Overview of the proposed methodology for predicting GHBPs that involved the following steps. (i) data set construction; (ii) feature extraction; (iii) feature ranking; (iv) exploration of various machine learning algorithms and an appropriate selection based on the performance produced using sequential forward search; (v) construction of the final prediction model that separates the input into putative GHBPs and non-GHBPs.
Reference
iGHBP: Computational Identification of Growth Hormone Binding Proteins from Sequences Using Extremely Randomised Tree (Computational & Structural Biotechnology Journal16, 412-420). Please cite this paper if you find iGHBP useful in your research]
