Detecting and sorting targeting peptides with neural networks and support vector machines

This paper presents a composite multi-layer classifier system for predicting the subcellular localization of proteins based on their amino acid sequence. The work is an extension of our previous predictor PProwler v1.1 which is itself built upon the series of predictors SignalP and TargetP. In this study we outline experiments conducted to improve the classifier design. The major improvement came from using Support Vector machines as a "smart gate" sorting the outputs of several different targeting peptide detection networks. Our final model (PProwler v1.2) gives MCC values of 0.873 for non-plant and 0.849 for plant proteins. The model improves upon the accuracy of our previous subcellular localization predictor (PProwler v1.1) by 2% for plant data (which represents 7.5% improvement upon TargetP).     

Prediction of subcellular localization using sequence-biased recurrent networks

MOTIVATION: Targeting peptides direct nascent proteins to their specific subcellular compartment. Knowledge of targeting signals enables informed drug design and reliable annotation of gene products. However, due to the low similarity of such sequences and the dynamical nature of the sorting process, the computational prediction of subcellular localization of proteins is challenging. RESULTS: We contrast the use of feed forward models as employed by the popular TargetP/SignalP predictors with a sequence-biased recurrent network model. The models are evaluated in terms of performance at the residue level and at the sequence level, and demonstrate that recurrent networks improve the overall prediction performance. Compared to the original results reported for TargetP, an ensemble of the tested models increases the accuracy by 6 and 5% on non-plant and plant data, respectively. AVAILABILITY: The Protein Prowler incorporating the recurrent network predictor described in this paper is available online at http://pprowler.imb.uq.edu.au/     

基于茶蛋白质组学数据分析植物亚细胞定位预测软件的应用

以500个茶（Camellia sinensis（L.）O.Ktze.）叶片的蛋白质作为数据集,比较TargetP、WoLF PSORT、LocTree和Plant-mPLoc 4种软件预测亚细胞定位的可信度和灵敏度。结果显示,4种软件预测可信度均高于80%,依次排序为TargetP > LocTree > WoLF PSORT > Plant-mPLoc。其中,LocTree对细胞质蛋白和分泌蛋白检测灵敏度最高,但对叶绿体蛋白灵敏度最低;Plant-mPLoc检测核蛋白最灵敏,但对细胞质蛋白最不敏感;TargetP检测叶绿体蛋白最灵敏,但仅能区分3个亚细胞器官;WoLF PSORT对分泌蛋白检测灵敏度最低,但对其他蛋白均较灵敏。基于上述结果,该研究针对4种软件提出了合理的使用建议。     

Predicting subcellular localization of proteins based on their N-terminal amino acid sequence

A neural network-based tool, TargetP, for large-scale subcellular location prediction of newly identified proteins has been developed. Using N-terminal sequence information only, it discriminates between proteins destined for the mitochondrion, the chloroplast, the secretory pathway, and "other" localizations with a success rate of 85% (plant) or 90% (non-plant) on redundancy-reduced test sets. From a TargetP analysis of the recently sequenced Arabidopsis thaliana chromosomes 2 and 4 and the Ensembl Homo sapiens protein set, we estimate that 10% of all plant proteins are mitochondrial and 14% chloroplastic, and that the abundance of secretory proteins, in both Arabidopsis and Homo, is around 10%. TargetP also predicts cleavage sites with levels of correctly predicted sites ranging from approximately 40% to 50% (chloroplastic and mitochondrial presequences) to above 70% (secretory signal peptides). TargetP is available as a web-server at http://www.cbs.dtu.dk/services/TargetP/.     

