Chou׳s pseudo amino acid composition improves sequence-based antifreeze protein prediction

A stacking-based algorithm for antifreeze protein identification using combined physicochemical, pseudo amino acid composition, and reduction property features

Antifreeze proteins have wide applications in the medical and food industries. In this study, we propose a stacking-based classifier that can effectively identify antifreeze proteins. Initially, feature extraction was performed in three aspects: reduction properties, scalable pseudo amino acid composition, and physicochemical properties. A hybrid feature set comprised of the combined information from these three categories was obtained. Subsequently, we trained the training set based on LightGBM, XGBoost, and RandomForest algorithms, and the training outcomes were passed to the Logistic algorithm for matching, thereby establishing a stacking algorithm. The proposed algorithm was tested on the test set and an independent validation set. Experimental data indicates that the algorithm achieved a recognition accuracy of 98.3 %, and an accuracy of 98.5 % on the validation set. Lastly, we analyzed the reasons why numerical features achieved high recognition capabilities from multiple aspects. Data dimensionality reduction and the analysis from two-dimensional and three-dimensional views revealed separability between positive and negative samples, and the protein three-dimensional structure further demonstrated significant differences in related features between the two samples. Analysis of the classifier revealed that Hr*Hr, HrHr, and Sc-PseAAC_1, 188D(152,116,57,183) were among the seven most important numerical features affecting algorithm recognition. For Hr*Hr and HrHr, supportive sequence level evidence for the reduction dictionary was found in terms of conservation area analysis, multiple sequence alignment, and amino acid conservative substitution. Moreover, the importance of the reduction dictionary was recognized through a comparative analysis of importance before and after the reduction, realizing the effectiveness of the dictionary in improving feature importance. A decision tree model has been utilized to discern the distinctions between dipeptides associated with the physical and chemical properties of His(H), Iso(I), Leu(L), and Lys(K) and other dipeptides. We finally analyzed the other seven features of importance, and data analysis confirmed that hydrophobicity, secondary structure, charge properties, van der Waals forces, and solvent accessibility are also factors affecting the antifreeze capability of proteins.

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

Antifreeze proteins (AFPs) bind to growing iceplanes owing to their structural complementarity nature, thereby inhibiting the ice-crystal growth by thermal hysteresis. Classification of AFPs from sequence is a difficult task due to their low sequence similarity, and therefore, the usual sequence similarity algorithms, like Blast and PSI-Blast, are not efficient. Here, a method combining n-gram feature vectors and machine learning models to accelerate the identification of potential AFPs from sequences is proposed. All these n-gram features are extracted from the K-mer counting method. The comparative analysis reveals that, among different machine learning models, Xgboost outperforms others in predicting AFPs from sequence when penta-mers are used as a feature vector. When tested on an independent dataset, our method performed better compared to other existing ones with sensitivity of 97.50%, recall of 98.30%, and f1 score of 99.10%. Further, we used the SHAP method, which provides important insight into the functional activity of AFPs.

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

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%.

Prediction of antifreeze proteins using machine learning

Living organisms including fishes, microbes, and animals can live in extremely cold weather. To stay alive in cold environments, these species generate antifreeze proteins (AFPs), also referred to as ice-binding proteins. Moreover, AFPs are extensively utilized in many important fields including medical, agricultural, industrial, and biotechnological. Several predictors were constructed to identify AFPs. However, due to the sequence and structural heterogeneity of AFPs, correct identification is still a challenging task. It is highly desirable to develop a more promising predictor. In this research, a novel computational method, named AFP-LXGB has been proposed for prediction of AFPs more precisely. The information is explored by Dipeptide Composition (DPC), Grouped Amino Acid Composition (GAAC), Position Specific Scoring Matrix-Segmentation-Autocorrelation Transformation (Sg-PSSM-ACT), and Pseudo Position Specific Scoring Matrix Tri-Slicing (PseTS-PSSM). Keeping the benefits of ensemble learning, these feature sets are concatenated into different combinations. The best feature set is selected by Extremely Randomized Tree-Recursive Feature Elimination (ERT-RFE). The models are trained by Light eXtreme Gradient Boosting (LXGB), Random Forest (RF), and Extremely Randomized Tree (ERT). Among classifiers, LXGB has obtained the best prediction results. The novel method (AFP-LXGB) improved the accuracies by 3.70% and 4.09% than the best methods. These results verified that AFP-LXGB can predict AFPs more accurately and can participate in a significant role in medical, agricultural, industrial, and biotechnological fields.

Cold adaptation strategies in plants—An emerging role of epigenetics and antifreeze proteins to engineer cold resilient plants

Cold stress adversely affects plant growth, development, and yield. Also, the spatial and geographical distribution of plant species is influenced by low temperatures. Cold stress includes chilling and/or freezing temperatures, which trigger entirely different plant responses. Freezing tolerance is acquired via the cold acclimation process, which involves prior exposure to non-lethal low temperatures followed by profound alterations in cell membrane rigidity, transcriptome, compatible solutes, pigments and cold-responsive proteins such as antifreeze proteins. Moreover, epigenetic mechanisms such as DNA methylation, histone modifications, chromatin dynamics and small non-coding RNAs play a crucial role in cold stress adaptation. Here, we provide a recent update on cold-induced signaling and regulatory mechanisms. Emphasis is given to the role of epigenetic mechanisms and antifreeze proteins in imparting cold stress tolerance in plants. Lastly, we discuss genetic manipulation strategies to improve cold tolerance and develop cold-resistant plants.

