HPSLPred: An Ensemble Multi‐Label Classifier for Human Protein Subcellular Location Prediction with Imbalanced Source

Predicting the subcellular localization of proteins is an important and challenging problem. Traditional experimental approaches are often expensive and time‐consuming. Consequently, a growing number of research efforts employ a series of machine learning approaches to predict the subcellular location of proteins. There are two main challenges among the state‐of‐the‐art prediction methods. First, most of the existing techniques are designed to deal with multi‐class rather than multi‐label classification, which ignores connections between multiple labels. In reality, multiple locations of particular proteins imply that there are vital and unique biological significances that deserve special focus and cannot be ignored. Second, techniques for handling imbalanced data in multi‐label classification problems are necessary, but never employed. For solving these two issues, we have developed an ensemble multi‐label classifier called HPSLPred, which can be applied for multi‐label classification with an imbalanced protein source. For convenience, a user‐friendly webserver has been established at http://server.malab.cn/HPSLPred.     

人微丝相关蛋白hHBRK1突变体的亚细胞定位

 hHBrk1是本研究室利用抑制性消减杂交手段,从人支气管上皮细胞恶性转化株BERP3 5中克隆到的差异高表达基因.hHBRK1蛋白家族序列在动、植物界高度保守,含有一个7重复 (heptad repeat, HR) 结构域.利用绿色荧光蛋白(GFP)报告系统,发现野生型hHBRK1蛋白在胞浆中弥散分布,在细胞运动前沿富集,与细胞片状伪足的微丝共定位.hHBRK1- R54和hHBRK1-S56 G57蛋白在胞浆弥散分布,但失去了在细胞运动前沿富集的特征.hHBRK1ΔN(1-45)在细胞内弥散分布,而hHBRK1ΔC(46-75)选择性地在高尔基体富集.研究提示,hHBRK1蛋白为微丝相关蛋白,结构的完整性是其发挥功能的前提.hHBRK1蛋白可能通过HR结构域调控微丝聚合,从而参与微丝依赖性的细胞运动或物质运输.     

利用分组重量编码预测细胞凋亡蛋白的亚细胞定位

从氨基酸的物化特性出发,利用物理学中“粗粒化”和“分组”的思想,提出了一种新的蛋白质序列特征提取方法——分组重量编码方法。采用组分耦合算法作为分类器,从蛋白质一级序列出发对细胞凋亡蛋白的亚细胞定位进行研究。针对Zhou和Doctor使用的数据集,Re—substitution和Jackknife检验总体预测精度分别为98、O％和85．7％,比基于氨基酸组成和组分耦合算法的总体预测精度提高了7．2％和13．2％;针对陈颖丽和李前忠使用的数据集,Re—substitution和Jackknife检验总体预测精度分别为94．0％和80、1％,比基于二肽组成和离散增量算法的总体预测精度提高了5．9％和2、0％。针对我们自己整理的最新数据集,通过Re—substitution和Jackknife检验,总体预测精度分别为97．33％和75、11％。实验结果表明蛋白质序列的分组重量编码对于细胞凋亡蛋白的定位研究是一种有效的特征提取方法。     

Subcellular Location and Expression of Tobacco Necrosis Necrovirus p7a Protein

A putative movement protein (p7a) of tobacco necrosis Necrovirus , strain D (TNV-D), produced in Escherichia coli using an expression vector, was used to raise an antiserum. Immunoblot analysis using this antiserum showed that the p7a protein was detectable only in the combined cell wall and cell membrane fraction prepared from TNV-D infected Phaseolus vulgaris leaves. The p7a protein was detectable 1 day after inoculation and reached a maximum 3 days later, before declining, whereas coat protein was not detectable until 3 days after inoculation and continued to increase in concentration for a further 2 days before declining. Differences in the detectable amounts of both proteins may reflect their differential stability in extracts from necrotic tissue and/or the transient expression of the putative movement protein early in the replication cycle of TNV-D.     

一种预测细胞凋亡蛋白的亚细胞定位的新方法

细胞凋亡蛋白对生物体的发育、维持内环境稳定及人们理解细胞凋亡机制非常重要。文中提出了一种新的蛋白质序列特征提取方法—三肽离散源方法。计算了蛋白质序列中紧邻三联体的出现个数,利用离散增量极小化对凋亡蛋白进行定位预测;同时推广了张春霆等提出的内容平衡精度指数,使其能评估任意类的分类问题。实验结果表明:在凋亡蛋白定位预测研究中,三肽离散源方法在提高总体预测精度的同时,能够较好的解决样本不均衡问题;而内容平衡精度指数能比传统的总体预测精度更准确的评估预测算法的预测能力,有效的反映预测算法对样本不均衡问题的相容能力。     

酵母蛋白质相互作用与基因表达谱和亚细胞定位的相关性

研究酵母（yeast）蛋白质相互作用与基因表达谱和蛋白质亚细胞定位的关系.首先,构建了蛋白质相互作用正样本集、负样本集、随机组对负样本集和混合样本集.然后,对于4个数据集中的所有蛋白质对,通过比较它们的基于距离的基因共表达的分布以及它们中具有已知亚细胞定位的蛋白质对的共定位出现率,实现了这些高通量数据的交叉量化分析.结果揭示,与非相互作用蛋白质对相比,相互作用蛋白质对的基因表达谱具有较高的相似性;相互作用蛋白质对更倾向于具有相同的亚细胞定位.结果还揭示出这些蛋白质特征相关的总体趋势.     

