A probabilistic classification system for predicting the cellular localization sites of proteins.

P. Horton, K. Nakai

Research output: Contribution to journalArticlepeer-review

230 Citations (Scopus)

Abstract

We have defined a simple model of classification which combines human provided expert knowledge with probabilistic reasoning. We have developed software to implement this model and have applied it to the problem of classifying proteins into their various cellular localization sites based on their amino acid sequences. Since our system requires no hand tuning to learn training data, we can now evaluate the prediction accuracy of protein localization sites by a more objective cross-validation method than earlier studies using production rule type expert systems. 336 E. coli proteins were classified into 8 classes with an accuracy of 81% while 1484 yeast proteins were classified into 10 classes with an accuracy of 55%. Additionally we report empirical results using three different strategies for handling continuously valued variables in our probabilistic reasoning system.

Original languageEnglish
Pages (from-to)109-115
Number of pages7
JournalProceedings / ... International Conference on Intelligent Systems for Molecular Biology ; ISMB. International Conference on Intelligent Systems for Molecular Biology
Volume4
Publication statusPublished - 1996

All Science Journal Classification (ASJC) codes

  • Medicine(all)

Fingerprint Dive into the research topics of 'A probabilistic classification system for predicting the cellular localization sites of proteins.'. Together they form a unique fingerprint.

Cite this