R5hmCFDV: computational identification of RNA 5-hydroxymethylcytosine based on deep feature fusion and deep voting

RNA 5-hydroxymethylcytosine (5hmC) is a kind of RNA modification, which is related to the life activities of many organisms. Studying its distribution is very important to reveal its biological function. Previously, high-throughput sequencing was used to identify 5hmC, but it is expensive and inefficient. Therefore, machine learning is used to identify 5hmC sites. Here, we design a model called R5hmCFDV, which is mainly divided into feature representation, feature fusion and classification. (i) Pseudo dinucleotide composition, dinucleotide binary profile and frequency, natural vector and physicochemical property are used to extract features from four aspects: nucleotide composition, coding, natural language and physical and chemical properties. (ii) To strengthen the relevance of features, we construct a novel feature fusion method. Firstly, the attention mechanism is employed to process four single features, stitch them together and feed them to the convolution layer. After that, the output data are processed by BiGRU and BiLSTM, respectively. Finally, the features of these two parts are fused by the multiply function. (iii) We design the deep voting algorithm for classification by imitating the soft voting mechanism in the Python package. The base classifiers contain deep neural network (DNN), convolutional neural network (CNN) and improved gated recurrent unit (GRU). And then using the principle of soft voting, the corresponding weights are assigned to the predicted probabilities of the three classifiers. The predicted probability values are multiplied by the corresponding weights and then summed to obtain the final prediction results. We use 10-fold cross-validation to evaluate the model, and the evaluation indicators are significantly improved. The prediction accuracy of the two datasets is as high as 95.41% and 93.50%, respectively. It demonstrates the stronger competitiveness and generalization performance of our model. In addition, all datasets and source codes can be found at https://github.com/HongyanShi026/R5hmCFDV.

βLact-Pred: A Predictor Developed for Identification of Beta-Lactamases Using Statistical Moments and PseAAC via 5-Step Rule

Beta-lactamase (β-lactamase) produced by different bacteria confers resistance against β-lactam-containing drugs. The gene encoding β-lactamase is plasmid-borne and can easily be transferred from one bacterium to another during conjugation. By such transformations, the recipient also acquires resistance against the drugs of the β-lactam family. β-Lactam antibiotics play a vital significance in clinical treatment of disastrous diseases like soft tissue infections, gonorrhoea, skin infections, urinary tract infections, and bronchitis. Herein, we report a prediction classifier named as βLact-Pred for the identification of β-lactamase proteins. The computational model uses the primary amino acid sequence structure as its input. Various metrics are derived from the primary structure to form a feature vector. Experimentally determined data of positive and negative beta-lactamases are collected and transformed into feature vectors. An operating algorithm based on the artificial neural network is used by integrating the position relative features and sequence statistical moments in PseAAC for training the neural networks. The results for the proposed computational model were validated by employing numerous types of approach, i.e., self-consistency testing, jackknife testing, cross-validation, and independent testing. The overall accuracy of the predictor for self-consistency, jackknife testing, cross-validation, and independent testing presents 99.76%, 96.07%, 94.20%, and 91.65%, respectively, for the proposed model. Stupendous experimental results demonstrated that the proposed predictor “βLact-Pred” has surpassed results from the existing methods.

AFP-CMBPred: Computational identification of antifreeze proteins by extending consensus sequences into multi-blocks evolutionary information

In extremely cold environments, living organisms like plants, animals, fishes, and microbes can die due to the intracellular ice formation in their bodies. To sustain life in such cold environments, some cold-blooded species produced Antifreeze proteins (AFPs), also called ice-binding proteins. AFPs are not only limited to the medical field but also have diverse significance in the area of biotechnology, agriculture, and the food industry. Different AFPs exhibit high heterogeneity in their structures and sequences. Keeping the significance of AFPs, several machine-learning-based models have been developed by scientists for the prediction of AFPs. However, due to the complex and diverse nature of AFPs, the prediction performance of the existing methods is limited. Therefore, it is highly indispensable for researchers to develop a reliable computational model that can accurately predict AFPs. In this connection, this study presents a novel predictor for AFPs, named AFP-CMBPred. The sequences of AFPs are formulated via four different feature representation methods, such as Amphiphilic pseudo amino acid composition (Amp-PseAAC), Dipeptide Deviation from Expected Mean (DDE), Multi-Blocks Position Specific Scoring Matrix (MB-PSSM), and Consensus Sequence-based on Multi-Blocks Position Specific Scoring Matrix (CS-MB-PSSM) to collect local and global descriptors. In the next step, the extracted feature vectors are evaluated via Support Vector Machine (SVM) and Random Forest (RF) based classification learners. The prediction performance of both classifiers is further assessed using three validation methods i.e., jackknife test, 10-fold cross-validation test, and independent test. After examining the prediction rates of all validation tests, it was found that our proposed model achieved the higher prediction accuracies of ∼2.65%, ∼2.84%, and ∼3.37% using jackknife, K-fold, and independent test, respectively. The experimental outcomes validate that our proposed "AFP-CMBPred" predictor secured the highest prediction results than the existing models for the identification of AFPs. It is further anticipated that our proposed AFP-CMBPred model will be considered a valuable tool in the research academia and drug development.

