FAIR Data Knowledge Graphs
Download as PPTX, PDF4 likes993 views
The document discusses the need for FAIR (Findable, Accessible, Interoperable, and Reusable) data principles in R&D to enhance the understanding of disease mechanisms and improve drug discovery processes. It outlines the challenges faced by researchers, such as fragmented data silos and bottlenecks in bioinformatics, and proposes the use of knowledge graphs to integrate and enrich biomedical data. A dataset catalog is emphasized as a crucial tool for ensuring data discoverability and supporting enterprise strategies.
FAIR Data Knowledge Graphs
- 1. FAIR* Data Knowledge Graphs Tom Plasterer, PhD Director, Bioinformatics, Research Bioinformatics 11 Mar 2019 * Findable, Accessible, Interoperable and Reusable
- 2. What do R&D Researchers want the ability to do? 3 âą Gain a greater understanding of the biology of the molecular mechanisms of diseases âą Use the human as a model organism to a greater degree âą Discover how the microbiome is involved with human pathogenesis âą Understanding molecular mechanisms of drug failures âą Use patient-level clinical data to identify subphenotypes of diseases Integrative Informatics: A hybrid approach to integrating data for Drug Discovery @Mathew Woodwark; Pharma 2020: March 28, 2018
- 3. Can R&D researchers do these things today? 4 âą Currently, data exists in file shares, on laptops, eLN, in silos of managed systems and unknown places âą The level of data integration is immature and fragmented âą Using systems biology approaches requires considerable time and effort âą Bioinformatics groups become a bottleneck to analyzing data âą Research scientists not empowered to use information and knowledge to answer complex questions Integrative Informatics: A hybrid approach to integrating data for Drug Discovery @Mathew Woodwark; Pharma 2020: March 28, 2018
- 4. 5 IIx Approach: Build a FAIR Data Knowledge Graph
- 5. 6 FAIR Principles: One-Slide Overview Findable: âą F1 (meta)data are assigned a globally unique and persistent identifier âą F2 data are described with rich metadata âą F3 metadata clearly and explicitly include the identifier of the data it describes âą F4 (meta)data are registered or indexed in a searchable resource The FAIR Guiding Principles for scientific data management and stewardship Sci. Data 3:160018 doi: 10.1038/sdata.2016.18 (2016) Accessible: âą A1 (meta)data are retrievable by their identifier using a standardized communications protocol âą A1.1 the protocol is open, free, and universally implementable âą A1.2 the protocol allows for an authentication and authorization procedure, where necessary; âą A2 metadata are accessible, even when the data are no longer available; Interoperable: âą I1 (meta)data use a formal, accessible, shared, and broadly applicable language for knowledge representation âą I2 (meta)data use vocabularies that follow FAIR principles âą I3 (meta)data include qualified references to other (meta)data Reusable: âą R1 meta(data) are richly described with a plurality of accurate and relevant attributes âą R1.1 (meta)data are released with a clear and accessible data usage license âą R1.2 (meta)data are associated with detailed provenance âą R1.3 (meta)data meet domain-relevant community standards
- 7. 8 Knowledge Graph: Innovation Trigger Gartner Identifies Five Emerging Technology Trends That Will Blur the Lines Between Human and Machine
- 8. 9 Knowledge Graph: Key Features and Differentiators Federation: âą Leave Data in place or ETL pipeline? âą URIs, indices really important Standards Support (Syntactic and Semantic) âą Universal structure or bespoke? âą Universal query language or bespoke? Analytics Enablement âą Reasoning, inferencing, graph methodologies Hybrid âą Underlying data in multiple shapes and repositories For Machines (and occasionally people) Cypher
- 9. 10 Starting Point: Modeling Business Questions core:Study core:Project core:Target core:Subject core:Drug core:Indication core:TherapeuticArea core:BiologicalSample core:Measurement core:Technologycore:Visit bdm:Cohort core:hasSubject core:hasProject core:hasDrug core:hasIndication bdm:hasArm bdm:participatesIn core:hasTA core:hasTarget core:hasMeasurement core:hasSample core:hasVisit core:measuredBy Find all subjects diagnosed with SLE with a disease activity score > 5 Find all studies evaluating the target PD-L1 with RNA Seq Datasets bnav:measuredInStudy
- 10. 11 Challenge is determining the âstickiestâ representation for a given instance âą Studies all have a âDâ-code and then a number of other internal and external identifiers âą API calls to an internal clinical study API and an external (licensed content) API to obtain the exact matches (skos:exactMatch) âą Process is abstracted in an Enrichment Service âą New relationships (triples) are added to the wrapped data model and pushed into a knowledge graph Enrichment: Core Ontology Classes & API mapping core:Study http://data.rd.astrazeneca.net/study/bdm/CP1103 http://clinicaltrials.astrazeneca.net/study/D4660C00001 http://identifiers.org/clinicaltrials/NCT01448850 http://trialtrove.citeline.com/ClinicalTrial/154466 skos:exactMatch "azct:D4660C00001" "ctg:NCT01448850" "trialtrove:154466" dct:identifier
