In prior study, our group have approved a tool for predicting Hydrophobic interaction of monoclonal antibodies using sequences, which called SSH.The the result of SSH is determined by the p-values of all the three models and SSH achieved an accuracy of 91.22%.

In this study, We used different feature extraction methods to characterize the sequences. The descending dimension method, MRMD2.0^[1], based on the PageRank algorithm allowed us to get fewer features than SSH and the sensitivity of SSH2.0 achieved 100%.