A semantic collaborative system for the management of translational - - PowerPoint PPT Presentation

▶
a semantic collaborative system for the management of
SMART_READER_LITE
LIVE PREVIEW

A semantic collaborative system for the management of translational - - PowerPoint PPT Presentation

Oct 30, 2022 274 likes •736 views

A semantic collaborative system for the management of translational research projects Matteo Gabetta, Giuseppe Milani, Cristiana Larizza, Valentina Favalli, Eloisa Arbustini, Riccardo Bellazzi INHERITANCE PROJECT UNIVERSIT DI PAVIA Outline

slide-1
SLIDE 1

UNIVERSITÀ DI PAVIA

A semantic collaborative system for the management of translational research projects

Matteo Gabetta, Giuseppe Milani, Cristiana Larizza, Valentina Favalli, Eloisa Arbustini, Riccardo Bellazzi INHERITANCE PROJECT

slide-2
SLIDE 2

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Outline

  • The INHERITANCE project
  • Biomedical Informatics Tools
  • Semantic Wiki
  • Technologies
  • Organizational Data Management
  • Scientific Data Management
  • NLP
  • Literature Mining
  • Conclusions
slide-3
SLIDE 3

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

Cardiomyopathies: “primary myocardial disorders of unknown cause“ 4 main subtypes:

  • Hypertrophic (HCM)
  • Dilated (DCM)
  • Restrictive (RCM)
  • Arrhythmogenic Right Ventricular (ARVC)
slide-4
SLIDE 4

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

Cardiomyopathies: “primary myocardial disorders of unknown cause“ 4 main subtypes:

  • Hypertrophic (HCM)
  • Dilated (DCM)
  • Restrictive (RCM)
  • Arrhythmogenic Right Ventricular (ARVC)
slide-5
SLIDE 5

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

Dilated Cardiomyopathy: “[…] myocardial disorder characterized by the presence of left ventricular dilatation and systolic impairment, in the absence of abnormal loading conditions (e.g. hypertension, valve disease) or coronary artery disease sufficient to cause global systolic dysfunction.“ *

* Elliott P, et al. Classification of the cardiomyopathies: a position statement from the European Society

  • f Cardiology Working Group on Myocardial and Pericardial Diseases. Eur Heart J. 2008; 29: 270–276.
slide-6
SLIDE 6

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

Dilated Cardiomyopathy: “[…] myocardial disorder characterized by the presence of left ventricular dilatation and systolic impairment, in the absence of abnormal loading conditions (e.g. hypertension, valve disease) or coronary artery disease sufficient to cause global systolic dysfunction.“ *

* Elliott P, et al. Classification of the cardiomyopathies: a position statement from the European Society

  • f Cardiology Working Group on Myocardial and Pericardial Diseases. Eur Heart J. 2008; 29: 270–276.
  • 20 disease-causing genes (to date)
slide-7
SLIDE 7

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

Dilated Cardiomyopathy:

* Elliott P, et al. Classification of the cardiomyopathies: a position statement from the European Society

  • f Cardiology Working Group on Myocardial and Pericardial Diseases. Eur Heart J. 2008; 29: 270–276.
slide-8
SLIDE 8

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

INtegrated HEart Research In TrANslational genetics of Cardiomyopathies in Europe

  • 3-year health research project
  • European Commission Funding Program 7
  • 11 European centers
slide-9
SLIDE 9

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

INtegrated HEart Research In TrANslational genetics of Cardiomyopathies in Europe Disease-specific features

(red flags)

Biological features

(genetic or metabolic pathways)

Translational strategy:

slide-10
SLIDE 10

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

INtegrated HEart Research In TrANslational genetics of Cardiomyopathies in Europe 6 research areas:

  • Clinical Cardiogenetics
  • -omics
  • Animal Studies
  • Structural Studies
  • Treatments
  • Biomedical Informatics
slide-11
SLIDE 11

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

The INHERITANCE project

INtegrated HEart Research In TrANslational genetics of Cardiomyopathies in Europe 6 research areas:

  • Clinical Cardiogenetics
  • -omics
  • Animal Studies
  • Structural Studies
  • Treatments
  • Biomedical Informatics
slide-12
SLIDE 12

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Biomedical Informatics Tools

  • Data Warehouse
  • Automated Literature Analysis
  • Case-Based Reasoning
  • Literature-Based Gene Prioritization
  • Semantic Wiki
slide-13
SLIDE 13

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Biomedical Informatics Tools

  • Data Warehouse
  • Automated Literature Analysis
  • Case-Based Reasoning
  • Literature-Based Gene Prioritization
  • Semantic Wiki
slide-14
SLIDE 14

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Biomedical Informatics Tools

  • Data Warehouse
  • Automated Literature Analysis
  • Case-Based Reasoning
  • Literature-Based Gene Prioritization
  • Semantic Wiki
slide-15
SLIDE 15

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Biomedical Informatics Tools