Prediction and analysis of antifreeze proteins

Antifreeze proteins (AFPs) are proteins that protect cellular fluids and body fluids from freezing by inhibiting the nucleation and growth of ice crystals and preventing ice recrystallization, thereby contributing to the maintenance of life in living organisms. They exist in fish, insects, microorganisms, and fungi. However, the number of known AFPs is currently limited, and it is essential to construct a reliable dataset of AFPs and develop a bioinformatics tool to predict AFPs. In this work, we first collected AFPs sequences from UniProtKB considering the reliability of annotations and, based on these datasets, developed a prediction system using random forest. We achieved accuracies of 0.961 and 0.947 for non-redundant sequences with less than 90% and 30% identities and achieved the accuracy of 0.953 for representative sequences for each species. Using the ability of random forest, we identified the sequence features that contributed to the prediction. Some sequence features were common to AFPs from different species. These features include the Cys content, Ala-Ala content, Trp-Gly content, and the amino acids' distribution related to the disorder propensity. The computer program and the dataset developed in this work are available from the GitHub site: https://github.com/ryomiya/Prediction-and-analysis-of-antifreeze-proteins.

Predicting antifreeze proteins with weighted generalized dipeptide composition and multi-regression feature selection ensemble

BACKGROUND

Antifreeze proteins (AFPs) are a group of proteins that inhibit body fluids from growing to ice crystals and thus improve biological antifreeze ability. It is vital to the survival of living organisms in extremely cold environments. However, little research is performed on sequences feature extraction and selection for antifreeze proteins classification in the structure and function prediction, which is of great significance.

RESULTS

In this paper, to predict the antifreeze proteins, a feature representation of weighted generalized dipeptide composition (W-GDipC) and an ensemble feature selection based on two-stage and multi-regression method (LRMR-Ri) are proposed. Specifically, four feature selection algorithms: Lasso regression, Ridge regression, Maximal information coefficient and Relief are used to select the feature sets, respectively, which is the first stage of LRMR-Ri method. If there exists a common feature subset among the above four sets, it is the optimal subset; otherwise we use Ridge regression to select the optimal subset from the public set pooled by the four sets, which is the second stage of LRMR-Ri. The LRMR-Ri method combined with W-GDipC was performed both on the antifreeze proteins dataset (binary classification), and on the membrane protein dataset (multiple classification). Experimental results show that this method has good performance in support vector machine (SVM), decision tree (DT) and stochastic gradient descent (SGD). The values of ACC, RE and MCC of LRMR-Ri and W-GDipC with antifreeze proteins dataset and SVM classifier have reached as high as 95.56%, 97.06% and 0.9105, respectively, much higher than those of each single method: Lasso, Ridge, Mic and Relief, nearly 13% higher than single Lasso for ACC.

CONCLUSION

The experimental results show that the proposed LRMR-Ri and W-GDipC method can significantly improve the accuracy of antifreeze proteins prediction compared with other similar single feature methods. In addition, our method has also achieved good results in the classification and prediction of membrane proteins, which verifies its widely reliability to a certain extent.

Analysis of the Sequence Characteristics of Antifreeze Protein

Antifreeze protein (AFP) is a proteinaceous compound with improved antifreeze ability and binding ability to ice to prevent its growth. As a surface-active material, a small number of AFPs have a tremendous influence on the growth of ice. Therefore, identifying novel AFPs is important to understand protein–ice interactions and create novel ice-binding domains. To date, predicting AFPs is difficult due to their low sequence similarity for the ice-binding domain and the lack of common features among different AFPs. Here, a computational engine was developed to predict the features of AFPs and reveal the most important 39 features for AFP identification, such as antifreeze-like/N-acetylneuraminic acid synthase C-terminal, insect AFP motif, C-type lectin-like, and EGF-like domain. With this newly presented computational method, a group of previously confirmed functional AFP motifs was screened out. This study has identified some potential new AFP motifs and contributes to understanding biological antifreeze mechanisms.

iPhosH-PseAAC: Identify Phosphohistidine Sites in Proteins by Blending Statistical Moments and Position Relative Features According to the Chou's 5-Step Rule and General Pseudo Amino Acid Composition

Protein phosphorylation is one of the key mechanism in prokaryotes and eukaryotes and is responsible for various biological functions such as protein degradation, intracellular localization, the multitude of cellular processes, molecular association, cytoskeletal dynamics, and enzymatic inhibition/activation. Phosphohistidine (PhosH) has a key role in a number of biological processes, including central metabolism to signalling in eukaryotes and bacteria. Thus, identification of phosphohistidine sites in a protein sequence is crucial, and experimental identification can be expensive, time-taking, and laborious. To address this problem, here, we propose a novel computational model namely iPhosH-PseAAC for prediction of phosphohistidine sites in a given protein sequence using pseudo amino acid composition (PseAAC), statistical moments, and position relative features. The results of the proposed predictor are validated through self-consistency testing, 10-fold cross-validation, and jackknife testing. The self-consistency validation gave the 100 percent accuracy, whereas, for cross-validation, the accuracy achieved is 94.26 percent. Moreover, jackknife testing gave 97.07 percent accuracy for the proposed model. Thus, the proposed model iPhosH-PseAAC for prediction of iPhosH site has the great ability to predict the PhosH sites in given proteins.

