Predicting Transmembrane β-barrel Segments with Chain Learning and Sparse Coding

摘要

We developed a novel method named MemBrain-TMB to predict the spanning segments of transmembrane β-barrel from amino acid sequence. MemBrain-beta is a statistical machine learning-based model, which is constructed using a new chain learning algorithm with the input features are encoded by the image sparse representation approach. To deal with the diverse loop length problem, we applied a dynamic threshold method, which is particularly useful for enhancing the recognition of short loops and tight turns. MemBrain-TMB achieves a Q2 accuracy of 93% and SOV of 97% on the benchmark dataset, which is 5%～10% higher than other existing predictors.