Discrimination of intracellular and extracellular proteins using amino acid composition and residue-pair frequencies

Protein Classes Predicted by Molecular Surface Chemical Features: Machine Learning-Assisted Classification of Cytosol and Secreted Proteins

Chemical structures of protein surfaces govern intermolecular interaction, and protein functions include specific molecular recognition, transport, self-assembly, etc. Therefore, the relationship between the chemical structure and protein functions provides insights into the understanding of the mechanism underlying protein functions and developments of new biomaterials. In this study, we analyze protein surface features, including surface amino acid populations and secondary structure ratios, instead of entire sequences as input for the classifier, intending to provide deeper insights into the determination of protein classes (cytosol or secreted). We employed a random forest-based classifier for the prediction of protein locations. Our training and testing data sets consisting of secreted and cytosol proteins were constructed using filtered information from UniProt and 3D structures from AlphaFold. The classifier achieved a testing accuracy of 93.9% with a feature importance ranking and quantitative boundary values for the top three features. We discuss the significance of these features quantitatively and the hidden rules to determine the protein classes (cytosol or secreted).

Protein Sorting Prediction

Many computational methods are available for predicting protein sorting in bacteria. When comparing them, it is important to know that they can be grouped into three fundamentally different approaches: signal-based, global property-based, and homology-based prediction. In this chapter, the strengths and drawbacks of each of these approaches are described through many examples of methods that predict secretion, integration into membranes, or subcellular locations in general. The aim of this chapter is to provide a user-level introduction to the field with a minimum of computational theory.

SignalP: The Evolution of a Web Server

SignalP ( https://services.healthtech.dtu.dk/services/SignalP-6.0/ ) is a very popular prediction method for signal peptides, the intrinsic signals that make proteins secretory. The SignalP web server has existed since 1995 and is now in its sixth major version. In this historical account, we (three authors who have taken part in the entire journey plus the first author of the latest version) describe the differences between the versions and discuss the various decisions taken along the way.

In Silico Analysis of the Dextransucrase Obtained From Leuconostoc mesenteroides Strain IBUN 91.2.98

The DSR-IBUN dextransucrase produced by Leuconostoc mesenteroides strain IBUN 91.2.98 has a short production time (4.5 hours), an enzymatic activity of 24.8 U/mL, and a specific activity of purified enzyme 2 times higher (331.6 U/mg) than that reported for similar enzymes. The aim of this study was to generate a structural model that, from an in silico approach, allows a better understanding, from the structural point of view, of the activity obtained by the enzyme of interest, which is key to continue with its study and industry application. For this, we translated the nucleotide sequence of the dsr_IBUN gene. With the primary structure of DSR-IBUN, the in silico prediction of physicochemical parameters, the possible subcellular localization, the presence of signal peptide, and the location of domains and functional and structural motifs of the protein were established. Subsequently, its secondary and tertiary structure were predicted and a homology model of the dextransucrase under study was constructed using Swiss-Model, performing careful template selection. The values obtained for the model, Global Model Quality Estimation (0.63), Quality Mean (-1.49), and root-mean-square deviation (0.09), allow us to affirm that the model for the enzyme dextransucrase DSR-IBUN is of adequate quality and can be used as a source of information for this protein.

Genome-wide analysis and characterization of the LRR-RLK gene family provides insights into anthracnose resistance in common bean

Anthracnose, caused by the hemibiotrophic fungus Colletotrichum lindemuthianum, is a damaging disease of common beans that can drastically reduce crop yield. The most effective strategy to manage anthracnose is the use of resistant cultivars. There are many resistance loci that have been identified, mapped and associated with markers in common bean chromosomes. The Leucine-rich repeat kinase receptor protein (LRR-RLK) family is a diverse group of transmembrane receptors, which potentially recognizes pathogen-associated molecular patterns and activates an immune response. In this study, we performed in silico analyses to identify, classify, and characterize common bean LRR-RLKs, also evaluating their expression profile in response to the infection by C. lindemuthianum. By analyzing the entire genome of Phaseolus vulgaris, we could identify and classify 230 LRR-RLKs into 15 different subfamilies. The analyses of gene structures, conserved domains and motifs suggest that LRR-RLKs from the same subfamily are consistent in their exon/intron organization and composition. LRR-RLK genes were found along the 11 chromosomes of the species, including regions of proximity with anthracnose resistance markers. By investigating the duplication events within the LRR-RLK family, we associated the importance of such a family with an expansion resulting from a strong stabilizing selection. Promoter analysis was also performed, highlighting cis-elements associated with the plant response to biotic stress. With regard to the expression pattern of LRR-RLKs in response to the infection by C. lindemuthianum, we could point out several differentially expressed genes in this subfamily, which were associated to specific molecular patterns of LRR-RLKs. Our work provides a broad analysis of the LRR-RLK family in P. vulgaris, allowing an in-depth structural and functional characterization of genes and proteins of this family. From specific expression patterns related to anthracnose response, we could infer a direct participation of RLK-LRR genes in the mechanisms of resistance to anthracnose, highlighting important subfamilies for further investigations.

A review from biological mapping to computation-based subcellular localization

Subcellular localization is crucial to the study of virus and diseases. Specifically, research on protein subcellular localization can help identify clues between virus and host cells that can aid in the design of targeted drugs. Research on RNA subcellular localization is significant for human diseases (such as Alzheimer's disease, colon cancer, etc.). To date, only reviews addressing subcellular localization of proteins have been published, which are outdated for reference, and reviews of RNA subcellular localization are not comprehensive. Therefore, we collated (the most up-to-date) literature on protein and RNA subcellular localization to help researchers understand changes in the field of protein and RNA subcellular localization. Extensive and complete methods for constructing subcellular localization models have also been summarized, which can help readers understand the changes in application of biotechnology and computer science in subcellular localization research and explore how to use biological data to construct improved subcellular localization models. This paper is the first review to cover both protein subcellular localization and RNA subcellular localization. We urge researchers from biology and computational biology to jointly pay attention to transformation patterns, interrelationships, differences, and causality of protein subcellular localization and RNA subcellular localization.