Predicting LncRNA Subcellular Localization Using Unbalanced Pseudo-k Nucleotide Compositions

Background:

Long non-coding RNAs (lncRNAs) are transcripts with a length more than 200 nucleotides, functioning in the regulation of gene expression. More evidence has shown that the biological functions of lncRNAs are intimately related to their subcellular localizations. Therefore, it is very important to confirm the lncRNA subcellular localization.

Methods:

In this paper, we proposed a novel method to predict the subcellular localization of lncRNAs. To more comprehensively utilize lncRNA sequence information, we exploited both kmer nucleotide composition and sequence order correlated factors of lncRNA to formulate lncRNA sequences. Meanwhile, a feature selection technique which was based on the Analysis Of Variance (ANOVA) was applied to obtain the optimal feature subset. Finally, we used the support vector machine (SVM) to perform the prediction.

Results:

The AUC value of the proposed method can reach 0.9695, which indicated the proposed predictor is an efficient and reliable tool for determining lncRNA subcellular localization. Furthermore, the predictor can reach the maximum overall accuracy of 90.37% in leave-one-out cross validation, which clearly outperforms the existing state-of- the-art method.

Conclusion:

It is demonstrated that the proposed predictor is feasible and powerful for the prediction of lncRNA subcellular. To facilitate subsequent genetic sequence research, we shared the source code at https://github.com/NicoleYXF/lncRNA.

Identification of Lysine Carboxylation Sites in Proteins by Integrating Statistical Moments and Position Relative Features via General PseAAC

Background:

Carboxylation is one of the most biologically important post-translational modifications and occurs on lysine, arginine, and glutamine residues of a protein. Among all these three, the covalent attachment of the carboxyl group with the lysine side chain is the most frequent and biologically important type of carboxylation. For studying such biological functions, it is essential to correctly determine the lysine sites sensitive to carboxylation.

Objective:

Herein, we present a computational model for the prediction of the carboxylysine site which is based on machine learning.

Methods:

Various position and composition relative features have been incorporated into the Pse- AAC for construction of feature vectors and a neural network is employed as a classifier. The model is validated by jackknife, cross-validation, self-consistency, and independent testing.

Results:

The results of the self-consistency test elaborated that model has 99.76% Acc, 99.76% Sp, 99.76% Sp, and 0.99 MCC. Using the jackknife method, prediction model validation gave 97.07% Acc, while for 10-fold cross-validation, prediction model validation gave 95.16% Acc.

Conclusion:

The results of independent dataset testing were 94.3% which illustrated that the proposed model has better performance as compared to the existing model PreLysCar; however, the accuracy can be improved further, in the future, due to the increasing number of carboxylysine sites in proteins.

Identification of 4-carboxyglutamate residue sites based on position based statistical feature and multiple classification

Glutamic acid is an alpha-amino acid used by all living beings in protein biosynthesis. One of the important glutamic acid modifications is post-translationally modified 4-carboxyglutamate. It has a significant role in blood coagulation. 4-carboxyglumates are required for the binding of calcium ions. On the contrary, this modification can also cause different diseases such as bone resorption, osteoporosis, papilloma, and plaque atherosclerosis. Considering its importance, it is necessary to predict the occurrence of glutamic acid carboxylation in amino acid stretches. As there is no computational based prediction model available to identify 4-carboxyglutamate modification, this study is, therefore, designed to predict 4-carboxyglutamate sites with a less computational cost. A machine learning model is devised with a Multilayered Perceptron (MLP) classifier using Chou's 5-step rule. It may help in learning statistical moments and based on this learning, the prediction is to be made accurately either it is 4-carboxyglutamate residue site or detected residue site having no 4-carboxyglutamate. Prediction accuracy of the proposed model is 94% using an independent set test, while obtained prediction accuracy is 99% by self-consistency tests.

Accurate multistage prediction of protein crystallization propensity using deep-cascade forest with sequence-based features

X-ray crystallography is the major approach for determining atomic-level protein structures. Because not all proteins can be easily crystallized, accurate prediction of protein crystallization propensity provides critical help in guiding experimental design and improving the success rate of X-ray crystallography experiments. This study has developed a new machine-learning-based pipeline that uses a newly developed deep-cascade forest (DCF) model with multiple types of sequence-based features to predict protein crystallization propensity. Based on the developed pipeline, two new protein crystallization propensity predictors, denoted as DCFCrystal and MDCFCrystal, have been implemented. DCFCrystal is a multistage predictor that can estimate the success propensities of the three individual steps (production of protein material, purification and production of crystals) in the protein crystallization process. MDCFCrystal is a single-stage predictor that aims to estimate the probability that a protein will pass through the entire crystallization process. Moreover, DCFCrystal is designed for general proteins, whereas MDCFCrystal is specially designed for membrane proteins, which are notoriously difficult to crystalize. DCFCrystal and MDCFCrystal were separately tested on two benchmark datasets consisting of 12 289 and 950 proteins, respectively, with known crystallization results from various experimental records. The experimental results demonstrated that DCFCrystal and MDCFCrystal increased the value of Matthew's correlation coefficient by 199.7% and 77.8%, respectively, compared to the best of other state-of-the-art protein crystallization propensity predictors. Detailed analyses show that the major advantages of DCFCrystal and MDCFCrystal lie in the efficiency of the DCF model and the sensitivity of the sequence-based features used, especially the newly designed pseudo-predicted hybrid solvent accessibility (PsePHSA) feature, which improves crystallization recognition by incorporating sequence-order information with solvent accessibility of residues. Meanwhile, the new crystal-dataset constructions help to train the models with more comprehensive crystallization knowledge.

