Human Protein Subcellular Localization with Integrated Source and Multi-label Ensemble Classifier

A Review for Artificial Intelligence Based Protein Subcellular Localization

Proteins need to be located in appropriate spatiotemporal contexts to carry out their diverse biological functions. Mislocalized proteins may lead to a broad range of diseases, such as cancer and Alzheimer's disease. Knowing where a target protein resides within a cell will give insights into tailored drug design for a disease. As the gold validation standard, the conventional wet lab uses fluorescent microscopy imaging, immunoelectron microscopy, and fluorescent biomarker tags for protein subcellular location identification. However, the booming era of proteomics and high-throughput sequencing generates tons of newly discovered proteins, making protein subcellular localization by wet-lab experiments a mission impossible. To tackle this concern, in the past decades, artificial intelligence (AI) and machine learning (ML), especially deep learning methods, have made significant progress in this research area. In this article, we review the latest advances in AI-based method development in three typical types of approaches, including sequence-based, knowledge-based, and image-based methods. We also elaborately discuss existing challenges and future directions in AI-based method development in this research field.

ncRNALocate-EL: a multi-label ncRNA subcellular locality prediction model based on ensemble learning

Subcellular localizations of ncRNAs are associated with specific functions. Currently, an increasing number of biological researchers are focusing on computational approaches to identify subcellular localizations of ncRNAs. However, the performance of the existing computational methods is low and needs to be further studied. First, most prediction models are trained with outdated databases. Second, only a few predictors can identify multiple subcellular localizations simultaneously. In this work, we establish three human ncRNA subcellular datasets based on the latest RNALocate, including lncRNA, miRNA and snoRNA, and then we propose a novel multi-label classification model based on ensemble learning called ncRNALocate-EL to identify multi-label subcellular localizations of three ncRNAs. The results show that the ncRNALocate-EL outperforms previous methods. Our method achieved an average precision of 0.709,0.977 and 0.730 on three human ncRNA datasets. The web server of ncRNALocate-EL has been established, which can be accessed at https://bliulab.net/ncRNALocate-EL.

Dual-Signal Feature Spaces Map Protein Subcellular Locations Based on Immunohistochemistry Image and Protein Sequence

Protein is one of the primary biochemical macromolecular regulators in the compartmental cellular structure, and the subcellular locations of proteins can therefore provide information on the function of subcellular structures and physiological environments. Recently, data-driven systems have been developed to predict the subcellular location of proteins based on protein sequence, immunohistochemistry (IHC) images, or immunofluorescence (IF) images. However, the research on the fusion of multiple protein signals has received little attention. In this study, we developed a dual-signal computational protocol by incorporating IHC images into protein sequences to learn protein subcellular localization. Three major steps can be summarized as follows in this protocol: first, a benchmark database that includes 281 proteins sorted out from 4722 proteins of the Human Protein Atlas (HPA) and Swiss-Prot database, which is involved in the endoplasmic reticulum (ER), Golgi apparatus, cytosol, and nucleoplasm; second, discriminative feature operators were first employed to quantitate protein image-sequence samples that include IHC images and protein sequence; finally, the feature subspace of different protein signals is absorbed to construct multiple sub-classifiers via dimensionality reduction and binary relevance (BR), and multiple confidence derived from multiple sub-classifiers is adopted to decide subcellular location by the centralized voting mechanism at the decision layer. The experimental results indicated that the dual-signal model embedded IHC images and protein sequences outperformed the single-signal models with accuracy, precision, and recall of 75.41%, 80.38%, and 74.38%, respectively. It is enlightening for further research on protein subcellular location prediction under multi-signal fusion of protein.