Prediction of lysine HMGylation sites using multiple feature extraction and fuzzy support vector machine

Protein 3-hydroxyl-3-methylglutarylation (HMGylation) is newly discovered lysine acylation modification in mitochondrion. The accurate identification of HMGylation sites is the premise and key to further explore the molecular mechanisms of HMGylation. In this study, a novel bioinformatics tool named HMGPred is developed to predict HMGylation sites. Multiple effective features, including amino acid composition, amino acid factors, binary encoding, and the composition of k-spaced amino acid pairs, are integrated to encode HMGylation sites. And F-score feature ranking with incremental feature selection was used to eliminate redundant features. Moreover, a fuzzy support vector machine algorithm is used to effectively reduce the influence of noise problem by assigning different samples to different fuzzy membership degrees. As illustrated by 10-fold cross-validation, HMGPred achieves a satisfactory performance with an area under receiver operating characteristic curve of 0.9110. Feature analysis indicates that some k-spaced amino acid pair features, such as 'KxxxT' and 'DxxxE', play a critical role in the prediction of HMGylation sites. The results of prediction and analysis might be helpful for investigating the mechanisms of HMGylation. For the convenience of experimental researchers, HMGPred is implemented as a web server at http://123.206.31.171/HMGPred/.

Optimized Data Set and Feature Construction for Substrate Prediction of Membrane Transporters

α-Helical transmembrane proteins termed membrane transporters mediate the passage of small hydrophilic substrate molecules across biological lipid bilayer membranes. Annotating the specific substrates of the dozens to hundreds of individual transporters of an organism is an important task. In the past, machine learning classifiers have been successfully trained on pan-organism data sets to predict putative substrates of transporters. Here, we critically examine the selection of an optimal data set of protein sequence features for the classification task. We focus on membrane transporters of the three model organisms Escherichia coli, Arabidopsis thaliana, and Saccharomyces cerevisiae, as well as human. We show that organism-specific classifiers can be robustly trained if at least 20 samples are available for each substrate class. If information from position-specific scoring matrices is included, such classifiers have F1 scores between 0.85 and 1.00. For the largest data set (A. thaliana), a 4-class classifier yielded an F-score of 0.97. On a pan-organism data set composed of transporters of all four organisms, amino acid and sugar transporters were predicted with an F1 score of 0.91.

In silico functional annotation of hypothetical proteins from the Bacillus paralicheniformis strain Bac84 reveals proteins with biotechnological potentials and adaptational functions to extreme environments

Members of the Bacillus genus are industrial cell factories due to their capacity to secrete significant quantities of biomolecules with industrial applications. The Bacillus paralicheniformis strain Bac84 was isolated from the Red Sea and it shares a close evolutionary relationship with Bacillus licheniformis. However, a significant number of proteins in its genome are annotated as functionally uncharacterized hypothetical proteins. Investigating these proteins' functions may help us better understand how bacteria survive extreme environmental conditions and to find novel targets for biotechnological applications. Therefore, the purpose of our research was to functionally annotate the hypothetical proteins from the genome of B. paralicheniformis strain Bac84. We employed a structured in-silico approach incorporating numerous bioinformatics tools and databases for functional annotation, physicochemical characterization, subcellular localization, protein-protein interactions, and three-dimensional structure determination. Sequences of 414 hypothetical proteins were evaluated and we were able to successfully attribute a function to 37 hypothetical proteins. Moreover, we performed receiver operating characteristic analysis to assess the performance of various tools used in this present study. We identified 12 proteins having significant adaptational roles to unfavorable environments such as sporulation, formation of biofilm, motility, regulation of transcription, etc. Additionally, 8 proteins were predicted with biotechnological potentials such as coenzyme A biosynthesis, phenylalanine biosynthesis, rare-sugars biosynthesis, antibiotic biosynthesis, bioremediation, and others. Evaluation of the performance of the tools showed an accuracy of 98% which represented the rationality of the tools used. This work shows that this annotation strategy will make the functional characterization of unknown proteins easier and can find the target for further investigation. The knowledge of these hypothetical proteins' potential functions aids B. paralicheniformis strain Bac84 in effectively creating a new biotechnological target. In addition, the results may also facilitate a better understanding of the survival mechanisms in harsh environmental conditions.

Functional Analysis of Conserved Hypothetical Proteins from the Antarctic Bacterium, Pedobacter cryoconitis Strain BG5 Reveals Protein Cold Adaptation and Thermal Tolerance Strategies

Pedobacter cryoconitis BG5 is an obligate psychrophilic bacterium that was first isolated on King George Island, Antarctica. Over the last 50 years, the West Antarctic, including King George Island, has been one of the most rapidly warming places on Earth, hence making it an excellent area to measure the resilience of living species in warmed areas exposed to the constantly changing environment due to climate change. This bacterium encodes a genome of approximately 5694 protein-coding genes. However, 35% of the gene models for this species are found to be hypothetical proteins (HP). In this study, three conserved HP genes of P. cryoconitis, designated pcbg5hp1, pcbg5hp2 and pcbg5hp12, were cloned and the proteins were expressed, purified and their functions and structures were evaluated. Real-time quantitative PCR analysis revealed that these genes were expressed constitutively, suggesting a potentially important role where the expression of these genes under an almost constant demand might have some regulatory functions in thermal stress tolerance. Functional analysis showed that these proteins maintained their activities at low and moderate temperatures. Meanwhile, a low citrate synthase aggregation at 43 °C in the presence of PCBG5HP1 suggested the characteristics of chaperone activity. Furthermore, our comparative structural analysis demonstrated that the HPs exhibited cold-adapted traits, most notably increased flexibility in their 3D structures compared to their counterparts. Concurrently, the presence of a disulphide bridge and aromatic clusters was attributed to PCBG5HP1’s unusual protein stability and chaperone activity. Thus, this suggested that the HPs examined in this study acquired strategies to maintain a balance between molecular stability and structural flexibility. Conclusively, this study has established the structure–function relationships of the HPs produced by P. cryoconitis and provided crucial experimental evidence indicating their importance in thermal stress response.

