@Article{Kundu_Costa_Backofen-graph_kerne_appro-2013,
  author =	 {Kundu, Kousik and Costa, Fabrizio and Backofen, Rolf},
  title =	 {A graph kernel approach for alignment-free domain-peptide 
                  interaction prediction with an application to human {SH3} 
                  domains},
  journal =	 {Bioinformatics},
  year =	 {2013},
  volume =	 {29},
  number =	 {13},
  pages =	 {i335-i343},
  user =	 {kousik},
  pmid =	 {23813002},
  doi = 	 {10.1093/bioinformatics/btt220},
  issn = 	 {1367-4811},
  issn = 	 {1367-4803},
  abstract =	 {MOTIVATION: State-of-the-art experimental data for 
                  determining binding specificities of peptide recognition 
                  modules (PRMs) is obtained by high-throughput approaches 
                  like peptide arrays. Most prediction tools applicable to 
                  this kind of data are based on an initial multiple alignment 
                  of the peptide ligands. Building an initial alignment can be 
                  error-prone, especially in the case of the proline-rich 
                  peptides bound by the SH3 domains. RESULTS: Here, we present 
                  a machine-learning approach based on an efficient 
                  graph-kernel technique to predict the specificity of a large 
                  set of 70 human SH3 domains, which are an important class of 
                  PRMs. The graph-kernel strategy allows us to (i) integrate 
                  several types of physico-chemical information for each amino 
                  acid, (ii) consider high-order correlations between these 
                  features and (iii) eliminate the need for an initial peptide 
                  alignment. We build specialized models for each human SH3 
                  domain and achieve competitive predictive performance of 
                  0.73 area under precision-recall curve, compared with 0.27 
                  area under precision-recall curve for state-of-the-art 
                  methods based on position weight matrices. We show that 
                  better models can be obtained when we use information on the 
                  noninteracting peptides (negative examples), which is 
                  currently not used by the state-of-the art approaches based 
                  on position weight matrices. To this end, we analyze two 
                  strategies to identify subsets of high confidence negative 
                  data. The techniques introduced here are more general and 
                  hence can also be used for any other protein domains, which 
                  interact with short peptides (i.e. other PRMs). 
                  AVAILABILITY: The program with the predictive models can be 
                  found at 
                  http://www.bioinf.uni-freiburg.de/Software/SH3PepInt/SH3PepInt.tar.gz. 
                  We also provide a genome-wide prediction for all 70 human 
                  SH3 domains, which can be found under 
                  http://www.bioinf.uni-freiburg.de/Software/SH3PepInt/Genome-Wide-Predictions.tar. 
                  gz. CONTACT: backofen@informatik.uni-freiburg.de 
                  SUPPLEMENTARY INFORMATION: Supplementary data are available 
                  at Bioinformatics online.}
}