Semantic Segmentation of Cell Painted Organelles using DeepLabv3plus Model

Cell painting based high content fluorescence imaging technique offers deep insight into the functional and biological changes in subcellular structures. However, advanced instrumentation and the limited availability of suitable fluorescent dyes restricts the tool to comprehensively characterize the cell morphology. Therefore, generating fluorescent specific organelle images using transmitted light microscopy provides an alternative solution for clinical applications. In this work, the utility of semantic segmentation deep network for predicting the Endoplasmic Reticulum (ER), cytoplasm and nuclei from a composite image is investigated. To perform this study, a public dataset consisting of 3456 composite images are considered from Broad Bioimage Benchmark collection. The pixel wise labeling is carried out with the generated binary masks for ER, cytoplasm and nuclei. DeepLabv3plus architecture with Atrous Spatial Pyramid Pooling (ASPP) and depth wise separable convolution is used as a learning model to perform semantic segmentation. The accuracy and loss function at different learning rates are analyzed and the segmentation results are validated using Jaccard index, mean Boundary F (BF) score and dice index. The trained model achieved 97.86% accuracy with a loss of 0.07 at the learning rate of 0.01. Mean BF score, dice index and Jaccard index for nuclei, ER and cytoplasm are (0.98, 0.94, 0.88), (0.97, 0.82, 0.7) and (0.95, 0.88, 0.66) respectively. The obtained results indicate that the adopted methodology could delineate the subcellular structures by accurately detecting sharp object boundaries. Therefore, this study could be useful for predicting the cell painted images from transmitted light microscopy without the requirement of fluorescent labeling.

FungiProteomeDB: a database for the molecular weight and isoelectric points of the fungal proteomes

Proteins' molecular weight (MW) and isoelectric point (pI) are crucial for their subcellular localization and subsequent function. These are also useful in 2D gel electrophoresis, liquid chromatography-mass spectrometry and X-ray protein crystallography. Moreover, visualizations like a virtual 2D proteome map of pI vs. MW are worthwhile to discuss the proteome diversity among different species. Although the genome sequence data of the fungi kingdom improved enormously, the proteomic details have been poorly elaborated. Therefore, we have calculated the MW and pI of the fungi proteins and reported them in, FungiProteomeDB, an online database (DB) https://vision4research.com/fungidb/. We analyzed the proteome of 685 fungal species that contain 7 127 141 protein sequences. The DB provides an easy-to-use and efficient interface for various search options, summary statistics and virtual 2D proteome map visualizations. The MW and pI of a protein can be obtained by searching the name of a protein, a keyword or a list of accession numbers. It also allows querying protein sequences. The DB will be helpful in hypothesis formulation and in various biotechnological applications. Database URL https://vision4research.com/fungidb/.

PScL-2LSAESM: bioimage-based prediction of protein subcellular localization by integrating heterogeneous features with the two-level SAE-SM and mean ensemble method

MOTIVATION

Over the past decades, a variety of in silico methods have been developed to predict protein subcellular localization within cells. However, a common and major challenge in the design and development of such methods is how to effectively utilize the heterogeneous feature sets extracted from bioimages. In this regards, limited efforts have been undertaken.

RESULTS

We propose a new two-level stacked autoencoder network (termed 2L-SAE-SM) to improve its performance by integrating the heterogeneous feature sets. In particular, in the first level of 2L-SAE-SM, each optimal heterogeneous feature set is fed to train our designed stacked autoencoder network (SAE-SM). All the trained SAE-SMs in the first level can output the decision sets based on their respective optimal heterogeneous feature sets, known as 'intermediate decision' sets. Such intermediate decision sets are then ensembled using the mean ensemble method to generate the 'intermediate feature' set for the second-level SAE-SM. Using the proposed framework, we further develop a novel predictor, referred to as PScL-2LSAESM, to characterize image-based protein subcellular localization. Extensive benchmarking experiments on the latest benchmark training and independent test datasets collected from the human protein atlas databank demonstrate the effectiveness of the proposed 2L-SAE-SM framework for the integration of heterogeneous feature sets. Moreover, performance comparison of the proposed PScL-2LSAESM with current state-of-the-art methods further illustrates that PScL-2LSAESM clearly outperforms the existing state-of-the-art methods for the task of protein subcellular localization.

AVAILABILITY AND IMPLEMENTATION

https://github.com/csbio-njust-edu/PScL-2LSAESM.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Pixel-level multimodal fusion deep networks for predicting subcellular organelle localization from label-free live-cell imaging

Complex intracellular organizations are commonly represented by dividing the metabolic process of cells into different organelles. Therefore, identifying sub-cellular organelle architecture is significant for understanding intracellular structural properties, specific functions, and biological processes in cells. However, the discrimination of these structures in the natural organizational environment and their functional consequences are not clear. In this article, we propose a new pixel-level multimodal fusion (PLMF) deep network which can be used to predict the location of cellular organelle using label-free cell optical microscopy images followed by deep-learning-based automated image denoising. It provides valuable insights that can be of tremendous help in improving the specificity of label-free cell optical microscopy by using the Transformer-Unet network to predict the ground truth imaging which corresponds to different sub-cellular organelle architectures. The new prediction method proposed in this article combines the advantages of a transformer's global prediction and CNN's local detail analytic ability of background features for label-free cell optical microscopy images, so as to improve the prediction accuracy. Our experimental results showed that the PLMF network can achieve over 0.91 Pearson's correlation coefficient (PCC) correlation between estimated and true fractions on lung cancer cell-imaging datasets. In addition, we applied the PLMF network method on the cell images for label-free prediction of several different subcellular components simultaneously, rather than using several fluorescent labels. These results open up a new way for the time-resolved study of subcellular components in different cells, especially for cancer cells.