Gm-PLoc: A Subcellular Localization Model of Multi-Label Protein Based on GAN and DeepFM

Identifying the subcellular localization of a given protein is an essential part of biological and medical research, since the protein must be localized in the correct organelle to ensure physiological function. Conventional biological experiments for protein subcellular localization have some limitations, such as high cost and low efficiency, thus massive computational methods are proposed to solve these problems. However, some of these methods need to be improved further for protein subcellular localization with class imbalance problem. We propose a new model, generating minority samples for protein subcellular localization (Gm-PLoc), to predict the subcellular localization of multi-label proteins. This model includes three steps: using the position specific scoring matrix to extract distinguishable features of proteins; synthesizing samples of the minority category to balance the distribution of categories based on the revised generative adversarial networks; training a classifier with the rebalanced dataset to predict the subcellular localization of multi-label proteins. One benchmark dataset is selected to evaluate the performance of the presented model, and the experimental results demonstrate that Gm-PLoc performs well for the multi-label protein subcellular localization.

DeepStack-DTIs: Predicting Drug-Target Interactions Using LightGBM Feature Selection and Deep-Stacked Ensemble Classifier

Accurate prediction of drug-target interactions (DTIs), which is often used in the fields of drug discovery and drug repositioning, is regarded a key challenge in the study of drug science. In this paper, a new method called DeepStack-DTIs is proposed to predict DTIs. First, for the target protein, pseudo-position specific score matrix, pseudo amino acid composition and SPIDER3 are used to extract the different feature information of the target protein. Meanwhile, the path-based fingerprint features of each drug are extracted. Then, the synthetic minority oversampling technique (SMOTE) and light gradient boosting machine (LightGBM) are used for data balancing and feature selection, respectively. Finally, the processed features are input to the deep-stacked ensemble classifier composed of gated recurrent unit (GRU), deep neural network (DNN), support vector machine (SVM), eXtreme gradient boosting (XGBoost) and logistic regression (LR) to predict DTIs. Under the five-fold cross-validation and compared with existing methods, the proposed method achieves higher prediction accuracy on the gold standard dataset. To evaluate the predictive power of DeepStack-DTIs, we validate the method on another dataset and predict the drug-target interaction network. The results indicate that DeepStack-DTIs has excellent predictive ability than the other methods, and provides novel insights for the prediction of DTIs. A novel method DeepStack-DTIs for drug-target interactions prediction. PsePSSM, PseAAC, SPIDER3 and FP2 are fused to convert protein sequence and drug molecule information into digital information, respectively. The SMOTE algorithm is used to balance the dataset and LightGBM feature selection algorithm is employed to remove redundant and irrelevant features to select the optimal feature subset. This optimal feature subset is inputted into the deep-stacked ensemble classifier to predict drug-target interactions. The experimental results show DeepStack-DTIs method can significantly improve the prediction accuracy of drug-target interactions.

Development and validation of multiple machine learning algorithms for the classification of G-protein-coupled receptors using molecular evolution model-based feature extraction strategy

Machine learning is one of the most potential ways to realize the function prediction of the incremental large-scale G-protein-coupled receptors (GPCR). Prior research reveals that the key to determining the overall classification accuracy of GPCR is extracting valuable features and filtering out redundancy. To achieve a more efficient classification model, we put the feature synonym problem into consideration and create a new method based on functional word clustering and integration. Through evaluating the evolution correlation between features using the transition scores in mature molecular substitution matrices, candidate features are clustered into synonym groups. Each group of the clustered features is then integrated and represented by a unique key functional word. These retained key functional words are used to form a feature knowledge base. The original GPCR sequences are then transferred into feature vectors based on a feature re-extraction strategy according to the features in the knowledge base before the training and testing stage. We create multiple machine learning models based on Naïve Bayesian (NB), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) algorithms. The established model is applied to classify two public data sets containing 8354 and 12,731 GPCRs, respectively. These models achieve significant performance in almost all evaluation criteria in comparison with state-of-the art. This work demonstrated the potential of the novel feature extraction strategy and provided an effective theoretical design for the hierarchical classification of GPCRs.

In-Pero: Exploiting Deep Learning Embeddings of Protein Sequences to Predict the Localisation of Peroxisomal Proteins

Peroxisomes are ubiquitous membrane-bound organelles, and aberrant localisation of peroxisomal proteins contributes to the pathogenesis of several disorders. Many computational methods focus on assigning protein sequences to subcellular compartments, but there are no specific tools tailored for the sub-localisation (matrix vs. membrane) of peroxisome proteins. We present here In-Pero, a new method for predicting protein sub-peroxisomal cellular localisation. In-Pero combines standard machine learning approaches with recently proposed multi-dimensional deep-learning representations of the protein amino-acid sequence. It showed a classification accuracy above 0.9 in predicting peroxisomal matrix and membrane proteins. The method is trained and tested using a double cross-validation approach on a curated data set comprising 160 peroxisomal proteins with experimental evidence for sub-peroxisomal localisation. We further show that the proposed approach can be easily adapted (In-Mito) to the prediction of mitochondrial protein localisation obtaining performances for certain classes of proteins (matrix and inner-membrane) superior to existing tools.

Applying Machine Learning to Predict the Exportome of Bovine and Canine Babesia Species That Cause Babesiosis

Babesia infection of red blood cells can cause a severe disease called babesiosis in susceptible hosts. Bovine babesiosis causes global economic loss to the beef and dairy cattle industries, and canine babesiosis is considered a clinically significant disease. Potential therapeutic targets against bovine and canine babesiosis include members of the exportome, i.e., those proteins exported from the parasite into the host red blood cell. We developed three machine learning-derived methods (two novel and one adapted) to predict for every known Babesia bovis, Babesia bigemina, and Babesia canis protein the probability of being an exportome member. Two well-studied apicomplexan-related species, Plasmodium falciparum and Toxoplasma gondii, with extensive experimental evidence on their exportome or excreted/secreted proteins were used as important benchmarks for the three methods. Based on 10-fold cross validation and multiple train-validation-test splits of training data, we expect that over 90% of the predicted probabilities accurately provide a secretory or non-secretory indicator. Only laboratory testing can verify that predicted high exportome membership probabilities are creditable exportome indicators. However, the presented methods at least provide those proteins most worthy of laboratory validation and will ultimately save time and money.

