Gene ontology-based protein function prediction by using sequence composition information.

Abstract:

:The prediction of protein function is a difficult and important problem in computational biology. In this study, an efficient method is presented to predict protein function with sequence composition information. Four kinds of basic building blocks of protein sequences are investigated, including N-grams, binary profiles, PFAM domains and InterPro domains. The protein sequences are mapped into high-dimensional vectors by using the occurrence frequencies of each kind of building blocks. The resulting vectors are then taken as input to support vector machine to predict their function based on gene ontology. Experiments are conducted over the subset of GOA database. The experimental results show that the protein function can be predicted from primary sequence information. The method based on InterPro domains outperforms the other building blocks, and gets an overall accuracy of 0.87 and ROC score is 0.93. We also demonstrate that the use of feature extraction algorithms such as latent semantic analysis and nonnegative matrix factorization, can efficiently remove noise and improve the prediction efficiency without significantly degrading the performance. The results obtained here are helpful for the prediction of protein function by using only sequence information.

journal_name

Protein Pept Lett

authors

Dong Q,Zhou S,Deng L,Guan J

doi

10.2174/092986610791190336

subject

Has Abstract

pub_date

2010-06-01 00:00:00

pages

789-95

issue

6

eissn

0929-8665

issn

1875-5305

pii

0098

journal_volume

17

pub_type

杂志文章
  • Crystallization and preliminary X-ray crystallographic analysis of Plasmodium falciparum S-adenosyl-L-homocysteine hydrolase.

    abstract::S-adenosyl-l-homocysteine hydrolase from a malaria parasite Plasmodium falciparum (PfSAHH) has been crystallized by the vapor diffusion method. The crystals belong to an orthorhombic space group P212121 with the cell dimensions of a = 76.66 A, b = 86.31 A, and c = 335.6 A. There are four subunits (one tetramer) per as...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866043478248

    authors: Tanaka N,Kusakabe Y,Shiraiwa K,Sakamoto Y,Nakanishi M,Kitade Y,Nakamura KT

    更新日期:2004-04-01 00:00:00

  • Preliminary estimation of rotary torque produced by proton-motive force in fully functional F0F1-ATPase.

    abstract::F(0)F(1)-ATPase is a rotary molecular motor. It is well known that the rotary torque is generated by ATP hydrolysis in F(1) but little is known about how it produces the proton-motive force (PMF) in F(0). Here a cross-linking approach was used to estimate the rotary torque produced by PMF. Three mutant E. coli strains...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986607779117164

    authors: Liu X,Cui Y,Chen C,Lai B,Yue J,Zhang Z

    更新日期:2007-01-01 00:00:00

  • Drugs against Mycobacterium tuberculosis 3-isopropylmalate dehydrogenase can be developed using homologous enzymes as surrogate targets.

    abstract::3-Isopropylmalate dehydrogenase (IPMDH) from Mycobacterium tuberculosis (Mtb) may be a target for specific drugs against this pathogenic bacterium. We have expressed and purified Mtb IPMDH and determined its physicalchemical and enzymological properties. Size-exclusion chromatography and dynamic light scattering measu...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:

    authors: Graczer E,Bacso A,Konya D,Kazi A,Soos T,Molnar L,Szimler T,Beinrohr L,Szilagyi A,Zavodszky P,Vas M

    更新日期:2014-01-01 00:00:00

  • The Influences of Palindromes in mRNA on Protein Folding Rates.

    abstract:BACKGROUND:It is currently believed that protein folding rates are influenced by protein structure, environment and temperature, amino acid sequence and so on. We have been working for long to determine whether and in what ways mRNA affects the protein folding rate. A large number of palindromes aroused our attention i...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866526666191014144015

    authors: Li R,Li H,Yang S,Feng X

    更新日期:2020-01-01 00:00:00

  • Protealysin is not Secreted Constitutively.

    abstract:BACKGROUND:Protealysin, a zinc metalloprotease of Serratia proteamaculans, is the prototype of a new group within the peptidase family M4. Protealysin-like proteases (PLPs) are widely spread in bacteria but are also found in fungi and archaea. The biological functions of PLPs have not been well studied, but published d...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866526666181212114907

    authors: Chukhontseva KN,Salnikov VV,Morenkov OS,Kostrov SV,Demidyuk IV

    更新日期:2019-01-01 00:00:00

  • Improved performance in protein secondary structure prediction by combining multiple predictions.

