A Novel Sequence-Based Method of Predicting Protein DNA-Binding Residues, Using a Machine Learning Approach

다국어 초록 (Multilingual Abstract)

Protein-DNA interactions play an essential role in tran-scriptional regulation, DNA repair, and many vital biologi-cal processes. The mechanism of protein-DNA binding, however, remains unclear. For the study of many diseases, researchers must improve their understanding of the amino acid motifs that recognize DNA. Because identifying these motifs experimentally is expensive and time-consuming, it is necessary to devise an approach for computational pre-diction. Some in silico methods have been developed, but there are still considerable limitations. In this study, we used a machine learning approach to develop a new se-quence-based method of predicting protein-DNA binding residues. To make these predictions, we used the proper-ties of the micro-environment of each amino acid from the AAIndex as well as conservation scores. Testing by the cross-validation method, we obtained an overall accuracy of 94.89%. Our method shows that the amino acid micro-environment is important for DNA binding, and that it is possible to identify the protein-DNA binding sites with it.

참고문헌 (Reference)

1 Qian, Z., "novel computational method to predict transcription factor DNA binding preference" 348 : 1034-1037, 2006

2 Horton, P., "WoLF PSORT: protein localization predictor" 35 : W585-W587, 2007

3 Berman, H.M., "The protein data bank" 28 : 235-242, 2000

4 Warner, J.B., "Systematic identification of mammalian regulatory motifs’ target genes and functions" 5 : 347-353, 2008

5 Jones, S., "Searching for functional sites in protein structures" 8 : 3-7, 2004

6 Valdar, W.S., "Scoring residue conservation" 48 : 227-241, 2002

7 Gromiha, M.M., "Role of inter and intramolecular interactions in protein-DNA recognition" 364 : 108-113, 2005

8 Bullock, A.N., "Rescuing the function of mutant p53" 1 : 68-76, 2001

9 Salamov, A.A., "Protein secondary structure prediction using local alignments" 268 : 31-36, 1997

10 Sim, J., "Prediction of protein solvent accessibility using fuzzy k-nearest neighbor method" 21 : 2844-2849, 2005

11 Vavouri, T., "Prediction of cis-regulatory elements using binding site matrices--the successes, the failures and the reasons for both" 15 : 395-402, 2005

12 Ofran, Y., "Prediction of DNAbinding residues from sequence" 23 : i347-i353, 2007

13 Wu, J., "Prediction of DNA-binding residues in proteins from amino acid sequences using a random forest model with a hybrid feature" 25 : 30-35, 2009

14 Wang, L., "Prediction of DNA-binding residues from sequence features" 4 : 1141-1158, 2006

15 Jamal Rahi, S., "Predicting transcription factor specificity with all-atom models" 36 : 6209-6217, 2008

16 Pietsch, E.C., "Oligomerization of BAK by p53 utilizes conserved residues of the p53 DNA binding domain" 283 : 21294-21304, 2008

17 Tan, K., "Making connections between novel transcription factors and their DNA motifs" 15 : 312-320, 2005

18 Fugmann, S.D., "Identification of basic residues in RAG2 critical for DNA binding by the RAG1-RAG2 complex" 8 : 899-910, 2001

19 Whitington, T., "High-throughput chromatin information enables accurate tissue-specific prediction of transcription factor binding sites" 37 : 14-25, 2009

20 Cao, X., "Glutathionylation of two cysteine residues in paired domain regulates DNA binding activity of Pax-8" 280 : 25901-25906, 2005

21 Altschul, S.F., "Gapped BLAST and PSIBLAST: a new generation of protein database search programs" 25 : 3389-3402, 1997

22 Wong, W.S., "Finding cis-regulatory modules in Drosophila using phylogenetic hidden Markov models" 23 : 2031-2037, 2007

23 Peng, H., "Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy" 27 : 1226-1238, 2005

24 Ho, S.Y., "Design of accurate predictors for DNA-binding sites in proteins using hybrid SVM-PSSM method" 90 : 234-241, 2007

25 Hwang, S., "DP-Bind: a web server for sequence-based prediction of DNA-binding residues in DNA-binding proteins" 23 : 634-636, 2007

26 Gao, M., "DBD-Hunter: a knowledge-based method for the prediction of DNA-protein interactions" 36 : 3978-3992, 2008

27 Larkin, M.A., "Clustal W and Clustal X version 2.0" 23 : 2947-2948, 2007

28 Noyes, M.B., "Analysis of homeodomain specificities allows the family-wide prediction of preferred recognition sites" 133 : 1277-1289, 2008

29 Ahmad, S., "Analysis and prediction of DNA-binding proteins and their binding residues based on composition,sequence and structural information" 20 : 477-486, 2004

30 Luscombe, N.M., "An overview of the structures of protein-DNA complexes" 1 : REVIEWS001-, 2000

31 Kaplan, T., "Ab initio prediction of transcription factor targets using structural knowledge" 1 : e1-, 2005

32 Sinha, S., "A probabilistic method to detect regulatory modules" 19 : i292-i301, 2003

33 Cai, Y., "A novel computational approach to predict transcription factor DNA binding preference" 8 : 999-1003, 2009