingualism within
BioPortal
 Status of multilingualism in BioPortal – quite negative
 Set of propositions [MSW 2014]
 Representation of natural language property for an ontology
 Representation of the distinction between ontologies
 Representation of relation between ontologies
 Representation of multilingual translation mappings
 Reconciliation of multilingual mappings (possible PhD collaboration with
ESI)
 Currently being tested/implemented within our local instance
Atelier RISE 2015
30 juin 2015, Rennes

25. What is being multilingual?
 Interface internationalization = displaying static elements of
the user interface (e.g., menu names, help, etc.) in
different languages
 Content internationalization = displaying BioPortal content
(e.g., ontology labels, mappings, etc.) in different languages
 Multilingual = internationalization (display) + to enabling a
complete use of the functionalities and services of BioPortal
for multilingual ontologies or monolingual ontologies
 completely and properly addressed (languages, translations,
multilingual mappings, etc.)
 rich semantic description
 Being able to parse multilingual content in ontologies (from
xmllang to Lemon)
Atelier RISE 2015
30 juin 2015, Rennes

26. multilingual
ontology
Atelier RISE 2015
30 juin 2015, Rennes
en:disease
fr:maladie
...
en:cancer
fr:cancer
en:spindel cell sarcome
fr:sarcome à cellules fusiformes
en:melanoma
fr:mélanome
disease
... cancer
spindle cell sarcome melanoma
maladie
... cancer
sarcome à cellules
fusiformes
mélanome
language specific
ontology
(monolingual)

27. SIFR axes of research (3/8):
Automatic extraction of biomedical
terminology from text
 Context of the PhD of Juan Antonio Lossio
[LBM 2013][TALN 2014][PolTAL 2014]
 BioTex , software
http://tubo.lirmm.fr/biotex [ISWC 2014]
 Work in French, English and Spanish
 Motivations for automatic terminology
extraction
 Experiment and validate approaches for
French data
 Contribute to the ontology enrichment
process
 Acquire some NLP expertise for the
annotation workflow
Atelier RISE 2015
30 juin 2015, Rennes

28. Atelier RISE 2015
30 juin 2015, Rennes

29. Statistical methods
C-value: Improves the extraction of longest terms
soft contact soft contact lens
Frantzi, K., Ananiadou, S., & Mima, H. (2000). Automatic recognition of multi-word terms:. the
c-value/nc-value method. International Journal on Digital Libraries, 3(2), 115-130.
Atelier RISE 2015
30 juin 2015, Rennes

30. Atelier RISE 2015
30 juin 2015, Rennes

31. Atelier RISE 2015
30 juin 2015, Rennes

32. Include BioTex into BioPortal
 Use BioPortal dictionary for validation
 New ontology enrichment service… give a corpus of data and
see what are the terms not yet covered
Atelier RISE 2015
30 juin 2015, Rennes

33. SIFR axes of research (4/8):
Semantic distance framework
 Automatically compute existing (Rada, Wu&Palmer, Resnik)
semantic similarity measures over BioPortal ontologies
 For a given concept get all semantically closed concepts
 Get the semantic distance between 2 concepts
 Collaboration with LGI2P to reuse Semantic Measure Library
(SML) within BioPortal
 1st prototype: http://tubo.lirmm.fr/BioMedicalSemantic/web/app_dev.php
 To include SML within BioPortal backend to bring semantic
distance services to the ontologies and data annotated
Atelier RISE 2015
30 juin 2015, Rennes

34. SIFR axes of research (5/8):
Informal patient data analysis
 Dealing with public patient data on blogs, forums and
tweets (Sandra Bringay)
 Detection of emotion [EGC 2014][eTELEMED 2014]
 Patient vocabulary (crabe vs. cancer)
 Project “Parlons de nous” (www.lirmm.fr/patient-mind)
 MSH-M
 A patient vocabulary currently being constructed [IC 2015]
 Hosted and available in our local instance of BioPortal
 Used for annotations, indexing, information retrieval
Atelier RISE 2015
30 juin 2015, Rennes

35. SIFR axes of research (6/8):
Viewpoint: a subjective knowledge
representation formalism
 Collaboration with P. Lemoisson (CIRAD) & PhD of G. Surroca
 Graph based knowledge representation formalism
 Linked data from the semantic Web and user contributions
from the social Web.
 Unified topological approach
 First prototype for semantic search over HAL-LIRMM
publications [IC2014]
 Capture the phenomenon of Serendipity
(i.e., incidental learning) [IC 2015]
Atelier RISE 2015
30 juin 2015, Rennes

36. SIFR axes of research (7/8):
Pharmacogenomics use case
 PGx studies how individual gene variations cause variability in
drug responses
 Validation of pharmacogenomics state-of-the-art knowledge on
the basis of practice-based evidences
 Compare pharmacogenomics literature (in English) and electronic
health records (in French)
 EHRs from Paris (HEGP) & St Etienne hospitals
 Improvement of the AnnotatorS to come to handle clinical data:
negation, disambiguation, modularity, temporality
 Project submitted to ANR generic call 2015 (April 27th)
 Collaborative action lead by Adrien Coulet (LORIA)
 Stanford is in the loop (Russ, Mark, Michel, Nigam)
Atelier RISE 2015
30 juin 2015, Rennes

37. SIFR axes of research (8/8):
application to agronomy & plant
 Within the Institute of Computational Biology of
Montpellier
 Design of a semantic annotation workflow for plant data -
collaboration with IBC project [CO-PDI 2014]
 AgroLD: to build an RDF knowledge base to house plant data
resources: SouthGreen, Gramene, OryGeneDB… [RDA 2014]
 AgroPortal: reference ontology repository for the agronomic
domain [IN-OVIVE 2015]
 Experiment NCBO technologies for the plant community
 4 driving agronomic use cases
Atelier RISE 2015
30 juin 2015, Rennes

38. Objectives of AgroPortal project
 Develop and support a reference ontology repository for the
agronomic domain
 One-stop-shop for plant/agronomic related ontologies
 Primary focus on the agronomic & plant domain
 Reusing the NCBO BioPortal technology
 Avoid to re-implement what has been done
 Facilitate interoperability
 Reusing the scientific outcomes, experience & methods of the
biomedical domain
 Enable straightforward use of agronomic related ontologies
 Respect the requirements of the agronomic community
 Fully semantic web compliant infrastructure
Atelier RISE 2015
30 juin 2015, Rennes

39. AgroPortal
 50 ontologies relevant to agronomic and plant
Atelier RISE 2015
30 juin 2015, Rennes

40. A few conclusions
Atelier RISE 2015
30 juin 2015, Rennes

41. Next future
 Continue to move different prototypes into production
 Release of the French Annotator
 Find more use cases
 Collaboration with the plant/agro community
 Continue reusing and contributing to NCBO technology
Atelier RISE 2015
30 juin 2015, Rennes

42. Online resources
 Web page: www.lirmm.fr/sifr
 https://www.researchgate.net/projects
 Code repository: https://github.com/sifrproject
 13 developpers
 10 repositories
 Publications: http://bit.ly/194ImnR
 Direct link to HAL-LIRMM platform
with advance search features
 Portals & services:
 http://bioportal.lirmm.fr
 http://agroportal.lirmm.fr
Atelier RISE 2015
30 juin 2015, Rennes

43. Questions & Remarks ?
Atelier RISE 2015
30 juin 2015, Rennes