Prediction Of Protein Subcellular Localization Research Articles

Advances in the Prediction of Protein Subcellular Locations with Machine Learning

Background:Revealing the subcellular location of a newly discovered protein can bring insight into their function and guide research at the cellular level. The experimental methods currently used to identify the protein subcellular locations are both time-consuming and expensive. Thus, it is highly desired to develop computational methods for efficiently and effectively identifying the protein subcellular locations. Especially, the rapidly increasing number of protein sequences entering the genome databases has called for the development of automated analysis methods.Methods:In this review, we will describe the recent advances in predicting the protein subcellular locations with machine learning from the following aspects: i) Protein subcellular location benchmark dataset construction, ii) Protein feature representation and feature descriptors, iii) Common machine learning algorithms, iv) Cross-validation test methods and assessment metrics, v) Web servers.Result & Conclusion:Concomitant with a large number of protein sequences generated by highthroughput technologies, four future directions for predicting protein subcellular locations with machine learning should be paid attention. One direction is the selection of novel and effective features (e.g., statistics, physical-chemical, evolutional) from the sequences and structures of proteins. Another is the feature fusion strategy. The third is the design of a powerful predictor and the fourth one is the protein multiple location sites prediction.

Prediction of protein subcellular localization based on multilayer sparse coding

In order to provide a theoretical basis for better understanding the function and properties of proteins, we proposed a simple and effective feature extraction method for protein sequences to determine the subcellular localization of proteins. First, we introduced sparse coding combined with the information of amino acid composition to extract the feature values of protein sequences. Then the multilayer pooling integration was performed according to different sizes of dictionaries. Finally, the extracted feature values were sent into the support vector machine to test the effectiveness of our model. The success rates in data set ZD98, CH317 and Gram1253 were 95.9%, 93.4% and 94.7%, respectively as verified by the Jackknife test. Experiments showed that our method based on multilayer sparse coding can remarkably improve the accuracy of the prediction of protein subcellular localization.

Evaluation and Interpretation of Transcriptome Data Underlying Heterogeneous Chronic Obstructive Pulmonary Disease.

Chronic obstructive pulmonary disease (COPD) is a type of progressive lung disease, featured by airflow obstruction. Recently, a comprehensive analysis of the transcriptome in lung tissue of COPD patients was performed, but the heterogeneity of the sample was not seriously considered in characterizing the mechanistic dysregulation of COPD. Here, we established a new transcriptome analysis pipeline using a deconvolution process to reduce the heterogeneity and clearly identified that these transcriptome data originated from the mild or moderate stage of COPD patients. Differentially expressed or co-expressed genes in the protein interaction subnetworks were linked with mitochondrial dysfunction and the immune response, as expected. Computational protein localization prediction revealed that 19 proteins showing changes in subcellular localization were mostly related to mitochondria, suggesting that mislocalization of mitochondria-targeting proteins plays an important role in COPD pathology. Our extensive evaluation of COPD transcriptome data could provide guidelines for analyzing heterogeneous gene expression profiles and classifying potential candidate genes that are responsible for the pathogenesis of COPD.

A Brief Survey of Machine Learning Methods in Protein Sub-Golgi Localization

Background:The location of proteins in a cell can provide important clues to their functions in various biological processes. Thus, the application of machine learning method in the prediction of protein subcellular localization has become a hotspot in bioinformatics. As one of key organelles, the Golgi apparatus is in charge of protein storage, package, and distribution.Objective:The identification of protein location in Golgi apparatus will provide in-depth insights into their functions. Thus, the machine learning-based method of predicting protein location in Golgi apparatus has been extensively explored. The development of protein sub-Golgi apparatus localization prediction should be reviewed for providing a whole background for the fields.Method:The benchmark dataset, feature extraction, machine learning method and published results were summarized.Results:We briefly introduced the recent progresses in protein sub-Golgi apparatus localization prediction using machine learning methods and discussed their advantages and disadvantages.Conclusion:We pointed out the perspective of machine learning methods in protein sub-Golgi localization prediction.

Prediction of Protein Subcellular Localization Based on Fusion of Multi-view Features.

