Making gene networks through data integration
Download as PPT, PDF1 like480 views
This document discusses how to build gene networks by integrating various types of data through computational techniques and natural language processing of literature. Different databases contain molecular interaction data but in various formats and identifiers, so data integration requires mapping to common identifiers. Text mining can extract stated facts from literature with high precision but low recall, while computational predictions and techniques like co-mentioning analysis of literature can provide more comprehensive networks with lower precision.
![Gene and protein names
Cue words for entity
recognition
Verbs for relation extraction
[nxexpr The expression of
[nxgene the cytochrome
genes
[nxpg CYC1 and CYC7]]]
is controlled by
[nxpg HAP1]](https://image.slidesharecdn.com/jensen2014talk13-140706070014-phpapp02/85/Making-gene-networks-through-data-integration-77-320.jpg)
Making gene networks through data integration
- 1. Making gene networks through data integration Lars Juhl Jensen
- 6. proteins
- 10. non-coding RNAs
- 11. compartments
- 13. tissues
- 15. diseases
- 16. data integration
- 19. Korbel et al., Nature Biotechnology, 2004
- 20. TargetScan
- 22. gene expression
- 25. Jensen & Bork, Science, 2008
- 26. miRTarBase
- 29. Letunic & Bork, Trends in Biochemical Sciences, 2008
- 31. many databases
- 34. variable quality
- 35. not comparable
- 36. hard work
- 37. (Ph.D. students)
- 39. quality scores
- 40. von Mering et al., Nucleic Acids Research, 2005
- 42. von Mering et al., Nucleic Acids Research, 2005
- 44. Franceschini et al., Nucleic Acids Research, 2013
- 45. missing most of the data
- 46. text mining
- 47. >10 km
- 48. too much to read
- 49. computer
- 50. as smart as a dog
- 51. teach it specific tricks
- 56. let-7a-3p
- 57. let-7a*
- 59. let-7a
- 60. let7a
- 61. name expansions
- 62. let-7a
- 63. miR-let-7a
- 64. “black list”
- 65. SDS
- 66. co-mentioning
- 67. counting
- 68. within documents
- 70. within sentences
- 73. high recall
- 74. high precision
- 77. Gene and protein names Cue words for entity recognition Verbs for relation extraction [nxexpr The expression of [nxgene the cytochrome genes [nxpg CYC1 and CYC7]]] is controlled by [nxpg HAP1]
- 79. high precision
- 80. poor recall
- 81. Jensen et al., Nature Reviews Genetics, 2006
- 82. questions?