BioCreative VI Precision Medicine Track: creating a training corpus for mining protein-protein interactions affected by mutations.
Rezarta Islamaj DoganAndrew Chatr-aryamontriSun KimChih-Hsuan WeiYifan PengDonald C. ComeauZhiyong LuPublished in: BioNLP (2017)
Keyphrases
- protein protein interactions
- training corpus
- high precision
- text classification
- high throughput
- text mining
- data mining
- computational methods
- protein interaction
- biomedical literature
- network topology
- part of speech
- network analysis
- knowledge discovery
- biological data
- structural properties
- training data
- translation model
- statistical machine translation
- data sets
- association rules
- knowledge base
- data mining techniques
- collaborative filtering
- information extraction