    abstract::In this paper(1) we present a novel framework for protein secondary structure prediction. In this prediction framework, firstly we propose a novel parameterized semi-probability profile, which combines single sequence with evolutionary information effectively. Secondly, different semi-probability profiles are respecti...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986606778777551

    authors: Huang DS,Huang X

    更新日期:2006-01-01 00:00:00

  • Proteome analysis of rice root plasma membrane and detection of cold stress responsive proteins.

    abstract::To investigate the function of plant plasma membrane, proteins of rice plasma membrane were analyzed and the proteins changed by cold stress were identified. Plasma membrane proteins were purified with an aqueous two-phase partitioning method from root of rice seedlings, and activity of specific H(+)-ATPase localized ...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986609788490140

    authors: Hashimoto M,Toorchi M,Matsushita K,Iwasaki Y,Komatsu S

    更新日期:2009-01-01 00:00:00

  • Crystal Structure of the Type VI Secretion System Accessory Protein TagF from Pseudomonas Aeruginosa.

    abstract:BACKGROUND:Type VI Secretion System (T6SS) has been found in approximately onequarter of the gram-negative bacterial species, and its structural characteristics appear to slightly differ from species to species. The genes encoding T6SS are designated as type six secretion A-M (tssA-M). The expression of the tss gene cl...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866526666190119121859

    authors: Ok CK,Chang JH

    更新日期:2019-01-01 00:00:00

  • Expressed protein ligation: a new tool for the biosynthesis of cyclic polypeptides.

    abstract::The present paper reviews the use of expressed protein ligation for the biosynthesis of backbone cyclized polypeptides. This general method allows the in vivo and in vitro biosynthesis of cyclic polypeptides using recombinant DNA expression techniques. Biosynthetic access to backbone cyclic peptides opens the possibil...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章,评审

    doi:10.2174/0929866054864274

    authors: Kimura R,Camarero JA

    更新日期:2005-11-01 00:00:00

  • Kinetics of inactivation of phytase (phy A) during modification of histidine residue by IAA and DEP.

    abstract::Chemical probing of histidine residues using specific modifiers, iodoacetic acid (IAA) and diethylpyrocarbonate (DEP) resulted in the inactivation of phytase (phy A). The kinetic theory of the substrate reaction during the modification of enzyme activity was applied to a study of the kinetics of the course of inactiva...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986606777145788

    authors: Wang XY,Sun ML,Zhao DM,Wang M

    更新日期:2006-01-01 00:00:00

  • Prediction of cell wall lytic enzymes using Chou's amphiphilic pseudo amino acid composition.

    abstract::Discriminating cell wall lytic enzymes from non lytic enzymes is a very important task for curing bacterial infections. In this paper, based on Chou's amphiphilic pseudo amino acid composition, we develop fisher-discriminant based classifier to predict cell wall lytic enzymes. Experiments show that 66.7% sensitivity w...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986609787848045

    authors: Ding H,Luo L,Lin H

    更新日期:2009-01-01 00:00:00

  • Structural and dynamic properties of incomplete immunoglobulin-like fold domains.

    abstract::The immunoglobulin fold (Ig-fold) is a widespread structural motif that is detected in a variety of proteins involved in diversified biological processes. The Ig-fold contains 70-110 residues that are assembled in a characteristic sandwich-like structure formed by two facing β-sheets each made of antiparallel β-strand...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章,评审

    doi:10.2174/092986612802762732

    authors: Berisio R,Ciccarelli L,Squeglia F,De Simone A,Vitagliano L

    更新日期:2012-10-01 00:00:00

  • Spectroscopy and Molecular Modeling Study on Binding of Nickel Phthalocyanine to Human Serum Albumin.

    abstract::The interaction of nickel tetra sulfunated phthalocyanine( NiTSPc) with human serum albumin (HSA), in 20 mM phosphate buffer pH 7.4 was investigated using advanced techniques including fluorescence, synchronous fluorescence, Fourier transform infrared (FT-IR), circular dichroism (CD) spectroscopy and molecular docking...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866523666160719101707

    authors: Dezhampanah H,Firouzi R,Hasani L

    更新日期:2016-01-01 00:00:00

  • Preparation, crystallization and preliminary X-ray analysis of the Fab fragment of monoclonal antibody MN423, revealing the structural aspects of Alzheimer's paired helical filaments.

    abstract::Monoclonal antibody (mAb) MN423 recognizes Alzheimer's disease specific conformation of tau protein assembled into paired helical filaments (PHF). Since the three-dimensional structure of PHF is currently unavailable, the structure of MN423 binding site could provide important information about PHF conformation with t...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986606778256180

    authors: Csóková N,Skrabana R,Urbániková L,Kovácech B,Popov A,Sevcík J,Novák M

    更新日期:2006-01-01 00:00:00

  • Synthesis of N-succinyl-L,L-diaminopimelic acid mimetics via selective protection.

