Protein sub-nuclear localization prediction using SVM and Pfam domain information

Recent Advancements in Subcellular Proteomics: Growing Impact of Organellar Protein Niches on the Understanding of Cell Biology

The mammalian cell is a complex entity, with membrane-bound and membrane-less organelles playing vital roles in regulating cellular homeostasis. Organellar protein niches drive discrete biological processes and cell functions, thus maintaining cell equilibrium. Cellular processes such as signaling, growth, proliferation, motility, and programmed cell death require dynamic protein movements between cell compartments. Aberrant protein localization is associated with a wide range of diseases. Therefore, analyzing the subcellular proteome of the cell can provide a comprehensive overview of cellular biology. With recent advancements in mass spectrometry, imaging technology, computational tools, and deep machine learning algorithms, studies pertaining to subcellular protein localization and their dynamic distributions are gaining momentum. These studies reveal changing interaction networks because of "moonlighting proteins" and serve as a discovery tool for disease network mechanisms. Consequently, this review aims to provide a comprehensive repository for recent advancements in subcellular proteomics subcontexting methods, challenges, and future perspectives for method developers. In summary, subcellular proteomics is crucial to the understanding of the fundamental cellular mechanisms and the associated diseases.

MULocDeep web service for protein localization prediction and visualization at subcellular and suborganellar levels

Predicting protein localization and understanding its mechanisms are critical in biology and pathology. In this context, we propose a new web application of MULocDeep with improved performance, result interpretation, and visualization. By transferring the original model into species-specific models, MULocDeep achieved competitive prediction performance at the subcellular level against other state-of-the-art methods. It uniquely provides a comprehensive localization prediction at the suborganellar level. Besides prediction, our web service quantifies the contribution of single amino acids to localization for individual proteins; for a group of proteins, common motifs or potential targeting-related regions can be derived. Furthermore, the visualizations of targeting mechanism analyses can be downloaded for publication-ready figures. The MULocDeep web service is available at https://www.mu-loc.org/.

Computational methods for protein localization prediction

The accurate annotation of protein localization is crucial in understanding protein function in tandem with a broad range of applications such as pathological analysis and drug design. Since most proteins do not have experimentally-determined localization information, the computational prediction of protein localization has been an active research area for more than two decades. In particular, recent machine-learning advancements have fueled the development of new methods in protein localization prediction. In this review paper, we first categorize the main features and algorithms used for protein localization prediction. Then, we summarize a list of protein localization prediction tools in terms of their coverage, characteristics, and accessibility to help users find suitable tools based on their needs. Next, we evaluate some of these tools on a benchmark dataset. Finally, we provide an outlook on the future exploration of protein localization methods.

Application of Machine Learning Methods in Predicting Nuclear Receptors and their Families

Nuclear receptors (NRs) are a superfamily of ligand-dependent transcription factors that are closely related to cell development, differentiation, reproduction, homeostasis, and metabolism. According to the alignments of the conserved domains, NRs are classified and assigned the following seven subfamilies or eight subfamilies: (1) NR1: thyroid hormone like (thyroid hormone, retinoic acid, RAR-related orphan receptor, peroxisome proliferator activated, vitamin D3- like), (2) NR2: HNF4-like (hepatocyte nuclear factor 4, retinoic acid X, tailless-like, COUP-TFlike, USP), (3) NR3: estrogen-like (estrogen, estrogen-related, glucocorticoid-like), (4) NR4: nerve growth factor IB-like (NGFI-B-like), (5) NR5: fushi tarazu-F1 like (fushi tarazu-F1 like), (6) NR6: germ cell nuclear factor like (germ cell nuclear factor), and (7) NR0: knirps like (knirps, knirpsrelated, embryonic gonad protein, ODR7, trithorax) and DAX like (DAX, SHP), or dividing NR0 into (7) NR7: knirps like and (8) NR8: DAX like. Different NRs families have different structural features and functions. Since the function of a NR is closely correlated with which subfamily it belongs to, it is highly desirable to identify NRs and their subfamilies rapidly and effectively. The knowledge acquired is essential for a proper understanding of normal and abnormal cellular mechanisms. With the advent of the post-genomics era, huge amounts of sequence-known proteins have increased explosively. Conventional methods for accurately classifying the family of NRs are experimental means with high cost and low efficiency. Therefore, it has created a greater need for bioinformatics tools to effectively recognize NRs and their subfamilies for the purpose of understanding their biological function. In this review, we summarized the application of machine learning methods in the prediction of NRs from different aspects. We hope that this review will provide a reference for further research on the classification of NRs and their families.

