Prediction of transcription factor binding to DNA using rule induction methods
2006 (English)In: Journal of Integrative Bioinformatics - JIB, ISSN 1613-4516, Vol. 3, no 2, 42- p.Article in journal (Refereed) Published
In this study, we seek to develop a predictive model for finding the strength of bindingbetween a particular transcription factor (TF) variant and a particular DNA target variant.The DNA binding paired domains of the Pax transcription factors, which are our mainfocus, show seemingly fuzzy and degenerate binding to various DNA targets, and paireddomain-DNA binding is not a problem well suited for previously proposed algorithms.Here, we introduce a simple way to use rule induction for predicting the strength of TFDNAbinding. We have created a dataset consisting of 597 example cases for paireddomain-DNA binding by collecting information about all published and quantifiedinteractions between TF and DNA sequence variants. Application of the rule inductionbased method on this dataset yields a high, although far from ideal accuracy of 69.7%(based on cross-validation), but perhaps more importantly, several useful rules forpredicting the binding strength have been found. Although the primary motivation forintroducing the rule induction based methods is the lack of efficient algorithms for paireddomain-DNA binding prediction, we also show that the method can be applied with somesuccess to a more well-studied TF-DNA binding prediction task involving the earlygrowth response (EGR) TF family.
Place, publisher, year, edition, pages
2006. Vol. 3, no 2, 42- p.
Bioinformatics (Computational Biology)
IdentifiersURN: urn:nbn:se:uu:diva-183602DOI: 10.2390/biecoll-jib-2006-42OAI: oai:DiVA.org:uu-183602DiVA: diva2:563437
3rd Integrative Bioinformatics Workshop, September 4-6th, 2006, Harpenden, United Kingdom