Abstract
Protein-protein interaction (PPI) networks are naturally viewed as infrastructure to infer signalling pathways. The descriptors of signal events between two interacting proteins such as upstream/downstream signal flow, activation/inhibition relationship and protein modification are indispensable for inferring signalling pathways from PPI networks. However, such descriptors are not available in most cases as most PPI networks are seldom semantically annotated. In this work, we extend ℓ2-regularized logistic regression to the scenario of multi-label learning for predicting the activation/inhibition relationships in human PPI networks. The phenomenon that both activation and inhibition relationships exist between two interacting proteins is computationally modelled by multi-label learning framework. The problem of GO (gene ontology) sparsity is tackled by introducing the homolog knowledge as independent homolog instances. ℓ2-regularized logistic regression is accordingly adopted here to penalize the homolog noise and to reduce the computational complexity of the double-sized training data. Computational results show that the proposed method achieves satisfactory multi-label learning performance and outperforms the existing phenotype correlation method on the experimental data of Drosophila melanogaster. Several predictions have been validated against recent literature. The predicted activation/inhibition relationships in human PPI networks are provided in the supplementary file for further biomedical research.
Highlights
Protein-protein interactions (PPIs) play important roles in mediating gene expression & regulation, cell signalling and organismal development
In14, functional PPIs are annotated with activation/inhibition relationships. Those activation/inhibition relationships annotated to functional PPIs are removed, as we primarily focus on signal transduction via physical protein-protein interactions
To construct the third class others, we randomly sample in the physical PPI space that is generated by combining the PPIs in HPRD and HitPredict and excluding those activation/inhibition relationships that already occur in the training set
Summary
Is to date no computational method developed for predicting the activation/inhibition relationships in human PPI networks. The only existing computational method that predicts activation/inhibition relationships focuses on relatively small-scale Drosophila melanogaster PPI networks[10]. We extend l2-regularized logistic regression method to multi-label learning scenario for predicting the activation/inhibition relationships in human PPI networks. In this method, the available experimental activation/inhibition data are directly exploited as training data. The available experimental activation/inhibition data are directly exploited as training data The phenomenon that both activation and inhibition exist between two interacting proteins is computationally modelled by multi-label learning framework. To demonstrate the efficacies of the proposed method, we conduct ten-fold cross validation &independent test on human activation/inhibition data and performance comparison with the existing phenotype correlation method on Drosophila melanogaster activation/inhibition data. We apply the trained model to annotate human PPI networks with activation/inhibition relationships for further biomedical research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
