随机森林方法预测膜蛋白类型

膜蛋白的类型与其功能是密切相关的,因此膜蛋白类型的预测是研究其功能的重要手段,从蛋白质的氨基酸序列出发对膜蛋白的类型进行预测有重要意义。文章基于蛋白质的氨基酸序列,将组合离散增量和伪氨基酸组分信息共同作为预测参数,采用随机森林分类器,对8类膜蛋白进行了预测。在Jackknife检验下的预测精度为86.3%,独立检验的预测精度为93.8%,取得了好于前人的预测结果。     

基于离散增量结合支持向量机方法的凋亡蛋白亚细胞位置预测

根据凋亡蛋白的亚细胞位置主要决定于它的氨基酸序列这一观点,基于局部氨基酸序列的n肽组分和序列的亲疏水性分布信息,采用离散增量结合支持向量机(ID_SVM)算法,对六类细胞凋亡蛋白的亚细胞位置进行预测。结果表明,在Re-substitution检验和Jackknife检验下,ID_SVM算法的总体预测成功率分别达到了94.6%和84.2%;在5-fold检验和10-fold检验下,其总体预测成功率也都达到了83%以上。通过比较ID和ID_SVM两种方法的预测能力发现,结合了支持向量机的离散增量算法能够改进预测成功率,结果表明ID_SVM是预测凋亡蛋白亚细胞位置的一种很有效的方法。     

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。     

基于压缩氨基酸和支持向量机进行膜蛋白类型识别

膜蛋白是一类结构独特的蛋白质,是细胞执行各种功能的物质基础。根据其在细胞膜上的不同存在方式,主要分为六种类型。本文利用压缩的氨基酸对原始膜蛋白序列进行信息压缩,再对压缩序列进行氨基酸组成和顺序特征的提取,最后采用支持向量机构建分类模型。通过五叠交叉验证的结果表明,该方法对于六种膜蛋白的分类预测,准确度最高可达98％以上,平均预测准确度在85％以上,可有效实现膜蛋白六种类型的划分,为进一步分析膜蛋白的结构和功能奠定基础。     

用离散量的方法识别蛋白质的超二级结构

用离散量的方法,对2208个分辨率在2.5I以上的高精度的蛋白质结构中四类超二级结构进行了识别。从蛋白质一级序列出发,以氨基酸(20种氨基酸加一个空位)和其紧邻关联共同为参数,当序列模式固定长取8个氨基酸残基时,对“822”序列模式3交叉检验的平均预测精度达到78.1%,jack-knife检验的平均预测精度达到76.7%;当序列模式固定长取10个氨基酸残基时,对“1041”序列模式3交叉检验的平均预测精度达到83.1%,jack-knife检验的平均预测精度达到79.8%。     

相似性比对预测蛋白质亚细胞区间

【目的】对蛋白质所属的亚细胞区间进行预测,为进一步研究蛋白质的生物学功能提供基础。【方法】以蛋白质序列的氨基酸组成、二肽、伪氨基酸组成作为序列特征,用BLAST比对改进K最近邻分类算法(K-nearest neighbor,KNN)实现蛋白序列所属亚细胞区间预测。【结果】在Jackknife检验下,数据集CH317三种特征的成功率分别为91.5%、91.5%和89.3%,数据集ZD98成功率分别为93.9%、92.9%和89.8%。【结论】BLAST比对改进KNN算法是预测蛋白质亚细胞区间的一种有效方法。     

离散增量结合二次判别分析预测人类DNA甲基化位点

DNA甲基化作为直接作用于DNA序列的一种表观遗传修饰,能够在不改变DNA分子一级结构的情况下影响基因表达,在生命活动中扮演着重要的角色.在哺乳动物中,DNA甲基化主要发生在C_pG二核苷酸的胞嘧啶上,并且在基因组中呈现不均匀分布.准确预测DNA甲基化位点有助于阐明DNA甲基化对基因表达的调控作用,并为肿瘤的早期诊断及治疗提供新的依据.本文应用离散增量结合二次判别分析的方法,对人类的C_pG二核苷酸甲基化状态进行了识别.5折交叉检验的整体准确率超过了80%,受试者操作特性曲线面积也达到了0.86.与现有方法相比,预测成功率显著提高.这说明离散增量结合二次判别分析方法适用于甲基化位点的预测;基因组序列中甲基化位点具有序列依赖性.     

利用伪氨基酸组分预测分枝杆菌膜蛋白类型

膜蛋白是重要的药物靶位点,对膜蛋白类型的研究有助于药物的成功设计,因此正确预测膜蛋白类型对于药物研发是十分必要的。本文采用由274条分枝杆菌膜蛋白序列组成的一致性小于40%的数据集,以经过优化的伪氨基酸组分为特征,利用支持向量机分类算法预测分枝杆菌膜蛋白类型,在Jackknife检验下,得到85.4%的总体准确率和72.2%的平均准确率。结果说明,该方法可用于分枝杆菌膜蛋白类型的识别,将有助于抗分枝杆菌药物的开发。     