粗糙脉孢菌基因组分泌蛋白的初步分析

文章报道利用信号肽预测软件SignalP v3.0和PSORT,跨膜螺旋结构预测软件TMHMMv2.0和THUMBUP,GPI-锚定位点预测软件big-PI Predictor和亚细胞器中蛋白定位分布预测软件TargetP v1.01对粗糙脉孢菌全基因组数据库中已公布的10 082个氨基酸序列进行预测分析。结果表明在粗糙脉孢菌中有437个蛋白为分泌蛋白,编码这些蛋白最小的可读框（open reading frame,ORF）为252 bp,最大为6 604 bp,平均1 433 bp,分泌蛋白信号肽长度介于15~59个氨基酸之间。在437个分泌蛋白中,205个具有功能描述,主要包括各种酶类、细胞能量生成、运转以及自身修复、防卫等多种功能。这些蛋白所参与的生化过程可能发生在膜外的周质空间或是菌体外的场所,为该物种营养的摄取,以及对环境做出响应服务。      

Comparative analysis of an experimental subcellular protein localization assay and in silico prediction methods

The subcellular localization of a protein can provide important information about its function within the cell. As eukaryotic cells and particularly mammalian cells are characterized by a high degree of compartmentalization, most protein activities can be assigned to particular cellular compartments. The categorization of proteins by their subcellular localization is therefore one of the essential goals of the functional annotation of the human genome. We previously performed a subcellular localization screen of 52 proteins encoded on human chromosome 21. In the current study, we compared the experimental localization data to the in silico results generated by nine leading software packages with different prediction resolutions. The comparison revealed striking differences between the programs in the accuracy of their subcellular protein localization predictions. Our results strongly suggest that the recently developed predictors utilizing multiple prediction methods tend to provide significantly better performance over purely sequence-based or homology-based predictions.     

Evaluating eukaryotic secreted protein prediction

Background  

Improvements in protein sequence annotation and an increase in the number of annotated protein databases has fueled development of an increasing number of software tools to predict secreted proteins. Six software programs capable of high throughput and employing a wide range of prediction methods, SignalP 3.0, SignalP 2.0, TargetP 1.01, PrediSi, Phobius, and ProtComp 6.0, are evaluated.     

Predicting subcellular localization of proteins using machine-learned classifiers

MOTIVATION: Identifying the destination or localization of proteins is key to understanding their function and facilitating their purification. A number of existing computational prediction methods are based on sequence analysis. However, these methods are limited in scope, accuracy and most particularly breadth of coverage. Rather than using sequence information alone, we have explored the use of database text annotations from homologs and machine learning to substantially improve the prediction of subcellular location. RESULTS: We have constructed five machine-learning classifiers for predicting subcellular localization of proteins from animals, plants, fungi, Gram-negative bacteria and Gram-positive bacteria, which are 81% accurate for fungi and 92-94% accurate for the other four categories. These are the most accurate subcellular predictors across the widest set of organisms ever published. Our predictors are part of the Proteome Analyst web-service.     

PredSL： A Tool for the N-terminal Sequence-based Prediction of Protein Subcellular Localization

The ability to predict the subcellular localization of a protein from its sequence is of great importance, as it provides information about the protein＇s function. We present a computational tool, PredSL, which utilizes neural networks, Markov chains, profile hidden Markov models, and scoring matrices for the prediction of the subcellular localization of proteins in eukaryotic cells from the N-terminal amino acid sequence. It aims to classify proteins into five groups： chloroplast, thylakoid, mitochondrion, secretory pathway, and ＂other＂. When tested in a fivefold cross-validation procedure, PredSL demonstrates 86.7% and 87.1% overall accuracy for the plant and non-plant datasets, respectively. Compared with TargetP, which is the most widely used method to date, and LumenP, the results of PredSL are comparable in most cases. When tested on the experimentally verified proteins of the Saccharomyces cerevisiae genome, PredSL performs comparably if not better than any available algorithm for the same task. Furthermore, PredSL is the only method capable for the prediction of these subcellular localizations that is available as a stand-alone application through the URL： http：//bioinformatics.biol.uoa.gr/PredSL/.     

