Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 1, 2001BioinformaticsOpen Access

Automatic rule generation for protein annotation with the C4.5 data mining algorithm applied on SWISS-PROT

View Full Paper
Ask AI
Bookmark
Share

Authors

EKErnst KretschmannEuropean Bioinformatics InstituteWFWolfgang FleischmannEuropean Bioinformatics InstituteRARolf ApweilerEuropean Bioinformatics Institute

Discussion

Loading...

Member takes

Implication

Randomized trial demonstrates improved keyword annotation in protein databases, suggesting enhanced data utility.

Key Points

  • This research aims to develop automated tools to enhance the functional annotation of protein data in public databases.
  • Applied the C4.5 data mining algorithm to generate rules for protein keyword annotation in SWISS-PROT.
  • Generated 11,306 rules based on organism taxonomy and sequence signature matches.
  • Conducted cross-validation to assess the accuracy and coverage of the generated rules.
  • Achieved 33% keyword annotation generation with an error rate of 1.5%.
  • Increased keyword annotation coverage rate to 60% with a higher error rate of 5%.
  • Rules can be applied to unannotated protein sequences via a web database.

Cite This Study

Kretschmann et al. (2001) studied this question.

synapsesocial.com/papers/6a0d7cabcae7912d2fa50882https://doi.org/10.1093/bioinformatics/17.10.920
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1The PROSITE database, its status in 19951996 · 1,928 citations
  2. 2Functional information in SWISS-PROT: The basis for large-scale characterisation of protein sequences2001 · 63 citations
  3. 3Representation of functional information in the SWISS-PROT Data Bank1999 · 46 citations
  4. 4EDITtoTrEMBL: a distributed approach to high-quality automated protein sequence annotation.1999 · 47 citations
  5. 5CluSTr: a database of clusters of SWISS-PROT+TrEMBL proteins2001 · 121 citations