SeqDeepCys is a deep neural network and machine learning based multiple cysteine post-translational modification prediction based on the protein sequence.The algorithm predicts for seven cysteine post-translational modifications namelyDisulphide,Metal-binding,S-glutathionylation, S-nitrosylation,S-palmitoylation,S-sulphenylation and Thioether based on the protein sequence. This neural network or machine learning model was trained and tested on two independent datasets curated from the protein sequences.The prediction method requires two inputs namely Sequence, and Residue ID for a given cysteine and outputs the probabilities of seven cysteine post-translational modifications.
In this study we present a deep neural network and machine learning-based approach to predict any one of the seven most abundant cysteine post-translational modifications. Novelty of this work was prediction of maximum number of cysteine modifications. Moreover, Thioether prediction was not attempted earlier.The SeqDeepCys model developed in this work requires the protein Sequence and the Residue number. Two features were either extracted or computed from the sequence those were used by the deep neural network and machine learning approach.The final output was the probability values for seven cysteine modifications,namely,Disulphide, Metal-Binding, Thioether, S-glutathionylation, S-nitrosylation, S-palmitoylation and S-sulphenylation. The modification with highest probability was reported as the predicted modification.