Bird Eye View of Protein Subcellular Localization Prediction

Proteins are made up of long chain of amino acids that perform a variety of functions in different organisms. The activity of the proteins is determined by the nucleotide sequence of their genes and by its 3D structure. In addition, it is essential for proteins to be destined to their specific locations or compartments to perform their structure and functions. The challenge of computational prediction of subcellular localization of proteins is addressed in various in silico methods. In this review, we reviewed the progress in this field and offered a bird eye view consisting of a comprehensive listing of tools, types of input features explored, machine learning approaches employed, and evaluation matrices applied. We hope the review will be useful for the researchers working in the field of protein localization predictions.

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.

DeepMito: accurate prediction of protein sub-mitochondrial localization using convolutional neural networks

Motivation

The correct localization of proteins in cell compartments is a key issue for their function. Particularly, mitochondrial proteins are physiologically active in different compartments and their aberrant localization contributes to the pathogenesis of human mitochondrial pathologies. Many computational methods exist to assign protein sequences to subcellular compartments such as nucleus, cytoplasm and organelles. However, a substantial lack of experimental evidence in public sequence databases hampered so far a finer grain discrimination, including also intra-organelle compartments.

Results

We describe DeepMito, a novel method for predicting protein sub-mitochondrial cellular localization. Taking advantage of powerful deep-learning approaches, such as convolutional neural networks, our method is able to achieve very high prediction performances when discriminating among four different mitochondrial compartments (matrix, outer, inner and intermembrane regions). The method is trained and tested in cross-validation on a newly generated, high-quality dataset comprising 424 mitochondrial proteins with experimental evidence for sub-organelle localizations. We benchmark DeepMito towards the only one recent approach developed for the same task. Results indicate that DeepMito performances are superior. Finally, genomic-scale prediction on a highly-curated dataset of human mitochondrial proteins further confirms the effectiveness of our approach and suggests that DeepMito is a good candidate for genome-scale annotation of mitochondrial protein subcellular localization.

Availability and implementation

The DeepMito web server as well as all datasets used in this study are available at http://busca.biocomp.unibo.it/deepmito. A standalone version of DeepMito is available on DockerHub at https://hub.docker.com/r/bolognabiocomp/deepmito. DeepMito source code is available on GitHub at https://github.com/BolognaBiocomp/deepmito

Supplementary information

Supplementary data are available at Bioinformatics online.

Identification and evolutionary analysis of the nucleolar proteome of Giardia lamblia

Background

The nucleoli, including their proteomes, of higher eukaryotes have been extensively studied, while few studies about the nucleoli of the lower eukaryotes – protists were reported. Giardia lamblia, a protist with the controversy of whether it is an extreme primitive eukaryote or just a highly evolved parasite, might be an interesting object for carrying out the nucleolar proteome study of protists and for further examining the controversy.

Results

Using bioinformatics methods, we reconstructed G. lamblia nucleolar proteome (GiNuP) and the common nucleolar proteome of the three representative higher eukaryotes (human, Arabidopsis, yeast) (HEBNuP). Comparisons of the two proteomes revealed that: 1) GiNuP is much smaller than HEBNuP, but 78.4% of its proteins have orthologs in the latter; 2) More than 68% of the GiNuP proteins are involved in the “Ribosome related” function, and the others participate in the other functions, and these two groups of proteins are much larger and much smaller than those in HEBNuP, respectively; 3) Both GiNuP and HEBNuP have their own specific proteins, but HEBNuP has a much higher proportion of such proteins to participate in more categories of nucleolar functions.