The prediction of protein subcellular localization is critical for inferring protein functions, gene regulations and protein-protein interactions. With the advances of high-throughput sequencing technologies and proteomic methods, the protein sequences of numerous yeasts have become publicly available, which enables us to computationally predict yeast protein subcellular localization. However, widely-used protein sequence representation techniques, such as amino acid composition and the Chou’s pseudo amino acid composition (PseAAC), are difficult in extracting adequate information about the interactions between residues and position distribution of each residue. Therefore, it is still urgent to develop novel sequence representations. In this study, we have presented two novel protein sequence representation techniques including Generalized Chaos Game Representation (GCGR) based on the frequency and distributions of the residues in the protein primary sequence, and novel statistics and information theory (NSI) reflecting local position information of the sequence. In the GCGR + NSI representation, a protein primary sequence is simply represented by a 5-dimensional feature vector, while other popular methods like PseAAC and dipeptide adopt features of more than hundreds of dimensions. In practice, the feature representation is highly efficient in predicting protein subcellular localization. Even without using machine learning-based classifiers, a simple model based on the feature vector can achieve prediction accuracies of 0.8825 and 0.7736 respectively for the CL317 and ZW225 datasets. To further evaluate the effectiveness of the proposed encoding schemes, we introduce a multi-view features-based method to combine the two above-mentioned features with other well-known features including PseAAC and dipeptide composition, and use support vector machine as the classifier to predict protein subcellular localization. This novel model achieves prediction accuracies of 0.927 and 0.871 respectively for the CL317 and ZW225 datasets, better than other existing methods in the jackknife tests. The results suggest that the GCGR and NSI features are useful complements to popular protein sequence representations in predicting yeast protein subcellular localization. Finally, we validate a few newly predicted protein subcellular localizations by evidences from some published articles in authority journals and books.

Prediction of apoptosis protein subcellular localization via heterogeneous features and hierarchical extreme learning machine

ABSTRACTApoptosis is a fundamental process controlling normal tissue homeostasis by regulating a balance between cell proliferation and death. Predicting the subcellular location of apoptosis proteins is very helpful for understanding the mechanism of programmed cell death. Predicting protein subcellular localization with bioinformatic techniques provides quite a few opportunities in related fields. In this work, we propose the use of a hierarchical extreme learning machine (H-ELM) to make a classification of high-dimensional input data without demanding a dimension reduction process, which yields acceptable results. An attempt is made to extract features from different perspectives, and a feature fusion process is accomplished. Regarding the position-specific scoring matrix, the first type depicts the correlation within the sequence with the autocorrelation function for relatively random sections from the sequence; and the second type is the Kullback-Leibler (K-L) divergence of the two distributions formed by the amino acids’ constitutuent proportions. It is illustrated in an experiment with features from different sources mixed by simple concatenation yielding a poor result, but the synthetical feature fused with stochastic nonlinear embedding (t-SNE) greatly improved the classification. Finally, the highest overall accuracy of ZD98 is 87.5% by adjusting the hyper-parameters of H-ELM, and of CL317 is 92.4%.

Tissue-Specific Subcellular Localization Prediction Using Multi-Label Markov Random Fields.

The understanding of subcellular localization (SCL) of proteins and proteome variation in the different tissues and organs of the human body are two crucial aspects for increasing our knowledge of the dynamic rules of proteins, the cell biology, and the mechanism of diseases. Although there have been tremendous contributions to these two fields independently, the lack of knowledge of the variation of spatial distribution of proteins in the different tissues still exists. Here, we proposed an approach that allows predicting protein SCL on tissue specificity through the use of tissue-specific functional associations and physical protein-protein interactions (PPIs). We applied our previously developed Bayesian collective Markov random fields (BCMRFs) on tissue-specific protein-protein interaction network (PPI network) for nine types of tissues focusing on eight high-level SCL. The evaluated results demonstrate the strength of our approach in predicting tissue-specific SCL. We identified 1,314 proteins that their SCL were previously proven cell line dependent. We predicted 549 novel tissue-specific localized candidate proteins while some of them were validated via text-mining.

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.

A Novel Protein Subcellular Localization Method With CNN-XGBoost Model for Alzheimer's Disease.

The disorder distribution of protein in the compartment or organelle leads to many human diseases, including neurodegenerative diseases such as Alzheimer's disease. The prediction of protein subcellular localization play important roles in the understanding of the mechanism of protein function, pathogenes and disease therapy. This paper proposes a novel subcellular localization method by integrating the Convolutional Neural Network (CNN) and eXtreme Gradient Boosting (XGBoost), where CNN acts as a feature extractor to automatically obtain features from the original sequence information and a XGBoost classifier as a recognizer to identify the protein subcellular localization based on the output of the CNN. Experiments are implemented on three protein datasets. The results prove that the CNN-XGBoost method performs better than the general protein subcellular localization methods.

Application of deep convolutional neural networks in classification of protein subcellular localization with microscopy images.

Single-cell microscopy image analysis has proved invaluable in protein subcellular localization for inferring gene/protein function. Fluorescent-tagged proteins across cellular compartments are tracked and imaged in response to genetic or environmental perturbations. With a large number of images generated by high-content microscopy while manual labeling is both labor-intensive and error-prone, machine learning offers a viable alternative for automatic labeling of subcellular localizations. Contrarily, in recent years applications of deep learning methods to large datasets in natural images and other domains have become quite successful. An appeal of deep learning methods is that they can learn salient features from complicated data with little data preprocessing. For such purposes, we applied several representative types of deep convolutional neural networks (CNNs) and two popular ensemble methods, random forests and gradient boosting, to predict protein subcellular localization with a moderately large cell image data set. We show a consistently better predictive performance of CNNs over the two ensemble methods. We also demonstrate the use of CNNs for feature extraction. In the end, we share our computer code and pretrained models to facilitate CNN's applications in genetics and computational biology.

