BindN+ for predicting DNA and RNA-binding residues in protein sequences

BindN+, an upgraded version of BindN, applies support vector machines (SVMs) to sequence-based prediction of DNA or RNA-binding residues from biochemical features and evolutionary information. The SVM classifiers have been constructed using two curated datasets (PDNA-62 and PRINR25) from the Protein Data Bank. For a query sequence, the BindN+ system performs a three-iteration PSI-BLAST search against the UniProtKB database to derive evolutionary information. Because of the PSI-BLAST search, BindN+ runs more slowly than BindN. Please be patient.

For DNA-binding residues, the prediction accuracy estimated from cross-validation is about 79% with equal sensitivity and specificity. For RNA-binding residues, the estimated accuracy is over 75%. The performance of BindN+ has further been verified using two separate test datasets (TestPDB and TestSP). Please send your comments or suggestions to liangjw@clemson.edu.

	BindN+ for sequence-based prediction of DNA and RNA-binding residues

	BindN+, an upgraded version of BindN, applies support vector machines (SVMs) to sequence-based prediction of DNA or RNA-binding residues from biochemical features and evolutionary information. The SVM classifiers have been constructed using two curated datasets (PDNA-62 and PRINR25) from the Protein Data Bank. For a query sequence, the BindN+ system performs a three-iteration PSI-BLAST search against the UniProtKB database to derive evolutionary information. Because of the PSI-BLAST search, BindN+ runs more slowly than BindN. Please be patient. For DNA-binding residues, the prediction accuracy estimated from cross-validation is about 79% with equal sensitivity and specificity. For RNA-binding residues, the estimated accuracy is over 75%. The performance of BindN+ has further been verified using two separate test datasets (TestPDB and TestSP). Please send your comments or suggestions to liangjw@clemson.edu.

Paste your amino acid sequence in FASTA format: