The pragmatic text miner: It’s just another type of poorly standardized data
Download as PPT, PDF0 likes646 views
This document discusses text mining and challenges working with unstructured biomedical data from various sources. It describes using named entity recognition, expansion rules, and co-mentioning within texts to identify related entities. Integrating text mining with curated knowledge bases and other data can provide more insights but requires common identifiers and dealing with different formats, licenses, and qualities of information from multiple sources. Collaboration is important to make the most of technology and domain expertise.
The pragmatic text miner: It’s just another type of poorly standardized data
- 1. Lars Juhl Jensen The pragmatic text miner It’s just another type of poorly standardized data
- 3. data mining
- 9. >10 km
- 10. too much to read
- 11. computer
- 12. as smart as a dog
- 13. teach it specific tricks
- 18. synonyms
- 20. KLK3
- 21. expansion rules
- 23. KLK3
- 24. hKLK3
- 29. “black list”
- 30. SDS
- 31. co-mentioning
- 32. within documents
- 34. within sentences
- 35. weighted score
- 36. text corpus
- 37. what we normally use
- 39. what we should use
- 41. many publishers
- 45. unclear terms
- 46. unifying text & data
- 47. text mining
- 52. protein networks
- 53. string-db.org
- 55. stitch-db.org
- 61. many sources
- 64. variable quality
- 65. not comparable
- 66. hard work
- 68. quality scores
- 72. domain experts
- 73. what?
- 74. why?
- 75. problem
- 76. manpower
- 77. me
- 78. how?
- 79. technology
- 80. guidance
- 81. biodiversity
- 82. organisms
- 83. environments
- 87. drugs
- 91. what we need
- 93. one place to get all
- 94. the format is not crucial
- 95. the license is
- 96. Acknowledgments Protein networks Michael Kuhn Damian Szklarczyk Andrea Franceschini Milan Simonovic Alexander Roth Sune Pletscher- Frankild Jianyi Lin Pablo Minguez Christian von Mering Peer Bork Localization and disease Sune Pletscher-Frankild Alberto Santos Janos Binder Kalliopi Tsafou Christian Stolte Albert Palleja Heiko Horn Evangelos Pafilis Reinhardt Schneider Sean O’ Donoghue