Bioluminescent Proteins Prediction with Voting Strategy

Background:

Bioluminescence is a unique and significant phenomenon in nature. Bioluminescence is important for the lifecycle of some organisms and is valuable in biomedical research, including for gene expression analysis and bioluminescence imaging technology. In recent years, researchers have identified a number of methods for predicting bioluminescent proteins (BLPs), which have increased in accuracy, but could be further improved.

Method:

In this study, a new bioluminescent proteins prediction method, based on a voting algorithm, is proposed. Four methods of feature extraction based on the amino acid sequence were used. 314 dimensional features in total were extracted from amino acid composition, physicochemical properties and k-spacer amino acid pair composition. In order to obtain the highest MCC value to establish the optimal prediction model, a voting algorithm was then used to build the model. To create the best performing model, the selection of base classifiers and vote counting rules are discussed.

Results:

The proposed model achieved 93.4% accuracy, 93.4% sensitivity and 91.7% specificity in the test set, which was better than any other method. A previous prediction of bioluminescent proteins in three lineages was also improved using the model building method, resulting in greatly improved accuracy.

Basic polar and hydrophobic properties are the main characteristics that affect the binding of transcription factors to methylation sites

MOTIVATION

Methylation and transcription factors (TFs) are part of the mechanisms regulating gene expression. However, the numerous mechanisms regulating the interactions between methylation and TFs remain unknown. We employ machine-learning techniques to discover the characteristics of TFs that bind to methylation sites.

RESULTS

The classical machine-learning analysis process focuses on improving the performance of the analysis method. Conversely, we focus on the functional properties of the TF sequences. We obtain the principal properties of TFs, namely, the basic polar and hydrophobic Ile amino acids affecting the interaction between TFs and methylated DNA. The recall of the positive instances is 0.878 when their basic polar value is >0.1743. Both basic polar and hydrophobic Ile amino acids distinguish 74% of TFs bound to methylation sites. Therefore, we infer that basic polar amino acids affect the interactions of TFs with methylation sites. Based on our results, the role of the hydrophobic Ile residue is consistent with that described in previous studies, and the basic polar amino acids may also be a key factor modulating the interactions between TFs and methylation.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Tracing the path of inhaled nitric oxide: Biological consequences of protein nitrosylation

Nitric oxide (NO) is a comprehensive regulator of vascular and airway tone. Endogenous NO produced by nitric oxide synthases regulates multiple signaling cascades, including activation of soluble guanylate cyclase to generate cGMP, relaxing smooth muscle cells. Inhaled NO is an established therapy for pulmonary hypertension in neonates, and has been recently proposed for the treatment of hypoxic respiratory failure and acute respiratory distress syndrome due to COVID-19. In this review, we summarize the effects of endogenous and exogenous NO on protein S-nitrosylation, which is the selective and reversible covalent attachment of a nitrogen monoxide group to the thiol side chain of cysteine. This posttranslational modification targets specific cysteines based on the acid/base sequence of surrounding residues, with significant impacts on protein interactions and function. S-nitrosothiol (SNO) formation is tightly compartmentalized and enzymatically controlled, but also propagated by nonenzymatic transnitrosylation of downstream protein targets. Redox-based nitrosylation and denitrosylation pathways dynamically regulate the equilibrium of SNO-proteins. We review the physiological roles of SNO proteins, including nitrosohemoglobin and autoregulation of blood flow through hypoxic vasodilation, and pathological effects of nitrosylation including inhibition of critical vasodilator enzymes; and discuss the intersection of NO source and dose with redox environment, in determining the effects of protein nitrosylation.

Prediction of Neddylation Sites Using the Composition of k-spaced Amino Acid Pairs and Fuzzy SVM

Introduction:

Neddylation is the process of ubiquitin-like protein NEDD8 attaching substrate lysine via isopeptide bonds. As a highly dynamic and reversible post-translational modification, lysine neddylation has been found to be involved in various biological processes and closely associated with many diseases.

Objective:

The accurate identification of neddylation sites is necessary to elucidate the underlying molecular mechanisms of neddylation. As traditional experimental methods are often expensive and time-consuming, it is imperative to design computational methods to identify neddylation sites.

Methods:

In this study, a novel predictor named CKSAAP_NeddSite is developed to detect neddylation sites. An effective feature encoding technology, the composition of k-spaced amino acid pairs, is used to encode neddylation sites. And the F-score feature selection method is adopted to remove the redundant features. Moreover, a fuzzy support vector machine algorithm is employed to overcome the class imbalance and noise problem.

Results:

As illustrated by 10-fold cross-validation, CKSAAP_NeddSite achieves an AUC of 0.9848. Independent tests also show that CKSAAP_NeddSite significantly outperforms existing neddylation sites predictor. Therefore, CKSAAP_NeddSite can be a useful bioinformatics tool for the prediction of neddylation sites. Feature analysis shows that some residues around neddylation sites may play an important role in the prediction.

Conclusion:

The results of analysis and prediction could offer useful information for elucidating the molecular mechanisms of neddylation. A user-friendly web-server for CKSAAP_NeddSite is established at 123.206.31.171/CKSAAP_NeddSite.

Genes Identification, Molecular Docking and Dynamics Simulation Analysis of Laccases from Amylostereum areolatum Provides Molecular Basis of Laccase Bound to Lignin

An obligate mutualistic relationship exists between the fungus Amylostereum areolatum and woodwasp Sirex noctilio. The fungus digests lignin in the host pine, providing essential nutrients for the growing woodwasp larvae. However, the functional properties of this symbiosis are poorly described. In this study, we identified, cloned, and characterized 14 laccase genes from A. areolatum. These genes encoded proteins of 508 to 529 amino acids and contained three typical copper-oxidase domains, necessary to confer laccase activity. Besides, we performed molecular docking and dynamics simulation of the laccase proteins in complex with lignin compounds (monomers, dimers, trimers, and tetramers). AaLac2, AaLac3, AaLac6, AaLac8, and AaLac10 were found that had low binding energies with all lignin model compounds tested and three of them could maintain stability when binding to these compounds. Among these complexes, amino acid residues ALA, GLN, LEU, PHE, PRO, and SER were commonly present. Our study reveals the molecular basis of A. areolatum laccases interacting with lignin, which is essential for understanding how the fungus provides nutrients to S. noctilio. These findings might also provide guidance for the control of S. noctilio by informing the design of enzyme mutants that could reduce the efficiency of lignin degradation.