Validating subcellular localization prediction tools with mycobacterial proteins

Background  

The computational prediction of mycobacterial proteins' subcellular localization is of key importance for proteome annotation and for the identification of new drug targets and vaccine candidates. Several subcellular localization classifiers have been developed over the past few years, which have comprised both general localization and feature-based classifiers. Here, we have validated the ability of different bioinformatics approaches, through the use of SignalP 2.0, TatP 1.0, LipoP 1.0, Phobius, PA-SUB 2.5, PSORTb v.2.0.4 and Gpos-PLoc, to predict secreted bacterial proteins. These computational tools were compared in terms of sensitivity, specificity and Matthew's correlation coefficient (MCC) using a set of mycobacterial proteins having less than 40% identity, none of which are included in the training data sets of the validated tools and whose subcellular localization have been experimentally confirmed. These proteins belong to the TBpred training data set, a computational tool specifically designed to predict mycobacterial proteins.     

Transit peptide cleavage sites of integral thylakoid membrane proteins

A set of 58 nuclearly encoded thylakoid-integral membrane proteins from four plant species was identified, and their amino termini were assigned unequivocally based upon mass spectrometry of intact proteins and peptide fragments. The dataset was used to challenge the Web tools ChloroP, TargetP, SignalP, PSORT, Predotar, and MitoProt II for predicting organelle targeting and transit peptide proteolysis sites. ChloroP and TargetP reliably predicted chloroplast targeting but only reliably predicted transit peptide cleavage sites for soluble proteins targeted to the stroma. SignalP (eukaryote settings) accurately predicted the transit peptide cleavage site for soluble proteins targeted to the lumen. SignalP (Gram-negative bacteria settings) reliably predicted peptide cleavage of integral thylakoid proteins inserted into the membrane via the "spontaneous" pathway. The processing sites of more common thylakoid-integral proteins inserted by the signal recognition peptide-dependent pathway were not well predicted by any of the programs. The results suggest the presence of a second thylakoid processing protease that recognizes the transit peptide of integral proteins inserted via the spontaneous mechanism and that this mechanism may be related to the secretory mechanism of Gram-negative bacteria.     

PSI: A Comprehensive and Integrative Approach for Accurate Plant Subcellular Localization Prediction

Predicting the subcellular localization of proteins conquers the major drawbacks of high-throughput localization experiments that are costly and time-consuming. However, current subcellular localization predictors are limited in scope and accuracy. In particular, most predictors perform well on certain locations or with certain data sets while poorly on others. Here, we present PSI, a novel high accuracy web server for plant subcellular localization prediction. PSI derives the wisdom of multiple specialized predictors via a joint-approach of group decision making strategy and machine learning methods to give an integrated best result. The overall accuracy obtained (up to 93.4%) was higher than best individual (CELLO) by ∼10.7%. The precision of each predicable subcellular location (more than 80%) far exceeds that of the individual predictors. It can also deal with multi-localization proteins. PSI is expected to be a powerful tool in protein location engineering as well as in plant sciences, while the strategy employed could be applied to other integrative problems. A user-friendly web server, PSI, has been developed for free access at http://bis.zju.edu.cn/psi/.     

基于序列拓扑和二阶隐马尔可夫模型的跨膜蛋白亚细胞定位预测

现有蛋白质亚细胞定位方法针对水溶性蛋白质而设计,对跨膜蛋白并不适用。而专门的跨膜拓扑预测器,又不是为亚细胞定位而设计的。文章改进了跨膜拓扑预测器TMPHMMLoc的模型结构,设计了一个新的二阶隐马尔可夫模型;采用推广到二阶模型的Baum-Welch算法估计模型参数,并把将各个亚细胞位置建立的模型整合为一个预测器。数据集上测试结果表明,此方法性能显著优于针对可溶性蛋白设计的支持向量机方法和模糊k最邻近方法,也优于TMPHMMLoc中提出的隐马尔可夫模型方法,是一个有效的跨膜蛋白亚细胞定位预测方法。     