Multiple Parallel Fusion Network for Predicting Protein Subcellular Localization from Stimulated Raman Scattering (SRS) Microscopy Images in Living Cells

Stimulated Raman Scattering Microscopy (SRS) is a powerful tool for label-free detailed recognition and investigation of the cellular and subcellular structures of living cells. Determining subcellular protein localization from the cell level of SRS images is one of the basic goals of cell biology, which can not only provide useful clues for their functions and biological processes but also help to determine the priority and select the appropriate target for drug development. However, the bottleneck in predicting subcellular protein locations of SRS cell imaging lies in modeling complicated relationships concealed beneath the original cell imaging data owing to the spectral overlap information from different protein molecules. In this work, a multiple parallel fusion network, MPFnetwork, is proposed to study the subcellular locations from SRS images. This model used a multiple parallel fusion model to construct feature representations and combined multiple nonlinear decomposing algorithms as the automated subcellular detection method. Our experimental results showed that the MPFnetwork could achieve over 0.93 dice correlation between estimated and true fractions on SRS lung cancer cell datasets. In addition, we applied the MPFnetwork method to cell images for label-free prediction of several different subcellular components simultaneously, rather than using several fluorescent labels. These results open up a new method for the time-resolved study of subcellular components in different cells, especially cancer cells.

PScL-DDCFPred: an ensemble deep learning-based approach for characterizing multiclass subcellular localization of human proteins from bioimage data

MOTIVATION

Characterization of protein subcellular localization has become an important and long-standing task in bioinformatics and computational biology, which provides valuable information for elucidating various cellular functions of proteins and guiding drug design.

RESULTS

Here, we develop a novel bioimage-based computational approach, termed PScL-DDCFPred, to accurately predict protein subcellular localizations in human tissues. PScL-DDCFPred first extracts multiview image features, including global and local features, as base or pure features; next, it applies a new integrative feature selection method based on stepwise discriminant analysis and generalized discriminant analysis to identify the optimal feature sets from the extracted pure features; Finally, a classifier based on deep neural network (DNN) and deep-cascade forest (DCF) is established. Stringent 10-fold cross-validation tests on the new protein subcellular localization training dataset, constructed from the human protein atlas databank, illustrates that PScL-DDCFPred achieves a better performance than several existing state-of-the-art methods. Moreover, the independent test set further illustrates the generalization capability and superiority of PScL-DDCFPred over existing predictors. In-depth analysis shows that the excellent performance of PScL-DDCFPred can be attributed to three critical factors, namely the effective combination of the DNN and DCF models, complementarity of global and local features, and use of the optimal feature sets selected by the integrative feature selection algorithm.

AVAILABILITY AND IMPLEMENTATION

https://github.com/csbio-njust-edu/PScL-DDCFPred.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

PlantMWpIDB: a database for the molecular weight and isoelectric points of the plant proteomes

The molecular weight and isoelectric point of the proteins are very important parameters that control their subcellular localization and subsequent function. Although the genome sequence data of the plant kingdom improved enormously, the proteomic details have been poorly elaborated. Therefore, we have calculated the molecular weight and isoelectric point of the plant proteins and reported them in this database. A database, PlantMWpIDB, containing protein data from 342 plant proteomes was created to provide information on plant proteomes for hypothesis formulation in basic research and for biotechnological applications. The Molecular weight and isoelectric point (pI) are important molecular parameters of proteins that are useful when conducting protein studies involving 2D gel electrophoresis, liquid chromatography-mass spectrometry, and X-ray protein crystallography. PlantMWpIDB provides an easy-to-use and efficient interface for search options and generates a summary of basic protein parameters. The database represents a virtual 2D proteome map of plants, and the molecular weight and pI of a protein can be obtained by searching on the name of a protein, a keyword, or by a list of accession numbers. The PlantMWpIDB database also allows one to query protein sequences. The database can be found in the following link https://plantmwpidb.com/ . The individual 2D virtual proteome map of the plant kingdom will enable us to understand the proteome diversity between different species. Further, the molecular weight and isoelectric point of individual proteins can enable us to understand their functional significance in different species.