Identification of Cancerlectins By Using Cascade Linear Discriminant Analysis and Optimal g-gap Tripeptide Composition

Background:

Lectins are a diverse group of glycoproteins or glycoconjugate proteins that can be extracted from plants, invertebrates and higher animals. Cancerlectins, a kind of lectins, which play a key role in the process of tumor cells interacting with each other and are being employed as therapeutic agents. A full understanding of cancerlectins is significant because it provides a tool for the future direction of cancer therapy.

Objective:

To develop an accurate and practically useful timesaving tool to identify cancerlectins. A novel sequence-based method is proposed along with a correlative webserver to access the proposed tool.

Methods:

Firstly, protein features were extracted in a newly feature building way termed, g-gap tripeptide composition. After which a proposed cascade linear discriminant analysis (Cascade LDA) is used to alleviate the high dimensional difficulties with the Analysis Of Variance (ANOVA) as a feature importance criterion. Finally, Support Vector Machine (SVM) is used as the classifier to identify cancerlectins.

Results:

The proposed method achieved an accuracy of 91.34% with sensitivity of 89.89%, specificity of 92.48% and an 0.8318 Mathew’s correlation coefficient based on only 13 fusion features in jackknife cross validation, the result of which is superior to other published methods in this domain.

Conclusion:

In this study, a new method based only on primary structure of protein is proposed and experimental results show that it could be a promising tool to identify cancerlectins. An openaccess webserver is made available in this work to facilitate other related works.

Protein Subnuclear Localization Based on Radius-SMOTE and Kernel Linear Discriminant Analysis Combined with Random Forest

Protein subnuclear localization plays an important role in proteomics, and can help researchers to understand the biologic functions of nucleus. To date, most protein datasets used by studies are unbalanced, which reduces the prediction accuracy of protein subnuclear localization—especially for the minority classes. In this work, a novel method is therefore proposed to predict the protein subnuclear localization of unbalanced datasets. First, the position-specific score matrix is used to extract the feature vectors of two benchmark datasets and then the useful features are selected by kernel linear discriminant analysis. Second, the Radius-SMOTE is used to expand the samples of minority classes to deal with the problem of imbalance in datasets. Finally, the optimal feature vectors of the expanded datasets are classified by random forest. In order to evaluate the performance of the proposed method, four index evolutions are calculated by Jackknife test. The results indicate that the proposed method can achieve better effect compared with other conventional methods, and it can also improve the accuracy for both majority and minority classes effectively.

Recognition of Mitochondrial Proteins in Plasmodium Based on the Tripeptide Composition

Mitochondria play essential roles in eukaryotic cells, especially in Plasmodium cells. They have several unusual evolutionary and functional features that are incredibly vital for disease diagnosis and drug design. Thus, predicting mitochondrial proteins of Plasmodium has become a worthwhile work. However, existing computational methods can only predict mitochondrial proteins of Plasmodium falciparum (P. falciparum for short), and these methods have low accuracy. It is highly desirable to design a classifier with high accuracy for predicting mitochondrial proteins for all Plasmodium species, not only P. falciparum. We proposed a novel method, named as PM-OTC, for predicting mitochondrial proteins in Plasmodium. PM-OTC uses the Support Vector Machine (SVM) as the classifier and the selected tripeptide composition as the features. We adopted the 5-fold cross-validation method to train and test PM-OTC. Results demonstrate that PM-OTC achieves an accuracy of 94.91%, and performances of PM-OTC are superior to other methods.

Prediction of oxidoreductase subfamily classes based on RFE-SND-CC-PSSM and machine learning methods

Oxidoreductase is an enzyme that widely exists in organisms. It plays an important role in cellular energy metabolism and biotransformation processes. Oxidoreductases have many subclasses with different functions, creating an important classification task in bioinformatics. In this paper, a dataset of 2640 oxidoreductase sequences was used to perform an analysis and comparison. The idea of dipeptides was introduced to process the Position Specific Score Matrix (PSSM), since each dipeptide consists of two amino acids and each column of PSSM corresponds to the information of one amino acid. Two kinds of dipeptide scores were proposed, the Standardization Normal Distribution PSSM (SND-PSSM) and the Correlation Coefficient PSSM (CC-PSSM). Recursive Feature Elimination (RFE) is used to extract features from the SND-PSSM and CC-PSSM, and the two sets of extracted features are combined to form a new feature matrix, the RFE-SND-CC-PSSM. The results show that, with the proposed method and a kernel-based nonlinear SVM classifier, the accuracy can reach 95.56% by the Jackknife test. Our method greatly improves the accuracy of oxidoreductase subclass prediction. Using this method to predict the categories of the 6 major types of enzymes effectively improves its prediction accuracy to 94.54%, indicating that this method has general applicability to other protein problems. The results show that our method is effective and universally applicable, and might be complementary to the existing methods.

Predicting protein subcellular location with network embedding and enrichment features

The subcellular location of a protein is highly related to its function. Identifying the location of a given protein is an essential step for investigating its related problems. Traditional experimental methods can produce solid determination. However, their limitations, such as high cost and low efficiency, are evident. Computational methods provide an alternative means to address these problems. Most previous methods constantly extract features from protein sequences or structures for building prediction models. In this study, we use two types of features and combine them to construct the model. The first feature type is extracted from a protein-protein interaction network to abstract the relationship between the encoded protein and other proteins. The second type is obtained from gene ontology and biological pathways to indicate the existing functions of the encoded protein. These features are analyzed using some feature selection methods. The final optimum features are adopted to build the model with recurrent neural network as the classification algorithm. Such model yields good performance with Matthews correlation coefficient of 0.844. A decision tree is used as a rule learning classifier to extract decision rules. Although the performance of decision rules is poor, they are valuable in revealing the molecular mechanism of proteins with different subcellular locations. The final analysis confirms the reliability of the extracted rules. The source code of the propose method is freely available at https://github.com/xypan1232/rnnloc.

An Insightful 10-year Recollection Since the Emergence of the 5-steps Rule

OBJECTIVE

One of the most challenging and also the most difficult problems is how to formulate a biological sequence with a vector but considerably keep its sequence order information.