Conclusion

For the first time the nucleolar proteome of a protist - Giardia was reconstructed. The results of comparison of it with the common proteome of three representative higher eukaryotes -- HEBNuP indicated that the simplicity of GiNuP is most probably a reflection of primitiveness but not just parasitic reduction of Giardia, and simultaneously revealed some interesting evolutionary phenomena about the nucleolus and even the eukaryotic cell, compositionally and functionally.

SChloro: directing Viridiplantae proteins to six chloroplastic sub-compartments

Motivation

Chloroplasts are organelles found in plants and involved in several important cell processes. Similarly to other compartments in the cell, chloroplasts have an internal structure comprising several sub-compartments, where different proteins are targeted to perform their functions. Given the relation between protein function and localization, the availability of effective computational tools to predict protein sub-organelle localizations is crucial for large-scale functional studies.

Results

In this paper we present SChloro, a novel machine-learning approach to predict protein sub-chloroplastic localization, based on targeting signal detection and membrane protein information. The proposed approach performs multi-label predictions discriminating six chloroplastic sub-compartments that include inner membrane, outer membrane, stroma, thylakoid lumen, plastoglobule and thylakoid membrane. In comparative benchmarks, the proposed method outperforms current state-of-the-art methods in both single- and multi-compartment predictions, with an overall multi-label accuracy of 74%. The results demonstrate the relevance of the approach that is eligible as a good candidate for integration into more general large-scale annotation pipelines of protein subcellular localization.

Availability and Implementation

The method is available as web server at http://schloro.biocomp.unibo.it

Contact

gigi@biocomp.unibo.it.

Prediction of Rare Palmitoylation Events in Proteins

Palmitoylation directs many cellular processes such as protein trafficking, sorting, signaling, interactions with other biomolecules, to name a few. Palmitoylation commonly occurs on cysteine; however, occasional palmitoylation of few other amino acids has also been reported. To date, comprehensive analysis on occasional palmitoylation is unavailable. In the present study, we reported a computational method to predict palmitoylation of glycine and serine residues in a protein. The method is based on support vector machine (SVM). It was trained on position-specific scoring matrix of amino acids that surrounds palmitoylated glycine and serine. During training, SVM models were evaluated on leave-one-out cross validation, and the maximum prediction accuracies achieved during training were 100% glycine palmitoylation and 99.94% for serine palmitoylation. Similar prediction for performance was also shown on independent data sets. The two SVM models were used to develop a prediction method called RAREPalm. We provide web-server and standalone of RAREPalm, using the user that can predict the potential glycine and serine palmitoylation site(s) in a protein. Comparative analysis of glycine, serine, and cysteine palmitoylation was also done to analyze pathways and classes to which different forms of palmitoylation belong. We hope that our attempt will be useful in finding more glycine and serine that may undergo palmitoylation and expanding the information on these lesser known sites of palmitoylation.

Protein subnuclear localization based on a new effective representation and intelligent kernel linear discriminant analysis by dichotomous greedy genetic algorithm

A wide variety of methods have been proposed in protein subnuclear localization to improve the prediction accuracy. However, one important trend of these means is to treat fusion representation by fusing multiple feature representations, of which, the fusion process takes a lot of time. In view of this, this paper novelly proposed a method by combining a new single feature representation and a new algorithm to obtain good recognition rate. Specifically, based on the position-specific scoring matrix (PSSM), we proposed a new expression, correlation position-specific scoring matrix (CoPSSM) as the protein feature representation. Based on the classic nonlinear dimension reduction algorithm, kernel linear discriminant analysis (KLDA), we added a new discriminant criterion and proposed a dichotomous greedy genetic algorithm (DGGA) to intelligently select its kernel bandwidth parameter. Two public datasets with Jackknife test and KNN classifier were used for the numerical experiments. The results showed that the overall success rate (OSR) with single representation CoPSSM is larger than that with many relevant representations. The OSR of the proposed method can reach as high as 87.444% and 90.3361% for these two datasets, respectively, outperforming many current methods. To show the generalization of the proposed algorithm, two extra standard datasets of protein subcellular were chosen to conduct the expending experiment, and the prediction accuracy by Jackknife test and Independent test is still considerable.

