ProsperousPlus: An integrated platform for protease-specific substrate and cleavage site prediction and machine learning models construction.
With the development of mass spectrometry technology, an enormous amount of protease substrate cleavage data has been generated and will continually grow in the future. Consequently, it is not efficient and practical to train new models based on these rapidly accumulated data every year and update the prediction server for the wider community. In addition, some proteomics labs prefer only to use prediction models trained by their own, in-house generated data, instead of publicly available servers to consider data privacy and IP. However, for most end users in proteomics, such a special need is difficult to address because of the need for related programming backgrounds and skill sets. Therefore, developing a user-friendly protease-specific cleavage site prediction server that addresses the above issues would be meaningful to the related fields. ProsperousPlus can allow users to train customised models based on in-house data, enabling the non-bioinformatics labs to readily utilise source codes and modify models according to specific needs. Hence, herein we present ProsperousPlus, a multi-faceted, versatile bioinformatics tool that is capable of accurately predicting protease-specific substrates and cleavage sites by leveraging the advantages and strengths of both scoring function-based and machine learning-based tools, as well as providing sought-after assistance for non-programming background users to build their in-house models and meet specific needs easily. ProsperousPlus represents a state-of-the-art tool that enables fast, accurate and high-throughput prediction of substrate cleavage sites for 110 proteases.
|