  • Data Warehouse
  • Automated Literature Analysis
  • Case-Based Reasoning
  • Literature-Based Gene Prioritization
  • Semantic Wiki
slide-16
SLIDE 16

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Biomedical Informatics Tools

  • Data Warehouse
  • Automated Literature Analysis
  • Case-Based Reasoning
  • Literature-Based Gene Prioritization
  • Semantic Wiki
slide-17
SLIDE 17

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Biomedical Informatics Tools

  • Data Warehouse
  • Automated Literature Analysis
  • Case-Based Reasoning
  • Literature-Based Gene Prioritization
  • Semantic Wiki
slide-18
SLIDE 18

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Semantic Wiki

  • Track project activities
  • Share ideas
  • Share data
  • Exchange information between investigators
  • Manage scientific research products

ORGANIZATIONAL ASPECTS SCIENTIFIC KNOWLEDGE

slide-19
SLIDE 19

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Semantic Wiki

  • Free web-based wiki software
  • Wikimedia Foundation / Wikipedia
  • Extensibility
  • MediaWiki extension
  • Semantic data
  • Semantic search
  • Data export (e.g. RDF)
slide-20
SLIDE 20

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Semantic Wiki

  • Open-source framework for NLP
  • Libraries of Text Mining tools
  • API’s for tools development
  • Querying tool
  • Graphical relation browser

Entrez Utilities Web Service

  • Pubmed access
  • Web service + APIs
  • SOAP protocol
slide-21
SLIDE 21

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Semantic MediaWiki

Building blocks:

  • Categories
  • Templates
  • Forms

 data model in the Wiki  define content of Categories

slide-22
SLIDE 22

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

RDF triplestore pages categories

Semantic Wiki pages

Categories:

  • Person
  • Organization
  • Meeting
  • Work Package

Person Organization Meeting Work Package

is organized by has leader

slide-23
SLIDE 23

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

Queries:

  • Built-in tool (inline queries)
  • RDF export  SPARQL
  • RelFinder
slide-24
SLIDE 24

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

Queries:

  • Built-in tool (inline queries)
  • RDF export  SPARQL
  • RelFinder
slide-25
SLIDE 25

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

Queries:

  • Built-in tool (inline queries)
  • RDF export  SPARQL
  • RelFinder
slide-26
SLIDE 26

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

Queries:

  • Built-in tool (inline queries)
  • RDF export  SPARQL
  • RelFinder
slide-27
SLIDE 27

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

Queries:

  • Built-in tool (inline queries)
  • RDF export  SPARQL
  • RelFinder
slide-28
SLIDE 28

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

  • Summary Page
slide-29
SLIDE 29

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

  • Summary Page
slide-30
SLIDE 30

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Organizational Aspects

  • Summary Page
slide-31
SLIDE 31

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Scientific Knowledge

NLP

Documents

RDF triplestore concepts documents categories

Semantic Wiki pages

Categories:

  • Gene
  • Protein
  • Dilated Cardiomyopathy

Document Protein DCM Document Gene

slide-32
SLIDE 32

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Natural Language Processing

  • GATE
  • accessed via servlet
  • .txt, .rtf, MS Word
  • API plugins + purposely developed plugins
  • GeneExtractor (NCBI Gene)
  • ProteinExtractor (Uniprot / Swiss-Prot)
slide-33
SLIDE 33

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Natural Language Processing

slide-34
SLIDE 34

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Natural Language Processing

slide-35
SLIDE 35

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Natural Language Processing

slide-36
SLIDE 36

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Natural Language Processing

slide-37
SLIDE 37

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Natural Language Processing

slide-38
SLIDE 38

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Natural Language Processing

slide-39
SLIDE 39

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Relevant Literature

  • NCBI E-utilities
  • for Genes and Proteins pages
  • 5 most recent articles in Pubmed
  • Gene/Protein + “Dilated Cardiomyopathy” (or synonyms)
  • retrieved “on the fly”
  • link to Pubmed
slide-40
SLIDE 40

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Relevant Literature

slide-41
SLIDE 41

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Relevant Literature

slide-42
SLIDE 42

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

In conclusion…

  • Collaborative Wiki System + Semantic features
  • Organizational + Scientific data management
  • NLP
  • Literature retrieval
  • Different query strategies
slide-43
SLIDE 43

Angelo Nuzzo IIT@SEMM, Milan, 2011 NETTAB Workshop – Como - November 16th, 2012 Matteo Gabetta

Future Developments

  • Improve scientific knowledge management
  • New Text Mining pipelines  New concepts
  • Link to new databases
  • Evaluate usage of INHERITANCE partners
  • Integration with other systems
slide-44
SLIDE 44

UNIVERSITÀ DI PAVIA

A semantic collaborative system for the management of translational research projects

Matteo Gabetta, Giuseppe Milani, Cristiana Larizza, Valentina Favalli, Eloisa Arbustini, Riccardo Bellazzi INHERITANCE PROJECT

THANKS FOR YOUR ATTENTION !