Bioinformatics Workflow for Gonococcal Proteomics.

High-throughput quantitative proteomics unravels secrets of Neisseria gonorrhoeae biology by profiling proteome responses to environmental and endogenous cues and opens translational research paths through identification of vaccine candidates, drug targets/virulence factors, and biomarkers. Bioinformatics tools and databases are indispensable for downstream analysis of proteomic datasets to generate biologically meaningful outcomes. In this chapter, we present a workflow for proteomic data analysis with emphasis on publicly available resources, software systems, and tools that predict protein subcellular localization (CELLO, PSORTb v3.0, SOSUI-GramN, SignalP 4.1, LipoP 1.0, TMHMM 2.0) and functional annotation (EggNOG-mapper 4.5.1., DAVID v6.8, and KEGG) of N. gonorrhoeae proteins. This computational step-by-step procedure may help to foster new hypotheses and to provide insights into the structure-function relationship of proteins.

Molecular factors associated with pathogenicity of Phytophthora cinnamomi: Fatores moleculares associados com a patogenicidade de Phytophthora cinnamomi

Phytophthora cinnamomi is soil pathogen that has a wide range of hosts in several countries and different climates. This fungus is responsible for the chestnut ink disease (Castanea sativa Miller) and death of the tree. Portugal stands out in the production of the European chestnut tree. However, between 2002 and 2004, there was a decrease of 27.3% in the distribution area of this tree due to P. cinnamomi. The aim of this study was to identify molecular factors possibly associated with the fungal pathogenicity through genomic sequences deposited at NCBI using bioinformatics tools. The first contig was used and the OFRs present in de sequences were identified. SmartBlast was used for homologous proteins. The prediction of cellular localization prediction of proteins was performed using four different tools: SignalP 4.1, Cello v.2.5, LOCTree3, Euk-mPLoc 2.0. Protein domains characterization was accomplished using PROSITE and the structure prediction was performed using Phyre2 server. We found 13 proteins probably associated with the pathogenicity of P. cinnamomi and its properties related to the infection were analyzed in silico. These results are important since they are a first step in the search for pathogenic factors.

Predicting Protein Localization Sites Using an Ensemble Self-Labeled Framework

Predicting Protein Localization Sites Using an Ensemble Self-Labeled Framework

Deep Forest-based Prediction of Protein Subcellular Localization.

Knowledge of the correct protein subcellular localization is necessary for understanding the function of a protein and revealing the mechanism of many human diseases due to protein subcellular mislocalization, which is required before approaching gene therapy to treat a disease. In addition, it is well-known that the gene therapy is an effective way to overcome disease by targeting a gene therapy product to a specific subcellular compartment. Deep neural networks to predict protein function have become increasingly popular due to large increases in the available genomics data due to its strong superiority in the non-linear classification ability. However, they still have some drawbacks such as too many hyper-parameters and sufficient amount of labeled data. We present a deep forest-based protein location algorithm relying on sequence information. The prediction model uses a random forest network with a multi-layered structure to identify the subcellular regions of protein. The model was trained and tested on a latest UniProt releases protein dataset, and we demonstrate that our deep forest predict the subcellular location of proteins given only the protein sequence with high accuracy, outperforming the current state-of-art algorithms. Meanwhile, unlike the deep neural networks, it has a significantly smaller number of parameters and is much easier to train.

Prediction of LncRNA Subcellular Localization with Deep Learning from Sequence Features

Long non-coding RNAs are involved in biological processes throughout the cell including the nucleus, chromatin and cytosol. However, most lncRNAs remain unannotated and functional annotation of lncRNAs is difficult due to their low conservation and their tissue and developmentally specific expression. LncRNA subcellular localization is highly informative regarding its biological function, although it is difficult to discover because few prediction methods currently exist. While protein subcellular localization prediction is a well-established research field, lncRNA localization prediction is a novel research problem. We developed DeepLncRNA, a deep learning algorithm which predicts lncRNA subcellular localization directly from lncRNA transcript sequences. We analyzed 93 strand-specific RNA-seq samples of nuclear and cytosolic fractions from multiple cell types to identify differentially localized lncRNAs. We then extracted sequence-based features from the lncRNAs to construct our DeepLncRNA model, which achieved an accuracy of 72.4%, sensitivity of 83%, specificity of 62.4% and area under the receiver operating characteristic curve of 0.787. Our results suggest that primary sequence motifs are a major driving force in the subcellular localization of lncRNAs.

