Background: The ligand-receptor interaction plays an important role in signal transduction required for cellular differentiation, proliferation, and immune response process. The analysis of ligand-receptor interactions is helpful to provide a deeper understanding of cellular proliferation/differentiation and other cell processes.
Method: The computational technique would be used to promote ligand-receptor interactions research in future proteomics research. In this paper, we propose a novel computational method to predict ligand-receptor interactions from amino acid sequences by a machine learning approach. We extract features from ligand and receptor sequences by Histogram of Oriented Gradient (HOG) and Discrete Cosine Transform (DCT). Then, these features are fed into the Fuzzy C-means clustering algorithm (FCM) for clustering, and also we get multiple training subsets to generate the same number of sub-classifiers. We choose an optimal sub-classifier for predicting ligand-receptor interactions according to the similarity from one sample to training subsets.
Observations: In order to verify the performance, we perform five-fold cross-validation experiments on a ligand-receptor interactions dataset and achieve 80.08% accuracy, 82.98% sensitivity and 80.02% specificity. Then, we test our extracted feature method on two protein-protein interactions (PPIs) datasets, and achieve accuracies of 93.79% and 87.46%, respectively.
Conclusion: Our proposed method can be a useful tool for identifying of ligand-receptor interactions. Related data sets and source code are available at https://github.com/guofei-tju/ligand-receptor-interactions.git.