Literature mining and large-scale data integration
Download as PPT, PDF0 likes322 views
The document discusses literature mining and large-scale data integration in the context of biological research, emphasizing the challenges of information retrieval and the importance of effective data extraction methods. It highlights techniques such as entity recognition, co-mentioning, and the need for accurate data benchmarking in protein interactions and gene expression studies. Overall, the document concludes that while literature mining is valuable, data integration offers superior benefits for enhancing knowledge discovery.
![Gene and protein names Cue words for entity recognition Verbs for relation extraction [ nxexpr T he expression of [ nxgene the cytochrome genes [ nxpg CYC1 and CYC7 ]]] is controlled by [ nxpg HAP1 ]](https://image.slidesharecdn.com/jen08talk2-1217977587561497-8/85/Literature-mining-and-large-scale-data-integration-52-320.jpg)
Literature mining and large-scale data integration
- 1. Literature mining and large-scale data integration Lars Juhl Jensen EMBL Heidelberg
- 3. why?
- 5. too much to read
- 8. ad hoc retrieval
- 10. “ yeast AND cell cycle”
- 11. stemming
- 12. yeast / yeasts
- 14. yeast / S. cerevisiae
- 15. ranking
- 24. 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
- 25. no tool will find it
- 28. 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
- 29. Cdc28 yeast
- 30. Cdc28 cell cycle
- 32. manual curation
- 34. CDC28
- 35. Cdc28p
- 36. disambiguation
- 37. hairy
- 38. SDS
- 39. APC
- 40. Cdc2
- 45. still too much to read
- 49. co-mentioning
- 51. NLP Natural Language Processing
- 52. Gene and protein names Cue words for entity recognition Verbs for relation extraction [ nxexpr T he expression of [ nxgene the cytochrome genes [ nxpg CYC1 and CYC7 ]]] is controlled by [ nxpg HAP1 ]
- 53. 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
- 56. text mining
- 60. fish oil
- 62. temporal trends
- 64. buzzwords
- 66. data integration
- 82. gene fusion
- 91. not comparable
- 92. benchmarking
- 93. calibrate vs. gold standard
- 96. spread over many species
- 97. 373 genomes
- 101. combine all evidence
- 102. P = 1-(1-P 1 ) . (1-P 2 ) . (1-P 3 ) …
- 103. web resources
- 106. signaling networks
- 107. phosphoproteomics
- 109. in vivo phosphosites
- 110. kinases are unknown
- 113. overprediction
- 114. context
- 115. scaffolders
- 116. association networks
- 118. NetworKIN
- 120. benchmarking
- 123. web resources
- 126. summary
- 127. literature mining is good
- 128. data integration is better
- 129. Acknowledgments Reflect & NLP Evangelos Pafilis Jasmin Saric Rossitza Ouzounova Sean O’Donoghue Isabel Rojas STRING & STITCH Christian von Mering Michael Kuhn Manuel Stark Samuel Chaffron Philippe Julien Tobias Doerks Jan Korbel Berend Snel Martijn Huynen Peer Bork NetworKIN & NetPhorest Rune Linding Martin Lee Miller Gerard Ostheimer Francesca Diella Karen Colwill Jing Jin Pavel Metalnikov Vivian Nguyen Adrian Pasculescu Jin Gyoon Park Leona D. Samson Nikolaj Blom Rob Russell Peer Bork Søren Brunak Michael Yaffe Tony Pawson