Prediction of endoplasmic reticulum resident proteins using fragmented amino acid composition and support vector machine

Background

The endoplasmic reticulum plays an important role in many cellular processes, which includes protein synthesis, folding and post-translational processing of newly synthesized proteins. It is also the site for quality control of misfolded proteins and entry point of extracellular proteins to the secretory pathway. Hence at any given point of time, endoplasmic reticulum contains two different cohorts of proteins, (i) proteins involved in endoplasmic reticulum-specific function, which reside in the lumen of the endoplasmic reticulum, called as endoplasmic reticulum resident proteins and (ii) proteins which are in process of moving to the extracellular space. Thus, endoplasmic reticulum resident proteins must somehow be distinguished from newly synthesized secretory proteins, which pass through the endoplasmic reticulum on their way out of the cell. Approximately only 50% of the proteins used in this study as training data had endoplasmic reticulum retention signal, which shows that these signals are not essentially present in all endoplasmic reticulum resident proteins. This also strongly indicates the role of additional factors in retention of endoplasmic reticulum-specific proteins inside the endoplasmic reticulum.

Methods

This is a support vector machine based method, where we had used different forms of protein features as inputs for support vector machine to develop the prediction models. During training leave-one-out approach of cross-validation was used. Maximum performance was obtained with a combination of amino acid compositions of different part of proteins.

Results

In this study, we have reported a novel support vector machine based method for predicting endoplasmic reticulum resident proteins, named as ERPred. During training we achieved a maximum accuracy of 81.42% with leave-one-out approach of cross-validation. When evaluated on independent dataset, ERPred did prediction with sensitivity of 72.31% and specificity of 83.69%. We have also annotated six different proteomes to predict the candidate endoplasmic reticulum resident proteins in them. A webserver, ERPred, was developed to make the method available to the scientific community, which can be accessed at http://proteininformatics.org/mkumar/erpred/index.html.

Discussion

We found that out of 124 proteins of the training dataset, only 66 proteins had endoplasmic reticulum retention signals, which shows that these signals are not an absolute necessity for endoplasmic reticulum resident proteins to remain inside the endoplasmic reticulum. This observation also strongly indicates the role of additional factors in retention of proteins inside the endoplasmic reticulum. Our proposed predictor, ERPred, is a signal independent tool. It is tuned for the prediction of endoplasmic reticulum resident proteins, even if the query protein does not contain specific ER-retention signal.

PredHSP: Sequence Based Proteome-Wide Heat Shock Protein Prediction and Classification Tool to Unlock the Stress Biology

Heat shock proteins are chaperonic proteins, which are present in every domain of life. They play a crucial role in folding/unfolding of proteins, their sorting and assembly into multi-protein complex, cell cycle control and also protect the cell during stress. Considering the fact that no web-based predictor is available for simultaneous prediction and classification of HSPs, it is imperative to develop a method, which can predict and classify them efficiently. In this study, we have developed coupled amino acid composition and support vector machine based two-tier method, PredHSP that identifies heat shock proteins (1st tier) and classifies it to different families (at 2nd tier). At 1st tier, we achieved maximum accuracy 76.66% with MCC 0.43, while at 2nd tier we achieved maximum accuracy 96.36% with MCC 0.87 for HSP20, 91.91% with MCC 0.83 for HSP40, 95.96% with MCC 0.72 for HSP60, 91.87% with MCC 0.71 for HSP70, 98.43% with MCC 0.70 for HSP90 and 97.48% with MCC 0.71 for HSP100. We have also developed a webserver, as well as standalone package for the use of scientific community, which can be accessed at http://14.139.227.92/mkumar/predhsp/index.html.

Protein Sub-Nuclear Localization Based on Effective Fusion Representations and Dimension Reduction Algorithm LDA

An effective representation of a protein sequence plays a crucial role in protein sub-nuclear localization. The existing representations, such as dipeptide composition (DipC), pseudo-amino acid composition (PseAAC) and position specific scoring matrix (PSSM), are insufficient to represent protein sequence due to their single perspectives. Thus, this paper proposes two fusion feature representations of DipPSSM and PseAAPSSM to integrate PSSM with DipC and PseAAC, respectively. When constructing each fusion representation, we introduce the balance factors to value the importance of its components. The optimal values of the balance factors are sought by genetic algorithm. Due to the high dimensionality of the proposed representations, linear discriminant analysis (LDA) is used to find its important low dimensional structure, which is essential for classification and location prediction. The numerical experiments on two public datasets with KNN classifier and cross-validation tests showed that in terms of the common indexes of sensitivity, specificity, accuracy and MCC, the proposed fusing representations outperform the traditional representations in protein sub-nuclear localization, and the representation treated by LDA outperforms the untreated one.

