Abstract
Antifreeze proteins (AFPs) are found in different living organisms like plants, insects, and fish. AFPs avoid the formation of ice crystals in these organisms and make them able to survive in high cold regions. AFPs are widely deployed in metabolic genetic engineering, food technology, yogurt making, and cryopreservation. Considering the significance of AFPs, several predictors were proposed to identify AFPs. However, due to the unsatisfactory results of the predictors, more accurate predictors are critical. We carried out a thorough survey and summarized AFPs predictors that were developed for identification of AFPs. We provided a brief description of applied datasets, feature descriptors, model training classifiers, performance assessment parameters, and web servers. In this review article, the drawbacks of the proposed predictors and the best predictors were highlighted. We explained the future insights and more effective feature descriptors, appropriate feature selection techniques, and efficient classifiers that can enhance the performance of novel predictors for fast and accurate identification of AFPs.
•Performed a survey of the existing predictors for prediction of antifreeze proteins.•Several predictors were developed for prediction of antifreeze proteins.•Provided a brief description of applied datasets, feature descriptors, and classifiers.•Highlighted the best methods for prediction of antifreeze proteins.