Large-scale integration of data and text
Download as PPT, PDF2 likes289 views
This document discusses large-scale integration of data and text in bioinformatics. It describes using text mining on millions of abstracts and articles to extract information on biological entities and their associations in order to build networks of proteins, genes, diseases and small molecules. This information is integrated with experimental data and computational predictions into web-centric databases and resources that can help researchers by saving them time over manually reviewing the literature. Visualization tools are also provided to project network data onto tissue and subcellular localization information extracted from text.
Large-scale integration of data and text
- 1. Large-scale integration of data and text Lars Juhl Jensen
- 2. Large-scale integration of data and text Lars Juhl Jensen
- 4. text mining
- 6. me
- 10. Jensen & Knudsen, Bioinformatics, 2000
- 12. Jensen, Gupta et al., Journal of Molecular Biology, 2002
- 15. protein networks
- 16. de Lichtenberg, Jensen et al., Science, 2005
- 17. chemoinformatics
- 18. Campillos, Kuhn et al., Science, 2008
- 23. data mining
- 24. text mining
- 29. STRING
- 31. Szklarczyk, Franceschini et al., Nucleic Acids Research, 2011
- 32. STITCH
- 34. Kuhn et al., Nucleic Acids Research, 2012
- 35. genomic context
- 36. gene fusion
- 37. Korbel et al., Nature Biotechnology, 2004
- 38. operons
- 39. Korbel et al., Nature Biotechnology, 2004
- 41. Korbel et al., Nature Biotechnology, 2004
- 43. Harrington et al., PNAS, 2007
- 45. Korbel et al., Nature Biotechnology, 2004
- 46. a real example
- 50. Cell Cellulosomes Cellulose
- 55. Jensen & Bork, Science, 2008
- 57. drug targets
- 58. complexes
- 59. pathways
- 60. Letunic & Bork, Trends in Biochemical Sciences, 2008
- 61. many databases
- 64. variable quality
- 65. not comparable
- 66. hard work
- 67. quality scores
- 68. von Mering et al., Nucleic Acids Research, 2005
- 69. calibrate vs. gold standard
- 70. missing most of the data
- 71. text mining
- 72. >10 km
- 73. too much to read
- 74. computer
- 75. as smart as a dog
- 76. teach it specific tricks
- 81. cyclin dependent kinase 1
- 82. CDK1
- 83. CDC2
- 86. cyclin dependent kinase 1
- 89. CDC2
- 90. hCdc2
- 91. “black list”
- 92. SDS
- 95. within documents
- 97. within sentences
- 98. scoring scheme
- 101. corpora
- 103. no access
- 104. ~4 million full-text articles
- 106. augmented browsing
- 107. Reflect
- 108. browser add-on
- 110. Pafilis, O’Donoghue, Jensen et al., Nature Biotechnology, 2009 O’Donoghue et al., Journal of Web Semantics, 2010
- 112. small molecules
- 113. proteins
- 114. compartments
- 115. tissues
- 116. diseases
- 117. organisms
- 118. environments
- 119. suite of web resources
- 121. jensenlab.org
- 122. text mining
- 123. curated knowledge
- 124. experimental data
- 126. quality scores
- 128. DISEASES
- 131. visualization
- 132. COMPARTMENTS
- 134. TISSUES
- 137. Szklarczyk, Franceschini et al., Nucleic Acids Research, 2011
- 141. summary
- 142. bioinformatics
- 143. more than alignment
- 144. data/text mining
- 145. save you much time
- 146. Acknowledgments STRING/STITCH Literature mining Christian von Mering Sune Frankild Damian Szklarczyk Evangelos Pafilis Michael Kuhn Janos Binder Manuel Stark Kalliopi Tsafou Samuel Chaffron Alberto Santos Chris Creevey Heiko Horn Jean Muller Michael Kuhn Tobias Doerks Nigel Brown Philippe Julien Reinhardt Schneider Alexander Roth Sean O’Donoghue Milan Simonovic Jan Korbel Berend Snel Martijn Huynen Peer Bork
- 148. Questions?