METHODS

To address such a problem, the approach of Pseudo Amino Acid Components or PseAAC has been developed.

RESULTS AND CONCLUSION

It has become increasingly clear via the 10-year recollection that the aforementioned proposal has been indeed very powerful.

Plant-mSubP: a computational framework for the prediction of single- and multi-target protein subcellular localization using integrated machine-learning approaches

The subcellular localization of proteins is very important for characterizing its function in a cell. Accurate prediction of the subcellular locations in computational paradigm has been an active area of interest. Most of the work has been focused on single localization prediction. Only few studies have discussed the multi-target localization, but have not achieved good accuracy so far; in plant sciences, very limited work has been done. Here we report the development of a novel tool Plant-mSubP, which is based on integrated machine learning approaches to efficiently predict the subcellular localizations in plant proteomes. The proposed approach predicts with high accuracy 11 single localizations and three dual locations of plant cell. Several hybrid features based on composition and physicochemical properties of a protein such as amino acid composition, pseudo amino acid composition, auto-correlation descriptors, quasi-sequence-order descriptors and hybrid features are used to represent the protein. The performance of the proposed method has been assessed through a training set as well as an independent test set. Using the hybrid feature of the pseudo amino acid composition, N-Center-C terminal amino acid composition and the dipeptide composition (PseAAC-NCC-DIPEP), an overall accuracy of 81.97 %, 84.75 % and 87.88 % is achieved on the training data set of proteins containing the single-label, single- and dual-label combined, and dual-label proteins, respectively. When tested on the independent data, an accuracy of 64.36 %, 64.84 % and 81.08 % is achieved on the single-label, single- and dual-label, and dual-label proteins, respectively. The prediction models have been implemented on a web server available at http://bioinfo.usu.edu/Plant-mSubP/. The results indicate that the proposed approach is comparable to the existing methods in single localization prediction and outperforms all other existing tools when compared for dual-label proteins. The prediction tool will be a useful resource for better annotation of various plant proteomes.

Predictions of Apoptosis Proteins by Integrating Different Features Based on Improving Pseudo-Position-Specific Scoring Matrix

Apoptosis proteins are strongly related to many diseases and play an indispensable role in maintaining the dynamic balance between cell death and division in vivo. Obtaining localization information on apoptosis proteins is necessary in understanding their function. To date, few researchers have focused on the problem of apoptosis data imbalance before classification, while this data imbalance is prone to misclassification. Therefore, in this work, we introduce a method to resolve this problem and to enhance prediction accuracy. Firstly, the features of the protein sequence are captured by combining Improving Pseudo-Position-Specific Scoring Matrix (IM-Psepssm) with the Bidirectional Correlation Coefficient (Bid-CC) algorithm from position-specific scoring matrix. Secondly, different features of fusion and resampling strategies are used to reduce the impact of imbalance on apoptosis protein datasets. Finally, the eigenvector adopts the Support Vector Machine (SVM) to the training classification model, and the prediction accuracy is evaluated by jackknife cross-validation tests. The experimental results indicate that, under the same feature vector, adopting resampling methods remarkably boosts many significant indicators in the unsampling method for predicting the localization of apoptosis proteins in the ZD98, ZW225, and CL317 databases. Additionally, we also present new user-friendly local software for readers to apply; the codes and software can be freely accessed at https://github.com/ruanxiaoli/Im-Psepssm.

Profiling of amino acids and their interactions with proteinaceous compounds for sewage sludge dewatering by Fenton oxidation treatment

During advanced oxidation treatment for enhancing sludge dewaterability, the peptide chains of protein can be decomposed into amino acids. Protein exhibits a great impact on sewage sludge dewaterability. However, the role of amino acids in sludge dewatering remains unclear. In this study, among the 23 types of amino acids investigated, tryptophane (Trp) and lysine (Lys) were identified as the key amino acids affecting sludge dewaterability during Fenton oxidation treatment. The content of lysine showed positive correlations with capillary suction time (CST), specific resistance to filtration (SRF), and bound water content, and the concentrations of total protein, low molecular weight protein, amines and amides, and 3-turn helix of proteinaceous compounds in bound extracellular polymeric substances (EPS), while the content of tryptophane showed negative correlations with the above parameters. The amino acids may be sourced from damage of the membrane and ribosomal proteins by hydroxyl radicals, and the peptide bonds connected with tryptophane were more inclined to be decomposed than other amino acids. Particularly, more amino acids of tryptophane can result in more hydrophobic interaction, and less necessary energy barrier for aggregation of particles. As such, regulating protein degradation towards production of tryptophane may be related with enhanced sludge dewaterability by Fenton oxidation treatment.

SPVec: A Word2vec-Inspired Feature Representation Method for Drug-Target Interaction Prediction

Drug discovery is an academical and commercial process of global importance. Accurate identification of drug-target interactions (DTIs) can significantly facilitate the drug discovery process. Compared to the costly, labor-intensive and time-consuming experimental methods, machine learning (ML) plays an ever-increasingly important role in effective, efficient and high-throughput identification of DTIs. However, upstream feature extraction methods require tremendous human resources and expert insights, which limits the application of ML approaches. Inspired by the unsupervised representation learning methods like Word2vec, we here proposed SPVec, a novel way to automatically represent raw data such as SMILES strings and protein sequences into continuous, information-rich and lower-dimensional vectors, so as to avoid the sparseness and bit collisions from the cumbersomely manually extracted features. Visualization of SPVec nicely illustrated that the similar compounds or proteins occupy similar vector space, which indicated that SPVec not only encodes compound substructures or protein sequences efficiently, but also implicitly reveals some important biophysical and biochemical patterns. Compared with manually-designed features like MACCS fingerprints and amino acid composition (AAC), SPVec showed better performance with several state-of-art machine learning classifiers such as Gradient Boosting Decision Tree, Random Forest and Deep Neural Network on BindingDB. The performance and robustness of SPVec were also confirmed on independent test sets obtained from DrugBank database. Also, based on the whole DrugBank dataset, we predicted the possibilities of all unlabeled DTIs, where two of the top five predicted novel DTIs were supported by external evidences. These results indicated that SPVec can provide an effective and efficient way to discover reliable DTIs, which would be beneficial for drug reprofiling.

