Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Open access - making the most of biomedical literature mining

567 views

Published on

Berlin 4 Open Access - From Promise to Practice,
Max-Planck-Institute for Gravitational Physics, Potsdam-Golm, Germany, March 29-31, 2006

Published in: Technology, Business
  • Be the first to comment

Open access - making the most of biomedical literature mining

  1. 1. Open access – making the most of biomedical literature mining Lars Juhl Jensen EMBL Heidelberg
  2. 2. why open access?
  3. 3. why biomedicine?
  4. 4. why literature mining?
  5. 5. M EDLINE
  6. 6. Jensen et al., Nature Reviews Genetics, 2006
  7. 7. information retrieval
  8. 8. finding the papers
  9. 10. Mitotic cyclin (Clb2)-bound Cdc28 (Cdk1 homolog) directly phosphorylated Swe1 and this modification served as a priming step to promote subsequent Cdc5-dependent Swe1 hyperphosphorylation and degradation
  10. 11. entity recognition
  11. 12. identifying the substance(s)
  12. 13. Mitotic cyclin ( Clb2 )-bound Cdc28 (Cdk1 homolog) directly phosphorylated Swe1 and this modification served as a priming step to promote subsequent Cdc5 -dependent Swe1 hyperphosphorylation and degradation
  13. 16. information extraction
  14. 17. formalizing the facts
  15. 18. co-mentioning
  16. 20. NLP Natural Language Processing
  17. 21. Mitotic cyclin ( Clb2 )-bound Cdc28 (Cdk1 homolog) directly phosphorylated Swe1 and this modification served as a priming step to promote subsequent Cdc5 -dependent Swe1 hyperphosphorylation and degradation
  18. 22. <ul><li>Gene and protein names </li></ul><ul><li>Cue words for entity recognition </li></ul><ul><li>Verbs for relation extraction </li></ul><ul><li>[ nxgene The GAL4 gene ] </li></ul><ul><li>[ nxexpr T he expression of [ nxgene the cytochrome genes [ nxpg CYC1 and CYC7 ]]] is controlled by [ nxpg HAP1 ] </li></ul>
  19. 23. Jensen et al., Nature Reviews Genetics, 2006
  20. 24. new discoveries
  21. 25. text mining
  22. 26. Jensen et al., Nature Reviews Genetics, 2006
  23. 27. integration of text and data
  24. 28. open access databases
  25. 29. von Mering et al., Nucleic Acids Research, 2005
  26. 31. network mining
  27. 32. genotype to phenotype
  28. 33. Korbel et al., PLoS Biology, 2005
  29. 34. Korbel et al., PLoS Biology, 2005
  30. 35. Korbel et al., PLoS Biology, 2005
  31. 36. where are we now?
  32. 37. Jensen et al., Nature Reviews Genetics, 2006
  33. 38. abstracts
  34. 39. complete papers
  35. 40. restricted access
  36. 41. open access
  37. 42. the tools are there
  38. 43. now we need the text!
  39. 44. Acknowledgments <ul><li>Work done in collaboration with </li></ul><ul><li>Peer Bork </li></ul><ul><li>Jasmin Saric </li></ul><ul><li>Rossitza Ouzounova </li></ul><ul><li>Michael Kuhn </li></ul><ul><li>Isabel Rojas </li></ul><ul><li>Presentation style stolen from </li></ul><ul><li>Lawrence Lessig </li></ul><ul><li>Dick Clarence Hardt </li></ul>
  40. 45. Thank you!

×