@inproceedings{bccce908bd1f4470bd42a6762e775522,
title = "Intelligent extraction versus advanced query: Recognize transcription factors from databases",
abstract = "Many entries in major biological databases have incomplete functional annotation and thus, frequently, it is difficult to identify entries for a specific functional category. We combined information of protein functional domains and gene ontology descriptions for highly accurate identification of transcription factor (TF) entries in Swiss-Prot and Entrez Gene databases. Our method utilizes support vector machines and it efficiently separates TF entries from non-TF entries. The 10-fold cross validation of predictions produced on average a positive predictive value of 97.5% and sensitivity of 93.4%. Using this method we have scanned the whole Swiss-Prot and Entrez Gene databases and extracted 13826 unique TF entries. Based on a separate manual test of 500 randomly chosen extracted TF entries, we found that the non-TF (erroneous) entries were present in 2% of the cases.",
author = "Zhuo Zhang and Merlin Veronika and Ng, {See Kiong} and Bajic, {Vladimir B.}",
year = "2006",
doi = "10.1007/11818564_15",
language = "English (US)",
isbn = "3540374469",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "133--139",
booktitle = "Pattern Recognition in Bioinformatics - International Workshop, PRIB 2006, Proceedings",
address = "Germany",
note = "International Workshop on Pattern Recognition in Bioinformatics, PRIB 2006 ; Conference date: 20-08-2006 Through 20-08-2006",
}