AFP-LSE: Antifreeze Proteins Prediction Using Latent Space Encoding of Composition of k-Spaced Amino Acid Pairs

Species living in extremely cold environments resist the freezing conditions through antifreeze proteins (AFPs). Apart from being essential proteins for various organisms living in sub-zero temperatures, AFPs have numerous applications in different industries. They possess very small resemblance to each other and cannot be easily identified using simple search algorithms such as BLAST and PSI-BLAST. Diverse AFPs found in fishes (Type I, II, III, IV and antifreeze glycoproteins (AFGPs)), are sub-types and show low sequence and structural similarity, making their accurate prediction challenging. Although several machine-learning methods have been proposed for the classification of AFPs, prediction methods that have greater reliability are required. In this paper, we propose a novel machine-learning-based approach for the prediction of AFP sequences using latent space learning through a deep auto-encoder method. For latent space pruning, we use the output of the auto-encoder with a deep neural network classifier to learn the non-linear mapping of the protein sequence descriptor and class label. The proposed method outperformed the existing methods, yielding excellent results in comparison. A comprehensive ablation study is performed, and the proposed method is evaluated in terms of widely used performance measures. In particular, the proposed method demonstrated a high Matthews correlation coefficient of 0.52, F-score of 0.49, and Youden’s index of 0.81 on an independent test dataset, thereby outperforming the existing methods for AFP prediction.

Identifying Antifreeze Proteins Based on Key Evolutionary Information

Antifreeze proteins are important antifreeze materials that have been widely used in industry, including in cryopreservation, de-icing, and food storage applications. However, the quantity of some commercially produced antifreeze proteins is insufficient for large-scale industrial applications. Further, many antifreeze proteins have properties such as cytotoxicity, severely hindering their applications. Understanding the mechanisms underlying the protein-ice interactions and identifying novel antifreeze proteins are, therefore, urgently needed. In this study, to uncover the mechanisms underlying protein-ice interactions and provide an efficient and accurate tool for identifying antifreeze proteins, we assessed various evolutionary features based on position-specific scoring matrices (PSSMs) and evaluated their importance for discriminating of antifreeze and non-antifreeze proteins. We then parsimoniously selected seven key features with the highest importance. We found that the selected features showed opposite tendencies (regarding the conservation of certain amino acids) between antifreeze and non-antifreeze proteins. Five out of the seven features had relatively high contributions to the discrimination of antifreeze and non-antifreeze proteins, as revealed by a principal component analysis, i.e., the conservation of the replacement of Cys, Trp, and Gly in antifreeze proteins by Ala, Met, and Ala, respectively, in the related proteins, and the conservation of the replacement of Arg in non-antifreeze proteins by Ser and Arg in the related proteins. Based on the seven parsimoniously selected key features, we established a classifier using support vector machine, which outperformed the state-of-the-art tools. These results suggest that understanding evolutionary information is crucial to designing accurate automated methods for discriminating antifreeze and non-antifreeze proteins. Our classifier, therefore, is an efficient tool for annotating new proteins with antifreeze functions based on sequence information and can facilitate their application in industry.

Identifying Acetylation Protein by Fusing Its PseAAC and Functional Domain Annotation

Acetylation is one of post-translational modification (PTM), which often reacts with acetic acid and brings an acetyl radical to an organic compound. It is helpful to identify acetylation protein correctly for understanding the mechanism of acetylation in biological systems. Although many acetylation sites have been identified by high throughput experimental studies via mass spectrometry, there still are lots of acetylation sites need to be discovered. Computational methods have showed their power for identifying acetylation sites with informatics techniques which usually reduce experiment cost and improve the effectiveness and efficiency. In fact, if there is an approach can distinguish the acetylated proteins from the non-acetylated ones, it is no doubt a very meaningful and effective method for this issue. Here, we proposed a novel computational method for identifying acetylation proteins by extracting features from the conservation information of sequence via gray system model and KNN scores based on the information of functional domain annotation and subcellular localization. The authors have performed the 5-fold cross-validation on three datasets along with much analysis of features and the Relief feature selection algorithm. The obtained accuracies are all satisfactory, as the mean performance, the accuracy is 77.10%, the Matthew's correlation coefficient is 0.5457, and the AUC value is 0.8389. These works might provide useful insights for the related experimental validation, and further studies of other PTM process. For the convenience of related researchers, the web-server named “iACetyP” was established and is accessible at http://www.jci-bioinfo.cn/iAcetyP.

iProtease-PseAAC(2L): A two-layer predictor for identifying proteases and their types using Chou's 5-step-rule and general PseAAC

