GasPhos: Protein Phosphorylation Site Prediction Using a New Feature Selection Approach with a GA-Aided Ant Colony System

Abstract

Protein phosphorylation is one of the most important post-translational modifications, and many biological processes are related to phosphorylation, such as DNA repair, transcriptional regulation and signal transduction and, therefore, abnormal regulation of phosphorylation usually causes diseases. If we can accurately predict human phosphorylation sites, this could help to solve human diseases. Therefore, we developed a kinase-specific phosphorylation prediction system, GasPhos, and proposed a new feature selection approach, called Gas, based on the ant colony system and a genetic algorithm and used performance evaluation strategies focused on different kinases to choose the best learning model. Gas uses the mean decrease Gini index (MDGI) as a heuristic value for path selection and adopts binary transformation strategies and new state transition rules. GasPhos can predict phosphorylation sites for six kinases and showed better performance than other phosphorylation prediction tools. The disease-related phosphorylated proteins that were predicted with GasPhos are also discussed. Finally, Gas can be applied to other issues that require feature selection, which could help to improve prediction performance. GasPhos is available at http://predictor.nchu.edu.tw/GasPhos.

In silico analysis of alpha‐synuclein protein variants and posttranslational modifications related to Parkinson's disease

“…All other algorithms use some form of machine learning and kinase‐specific information in their calculations. NetPhos3.1 uses neural networks, 49 GPS5.0 uses position‐specific scoring matrices, 50 PPSP uses Bayesian probability and decision, 51 Phos3D uses support vector machine, 52 and GasPhos uses a specific genetic algorithm‐aided ant colony system 53 …”

“…NetPhos3.1 uses neural networks, 49 GPS5.0 uses position-specific scoring matrices, 50 PPSP uses Bayesian probability and decision, 51 Phos3D uses support vector machine, 52 and GasPhos uses a specific genetic algorithm-aided ant colony system. 53 The SUMOplot™ Analysis Program is the only algorithm used that is a proprietary, closed source algorithm, it is freely available to use at: https://www. abcepta.com/sumoplot.…”

DF-Phos: Prediction of Protein Phosphorylation Sites by Deep Forest

“…Due to the larger number of negative sites than positive sites, it is very likely to train a biased classi er that would lead to predicting most of the unknown sites as negative [9]. Thus, to overcome the problem, we randomly selected negative sites to match the number of positive examples [29], [16]. Finally, the data obtained from human and mouse species were combined, and to reduce sequence redundancy in the extracted datasets and avoid potential bias in model training, the redundant sequences were removed using the CD-HIT tool [30] with a similarity threshold of 90%.…”

Editorial of Special Issue “Protein Post-Translational Modifications in Signal Transduction and Diseases”

“…Predicting PTM sites still remains one open challenge in biochemistry and biology. Aiming at improving the identification of potential disease-related phosphorylation patterns, Chen and colleagues developed a new in silico method for the prediction of kinase-specific phosphorylation, which has been dubbed GasPhos; the algorithm proposed by the authors could represent a useful tool to understand protein–kinase signaling in both physiological and pathological conditions [ 5 ].…”