稻瘟病菌含信号肽小蛋白的计算机分析

结合计算机技术和生物信息学的方法,采用组合的信号肽分析软件SignalPv3.0、TargetPv1.1、Big-PIpredictor、TMHMMv2.0和SecretomeP对已公布的1486个稻瘟菌(magnaporthegrisea)小蛋白基因的N-端氨基酸序列进行信号肽分析,同时系统分析了信号肽的类型及结构。分析结果表明,在1486个稻瘟病菌小蛋白中,119个具有N-端信号肽的典型分泌蛋白。其中116个具有分泌型信号肽,1个具RR-motif型信号肽,2个具信号肽酶II型信号肽。在稻瘟病菌基因组中,分泌型小蛋白的序列是高度趋异的,仅出现少数氨基酸组成完全一致的信号肽,为进一步确认具有相同信号肽的分泌蛋白是否具有同源性,分别用BLAST2SEQUENCES对具有相同信号肽的分泌蛋白进行了序列对比。结果表明,具有相同信号肽的分泌蛋白同源性非常高。同时还采用Sublocv1.0对1486个小蛋白的亚细胞位置进行了预测,结果显示小蛋白的可能功能场所包括细胞质、细胞外、线立体和细胞核,功能场所位于细胞核的小蛋白是最多的。     

Cell-PLoc: a package of Web servers for predicting subcellular localization of proteins in various organisms

Information on subcellular localization of proteins is important to molecular cell biology, proteomics, system biology and drug discovery. To provide the vast majority of experimental scientists with a user-friendly tool in these areas, we present a package of Web servers developed recently by hybridizing the 'higher level' approach with the ab initio approach. The package is called Cell-PLoc and contains the following six predictors: Euk-mPLoc, Hum-mPLoc, Plant-PLoc, Gpos-PLoc, Gneg-PLoc and Virus-PLoc, specialized for eukaryotic, human, plant, Gram-positive bacterial, Gram-negative bacterial and viral proteins, respectively. Using these Web servers, one can easily get the desired prediction results with a high expected accuracy, as demonstrated by a series of cross-validation tests on the benchmark data sets that covered up to 22 subcellular location sites and in which none of the proteins included had > or =25% sequence identity to any other protein in the same subcellular-location subset. Some of these Web servers can be particularly used to deal with multiplex proteins as well, which may simultaneously exist at, or move between, two or more different subcellular locations. Proteins with multiple locations or dynamic features of this kind are particularly interesting, because they may have some special biological functions intriguing to investigators in both basic research and drug discovery. This protocol is a step-by-step guide on how to use the Web-server predictors in the Cell-PLoc package. The computational time for each prediction is less than 5 s in most cases. The Cell-PLoc package is freely accessible at http://chou.med.harvard.edu/bioinf/Cell-PLoc.     

MetaLocGramN: A meta-predictor of protein subcellular localization for Gram-negative bacteria

Subcellular localization is a key functional characteristic of proteins. It is determined by signals encoded in the protein sequence. The experimental determination of subcellular localization is laborious. Thus, a number of computational methods have been developed to predict the protein location from sequence. However predictions made by different methods often disagree with each other and it is not always clear which algorithm performs best for the given cellular compartment. We benchmarked primary subcellular localization predictors for proteins from Gram-negative bacteria, PSORTb3, PSLpred, CELLO, and SOSUI-GramN, on a common dataset that included 1056 proteins. We found that PSORTb3 performs best on the average, but is outperformed by other methods in predictions of extracellular proteins. This motivated us to develop a meta-predictor, which combines the primary methods by using the logistic regression models, to take advantage of their combined strengths, and to eliminate their individual weaknesses. MetaLocGramN runs the primary methods, and based on their output classifies protein sequences into one of five major localizations of the Gram-negative bacterial cell: cytoplasm, plasma membrane, periplasm, outer membrane, and extracellular space. MetaLocGramN achieves the average Matthews correlation coefficient of 0.806, i.e. 12% better than the best individual primary method. MetaLocGramN is a meta-predictor specialized in predicting subcellular localization for proteins from Gram-negative bacteria. According to our benchmark, it performs better than all other tools run independently. MetaLocGramN is a web and SOAP server available for free use by all academic users at the URL http://iimcb.genesilico.pl/MetaLocGramN. This article is part of a Special Issue entitled: Computational Methods for Protein Interaction and Structural Prediction.     