Identify Lysine Neddylation Sites Using Bi-profile Bayes Feature Extraction via the Chou's 5-steps Rule and General Pseudo Components

Introduction

Neddylation is a highly dynamic and reversible post-translational modification. The abnormality of neddylation has previously been shown to be closely related to some human diseases. The detection of neddylation sites is essential for elucidating the regulation mechanisms of protein neddylation.

Objective

As the detection of the lysine neddylation sites by the traditional experimental method is often expensive and time-consuming, it is imperative to design computational methods to identify neddylation sites.

Methods

In this study, a bioinformatics tool named NeddPred is developed to identify underlying protein neddylation sites. A bi-profile bayes feature extraction is used to encode neddylation sites and a fuzzy support vector machine model is utilized to overcome the problem of noise and class imbalance in the prediction.

Results

Matthew's correlation coefficient of NeddPred achieved 0.7082 and an area under the receiver operating characteristic curve of 0.9769. Independent tests show that NeddPred significantly outperforms existing lysine neddylation sites predictor NeddyPreddy.

Conclusion

Therefore, NeddPred can be a complement to the existing tools for the prediction of neddylation sites. A user-friendly webserver for NeddPred is accessible at 123.206.31.171/NeddPred/.

ML-rRBF-ECOC: A Multi-Label Learning Classifier for Predicting Protein Subcellular Localization with Both Single and Multiple Sites

Background:

The subcellular localization of a protein is closely related with its functions and interactions. More and more evidences show that proteins may simultaneously exist at, or move between, two or more different subcellular localizations. Therefore, predicting protein subcellular localization is an important but challenging problem.

Observation:

Most of the existing methods for predicting protein subcellular localization assume that a protein locates at a single site. Although a few methods have been proposed to deal with proteins with multiple sites, correlations between subcellular localization are not efficiently taken into account. In this paper, we propose an integrated method for predicting protein subcellular localizations with both single site and multiple sites.

Methods:

Firstly, we extend the Multi-Label Radial Basis Function (ML-RBF) method to the regularized version, and augment the first layer of ML-RBF to take local correlations between subcellular localization into account. Secondly, we embed the modified ML-RBF into a multi-label Error-Correcting Output Codes (ECOC) method in order to further consider the subcellular localization dependency. We name our method ML-rRBF-ECOC. Finally, the performance of ML-rRBF-ECOC is evaluated on three benchmark datasets.

Results:

The results demonstrate that ML-rRBF-ECOC has highly competitive performance to the related multi-label learning method and some state-of-the-art methods for predicting protein subcellular localizations with multiple sites. Considering dependency between subcellular localizations can contribute to the improvement of prediction performance.

Conclusion:

This also indicates that correlations between different subcellular localizations really exist. Our method at least plays a complementary role to existing methods for predicting protein subcellular localizations with multiple sites.

Protein Subcellular Localization Prediction based on PSI-BLAST Profile and Principal Component Analysis

Background:

Prediction of protein subcellular location is a meaningful task which attracts much attention in recent years. Particularly, the number of new protein sequences yielded by the highthroughput sequencing technology in the post genomic era has increased explosively.

Objective:

Protein subcellular localization prediction based solely on sequence data remains to be a challenging problem of computational biology.

Methods:

In this paper, three sets of evolutionary features are derived from the position-specific scoring matrix, which has shown great potential in other bioinformatics problems. A fusion model is built up by the optimal parameters combination. Finally, principal component analysis and support vector machine classifier is applied to predict protein subcellular localization on NNPSL dataset and Cell- PLoc 2.0 dataset.

Results:

Our experimental results show that the proposed method remarkably improved the prediction accuracy, and the features derived from PSI-BLAST profile only are appropriate for protein subcellular localization prediction.

A Brief History of Protein Sorting Prediction

Ever since the signal hypothesis was proposed in 1971, the exact nature of signal peptides has been a focus point of research. The prediction of signal peptides and protein subcellular location from amino acid sequences has been an important problem in bioinformatics since the dawn of this research field, involving many statistical and machine learning technologies. In this review, we provide a historical account of how position-weight matrices, artificial neural networks, hidden Markov models, support vector machines and, lately, deep learning techniques have been used in the attempts to predict where proteins go. Because the secretory pathway was the first one to be studied both experimentally and through bioinformatics, our main focus is on the historical development of prediction methods for signal peptides that target proteins for secretion; prediction methods to identify targeting signals for other cellular compartments are treated in less detail.

Prediction of Apoptosis Protein Subcellular Localization with Multilayer Sparse Coding and Oversampling Approach

The prediction of apoptosis protein subcellular localization plays an important role in understanding the progress in cell proliferation and death. Recently computational approaches to this issue have become very popular, since the traditional biological experiments are so costly and time-consuming that they cannot catch up with the growth rate of sequence data anymore. In order to improve the prediction accuracy of apoptosis protein subcellular localization, we proposed a sparse coding method combined with traditional feature extraction algorithm to complete the sparse representation of apoptosis protein sequences, using multilayer pooling based on different sizes of dictionaries to integrate the processed features, as well as oversampling approach to decrease the influences caused by unbalanced data sets. Then the extracted features were input to a support vector machine to predict the subcellular localization of the apoptosis protein. The experiment results obtained by Jackknife test on two benchmark data sets indicate that our method can significantly improve the accuracy of the apoptosis protein subcellular localization prediction.

Predicting drug-target interactions using Lasso with random forest based on evolutionary information and chemical structure

The identification of drug-target interactions has great significance for pharmaceutical scientific research. Since traditional experimental methods identifying drug-target interactions is costly and time-consuming, the use of machine learning methods to predict potential drug-target interactions has attracted widespread attention. This paper presents a novel drug-target interactions prediction method called LRF-DTIs. Firstly, the pseudo-position specific scoring matrix (PsePSSM) and FP2 molecular fingerprinting were used to extract the features of drug-target. Secondly, using Lasso to reduce the dimension of the extracted feature information and then the Synthetic Minority Oversampling Technique (SMOTE) method was used to deal with unbalanced data. Finally, the processed feature vectors were input into a random forest (RF) classifier to predict drug-target interactions. Through 10 trials of 5-fold cross-validation, the overall prediction accuracies on the enzyme, ion channel (IC), G-protein-coupled receptor (GPCR) and nuclear receptor (NR) datasets reached 98.09%, 97.32%, 95.69%, and 94.88%, respectively, and compared with other prediction methods. In addition, we have tested and verified that our method not only could be applied to predict the new interactions but also could obtain a satisfactory result on the new dataset. All the experimental results indicate that our method can significantly improve the prediction accuracy of drug-target interactions and play a vital role in the new drug research and target protein development. The source code and all datasets are available at https://github.com/QUST-AIBBDRC/LRF-DTIs/ for academic use.