Multi Label Learning for Prediction of Human Protein Subcellular Localizations

Predicting protein subcellular locations has attracted much attention in the past decade. However, one of the most challenging problems is that many proteins were found simultaneously existing in, or moving between, two or more different cell components in a eukaryotic cell. Seldom previous predictors were able to deal with such multiplex proteins although they have extremely important implications in future drug discovery in terms of their specific subcellular targeting. Approximately 20% of the human proteome consists of such multiplex proteins with multiple sample labels. In order to efficiently handle such multiplex human proteins, we have developed a novel multi-label (ML) learning and prediction framework called ML-PLoc, which decomposes the multi-label prediction problem into multiple independent binary classification problems. ML-PLoc is constructed based on support vector machine (SVM) and sequential evolution information. Experimental results show that ML-PLoc can achieve an overall accuracy 64.6% and recall ratio 67.2% on a benchmark dataset consisting of 14 human subcellular locations, and is very powerful for dealing with multiplex proteins. The current approach represents a new strategy to deal with the multi-label biological problems. ML-PLoc software is freely available for academic use at: http://www.csbio.sjtu.edu.cn/bioinf/ML-PLoc.     

基于序列保守性和蛋白质相互作用的真核蛋白质亚细胞定位预测

蛋白质的亚细胞定位是进行蛋白质功能研究的重要信息.蛋白质合成后被转运到特定的细胞器中,只有转运到正确的部位才能参与细胞的各种生命活动,有效地发挥功能.尝试了将保守序列及蛋白质相互作用数据的编码信息结合传统的氨基酸组成编码,采用支持向量机进行蛋白质亚细胞定位预测,在真核生物中5轮交叉验证精度达到91.8%,得到了显著的提高.     

基于多样性指标的分枝杆菌蛋白质亚细胞定位预测

由于蛋白质亚细胞位置与其一级序列存在很强的相关性,利用多样性增量来描述蛋白质之间氨基酸组分和二肽组分的相似程度,采用修正的马氏判别式（这里称为IDQD方法）对分枝杆菌蛋白质的亚细胞位置进行了预测。利用Jackknife检验对不同序列相似度下的蛋白质数据集进行了预测研究,结果显示,当数据集的序列相似度小于等于70％时,算法的预测精度稳定在75％左右。在对整体852条蛋白质的预测成功率达到87．7％,这一结果优于已有算法的预测精度,说明IDQD是一种有效的分枝杆菌蛋白质亚细胞预测方法。     

Subcellular Location and Neuronal Release of Diazepam Binding Inhibitor

Diazepam binding inhibitor (DBI), a peptide located in CNS neurons, blocks the binding of benzodiazepines and beta-carbolines to the allosteric modulatory sites of gamma-aminobutyric acid (GABAA) receptors. Subcellular fractionation studies of rat brain indicate that DBI is compartmentalized. DBI-like immunoreactivity is highly enriched in synaptosomes obtained by differential centrifugation in isotonic sucrose followed by a Percoll gradient. In synaptosomal lysate, DBI-like immunoreactivity is primarily associated with synaptic vesicles partially purified by differential centrifugation and continuous sucrose gradient. Depolarization induced by high K+ levels (50 mM) or veratridine (50 microM) released DBI stored in neurons of superfused slices of hypothalamus, hippocampus, striatum, and cerebral cortex. The high K+ level-induced release is Ca2+ dependent, and the release induced by veratridine is blocked by 1.7 microM tetrodotoxin. Depolarization released GABA and Met5-enkephalin-Arg6-Phe7 together with DBI. DBI is also released by veratridine depolarization, in a tetrodotoxin-sensitive fashion, from primary cultures of cerebral cortical neurons, but not from cortical astrocytes. Depolarization fails to release DBI from slices of liver and other peripheral organs. These data support the view that DBI may be released as a putative neuromodulatory substance from rat brain neurons.     