Machine and Deep Learning for Prediction of Subcellular Localization

Protein subcellular localization prediction (PSLP), which plays an important role in the field of computational biology, identifies the position and function of proteins in cells without expensive cost and laborious effort. In the past few decades, various methods with different algorithms have been proposed in solving the problem of subcellular localization prediction; machine learning and deep learning constitute a large portion among those proposed methods. In order to provide an overview about those methods, the first part of this article will be a brief review of several state-of-the-art machine learning methods on subcellular localization prediction; then the materials used by subcellular localization prediction is described and a simple prediction method, that takes protein sequences as input and utilizes a convolutional neural network as the classifier, is introduced. At last, a list of notes is provided to indicate the major problems that may occur with this method.

Learning protein subcellular localization multi-view patterns from heterogeneous data of imaging, sequence and networks

Location proteomics seeks to provide automated high-resolution descriptions of protein location patterns within cells. Many efforts have been undertaken in location proteomics over the past decades, thereby producing plenty of automated predictors for protein subcellular localization. However, most of these predictors are trained solely from high-throughput microscopic images or protein amino acid sequences alone. Unifying heterogeneous protein data sources has yet to be exploited. In this paper, we present a pipeline called sequence, image, network-based protein subcellular locator (SIN-Locator) that constructs a multi-view description of proteins by integrating multiple data types including images of protein expression in cells or tissues, amino acid sequences and protein-protein interaction networks, to classify the patterns of protein subcellular locations. Proteins were encoded by both handcrafted features and deep learning features, and multiple combining methods were implemented. Our experimental results indicated that optimal integrations can considerately enhance the classification accuracy, and the utility of SIN-Locator has been demonstrated through applying to new released proteins in the human protein atlas. Furthermore, we also investigate the contribution of different data sources and influence of partial absence of data. This work is anticipated to provide clues for reconciliation and combination of multi-source data for protein location analysis.

Automated classification of protein subcellular localization in immunohistochemistry images to reveal biomarkers in colon cancer

BACKGROUND

Protein biomarkers play important roles in cancer diagnosis. Many efforts have been made on measuring abnormal expression intensity in biological samples to identity cancer types and stages. However, the change of subcellular location of proteins, which is also critical for understanding and detecting diseases, has been rarely studied.

RESULTS

In this work, we developed a machine learning model to classify protein subcellular locations based on immunohistochemistry images of human colon tissues, and validated the ability of the model to detect subcellular location changes of biomarker proteins related to colon cancer. The model uses representative image patches as inputs, and integrates feature engineering and deep learning methods. It achieves 92.69% accuracy in classification of new proteins. Two validation datasets of colon cancer biomarkers derived from published literatures and the human protein atlas database respectively are employed. It turns out that 81.82 and 65.66% of the biomarker proteins can be identified to change locations.

CONCLUSIONS

Our results demonstrate that using image patches and combining predefined and deep features can improve the performance of protein subcellular localization, and our model can effectively detect biomarkers based on protein subcellular translocations. This study is anticipated to be useful in annotating unknown subcellular localization for proteins and discovering new potential location biomarkers.

Prediction of Ion Channels and their Types from Protein Sequences: Comprehensive Review and Comparative Assessment

BACKGROUND

Ion channels are a large and growing protein family. Many of them are associated with diseases, and consequently, they are targets for over 700 drugs. Discovery of new ion channels is facilitated with computational methods that predict ion channels and their types from protein sequences. However, these methods were never comprehensively compared and evaluated.

OBJECTIVE

We offer first-of-its-kind comprehensive survey of the sequence-based predictors of ion channels. We describe eight predictors that include five methods that predict ion channels, their types, and four classes of the voltage-gated channels. We also develop and use a new benchmark dataset to perform comparative empirical analysis of the three currently available predictors.

RESULTS

While several methods that rely on different designs were published, only a few of them are currently available and offer a broad scope of predictions. Support and availability after publication should be required when new methods are considered for publication. Empirical analysis shows strong performance for the prediction of ion channels and modest performance for the prediction of ion channel types and voltage-gated channel classes. We identify a substantial weakness of current methods that cannot accurately predict ion channels that are categorized into multiple classes/types.