Identification of protein subcellular localization via integrating evolutionary and physicochemical information into Chou's general PseAAC

Identifying the location of proteins in a cell plays an important role in understanding their functions, such as drug design, therapeutic target discovery and biological research. However, the traditional subcellular localization experiments are time-consuming, laborious and small scale. With the development of next-generation sequencing technology, the number of proteins has grown exponentially, which lays the foundation of the computational method for identifying protein subcellular localization. Although many methods for predicting subcellular localization of proteins have been proposed, most of them are limited to single-location. In this paper, we propose a multi-kernel SVM to predict subcellular localization of both multi-location and single-location proteins. First, we make use of the evolutionary information extracted from position specific scoring matrix (PSSM) and physicochemical properties of proteins, by Chou's general PseAAC and other efficient functions. Then, we propose a multi-kernel support vector machine (SVM) model to identify multi-label protein subcellular localization. As a result, our method has a good performance on predicting subcellular localization of proteins. It achieves an average precision of 0.7065 and 0.6889 on two human datasets, respectively. All results are higher than those achieved by other existing methods. Therefore, we provide an efficient system via a novel perspective to study the protein subcellular localization.

Predicting lysine lipoylation sites using bi-profile bayes feature extraction and fuzzy support vector machine algorithm

Lipoylation is a highly conserved post-translational modification which has been found to be involved in many biological processes and closely associated with various metabolic diseases. The accurate identification of lipoylation sites is necessary to elucidate the underlying molecular mechanisms of lipoylation. As the traditional experimental methods are time consuming and expensive, it is desired to develop computational methods to predict lipoylation sites. In this study, a novel predictor named LipoPred is proposed to predict lysine lipoylation sites. On the one hand, an effective feature extraction method, bi-profile bayes encoding, is employed to encode lipoylation sites. On the other hand, a fuzzy support vector machine algorithm is proposed to solve the class imbalance and noise problem in the prediction of lipoylation sites. As illustrated by 10-fold cross-validation, LipoPred achieves an excellent performance with a Matthew's correlation coefficient of 0.9930. Therefore, LipoPred can be a useful bioinformatics tool for the prediction of lipoylation sites. Feature analysis shows that some residues around lipoylation sites may play an important role in the prediction. The results of analysis and prediction could offer useful information for elucidating the molecular mechanisms of lipoylation. A user-friendly web-server for LipoPred is established at 123.206.31.171/LipoPred/.

Identifying anticancer peptides by using a generalized chaos game representation

We generalize chaos game representation (CGR) to higher dimensional spaces while maintaining its bijection, keeping such method sufficiently representative and mathematically rigorous compare to previous attempts. We first state and prove the asymptotic property of CGR and our generalized chaos game representation (GCGR) method. The prediction follows that the dissimilarity of sequences which possess identical subsequences but distinct positions would be lowered exponentially by the length of the identical subsequence; this effect was taking place unbeknownst to researchers. By shining a spotlight on it now, we show the effect fundamentally supports (G)CGR as a similarity measure or feature extraction technique. We develop two feature extraction techniques: GCGR-Centroid and GCGR-Variance. We use the GCGR-Centroid to analyze the similarity between protein sequences by using the datasets 9 ND5, 24 TF and 50 beta-globin proteins. We obtain consistent results compared with previous studies which proves the significance thereof. Finally, by utilizing support vector machines, we train the anticancer peptide prediction model by using both GCGR-Centroid and GCGR-Variance, and achieve a significantly higher prediction performance by employing the 3 well-studied anticancer peptide datasets.

Net Evolutionary Loss of Residue Polarity in Drosophilid Protein Cores Indicates Ongoing Optimization of Amino Acid Composition

Amino acid frequencies in proteins may not be at equilibrium. We consider two possible explanations for the nonzero net residue fluxes in drosophilid proteins. First, protein interiors may have a suboptimal residue composition and be under a selective pressure favoring stability, that is, leading to the loss of polar (and the gain of large) amino acids. One would then expect stronger net fluxes on the protein interior than at the exposed sites. Alternatively, if most of the polarity loss occurs at the exposed sites and the selective constraint on amino acid composition at such sites decreases over time, net loss of polarity may be neutral and caused by disproportionally high occurrence of polar residues at exposed, least constrained sites. We estimated net evolutionary fluxes of residue polarity and volume at sites with different solvent accessibility in conserved protein families from 12 species of Drosophila. Net loss of polarity, miniscule in magnitude, but consistent across all lineages, occurred at all sites except the most exposed ones, where net flux of polarity was close to zero or, in membrane proteins, even positive. At the intermediate solvent accessibility the net fluxes of polarity and volume were similar to neutral predictions, whereas much of the polarity loss not attributable to neutral expectations occurred at the buried sites. These observations are consistent with the hypothesis that residue composition in many proteins is structurally suboptimal and continues to evolve toward lower polarity in the protein interior, in particular in proteins with intracellular localization. The magnitude of polarity and volume changes was independent from the protein’s evolutionary age, indicating that the approach to equilibrium has been slow or that no such single equilibrium exists.

A New Method for Recognizing Cytokines Based on Feature Combination and a Support Vector Machine Classifier

Research on cytokine recognition is of great significance in the medical field due to the fact cytokines benefit the diagnosis and treatment of diseases, but the current methods for cytokine recognition have many shortcomings, such as low sensitivity and low F-score. Therefore, this paper proposes a new method on the basis of feature combination. The features are extracted from compositions of amino acids, physicochemical properties, secondary structures, and evolutionary information. The classifier used in this paper is SVM. Experiments show that our method is better than other methods in terms of accuracy, sensitivity, specificity, F-score and Matthew's correlation coefficient.