Limits...
Computational learning on specificity-determining residue-nucleotide interactions.

Wong KC, Li Y, Peng C, Moses AM, Zhang Z - Nucleic Acids Res. (2015)

Bottom Line: Taking into account both sides (protein and DNA), we propose and describe a computational study for learning the specificity-determining residue-nucleotide interactions of different known DNA-binding domain families.The proposed learning models are compared to state-of-the-art models comprehensively, demonstrating its competitive learning performance.In addition, we describe and propose two applications which demonstrate how the learnt models can provide meaningful insights into protein-DNA interactions across different DNA binding families.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong kc.w@cityu.edu.hk.

Show MeSH
Training and Testing Classification Models for Predicting Residue-Nucleotide Interactions on protein–DNA binding sequence pairs. Description can be found on the main text.
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4666365&req=5

Figure 1: Training and Testing Classification Models for Predicting Residue-Nucleotide Interactions on protein–DNA binding sequence pairs. Description can be found on the main text.

Mentions: Based on the CISBP data and PDB data, we can train and test models for learning and predicting the specificity-determining residue–nucleotide interactions for each DBD family. The overall approach is summarized in Figure 1, which can be divided into two phases: training and testing.


Computational learning on specificity-determining residue-nucleotide interactions.

Wong KC, Li Y, Peng C, Moses AM, Zhang Z - Nucleic Acids Res. (2015)

Training and Testing Classification Models for Predicting Residue-Nucleotide Interactions on protein–DNA binding sequence pairs. Description can be found on the main text.
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4666365&req=5

Figure 1: Training and Testing Classification Models for Predicting Residue-Nucleotide Interactions on protein–DNA binding sequence pairs. Description can be found on the main text.
Mentions: Based on the CISBP data and PDB data, we can train and test models for learning and predicting the specificity-determining residue–nucleotide interactions for each DBD family. The overall approach is summarized in Figure 1, which can be divided into two phases: training and testing.

Bottom Line: Taking into account both sides (protein and DNA), we propose and describe a computational study for learning the specificity-determining residue-nucleotide interactions of different known DNA-binding domain families.The proposed learning models are compared to state-of-the-art models comprehensively, demonstrating its competitive learning performance.In addition, we describe and propose two applications which demonstrate how the learnt models can provide meaningful insights into protein-DNA interactions across different DNA binding families.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong kc.w@cityu.edu.hk.

Show MeSH