CONCLUSION

Several predictors of ion channels are available to the end users. They offer practical levels of predictive quality. Methods that rely on a larger and more diverse set of predictive inputs (such as PSIONplus) are more accurate. New tools that address multi-label prediction of ion channels should be developed.

PSIONplusm Server for Accurate Multi-Label Prediction of Ion Channels and Their Types

Computational prediction of ion channels facilitates the identification of putative ion channels from protein sequences. Several predictors of ion channels and their types were developed in the last quindecennial. While they offer reasonably accurate predictions, they also suffer a few shortcomings including lack of availability, parallel prediction mode, single-label prediction (inability to predict multiple channel subtypes), and incomplete scope (inability to predict subtypes of the voltage-gated channels). We developed a first-of-its-kind PSIONplus^m method that performs sequential multi-label prediction of ion channels and their subtypes for both voltage-gated and ligand-gated channels. PSIONplus^m sequentially combines the outputs produced by three support vector machine-based models from the PSIONplus predictor and is available as a webserver. Empirical tests show that PSIONplus^m outperforms current methods for the multi-label prediction of the ion channel subtypes. This includes the existing single-label methods that are available to the users, a naïve multi-label predictor that combines results produced by multiple single-label methods, and methods that make predictions based on sequence alignment and domain annotations. We also found that the current methods (including PSIONplus^m) fail to accurately predict a few of the least frequently occurring ion channel subtypes. Thus, new predictors should be developed when a larger quantity of annotated ion channels will be available to train predictive models.

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.

Resolution Matters: Correlating Quantitative Proteomics and Nanoscale-Precision Microscopy for Reconstructing Synapse Identity

For more than a century, the precision at which any protein (or RNA) could be localized in living cells depends on the spatial resolution of microscopy. Light microscopy, even recently benchmarked laser-scanning microscopy, is inherently liable to the diffraction limit of visible light. Electron microscopy that had existed as the only alternative for decades is, in turn, of low throughput and sensitive to processing artefacts. Therefore, researchers have looked for alternative technologies particularly with ever-growing interest in resolving structural underpinnings of cellular heterogeneity in the human body. Computational ("in silico") predictions provided only partial solutions given the incompleteness of existing databases and erroneous assumptions on evolutionarily conserved sequence homology across species. A breakthrough that facilitates subcellular protein localization came with the introduction of "super-resolution" microscopy, which yields 20-60 nm resolution by overcoming diffraction-limited technologies. The ensuing combination of "super-resolution" microscopy with unbiased proteomics continues to produce never-before-seen gains by quantitatively addressing the distribution, interaction, turnover, and secretion of proteins in living cells. Here, we illustrate the power of this combined work flow by the example of transmembrane receptor localization at the neuronal synapse. We also discuss how dynamic analysis allows for inferences be made for cellular physiology and pathobiology.

iAPSL-IF: Identification of Apoptosis Protein Subcellular Location Using Integrative Features Captured from Amino Acid Sequences

Apoptosis proteins (APs) control normal tissue homeostasis by regulating the balance between cell proliferation and death. The function of APs is strongly related to their subcellular location. To date, computational methods have been reported that reliably identify the subcellular location of APs, however, there is still room for improvement of the prediction accuracy. In this study, we developed a novel method named iAPSL-IF (identification of apoptosis protein subcellular location—integrative features), which is based on integrative features captured from Markov chains, physicochemical property matrices, and position-specific score matrices (PSSMs) of amino acid sequences. The matrices with different lengths were transformed into fixed-length feature vectors using an auto cross-covariance (ACC) method. An optimal subset of the features was chosen using a recursive feature elimination (RFE) algorithm method, and the sequences with these features were trained by a support vector machine (SVM) classifier. Based on three datasets ZD98, CL317, and ZW225, the iAPSL-IF was examined using a jackknife cross-validation test. The resulting data showed that the iAPSL-IF outperformed the known predictors reported in the literature: its overall accuracy on the three datasets was 98.98% (ZD98), 94.95% (CL317), and 97.33% (ZW225), respectively; the Matthews correlation coefficient, sensitivity, and specificity for several classes of subcellular location proteins (e.g., membrane proteins, cytoplasmic proteins, endoplasmic reticulum proteins, nuclear proteins, and secreted proteins) in the datasets were 0.92–1.0, 94.23–100%, and 97.07–100%, respectively. Overall, the results of this study provide a high throughput and sequence-based method for better identification of the subcellular location of APs, and facilitates further understanding of programmed cell death in organisms.

