AFP-SPTS: An Accurate Prediction of Antifreeze Proteins Using Sequential and Pseudo-Tri-Slicing Evolutionary Features with an Extremely Randomized Tree

Abstract

The development of intracellular ice in the bodies of cold-blooded living organisms may cause them to die. These species yield antifreeze proteins (AFPs) to live in subzero temperature environments. Additionally, AFPs are implemented in biotechnological, industrial, agricultural, and medical fields. Machine learning-based predictors were presented for AFP identification. However, more accurate predictors are still highly desirable for boosting the AFP prediction. This work presents a novel approach, named AFP-SPTS, for the correct prediction of AFPs. We explored the discriminative features with four schemes, namely, dipeptide deviation from the expected mean (DDE), reduced amino acid alphabet (RAAA), grouped dipeptide composition (GDPC), and a novel representative method, called pseudo-position-specific scoring matrix tri-slicing (PseTS-PSSM). Considering the advantages of ensemble learning strategy, we fused each feature vector into different combinations and trained the models with five machine learning algorithms, i.e., multilayer perceptron (MLP), extremely randomized tree (ERT), decision tree (DT), random forest (RF), and AdaBoost. Among all models, PseTS-PSSM + RAAA with an extremely randomized tree attained the best outcomes. The proposed predictor (AFP-SPTS) boosted the accuracies of AFPs in the literature by 1.82 and 4.1%.

Recent Advances in Machine Learning-Based Models for Prediction of Antiviral Peptides

“…It interprets the performance of classifier and addresses the model deficiency. Akbar et al used eXtreme Gradient Boosting classifier to perform classification and prediction tasks[ 43 ].…”

“…Keeping in view the majority voting benefits, the high variance or bias of a single tree can’t affect the overall performance of a model [ 63 ]. Onward, RF uses the weighting scheme that assigns a low weight if a tree has high error rate and boosts the tree performance[ 43 ]. RF is mostly favorable for large datasets, handling efficiently missing data, and detecting of outlier issues [ 64 ].…”

“…Generative model produces images from random noise and seeks to produce realistic images [ 43 ]. To complete this process, random noise is provided to generator that yields fake images.…”

Prediction of Amyloid Proteins Using Embedded Evolutionary & Ensemble Feature Selection Based Descriptors With eXtreme Gradient Boosting Model

“…However, DDE enhance the specific proteins associated with pathway prevention. DDE as compared to DPC has performed remarkably better for predicting different biological sequences such as Identification of Enzymes-specific Protein Domain [57], Pathway-Specific Protein Domain [58], and Antifreeze Proteins [59]. As compare to other formulation methods, these models reported the higher predictive rates via DDE features.…”

Accurate Prediction of Antifreeze Protein from Sequences through Natural Language Text Processing and Interpretable Machine Learning Approaches

“…We compared the model constructed in this study with the other existing methods. We have taken the results of recently developed methods for AFPs prediction: AFP-SPTS, AFP-Pred, CryoProtect, AFP-pseAAC, and AFP-LSE from the literature. Miyata et al 48 constructed different data sets for AFP prediction; as a result, we cannot compare the results with our method.…”