PRESENTATION OF KNIME VRE AND FSK-LAB AT 12TH KNIME SPRING SUMMIT
0 likes114 views
The document discusses the Federal Institute for Risk Assessment's goal of enhancing consumer health protection through scientific risk assessments and recommendations for food safety. It introduces the Food Safety Knowledge Lab (FSK-LAB), which aims to facilitate the exchange and integration of risk assessment models and promotes a community-driven approach to model repositories. Additionally, it highlights the benefits of improved model sharing for modellers, software developers, and researchers involved in food safety assessments.
PRESENTATION OF KNIME VRE AND FSK-LAB AT 12TH KNIME SPRING SUMMIT
- 1. FEDERALINSTITUTE FORRISKASSESSMENT Enabling Efficient Food Safety Knowledge Exchange with FSK-Lab Matthias Filter - on behalf of the FoodRisk-Lab team in unit 41 Federal Institute for Risk Assessment (BfR), Germany
- 2. Page 2Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Federal Institute for Risk Assessment Overall goal: Strengthening of consumer health protection Identifying health risks Scientific assessment of risks Drawing up of recommendations on risk reduction Communication of these processes
- 3. Page 3Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Work fields Food Safety Product Safety Risk Communication Chemical Safety © Julia Päpke© Fotolia
- 4. Page 4Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Risk Assessment = Knowledge Integration
- 5. Page 5Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Implications Risk assessors need to use “models”
- 6. Page 6Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Food Safety Models
- 7. Page 7Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Specific Challenges for Risk Assessment Models Science based Reproducible Transparent Fully annotated
- 8. Page 8Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Vision Community-driven, curated repositories for food safety models / model modules Newly generated models / re-implemented models / legacy models Model deployment Repository GUI with search, info and model download community repositories
- 9. Page 9Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Long Term Strategy http://www.researchgate.net/publication/273791203_A_strategy_to_establish_Food_Safety_Model_Repositories
- 10. Page 10Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 FSK-ML – a community standard for knowledge exchange Model metadata (generic module) “General information” “Scope” “Data background” “Model math / Data definition”
- 11. Page 11Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 FSKX – A file format for the exchange of models (and data)
- 12. Page 12Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Food Safety Knowledge Lab (FSK-Lab) • KNIME-extension for harmonized annotation, execution and integration of script-based models • the FSK-ML reference implementation
- 13. Page 13Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 FSK-Lab – facilitating harmonized annotation of models
- 14. Page 14Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 FSK-Lab – supporting knowledge integration
- 15. Page 15Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 FSK-Joiner – combining models graphically (JS)
- 16. Page 16Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 FSK-Lab – facilitating user-defined simulations
- 17. Page 17Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Deployment
- 18. Page 18Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 RAKIP Model Repository Run the models Search for the available models Select models Look into model metadata
- 19. Page 19Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Deployment: FSK-Lab in Virtual Research Environments (VRE)
- 20. Page 20Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Deployment: Running KNIME WF in VREs
- 21. Page 21Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Bonus – Easy Publishing
- 22. Page 22Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Benefits Modellers: • Sharing and deploying models / model scripts / code becomes much easier, e.g. via RAKIP model repository or as supplement to your publications Software developers: • An open information exchange format is available and can be jointly improved • Implementation of Machine-to-Machine communication features becomes possible Risk assessors and researchers: • Domain knowledge becomes more easily available and “applicable” in future risk assessments and research
- 23. Page 23Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Other BfR KNIME extensions DB Food Process Simulations Outbreak Analysis and Visualization Predictive Microbiology Knowledge Exchange http://foodrisklabs.bfr.bund.de/
- 24. Page 24Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Outreach
- 25. Page 25Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 The Team
- 26. Page 26Matthias Filter, KNIME Summit 2019, Berlin, 21.03.2019 Acknowledgement and Disclaimer This work was supported by the German Federal Institute for Risk Assessment (BfR), the National Food Institute (DTU Food) from the Technical University of Denmark (DTU), the French Agency for Food, Environmental and Occupational Health & Safety (ANSES), the AGINFRA PLUS project funded by the European Commission's Horizon 2020 research and innovation programme under grant agreement No 731001, the EFSA-BfR Framework Partnership Agreement GP/EFSA/AMU/2016/01 and by funds of the Federal Ministry of Food and Agriculture (BMEL) for the project "FoodAuthent" based on a decision of the Parliament of the Federal Republic of Germany via the Federal Office for Agriculture and Food (BLE) under the innovation support programme. The content of this talk does not reflect the official opinion of the European Union, EFSA, BMEL or BLE. Responsibility for the information and views expressed in this talk lies entirely with the presenter.
- 27. FEDERALINSTITUTE FORRISKASSESSMENT Thank you for your attention Matthias Filter Federal Institute for Risk Assessment Max-Dohrn-Str. 8-10 ⚫ 10589 Berlin, GERMANY Tel. +49 30 - 184 12 - 24109 ⚫ Fax +49 30 - 184 126 - 24109 matthias.filter@bfr.bund.de ⚫ www.bfr.bund.de