蛋白质亚细胞定位的识别

根据蛋白质的亚细胞定位,将蛋白质分为12类,用离散量的数学理论,以蛋白质中400个氨基酸二联体数目构成离散源,通过计算离散增量预测蛋白质的亚细胞定位,用Self-consistency和Jackknife两种方法测试均获得较高的预测成功率。结果表明：Self-consistency方法预测成功率为84．5％,Jackknife方法预测成功率为81．1％。     

基于统计CPG岛的基因预测方法

随着以功能基因组学和蛋白质组学为主要研究内容的后基因组时代的来临,人们面对着生物信息的数据呈指数增长,如何通过有效的计算方法由核酸和蛋白质的序列推导出它们的结构和功能,特别是识别DNA序列中编码蛋白质的基因预测问题是迫切需要解决的研究课题之一.本文在CpG岛对研究基因编码的特殊生物意义下,通过三种方法确定CpG岛的位置,并在此基础上,结合一种新的DNA序列字母向量,利用信息熵离散量预测基因序列,提高了识别基因编码的效率,而且计算的时间有显著的减少.     

Low-frequency Fourier spectrum for predicting membrane protein types

Cell membranes are vitally important to living cells. Although the infrastructure of biological membrane is provided by the lipid bilayer, membrane proteins perform most of the specific functions. Knowledge of membrane protein types often provides crucial hints toward determining the function of an uncharacterized membrane protein. With the avalanche of new protein sequences generated in the post-genomic era, it is highly demanded to develop a high throughput tool in identifying the type of newly found membrane proteins according to their primary sequences, so as to timely annotate them for reference usage in both basic research and drug discovery. To realize this, the key is to establish a powerful identifier that can catch their characteristic sequence patterns for different membrane protein types. However, it is not easy because they are buried in a pile of long and complicated sequences. In this paper, based on the concept of the pseudo-amino acid composition [K.C. Chou, PROTEINS: Struct., Funct., Genet. 43 (2001) 246-255], the low-frequency Fourier spectrum analysis is introduced. The merits by doing so are that the sequence pattern information can be more effectively incorporated into a set of discrete components, and that all the existing prediction algorithms can be straightforwardly used on such a formulation for protein samples. High success rates were observed by the re-substitution test, jackknife test, and independent dataset test, indicating that the low-frequency Fourier spectrum approach may become a very useful tool for membrane protein type prediction. The novel approach also holds a high potential for predicting many other attributes of proteins.     

Presenilin-1 processing of ErbB4 in fetal type II cells is necessary for control of fetal lung maturation

Maturation of pulmonary fetal type II cells to initiate adequate surfactant production is crucial for postnatal respiratory function. Little is known about specific mechanisms of signal transduction controlling type II cell maturation. The ErbB4 receptor and its ligand neuregulin (NRG) are critical for lung development. ErbB4 is cleaved at the cell membrane by the γ-secretase enzyme complex whose active component is either presenilin-1 (PSEN-1) or presenilin-2. ErbB4 cleavage releases the 80 kDa intracellular domain (4ICD), which associates with chaperone proteins such as YAP (Yes-associated protein) and translocates to the nucleus to regulate gene expression. We hypothesized that PSEN-1 and YAP have a development-specific expression in fetal type II cells and are important for ErbB4 signaling in surfactant production. In primary fetal mouse E16, E17, and E18 type II cells, PSEN-1 and YAP expression increased at E17 and E18 over E16. Subcellular fractionation showed a strong cytosolic and a weaker membrane location of both PSEN-1 and YAP. This was enhanced by NRG stimulation. Co-immunoprecipitations showed ErbB4 associated separately with PSEN-1 and with YAP. Their association, phosphorylation, and co-localization were induced by NRG. Confocal immunofluorescence and nuclear fractionation confirmed these associations in a time-dependent manner after NRG stimulation. Primary ErbB4-deleted E17 type II cells were transfected with a mutant ErbB4 lacking the γ-secretase binding site. When compared to transfection with wild-type ErbB4, the stimulatory effect of NRG on surfactant protein mRNA expression was lost. We conclude that PSEN-1 and YAP have crucial roles in ErbB4 signal transduction during type II cell maturation.     

Mutations in the membrane-spanning domain of the human immunodeficiency virus envelope glycoprotein that affect fusion activity.

A chimeric protein consisting of the human immunodeficiency virus type 1 (HIV-1) envelope protein (Env) ectodomain joined to the transmembrane and cytoplasmic-tail domains of vesicular stomatitis virus G protein lost the ability to fuse CD4+ HeLa cells yet was transported to the cell surface and cleaved normally. These results suggested some critical role of the HIV gp41 transmembrane or cytoplasmic domain in fusion. Subsequent mutagenic analysis of the HIV-1 Env transmembrane domain revealed that the sequence of amino acid residues from positions 696 to 707 of the transmembrane domain was important for fusion function but was not required for anchoring of the Env protein in the lipid bilayer or for transport to the cell surface. Further analysis indicated that the basic residues at positions 696 and 707 were critical for membrane fusion activity, as was the spacing between these residues. These results demonstrate that in addition to providing an anchoring function, the specific amino acid sequence in the transmembrane domain plays a crucial role in the membrane fusion process.     