    abstract::The search for potential inhibitors that target so far unexplored bacterial enzyme mono-N-succinyl-L,L-diaminopimelic acid desuccinylase (DapE) has stimulated a development of methodology for quick and efficient preparation of mono-N-acylated 2,6-diaminopimelic acid (DAP) derivatives bearing the different carboxyl gro...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986610790780387

    authors: Vanek V,Pícha J,Budesínský M,Sanda M,Jirácek J,Holz RC,Hlavácek J

    更新日期:2010-03-01 00:00:00

  • Crystallization and preliminary X-ray analysis of the splice variant of human ankyrin repeat and suppressor of cytokine signaling box protein 9 (hASB9-2).

    abstract::Human ankyrin repeat and suppressor of cytokine signaling box protein 9 (hASB9), a subunit of an Elongin C-cullin-SOCS box (ECS) E3 ubiquitin ligase complex, is believed to be involved in specific substrate-recognition for ubiquitination and degradation. In fact, this specific substrate-recognition is determined by th...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986609787601688

    authors: Fei X,Zhang Y,Gu X,Qiu R,Mao Y,Ji C

    更新日期:2009-01-01 00:00:00

  • Interaction between two residues in the inter-domain interface of Escherichia coli peptidase N modulates catalytic activity.

    abstract::The role of interaction between Asn259 (catalytic domain) with Gln821 (C-terminal domain) in PeptidaseN was investigated. The k(cat) of PeptidaseN containing Asn259Asp or Gln821Glu is enhanced whereas it is suppressed in Asn259AspGln821Glu. Structural analysis shows this interaction to change the relative disposition ...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986609787848081

    authors: Kumar A,Reddy S,Srinivasan N,Nandi D

    更新日期:2009-01-01 00:00:00

  • A comprehensive one-pot synthesis of protected cysteine and selenocysteine SPPS derivatives.

    abstract::A proof-of-principle methodology is presented in which all commercially-available cysteine (Cys) and selenocysteine (Sec) solid phase peptide synthesis (SPPS) derivatives are synthesized in high yield from easily prepared protected dichalcogenide precursors. A Zn-mediated biphasic reduction process applied to a series...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:

    authors: Flemer S

    更新日期:2014-01-01 00:00:00

  • Identification of immunogenic MHC class II Tyrosinase-derived peptides using HLA-DR1 and HLA-DR4 transgenic mice.

    abstract::The immunogenicity of "novel" MART-1 and Tyrosinase class-II peptides was assessed in transgenic mice. Tyrosinase(141-161) peptide was found to be immunogenic and endogenously processed in the HLA-DRbeta1*0101 and HLA-DRbeta1*0401 transgenic mice with peptide specific production of IFNgamma or IL-5 respectively. The M...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986607780782768

    authors: Horton RB,Laversin SA,Reeder SP,Rees RC,McArdle SE

    更新日期:2007-01-01 00:00:00

  • Transformation of a biologically active Peptide into peptoid analogs while retaining biological activity.

    abstract::We report the stepwise transformation of a linear peptide epitope recognized by the anti-transforming growth factor alpha monoclonal antibody Tab2 into peptomers and finally into peptoid analogs. The key experiment in this study is the substitution analysis in which each position of the peptide is exchanged by a set o...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986606777841299

    authors: Hoffmann B,Ast T,Polakowski T,Reineke U,Volkmer R

    更新日期:2006-01-01 00:00:00

  • Expression and purification of soluble non-fusion vasostatin in Escherichia coli.

    abstract::Vasostatin has previously been expressed in fused form or in inclusion body form in Escherichia coli. Here the protein was expressed in soluble non-fusion form in BL21(DE3)pLysS by IPTG induction. The expression level of vasostatin was about 15% of the total cellular protein. The expressed vasostatin was purified and ...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866054696163

    authors: Wu X,Li X,Su Z,Zheng Q,Xu H,Wu S,Feng Y,Zhao W

    更新日期:2005-10-01 00:00:00

  • The X-ray Crystallographic Structure of Human EAT2 (SH2D1B).

    abstract::Ewing's Sarcoma transcript-2 (EAT2) also known as SH2D1B is involved in regulation of signalling lymphocytic activation molecule (SLAM) family receptor functions. Cytoplasmic tails of SLAM family receptors contain tyrosine residues which mediate the downstream signal transduction through their phosphorylation. EAT2, c...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866523666160831162239

    authors: Taha M,Nezerwa E,Nam HJ

    更新日期:2016-01-01 00:00:00

  • Quantifying Serum Derived Differential Expressed and Low Molecular Weight Protein in Breast Cancer Patients.