Proteases are a type of enzymes, which perform the process of proteolysis. Proteolysis normally refers to protein and peptide degradation which is crucial for the survival, growth and wellbeing of a cell. Moreover, proteases have a strong association with therapeutics and drug development. The proteases are classified into five different types according to their nature and physiochemical characteristics. Mostly the methods used to differentiate protease from other proteins and identify their class requires a clinical test which is usually time-consuming and operator dependent. Herein, we report a classifier named iProtease-PseAAC (2L) for identifying proteases and their classes. The predictor is developed employing the flow of 5-step rule, initiating from the collection of benchmark dataset and terminating at the development of predictor. Rigorous verification and validation tests are performed and metrics are collected to calculate the authenticity of the trained model. The self-consistency validation gives the 98.32% accuracy, for cross-validation the accuracy is 90.71% and jackknife gives 96.07% accuracy. The average accuracy for level-2 i.e. protease classification is 95.77%. Based on the above-mentioned results, it is concluded that iProtease-PseAAC (2L) has the great ability to identify the proteases and their classes using a given protein sequence.

pLoc_bal-mVirus: Predict Subcellular Localization of Multi-Label Virus Proteins by Chou's General PseAAC and IHTS Treatment to Balance Training Dataset

Background/Objective:

Knowledge of protein subcellular localization is vitally important for both basic research and drug development. Facing the avalanche of protein sequences emerging in the post-genomic age, it is urgent to develop computational tools for timely and effectively identifying their subcellular localization based on the sequence information alone. Recently, a predictor called “pLoc-mVirus” was developed for identifying the subcellular localization of virus proteins. Its performance is overwhelmingly better than that of the other predictors for the same purpose, particularly in dealing with multi-label systems in which some proteins, known as “multiplex proteins”, may simultaneously occur in, or move between two or more subcellular location sites. Despite the fact that it is indeed a very powerful predictor, more efforts are definitely needed to further improve it. This is because pLoc-mVirus was trained by an extremely skewed dataset in which some subset was over 10 times the size of the other subsets. Accordingly, it cannot avoid the biased consequence caused by such an uneven training dataset.

Methods:

Using the Chou's general PseAAC (Pseudo Amino Acid Composition) approach and the IHTS (Inserting Hypothetical Training Samples) treatment to balance out the training dataset, we have developed a new predictor called “pLoc_bal-mVirus” for predicting the subcellular localization of multi-label virus proteins.

Results:

Cross-validation tests on exactly the same experiment-confirmed dataset have indicated that the proposed new predictor is remarkably superior to pLoc-mVirus, the existing state-of-theart predictor for the same purpose.

Conclusion:

Its user-friendly web-server is available at http://www.jci-bioinfo.cn/pLoc_balmVirus/, by which the majority of experimental scientists can easily get their desired results without the need to go through the detailed complicated mathematics. Accordingly, pLoc_bal-mVirus will become a very useful tool for designing multi-target drugs and in-depth understanding of the biological process in a cell.

iSulfoTyr-PseAAC: Identify Tyrosine Sulfation Sites by Incorporating Statistical Moments via Chou's 5-steps Rule and Pseudo Components

BACKGROUND

The amino acid residues, in protein, undergo post-translation modification (PTM) during protein synthesis, a process of chemical and physical change in an amino acid that in turn alters behavioral properties of proteins. Tyrosine sulfation is a ubiquitous posttranslational modification which is known to be associated with regulation of various biological functions and pathological pro-cesses. Thus its identification is necessary to understand its mechanism. Experimental determination through site-directed mutagenesis and high throughput mass spectrometry is a costly and time taking process, thus, the reliable computational model is required for identification of sulfotyrosine sites.

METHODOLOGY

In this paper, we present a computational model for the prediction of the sulfotyrosine sites named iSulfoTyr-PseAAC in which feature vectors are constructed using statistical moments of protein amino acid sequences and various position/composition relative features. These features are in-corporated into PseAAC. The model is validated by jackknife, cross-validation, self-consistency and in-dependent testing.

RESULTS

Accuracy determined through validation was 93.93% for jackknife test, 95.16% for cross-validation, 94.3% for self-consistency and 94.3% for independent testing.

CONCLUSION

The proposed model has better performance as compared to the existing predictors, how-ever, the accuracy can be improved further, in future, due to increasing number of sulfotyrosine sites in proteins.

iNR-2L: A two-level sequence-based predictor developed via Chou's 5-steps rule and general PseAAC for identifying nuclear receptors and their families

Nuclear receptor proteins (NRPs) perform a vital role in regulating gene expression. With the rapidity growth of NRPs in post-genomic era, it is highly recommendable to identify NRPs and their sub-families accurately from their primary sequences. Several conventional methods have been used for discrimination of NRPs and their sub-families, but did not achieve considerable results. In a sequel, a two-level new computational model "iNR-2 L" is developed. Two discrete methods namely: Dipeptide Composition and Tripeptide Composition were used to formulate NRPs sequences. Further, both the descriptor spaces were merged to construct hybrid space. Furthermore, feature selection technique minimum redundancy and maximum relevance was employed in order to select salient features as well as reduce the noise and redundancy. The experiential outcomes exhibited that the proposed model iNR-2 L achieved outstanding results. It is anticipated that the proposed computational model might be a practical and effective tool for academia and research community.