Cytoplasmic functions of long noncoding RNAs

Long noncoding RNAs (lncRNAs) are transcripts longer than 200 nucleotides found throughout the cell that lack protein-coding function. Their functions are closely linked to their interaction with RNA-binding proteins (RBPs) and nucleic acids. Nuclear lncRNAs have been studied extensively, revealing complexes with structural and regulatory roles that enable gene organization and control transcription. Cytoplasmic lncRNAs are less well understood, but accumulating evidence indicates that they also form complexes with diverse structural and regulatory functions. Here, we review our current knowledge of cytoplasmic lncRNAs and the different levels of gene regulation controlled by cytoplasmic lncRNA complexes, including mRNA turnover, translation, protein stability, sponging of cytosolic factors, and modulation of signaling pathways. We conclude by discussing areas of future study needed to elucidate comprehensively the biology of lncRNAs, to further understand the impact of lncRNAs on physiology and design lncRNA-centered therapeutic strategies. This article is categorized under: RNA Export and Localization > RNA Localization Regulatory RNAs/RNAi/Riboswitches > Regulatory RNAs RNA Interactions with Proteins and Other Molecules > Protein-RNA Interactions: Functional Implications.

Big Data in Drug Discovery

Interpretation of Big Data in the drug discovery community should enhance project timelines and reduce clinical attrition through improved early decision making. The issues we encounter start with the sheer volume of data and how we first ingest it before building an infrastructure to house it to make use of the data in an efficient and productive way. There are many problems associated with the data itself including general reproducibility, but often, it is the context surrounding an experiment that is critical to success. Help, in the form of artificial intelligence (AI), is required to understand and translate the context. On the back of natural language processing pipelines, AI is also used to prospectively generate new hypotheses by linking data together. We explain Big Data from the context of biology, chemistry and clinical trials, showcasing some of the impressive public domain sources and initiatives now available for interrogation.

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.

Predicting human protein subcellular localization by heterogeneous and comprehensive approaches

Drug development and investigation of protein function both require an understanding of protein subcellular localization. We developed a system, REALoc, that can predict the subcellular localization of singleplex and multiplex proteins in humans. This system, based on comprehensive strategy, consists of two heterogeneous systematic frameworks that integrate one-to-one and many-to-many machine learning methods and use sequence-based features, including amino acid composition, surface accessibility, weighted sign aa index, and sequence similarity profile, as well as gene ontology function-based features. REALoc can be used to predict localization to six subcellular compartments (cell membrane, cytoplasm, endoplasmic reticulum/Golgi, mitochondrion, nucleus, and extracellular). REALoc yielded a 75.3% absolute true success rate during five-fold cross-validation and a 57.1% absolute true success rate in an independent database test, which was >10% higher than six other prediction systems. Lastly, we analyzed the effects of Vote and GANN models on singleplex and multiplex localization prediction efficacy. REALoc is freely available at http://predictor.nchu.edu.tw/REALoc.

Subcellular localization prediction of apoptosis proteins based on evolutionary information and support vector machine

OBJECTIVES

In this paper, a high-quality sequence encoding scheme is proposed for predicting subcellular location of apoptosis proteins.

METHODS

In the proposed methodology, the novel evolutionary-conservative information is introduced to represent protein sequences. Meanwhile, based on the proportion of golden section in mathematics, position-specific scoring matrix (PSSM) is divided into several blocks. Then, these features are predicted by support vector machine (SVM) and the predictive capability of proposed method is implemented by jackknife test RESULTS: The results show that the golden section method is better than no segmentation method. The overall accuracy for ZD98 and CL317 is 98.98% and 91.11%, respectively, which indicates that our method can play a complimentary role to the existing methods in the relevant areas.

CONCLUSIONS

The proposed feature representation is powerful and the prediction accuracy will be improved greatly, which denotes our method provides the state-of-the-art performance for predicting subcellular location of apoptosis proteins.

iMulti-HumPhos: a multi-label classifier for identifying human phosphorylated proteins using multiple kernel learning based support vector machines

An efficient multi-label classifier for identifying human phosphorylated proteins has been developed by introducing multiple kernel learning based support vector machines.