Rice_Phospho 1.0: a new rice-specific SVM predictor for protein phosphorylation sites

Experimentally-determined or computationally-predicted protein phosphorylation sites for distinctive species are becoming increasingly common. In this paper, we compare the predictive performance of a novel classification algorithm with different encoding schemes to develop a rice-specific protein phosphorylation site predictor. Our results imply that the combination of Amino acid occurrence Frequency with Composition of K-Spaced Amino Acid Pairs (AF-CKSAAP) provides the best description of relevant sequence features that surround a phosphorylation site. A support vector machine (SVM) using AF-CKSAAP achieves the best performance in classifying rice protein phophorylation sites when compared to the other algorithms. We have used SVM with AF-CKSAAP to construct a rice-specific protein phosphorylation sites predictor, Rice_Phospho 1.0 (http://bioinformatics.fafu.edu.cn/rice_phospho1.0). We measure the Accuracy (ACC) and Matthews Correlation Coefficient (MCC) of Rice_Phospho 1.0 to be 82.0% and 0.64, significantly higher than those measures for other predictors such as Scansite, Musite, PlantPhos and PhosphoRice. Rice_Phospho 1.0 also successfully predicted the experimentally identified phosphorylation sites in LOC_Os03g51600.1, a protein sequence which did not appear in the training dataset. In summary, Rice_phospho 1.0 outputs reliable predictions of protein phosphorylation sites in rice, and will serve as a useful tool to the community.

MultiP-SChlo: multi-label protein subchloroplast localization prediction with Chou's pseudo amino acid composition and a novel multi-label classifier

MOTIVATION

Identifying protein subchloroplast localization in chloroplast organelle is very helpful for understanding the function of chloroplast proteins. There have existed a few computational prediction methods for protein subchloroplast localization. However, these existing works have ignored proteins with multiple subchloroplast locations when constructing prediction models, so that they can predict only one of all subchloroplast locations of this kind of multilabel proteins.

RESULTS

To address this problem, through utilizing label-specific features and label correlations simultaneously, a novel multilabel classifier was developed for predicting protein subchloroplast location(s) with both single and multiple location sites. As an initial study, the overall accuracy of our proposed algorithm reaches 55.52%, which is quite high to be able to become a promising tool for further studies.

AVAILABILITY AND IMPLEMENTATION

An online web server for our proposed algorithm named MultiP-SChlo was developed, which are freely accessible at http://biomed.zzuli.edu.cn/bioinfo/multip-schlo/.

CONTACT

pandaxiaoxi@gmail.com or gzli@tongji.edu.cn

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

NRfamPred: a proteome-scale two level method for prediction of nuclear receptor proteins and their sub-families

Nuclear receptor proteins (NRP) are transcription factor that regulate many vital cellular processes in animal cells. NRPs form a super-family of phylogenetically related proteins and divided into different sub-families on the basis of ligand characteristics and their functions. In the post-genomic era, when new proteins are being added to the database in a high-throughput mode, it becomes imperative to identify new NRPs using information from amino acid sequence alone. In this study we report a SVM based two level prediction systems, NRfamPred, using dipeptide composition of proteins as input. At the 1st level, NRfamPred screens whether the query protein is NRP or non-NRP; if the query protein belongs to NRP class, prediction moves to 2nd level and predicts the sub-family. Using leave-one-out cross-validation, we were able to achieve an overall accuracy of 97.88% at the 1st level and an overall accuracy of 98.11% at the 2nd level with dipeptide composition. Benchmarking on independent datasets showed that NRfamPred had comparable accuracy to other existing methods, developed on the same dataset. Our method predicted the existence of 76 NRPs in the human proteome, out of which 14 are novel NRPs. NRfamPred also predicted the sub-families of these 14 NRPs.