iPSW(2L)-PseKNC: A two-layer predictor for identifying promoters and their strength by hybrid features via pseudo K-tuple nucleotide composition

The promoter is a regulatory DNA region about 81-1000 base pairs long, usually located near the transcription start site (TSS) along upstream of a given gene. By combining a certain protein called transcription factor, the promoter provides the starting point for regulated gene transcription, and hence plays a vitally important role in gene transcriptional regulation. With explosive growth of DNA sequences in the post-genomic age, it has become an urgent challenge to develop computational method for effectively identifying promoters because the information thus obtained is very useful for both basic research and drug development. Although some prediction methods were developed in this regard, most of them were limited at merely identifying whether a query DNA sequence being of a promoter or not. However, based on their strength-distinct levels for transcriptional activation and expression, promoter should be divided into two categories: strong and weak types. Here a new two-layer predictor, called "iPSW(2L)-PseKNC", was developed by fusing the physicochemical properties of nucleotides and their nucleotide density into PseKNC (pseudo K-tuple nucleotide composition). Its 1st-layer serves to predict whether a query DNA sequence sample is of promoter or not, while its 2nd-layer is able to predict the strength of promoters. It has been observed through rigorous cross-validations that the 1st-layer sub-predictor is remarkably superior to the existing state-of-the-art predictors in identifying the promoters and non-promoters, and that the 2nd-layer sub-predictor can do what is beyond the reach of the existing predictors. Moreover, the web-server for iPSW(2L)-PseKNC has been established at http://www.jci-bioinfo.cn/iPSW(2L)-PseKNC, by which the majority of experimental scientists can easily get the results they need.

Analysis of Progression Toward Alzheimer's Disease Based on Evolutionary Weighted Random Support Vector Machine Cluster

Alzheimer’s disease (AD) could be described into following four stages: healthy control (HC), early mild cognitive impairment (EMCI), late MCI (LMCI) and AD dementia. The discriminations between different stages of AD are considerably important issues for future pre-dementia treatment. However, it is still challenging to identify LMCI from EMCI because of the subtle changes in imaging which are not noticeable. In addition, there were relatively few studies to make inferences about the brain dynamic changes in the cognitive progression from EMCI to LMCI to AD. Inspired by the above problems, we proposed an advanced approach of evolutionary weighted random support vector machine cluster (EWRSVMC). Where the predictions of numerous weighted SVM classifiers are aggregated for improving the generalization performance. We validated our method in multiple binary classifications using Alzheimer’s Disease Neuroimaging Initiative dataset. As a result, the encouraging accuracy of 90% for EMCI/LMCI and 88.89% for LMCI/AD were achieved respectively, demonstrating the excellent discriminating ability. Furthermore, disease-related brain regions underlying the AD progression could be found out on the basis of the amount of discriminative information. The findings of this study provide considerable insight into the neurophysiological mechanisms in AD development.

iRNA(m6A)-PseDNC: Identifying N6-methyladenosine sites using pseudo dinucleotide composition

As a prevalent post-transcriptional modification, N⁶-methyladenosine (m⁶A) plays key roles in a series of biological processes. Although experimental technologies have been developed and applied to identify m⁶A sites, they are still cost-ineffective for transcriptome-wide detections of m⁶A. As good complements to the experimental techniques, some computational methods have been proposed to identify m⁶A sites. However, their performance remains unsatisfactory. In this study, we firstly proposed an Euclidean distance based method to construct a high quality benchmark dataset. By encoding the RNA sequences using pseudo nucleotide composition, a new predictor called iRNA(m6A)-PseDNC was developed to identify m⁶A sites in the Saccharomyces cerevisiae genome. It has been demonstrated by the 10-fold cross validation test that the performance of iRNA(m6A)-PseDNC is superior to the existing methods. Meanwhile, for the convenience of most experimental scientists, established at the site http://lin-group.cn/server/iRNA(m6A)-PseDNC.php is its web-server, by which users can easily get their desired results without need to go through the detailed mathematics. It is anticipated that iRNA(m6A)-PseDNC will become a useful high throughput tool for identifying m⁶A sites in the S. cerevisiae genome.

iRNA-3typeA: Identifying Three Types of Modification at RNA's Adenosine Sites

RNA modifications are additions of chemical groups to nucleotides or their local structural changes. Knowledge about the occurrence sites of these modifications is essential for in-depth understanding of the biological functions and mechanisms and for treating some genomic diseases as well. With the avalanche of RNA sequences generated in the post-genomic age, many computational methods have been proposed for identifying various types of RNA modifications one by one. However, so far no method whatsoever has been developed for simultaneously identifying several different types of RNA modifications. To address such a challenge, we developed a predictor called "iRNA-3typeA," by which we can simultaneously identify the occurrence sites of the following three most frequently observed modifications in RNA: (1) N1-methyladenosine (m1A), (2) N6-methyladenosine (m6A), and (3) adenosine to inosine (A-to-I). It has been shown via rigorous cross-validations for the RNA sequences from Homo sapiens and Mus musculus transcriptomes that the success rates achieved by the powerful new predictor are quite high. For the convenience of broad experimental scientists, a user-friendly web server for iRNA-3typeA has been established at http://lin-group.cn/server/iRNA-3typeA/. It is anticipated that iRNA-3typeA may become a useful high throughput tool for genome analysis.