Identification of the subcellular localization of mycobacterial proteins using localization motifs

Mycobacterium, the most common disease-causing genus, infects billions of people and is notoriously difficult to treat. Understanding the subcellular localization of mycobacterial proteins can provide essential clues for protein function and drug discovery. In this article, we present a novel approach that focuses on local sequence information to identify localization motifs that are generated by a merging algorithm and are selected based on a binomially distributed model. These localization motifs are employed as features for identifying the subcellular localization of mycobacterial proteins. Our approach provides more accurate results than previous methods and was tested on an independent dataset recently obtained from an experimental study to provide a first and reasonably accurate prediction of subcellular localization. Our approach can also be used for large-scale prediction of new protein entries in the UniportKB database and of protein sequences obtained experimentally. In addition, our approach identified many local motifs involved with the subcellular localization that also interact with the environment. Thus, our method may have widespread applications both in the study of the functions of mycobacterial proteins and in the search for a potential vaccine target for designing drugs.     

pLoc_bal-mGpos: Predict subcellular localization of Gram-positive bacterial proteins by quasi-balancing training dataset and PseAAC

Knowledge of protein subcellular localization is vitally important for both basic research and drug development. With the avalanche of protein sequences emerging in the post-genomic age, it is highly desired to develop computational tools for timely and effectively identifying their subcellular localization purely based on the sequence information alone. Recently, a predictor called “pLoc-mGpos” was developed for identifying the subcellular localization of Gram-positive bacterial proteins. Its performance is overwhelmingly better than that of the other predictors for the same purpose, particularly in dealing with multi-label systems in which some proteins, called “multiplex proteins”, may simultaneously occur in two or more subcellular locations. Although it is indeed a very powerful predictor, more efforts are definitely needed to further improve it. This is because pLoc-mGpos was trained by an extremely skewed dataset in which some subset (subcellular location) was over 11 times the size of the other subsets. Accordingly, it cannot avoid the bias consequence caused by such an uneven training dataset. To alleviate such bias consequence, we have developed a new and bias-reducing predictor called pLoc_bal-mGpos by quasi-balancing the training dataset. Rigorous target jackknife tests on exactly the same experiment-confirmed dataset have indicated that the proposed new predictor is remarkably superior to pLoc-mGpos, the existing state-of-the-art predictor in identifying the subcellular localization of Gram-positive bacterial proteins. To maximize the convenience for most experimental scientists, a user-friendly web-server for the new predictor has been established at http://www.jci-bioinfo.cn/pLoc_bal-mGpos/, by which users can easily get their desired results without the need to go through the detailed mathematics.     

茎瘤固氮根瘤菌Azorhizobium caulinodans ORS571基因组分泌蛋白的生物信息学分析

为了获取茎瘤固氮根瘤菌(Azorhizobium caulinodans ORS571)的分泌蛋白,以便更深入地了解该菌的共生固氮作用,本研究采用SignalP、TMHMM、PSORTb、TargetP、LipoP、TatP和SecretomeP软件对该菌全部4717个蛋白序列进行分析预测。结果共识别了653个分泌蛋白,其中具有分泌型信号肽的蛋白54个,具有RR-motif型信号肽的蛋白1个,具有脂蛋白信号肽的蛋白2个和非经典分泌蛋白596个。该菌含信号肽分泌蛋白仅占全部蛋白的1.2%,低于其它固氮菌。在分泌蛋白中识别了核酸内切酶和核糖核酸酶等6个核酸酶。它们可能参与宿主植物遗传物质的降解,干扰宿主遗传代谢,进一步在宿主植物侵染过程中起到重要作用。此外还识别了超氧化物歧化酶、过氧化氢酶和谷胱甘肽S-转移酶等4个抗氧化酶。它们可能参与活性氧的清除以保护固氮酶,是该菌固氮过程的重要参与者。