Predicting apoptosis protein subcellular localization by integrating auto-cross correlation and PSSM into Chou’s PseAAC

The prediction of subcellular localization of an apoptosis protein is still a challenging task, and existing methods mainly based on protein primary sequences. In this study, we propose a novel model called MACC–PSSM by integrating Moran autocorrelation and cross correlation with PSSM. Then a 3600-dimensional feature vector is constructed to predict apoptosis protein subcellular localization. Finally, 210 features are selected using principal component analysis (PCA) on the ZW225 dataset, and support vector machine is adopted as classifier. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets: ZW225 and CL317. Our model achieves competitive performance on prediction accuracies, especially for the overall prediction accuracies for datasets ZW225 and CL317, which reach 84.9% and 90.5%, respectively. Comparison of our results with other methods demonstrates that MACC–PSSM model can be used as a potential candidate for the accurate prediction of apoptosis protein subcellular localization.

PROSES: A Web Server for Sequence-Based Protein Encoding.

Recently, the number of the amino acid sequences shared in online databases is growing rapidly in huge amounts. By using sequence-derived features, machine learning algorithms are successfully applied to prediction of protein functional classes, protein-protein interactions, subcellular location, and peptides of specific properties in many studies. Protein Sequence Encoding System (PROSES) is a web server designed as freely and easily accessible for all researchers who want to use computational methods on protein sequence data. That is, PROSES provides users to encode their protein sequences easily without writing any programming code.

Consistent prediction of GO protein localization

The GO-Cellular Component (GO-CC) ontology provides a controlled vocabulary for the consistent description of the subcellular compartments or macromolecular complexes where proteins may act. Current machine learning-based methods used for the automated GO-CC annotation of proteins suffer from the inconsistency of individual GO-CC term predictions. Here, we present FGGA-CC+, a class of hierarchical graph-based classifiers for the consistent GO-CC annotation of protein coding genes at the subcellular compartment or macromolecular complex levels. Aiming to boost the accuracy of GO-CC predictions, we make use of the protein localization knowledge in the GO-Biological Process (GO-BP) annotations to boost the accuracy of GO-CC prediction. As a result, FGGA-CC+ classifiers are built from annotation data in both the GO-CC and GO-BP ontologies. Due to their graph-based design, FGGA-CC+ classifiers are fully interpretable and their predictions amenable to expert analysis. Promising results on protein annotation data from five model organisms were obtained. Additionally, successful validation results in the annotation of a challenging subset of tandem duplicated genes in the tomato non-model organism were accomplished. Overall, these results suggest that FGGA-CC+ classifiers can indeed be useful for satisfying the huge demand of GO-CC annotation arising from ubiquitous high throughout sequencing and proteomic projects.

BUSCA: an integrative web server to predict subcellular localization of proteins.

Here, we present BUSCA (http://busca.biocomp.unibo.it), a novel web server that integrates different computational tools for predicting protein subcellular localization. BUSCA combines methods for identifying signal and transit peptides (DeepSig and TPpred3), GPI-anchors (PredGPI) and transmembrane domains (ENSEMBLE3.0 and BetAware) with tools for discriminating subcellular localization of both globular and membrane proteins (BaCelLo, MemLoci and SChloro). Outcomes from the different tools are processed and integrated for annotating subcellular localization of both eukaryotic and bacterial protein sequences. We benchmark BUSCA against protein targets derived from recent CAFA experiments and other specific data sets, reporting performance at the state-of-the-art. BUSCA scores better than all other evaluated methods on 2732 targets from CAFA2, with a F1 value equal to 0.49 and among the best methods when predicting targets from CAFA3. We propose BUSCA as an integrated and accurate resource for the annotation of protein subcellular localization.

Proteomic and bioinformatic analysis of proteins on cooking loss in yak longissimus thoracis

It is a challenging task for the meat industry to search for potential predictors of water-holding capacity (WHC) in meat. Based on the data obtained from cooking loss, longissimus thoracis (LT) of yak can be classified into low cooking loss (LCL) and high cooking loss (HCL) groups. Twenty-six proteins were found to be differentially abundant in the LCL and HCL groups. Results showed that cooking loss can be attributed to structural proteins, metabolic enzymes, stress-related proteins and transport protein. The expression level of desmin, troponin T and l-lactate dehydrogenase increased greatly in the HCL group. We then used western blot and hydrophobicity analysis to validate the representative proteins. Furthermore, prediction of protein subcellular localization revealed that the differentially abundant proteins were mostly positioned in the cytoplasm, nucleus and mitochondria. Accordingly, proteomic and bioinformatic analysis have proven excellent tools to quantify the changes of proteins linked to cooking loss, with which we can explain the processes behind WHC in yak muscle.