iRNAm5C-PseDNC: identifying RNA 5-methylcytosine sites by incorporating physical-chemical properties into pseudo dinucleotide composition

Occurring at cytosine (C) of RNA, 5-methylcytosine (m⁵C) is an important post-transcriptional modification (PTCM). The modification plays significant roles in biological processes by regulating RNA metabolism in both eukaryotes and prokaryotes. It may also, however, cause cancers and other major diseases. Given an uncharacterized RNA sequence that contains many C residues, can we identify which one of them can be of m⁵C modification, and which one cannot? It is no doubt a crucial problem, particularly with the explosive growth of RNA sequences in the postgenomic age. Unfortunately, so far no user-friendly web-server whatsoever has been developed to address such a problem. To meet the increasingly high demand from most experimental scientists working in the area of drug development, we have developed a new predictor called iRNAm5C-PseDNC by incorporating ten types of physical-chemical properties into pseudo dinucleotide composition via the auto/cross-covariance approach. Rigorous jackknife tests show that its anticipated accuracy is quite high. For most experimental scientists’ convenience, a user-friendly web-server for the predictor has been provided at http://www.jci-bioinfo.cn/iRNAm5C-PseDNC along with a step-by-step user guide, by which users can easily obtain their desired results without the need to go through the complicated mathematical equations involved. It has not escaped our notice that the approach presented here can also be used to deal with many other problems in genome analysis.

iHyd-PseCp: Identify hydroxyproline and hydroxylysine in proteins by incorporating sequence-coupled effects into general PseAAC

Protein hydroxylation is a posttranslational modification (PTM), in which a CH group in Pro (P) or Lys (K) residue has been converted into a COH group, or a hydroxyl group (−OH) is converted into an organic compound. Closely associated with cellular signaling activities, this type of PTM is also involved in some major diseases, such as stomach cancer and lung cancer. Therefore, from the angles of both basic research and drug development, we are facing a challenging problem: for an uncharacterized protein sequence containing many residues of P or K, which ones can be hydroxylated, and which ones cannot? With the explosive growth of protein sequences in the post-genomic age, the problem has become even more urgent. To address such a problem, we have developed a predictor called iHyd-PseCp by incorporating the sequence-coupled information into the general pseudo amino acid composition (PseAAC) and introducing the “Random Forest” algorithm to operate the calculation. Rigorous jackknife tests indicated that the new predictor remarkably outperformed the existing state-of-the-art prediction method for the same purpose. For the convenience of most experimental scientists, a user-friendly web-server for iHyd-PseCp has been established at http://www.jci-bioinfo.cn/iHyd-PseCp, by which users can easily obtain their desired results without the need to go through the complicated mathematical equations involved.

iRNA-AI: identifying the adenosine to inosine editing sites in RNA sequences

Catalyzed by adenosine deaminase (ADAR), the adenosine to inosine (A-to-I) editing in RNA is not only involved in various important biological processes, but also closely associated with a series of major diseases. Therefore, knowledge about the A-to-I editing sites in RNA is crucially important for both basic research and drug development. Given an uncharacterized RNA sequence that contains many adenosine (A) residues, can we identify which one of them can be of A-to-I editing, and which one cannot? Unfortunately, so far no computational method whatsoever has been developed to address such an important problem based on the RNA sequence information alone. To fill this empty area, we have proposed a predictor called iRNA-AI by incorporating the chemical properties of nucleotides and their sliding occurrence density distribution along a RNA sequence into the general form of pseudo nucleotide composition (PseKNC). It has been shown by the rigorous jackknife test and independent dataset test that the performance of the proposed predictor is quite promising. For the convenience of most experimental scientists, a user-friendly web-server for iRNA-AI has been established at http://lin.uestc.edu.cn/server/iRNA-AI/, by which users can easily get their desired results without the need to go through the mathematical details.

iOri-Human: identify human origin of replication by incorporating dinucleotide physicochemical properties into pseudo nucleotide composition

The initiation of replication is an extremely important process in DNA life cycle. Given an uncharacterized DNA sequence, can we identify where its origin of replication (ORI) is located? It is no doubt a fundamental problem in genome analysis. Particularly, with the rapid development of genome sequencing technology that results in a huge amount of sequence data, it is highly desired to develop computational methods for rapidly and effectively identifying the ORIs in these genomes. Unfortunately, by means of the existing computational methods, such as sequence alignment or kmer strategies, it could hardly achieve decent success rates. To address this problem, we developed a predictor called “iOri-Human”. Rigorous jackknife tests have shown that its overall accuracy and stability in identifying human ORIs are over 75% and 50%, respectively. In the predictor, it is through the pseudo nucleotide composition (an extension of pseudo amino acid composition) that 96 physicochemical properties for the 16 possible constituent dinucleotides have been incorporated to reflect the global sequence patterns in DNA as well as its local sequence patterns. Moreover, a user-friendly web-server for iOri-Human has been established at http://lin.uestc.edu.cn/server/iOri-Human.html, by which users can easily get their desired results without the need to through the complicated mathematics involved.