Protease Substrate Site Predictors Based on Multilevel Substrate Phage Display Data

摘要

BackgroundPredictions of the substrate sites in a proteome for the proteases would facilitate understanding the biological functions of the proteases. High throughput experiments could generate suitable dataset for machine learning to grasp complex relationships between the substrate sequences and the enzymatic specifieities.But the capability in predicting protease substrate sites by integrating the machine learning algorithms with the experimental methodology has yet to be demonstrated.Data & MethodsFactor Xa, a key regulatory protease in the blood coagulation system, was used as model system. A multilevel substrate phage display experiment together with quantitative enzyme-linked immuno sorbent assay (ELISA) were carried out to produce the dataset (Hsu, H.J., et al), named DS-312, consisting of 312 6-residue sequences as well as the corresponding kobs values which represent the binding specificity between the substrate sequences and factor Xa (fXa).