@article{Kundu_Costa_Huber-Semi_Predi_Inter-2013,
author = {Kundu, Kousik and Costa, Fabrizio and Huber, Michael and 
          Reth, Michael and Backofen, Rolf},
title = {Semi-{Supervised} {Prediction} of {SH2}-{Peptide} 
         {Interactions} from {Imbalanced} {High}-{Throughput} {Data}},
journal = {PLoS One},
year = {2013},
doi = {10.1371/journal.pone.0062732},
volume = {8},
user = {kousik},
pmid = {23690949},
pages = {e62732},
number = {5},
issn = {1932-6203},
abstract = {Src homology 2 (SH2) domains are the largest family of the 
            peptide-recognition modules (PRMs) that bind to 
            phosphotyrosine containing peptides. Knowledge about binding 
            partners of SH2-domains is key for a deeper understanding of 
            different cellular processes. Given the high binding 
            specificity of SH2, in-silico ligand peptide prediction is 
            of great interest. Currently however, only a few approaches 
            have been published for the prediction of SH2-peptide 
            interactions. Their main shortcomings range from limited 
            coverage, to restrictive modeling assumptions (they are 
            mainly based on position specific scoring matrices and do 
            not take into consideration complex amino acids 
            inter-dependencies) and high computational complexity. We 
            propose a simple yet effective machine learning approach for 
            a large set of known human SH2 domains. We used 
            comprehensive data from micro-array and peptide-array 
            experiments on 51 human SH2 domains. In order to deal with 
            the high data imbalance problem and the high signal-to-noise 
            ration, we casted the problem in a semi-supervised setting. 
            We report competitive predictive performance w.r.t. 
            state-of-the-art. Specifically we obtain 0.83 AUC ROC and 
            0.93 AUC PR in comparison to 0.71 AUC ROC and 0.87 AUC PR 
            previously achieved by the position specific scoring 
            matrices (PSSMs) based SMALI approach. Our work provides 
            three main contributions. First, we showed that better 
            models can be obtained when the information on the 
            non-interacting peptides (negative examples) is also used. 
            Second, we improve performance when considering high order 
            correlations between the ligand positions employing 
            regularization techniques to effectively avoid overfitting 
            issues. Third, we developed an approach to tackle the data 
            imbalance problem using a semi-supervised strategy. Finally, 
            we performed a genome-wide prediction of human SH2-peptide 
            binding, uncovering several findings of biological 
            relevance. We make our models and genome-wide predictions, 
            for all the 51 SH2-domains, freely available to the 
            scientific community under the following URLs: 
            http://www.bioinf.uni-freiburg.de/Software/SH2PepInt/SH2PepInt.tar.gz 
            and 
            http://www.bioinf.uni-freiburg.de/Software/SH2PepInt/Genome-wide-predictions.tar. 
            gz, respectively.}
}