    abstract:BACKGROUND:Searching the biomarker from complex heterogeneous material for early detection of disease is a challenging task in the field of biomedical sciences. OBJECTIVE:The study has been arranged to explore the proteomics serum derived profiling of the differential expressed and low molecular weight protein in brea...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866527666200110155609

    authors: Zafar A,Jabbar M,Manzoor Y,Gulzar H,Hassan SG,Nazir MA,Ain-Ul-Haq,Mustafa G,Sahar R,Masood A,Iqbal A,Hussain M,Hasan M

    更新日期:2020-01-01 00:00:00

  • Effect of Temperature and pH on the Secondary Structure and Denaturation Process of Jumbo Squid Hepatopancreas Cathepsin D.

    abstract:BACKGROUND:Cathepsin D is a lysosomal enzyme that is found in all organisms acting in protein turnover, in humans it is present in some types of carcinomas, and it has a high activity in Parkinson's disease and a low activity in Alzheimer disease. In marine organisms, most of the research has been limited to corroborat...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866526666190405124353

    authors: Francisco CC,Luis CJ,Marina EJ,Javier CF,Alexis LA,Del Carmen SH,Alfredo RI

    更新日期:2019-01-01 00:00:00

  • Life cycle of yeast prions: propagation mediated by amyloid fibrils.

    abstract::Currently, prion phenomena have been detected in various organisms, in addition to mammals affected by transmissible spongiform encephalopathies. In the budding yeast Saccharomyces cerevisiae, various proteins have prion properties and adopt atypical phenotypes as genetic elements, such as the Sup35 and Ure2 proteins,...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章,评审

    doi:10.2174/092986609787601796

    authors: Inoue Y

    更新日期:2009-01-01 00:00:00

  • Host defense peptides and the new line of defence against multiresistant infections.

    abstract::Increasing antibiotic resistance has led to an urgent need for new therapeutic approaches. Host defense peptides are known to be antimicrobial and have revealed broad immunomodulatory functions for both innate and adaptive immunity. This review will focus on the role of host defense peptides in infection and immune re...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章,评审

    doi:10.2174/092986608783744252

    authors: Hirsch T,Jacobsen F,Steinau HU,Steinstraesser L

    更新日期:2008-01-01 00:00:00

  • Prediction of binding motifs in hepatitis C virus NS5A and human proteins.

    abstract::From the extensive analysis, we identified three highly conserved sequence segments in HCV NS5A proteins and one binding motif in human proteins. The binding motif of human proteins often forms a full helix or an extended strand-loop structure, and is in good agreement with the experimental findings of previous studie...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986608784567500

    authors: Zhang GZ,Han K

    更新日期:2008-01-01 00:00:00

  • Crystallization and preliminary crystallographic analysis of human eukaryotic translation initiation factor 5A (eIF-5A).

    abstract::Eukaryotic translation initiation factor 5A (eIF-5A) is universally found in all eukaryotic cells. It is the only protein in nature known to contain the unusual amino acid hypusine, a post-translationally modified lysine. Recombinant human eIF-5A was crystallized by the hanging-drop vapor diffusion method. Crystals we...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/0929866054696091

    authors: Sun Y,Li X,Wu B,Sun P,Rao Z

    更新日期:2005-10-01 00:00:00

  • Free energy calculations and binding analysis of two potential anti- influenza drugs with Polymerase basic protein-2 (PB2).

    abstract::Influenza viruses cause a significant level of morbidity and mortality in the population every year. Their resistance to current anti-influenza drugs increases the difficulty of flu treatment. Thus, development of new anti-influenza drugs is necessary in regards of prevent the tragedy of influenza pandemic. The Polyme...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986611796378675

    authors: Lv HM,Guo XL,Gu RX,Wei DQ

    更新日期:2011-10-01 00:00:00

  • Target peptide recognition by S100P protein and role of central linker region and dimer interface.

    abstract::Interaction between S100P and its target protein is an essential step in several cellular functions. The amphipathic mellitin peptide binds tightly to S100P protein in the presence of calcium cation. Since little is known about the recognition sequence, mellitin interaction form a model for S100P. Interaction between ...

    journal_title:Protein and peptide letters

    pub_type: 杂志文章

    doi:10.2174/092986606775338380

    authors: Tutar Y

    更新日期:2006-01-01 00:00:00