Expression and Subcellular Location of Alpha-Synuclein During Mouse-Embryonic Development

Alpha-synuclein (α-SYN) is one of the major components of intracellular fibrillary aggregates in the brains of a subset of neurodegenerative disorders. Although α-SYN expression has been found in developing mouse brain, a detailed distribution during mouse-embryonic development has not been made. Here we describe the expression pattern of α-SYN during the development of mice from E9.5 to P0 by immunohistochemistry (IHC). As a result, α-SYN was detected as early as E9.5. During the embryonic stages, α-SYN was dynamically expressed in several regions of the brain. In the neocortex, expression was detected in the marginal zone (MZ) in the early stages and was later condensed in the MZ and in the subplate (SP); in the cerebellum, expression was initially detected in the deep cerebellar nuclei (DCN) and was later condensed in the Purkinje cells. These spatio-temporal expression patterns matched the neuronal migratory pathways and the formation of the synapse connections. Additionally, α-SYN was detected in the sensory systems, including the nasal mucosa, the optic cup, the sensory ganglia, and their dominating nerve fibers. Furthermore, the nuclear location of α-SYN protein was found in developing neurons in the early stages, and later it was mostly found in the non-nuclear compartments. This finding was further confirmed by Western blot analysis. These results suggest that α-SYN may be involved not only in the migration of neurons and in the synaptogenesis of the central nervous system (CNS) but also in the establishment of the sensory systems. The nuclear location of α-SYN may hint at an important function in these events.     

Interactions Between Soluble Enzymes and Subcellular Structur

Abstract

Soluble enzymes contribute significantly to the metabolic capabilities of living organisms, but it is becoming increasingly clear that the activities of these enzymes are significantly modified by their interactions with structural components of the cell, and that these interactions may make important contributions to metabolic regulation. In the past, specification of these interactions has been limited by the availability of suitable experimental techniques, but this deficiency is now being rectified and our understanding of these processes is advancing rapidly. Research in this area is moving into a second phase, with the emphasis no longer being focused on demonstrations of the biological reality of these interactions, but directed more towards quantitative aspects of binding, the determination of the characteristics of binding domains, and the theoretical basis of regulatory involvements. All of these aspects are discussed in the present review.     

The Human Actin-Regulatory Protein Cap G: Gene Structure and Chromosome Location

Cap G (formerly called macrophage capping protein or gCap39) is a member of the gelsolin/villin fanlily of actin-regulatory proteins. Unlike all other members of this family, Cap G caps the barbed ends of actin filaments, but does not sever them. This protein is half the molecular weight and contains half the number of repeat subunits (3 vs 6) of gelsolin and villin, suggesting that these two proteins may have arisen by gene duplication of the Cap G gene. To investigate this possibility we have cloned and sequenced the human Cap G gene (gene symbol CAPG). The gene is 16.6 kb in size, contains 10 exons and 9 introns and is located on the proximal short arm of chromosome 2. The open reading frame is 6.9 kb, having 9 exons and 8 introns. This region contains 3 splice sites that are nearly identical to the human gelsolin gene, but shares only one with villin, indicating that CAPG is more closely related to gelsolin. Further comparisons of these three genes, however, indicate that the evolutionary steps resulting in human gelsolin and villin are likely to have been more complex than a simple tandem duplication of the Cap G gene.     

Subcellular Location of Phosphoglucomutase and UDP Glucose Pyrophosphorylase in Avena Coleoptiles

Extraction of phosphoglucomutuse and UDP glucose pyrophosphorylase from oat coleoptiles using both aqueous and non-aqueous systems showed that both enzymes are largely soluble. Phosphoglucomutase was completely absent from the cell wall fraction. The inhibition of phosphoglucomutase by peroxyacetyl nitrate was confirmed and the enzyme in the subcellular participate fractions was shown to be more inhibited than that in the soluble fraction. UDP glucose pyrophosphorylase was not inhibited by peroxyacetyl nitrate or ozone in vivo but was inhibited by peroxyacetyl nitrate in vitro. The SH reagents, iodoacetamide and p-chloromercuribenzoate, inhibited phosphoglucomutase severely but UDP glucose pyrophosphorylase moderately or not at all.     

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/.     

DE-Cadherin, a Core Component of the Adherens Junction Complex Modifies Subcellular Localization of the Drosophila Gap Junction Protein Innexin2

The Drosophila innexin multigene family of gap junction encoding proteins consists of eight family members whose function in epithelial morphogenesis is mostly unknown. We have recently shown that innexin2 plays a crucial role in the organization of embryonic epithelia. Innexin2 protein accumulates in the epidermis in the apico-lateral membrane domain and colocalizes with core proteins of adherens junctions, such as DE-cadherin and Armadillo, the β -catenin homolog. Innexin2 localization is altered in both armadillo and DE-cadherin mutants Biochemical interaction studies point to a direct interaction of DE-cadherin and Armadillo with innexin2 suggesting a close link between gap junction and adherens junction biogenesis. We have used the Drosophila Schneider cell tissue culture system to further study the interaction of innexin2 with DE-cadherin. Our results provide evidence that DE-cadherin may be a key component to control trafficking, and localization of Innexin2 to the plasma membrane.