Prediction of the Types of Membrane Proteins Based on Discrete Wavelet Transform and Support Vector Machines

Membrane proteins are crucial for many biological functions and have become attractive targets for both basic research and drug discovery. With the unprecedented increasing of newly found protein sequences in the post-genomic era, it is both time-consuming and expensive to determine the types of newly found membrane proteins solely with traditional experiment, and so it is highly demanded to develop an automatic method for fast and accurately identifying the type of membrane proteins according to their amino acid sequences. In this study, the discrete wavelet transform (DWT) and support vector machine (SVM) have been used for the prediction of the types of membrane proteins. Maximum accuracy has been obtained using SVM with a wavelet function of bior2.4, a decomposition scale j = 4, and Kyte–Doolittle hydrophobicity scales. The results indicate that the proposed method may play an important complementary role to the existing methods in this area.     

The transmembrane domain of the respiratory syncytial virus F protein is an orientation-independent apical plasma membrane sorting sequence

The processes that facilitate transport of integral membrane proteins though the secretory pathway and subsequently target them to particular cellular membranes are relevant to almost every field of biology. These transport processes involve integration of proteins into the membrane of the endoplasmic reticulum (ER), passage from the ER to the Golgi, and post-Golgi trafficking. The respiratory syncytial virus (RSV) fusion (F) protein is a type I integral membrane protein that is uniformly distributed on the surface of infected nonpolarized cells and localizes to the apical plasma membrane of polarized epithelial cells. We expressed wild-type or altered RSV F proteins to gain a better understanding of secretory transport and plasma membrane targeting of type I membrane proteins in polarized and nonpolarized epithelial cells. Our findings reveal a novel, orientation-independent apical plasma membrane targeting function for the transmembrane domain of the RSV F protein in polarized epithelial cells. This work provides a basis for a more complete understanding of the role of the transmembrane domain and cytoplasmic tail of viral type I integral membrane proteins in secretory transport and plasma membrane targeting in polarized and nonpolarized cells.     

蛋白质亚细胞定位的生物信息学研究

细胞中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,如果定位发生偏差,将会对细胞功能甚至生命产生重大影响.蛋白质的亚细胞定位是蛋白质功能研究的重要方面,也是生物信息学中的热点问题,数据库的构建和亚细胞定位分析及预测加速了蛋白质结构和功能的研究.     

PIST regulates the intracellular trafficking and plasma membrane expression of Cadherin 23

Background  

The atypical cadherin protein cadherin 23 (CDH23) is crucial for proper function of retinal photoreceptors and inner ear hair cells. As we obtain more and more information about the specific roles of cadherin 23 in photoreceptors and hair cells, the regulatory mechanisms responsible for the transport of this protein to the plasma membrane are largely unknown.     

A novel hemocyte-specific membrane protein of Sarcophaga (flesh fly).

Extensive tissue remodeling takes place during metamorphosis of holometabolous insects. It has been shown that hemocytes play crucial roles in the recognition and elimination of apoptotic cells and larval tissue fragments produced during metamorphosis. We report the immunoaffinity purification, cDNA cloning, and characterization of a prepupal hemocyte membrane protein of Sarcophaga (flesh fly) with a molecular mass of 120 kDa. This protein is a novel type I transmembrane protein with 18 repeats of an epidermal growth factor-like domain in the predicted extracellular region. Expression of the protein was restricted exclusively to prepupal hemocytes. This protein is suggested to be a scavenger receptor for tissue remodeling.     

Structure-function comparisons of the proapoptotic protein Bax in yeast and mammalian cells.

Expression of the proapoptotic protein Bax under the control of a GAL10 promoter in Saccharomyces cerevisiae resulted in galactose-inducible cell death. Immunofluorescence studies suggested that Bax is principally associated with mitochondria in yeast cells. Removal of the carboxyl-terminal transmembrane (TM) domain from Bax [creating Bax (deltaTM)] prevented targeting to mitochondrial and completely abolished cytotoxic function in yeast cells, suggesting that membrane targeting is crucial for Bax-mediated lethality. Fusing a TM domain from Mas70p, a yeast mitochondrial outer membrane protein, to Bax (deltaTM) restored targeting to mitochondria and cytotoxic function in yeast cells. Deletion of four well-conserved amino acids (IGDE) from the BH3 domain of Bax ablated its ability to homodimerize and completely abrogated lethality in yeast cells. In contrast, several Bax mutants which retained ability to homodimerize (deltaBH1, deltaBH2, and delta1-58) also retained at least partial lethal function in yeast cells. In coimmunoprecipitation experiments, expression of the wild-type Bax protein in Rat-1 fibroblasts and 293 epithelial cells induced apoptosis, whereas the Bax (deltaIGDE) mutant failed to induce apoptosis and did not associate with endogenous wild-type Bax protein. In contrast to yeast cells, Bax (deltaTM) protein retained cytotoxic function in Rat-1 and 293 cells, was targeted largely to mitochondria, and dimerized with endogenous Bax in mammalian cells. Thus, the dimerization-mediating BH3 domain and targeting to mitochondrial membranes appear to be essential for the cytotoxic function of Bax in both yeast and mammalian cells.