- 11. 12 Now find âstickiestâ representation for a given instance from a label âą Use system label for the indication âą Send to Enrichment API (augmented public disease vocabularies) and generate the preferred URI to obtain the close matches (skos:closeMatch) âą Process is abstracted in an Enrichment Service âą New relationships (triples) are added to the wrapped data model and pushed into a knowledge graph Enrichment: Core Ontology Classes & Label Matching core:Indication http://data.rd.astrazeneca.net/indication/bdm/Rheumatoid%20Arthritis http://purl.obolibrary.org/obo/DOID_7148 http://identifiers.org/mesh/D001172 skos:closeMatch "Rheumatoid Arthritis (D001172) " bnav:diseaseNameSymbol "Rheumatoid Arthritis" skos:prefLabel
- 12. 13 Now find âstickiestâ representation for a given instance from a label without a good vocabulary âą Aligned internal Technology vocabulary with best public label and URI âą Send to Enrichment API (augmented BDM-technology vocabulary) and generate the preferred URI to obtain the close matches (skos:exactMatch) âą Process is abstracted in an Enrichment Service âą New relationships (triples) are added to the wrapped data model and pushed into a knowledge graph Enrichment: Core Ontology Classes & Mixed Vocabs core:Technology http://data.rd.astrazeneca.net/technology/bdm/BDMTECH00005 "Blood Gas" skos:prefLabel http://identifiers.org/ncit/C71252 skos:exactMatch "Arterial Blood Gas Measurement" skos:prefLabel
- 13. 14 Key Lesson: Where is Enrichment Critical? core:Study core:Project core:Target core:Subject core:Drug core:Indication core:TherapeuticArea core:BiologicalSample core:Measurement core:Technologycore:Visit bdm:Cohort core:hasSubject core:hasProject core:hasDrug core:hasIndication bdm:hasArm bdm:participatesIn core:hasTA core:hasTarget core:hasMeasurement core:hasSample core:hasVisit core:measuredBy External Internal Mix
- 14. 15 Dataset Catalogs: Find me Datasets about: Projects Study Indication/ Disease Technology Targets Cohort DatesAgent Therapeutic Area Drugs
- 15. 16 Dataset Catalog is a collection of Dataset Records âą Catalogs are needed to supporting FAIR (Findable) data âą Catalogs can and should support Enterprise MDM strategies âą Consumers can be internal or external Dataset Catalogs are needed so data consumers can find Datasets âą Dataset records need sufficient metadata to support discoverability âą Dataset terms are NOT the data instance Dataset Catalogs surface dataset provenance and enable data access Dataset Catalogs can provide datasets for multiple consumption patters âą Analytics readiness and fit âą âWalkingâ across information models Dataset Catalogs: Findability Starts Here
- 16. 17 The Backbone: A DCAT conformant Data Catalog https://www.w3.org/TR/hcls-dataset/ https://www.w3.org/TR/vocab-dcat/#vocabulary-overview Semantic tagging of datasets with concepts from taxonomies: âą provides context âą multi-dimensional & flexible âą effective for discoverability âą light-weight semantics skos:Concept dcat:Catalog skos:ConceptScheme dctypes:Dataset (summary) dct:title dct:publisher <foaf:Agent> foaf:page void:sparqlEndpoint dct:accrualPeriodicity dcat:keyword dcat:dataset dcat:theme dctypes:Dataset (version) dcat:Distribution (dctypes:Dataset) void:vocabulary dct:conformsTo void:exampleResource âŠother void properties dcat:distribution dcat:themeTaxonomy dct:isVersionOf pav:previousVersion dct:hasPart pav:hasCurrentVersion dct:hasPart dct:title dct:publisher <foaf:Agent> pav:version dct:creator <foaf:Agent> dct:created dct:source dct:creator <foaf:Agent> dct:license dct:format pav:retrievedFrom dct:created pav:createdWith dcat:accessURL dcat:downloadURL void:Dataset dct:title dctDescription dct:publisher <foaf:Agent>
- 17. Data Discoverability: Multi-phase Filtering Data Catalog Filter Phase 1 Experiment Metadata Filter Phase 2 Ad hoc Analyses Filtering Phase 3 Outbound to Data Analytics Data Science Tools Statistical Filtering e.g., clinical trial with > 50 participants Dataset Catalog Descriptions
- 19. R&D | RDI Multi-Phase Filtering joins the Catalog and Domain Model âą Balance to what belongs in a catalog record vs. instance data Public Domain Ontologies and Identifiers should be reused âą Consensus is emerging around best practices and cross-mapping DCTERMS, DCAT, VoID are almost sufficient âą Extend for local needs Lots of Activity to Learn and Shape Best Practices âą Didnât reinvent a wheel FAIR Knowledge Graph: Take-aways
- 20. R&D | RDI Thanks Key Influencers David Wood Tim Berners-Lee Lee Harland Jane Lomax James Malone Dean Allemang Barend Mons Carole Goble Bernadette Hyland Bob Stanley Eric Little Michel Dumontier John Wilbanks Hans Constandt Filip Pattyn Dan Crowther Tim Hoctor Ian Harrow AstraZeneca/Pistoia FAIR Data Community Mathew Woodwark Rajan Desai Nic Sinibaldi Chia-Chien Chiang Kerstin Forsberg Ola Engkvist Ian Dix Colin Wood Ted Slater Martin Romacker Eric Neumann Jeff Saltzman Kathy Reinold Nirmal Keshava Bryan Takasaki
Editor's Notes
- #6: KG around subject, 20 measurements and types
- #8: https://www.topquadrant.com/2018/07/12/knowledge-graphs-for-integrated-data-governance/ https://en.wikipedia.org/wiki/Knowledge_Graph https://en.wikipedia.org/wiki/Ontology_(information_science)
- #9: https://www.gartner.com/en/newsroom/press-releases/2018-08-20-gartner-identifies-five-emerging-technology-trends-that-will-blur-the-lines-between-human-and-machine
- #10: https://lod-cloud.net/ https://en.wikipedia.org/wiki/First-order_logic
- #16: Images: http://senior-project-led-cube.wikispaces.com/ (https://creativecommons.org/licenses/by-sa/3.0/) http://opensource.org/node/688 (https://creativecommons.org/licenses/by/4.0/)