alexa Protein subcellular localization prediction based on compartment-specific features and structure conservation
Biomedical Sciences

Biomedical Sciences

International Journal of Biomedical Data Mining

Author(s): Emily ChiaYu Su, HuaSheng Chiu, Allan Lo, JennKang Hwang, TingYi Sung

Abstract Share this page

Background Protein subcellular localization is crucial for genome annotation, protein function prediction, and drug discovery. Determination of subcellular localization using experimental approaches is time-consuming; thus, computational approaches become highly desirable. Extensive studies of localization prediction have led to the development of several methods including composition-based and homology-based methods. However, their performance might be significantly degraded if homologous sequences are not detected. Moreover, methods that integrate various features could suffer from the problem of low coverage in high-throughput proteomic analyses due to the lack of information to characterize unknown proteins. Results We propose a hybrid prediction method for Gram-negative bacteria that combines a one-versus-one support vector machines (SVM) model and a structural homology approach. The SVM model comprises a number of binary classifiers, in which biological features derived from Gram-negative bacteria translocation pathways are incorporated. In the structural homology approach, we employ secondary structure alignment for structural similarity comparison and assign the known localization of the top-ranked protein as the predicted localization of a query protein. The hybrid method achieves overall accuracy of 93.7% and 93.2% using ten-fold cross-validation on the benchmark data sets. In the assessment of the evaluation data sets, our method also attains accurate prediction accuracy of 84.0%, especially when testing on sequences with a low level of homology to the training data. A three-way data split procedure is also incorporated to prevent overestimation of the predictive performance. In addition, we show that the prediction accuracy should be approximately 85% for non-redundant data sets of sequence identity less than 30%. Conclusion Our results demonstrate that biological features derived from Gram-negative bacteria translocation pathways yield a significant improvement. The biological features are interpretable and can be applied in advanced analyses and experimental designs. Moreover, the overall accuracy of combining the structural homology approach is further improved, which suggests that structural conservation could be a useful indicator for inferring localization in addition to sequence homology. The proposed method can be used in large-scale analyses of proteomes.

  • To read the full article Visit
  • Open Access
This article was published in BMC Bioinformatics and referenced in International Journal of Biomedical Data Mining

Relevant Expert PPTs

Relevant Speaker PPTs

  • Anne Stinn
    Deciphering the crystal structure of NF-CU - a novel bispecific antibody for the treatment of acute myeloid leukemia
    PPT Version | PDF Version
  • Bozena Futoma-Koloch
    C3 component deposition on Salmonella O48 cells characterized by sialylated lipopolysaccharide and different pattern of outer membrane proteins
    PPT Version | PDF Version
  • Sumru Savas
    No relationship between lipoprotein-associated phospholipase A2, proinflammatory cytokines, and neopterin   in Alzheimer's disease
    PPT Version | PDF Version
  • A K Sreekala
    Floral structure in relation to pollination and breeding system of selected endemic Impatiens of Western Ghats
    PPT Version | PDF Version
  • Albert Owusu
    Albert-Owusu-Bana-Consulting-Engineers-Australia-Rethinking-the-Application-of-Engineering-Structural-Analysis-of-Economic-Impact-Risk-Propagation-in-Infra-structures
    PPT Version | PDF Version
  • M.Manikandan
    M-Manikandan-Gulf-Consult-Kuwait-Design-and-Behavior-of-Steel-Structure’s-from-Constructability-Perspectives
    PPT Version | PDF Version
  • Zuheir Barsoum
    Zuheir-Barsoum-Khalifa-University-UAE-Life-extension-upgrade-and-repair-of-welded-structures-Towards-the-use-of-High-Strength-Steels
    PPT Version | PDF Version
  • Osama O. Ibrahim
    Chemicals structure, properties, regulations and applications of non-nutritive-high intensity sweeteners
    PDF Version
  • Mapitsi S Thantsha
    In vitro antagonistic effects of Listeria adhesion protein (LAP)-expressing Lactobacillus casei against Listeria monocytogenes and Salmonella Typhimurium Copenhagen
    PPT Version | PDF Version
  • Tibor Tot
    Multiparameter characterization of breast carcinoma: subgross, microscopy, proteins, and genes
    PPT Version | PDF Version
  • Monray Edward Williams
    Molecular validation of putative antimicrobial peptides for improved Human Immunodeficiency Virus diagnostics via HIV protein p24
    PPT Version | PDF Version
  • Kuna Yellamma
    Kuna-Yellamma-Sri-Venkateswara-University-India-Evaluation-of-neuroprotective-effect-of-silk-protein
    PPT Version | PDF Version
  • Yosef Yarden
    Classically, the 3’untranslated region (3’UTR) is that region in eukaryotic protein-coding genes from the translation termination codon to the polyA signal. It is transcribed as an integral part of the mRNA encoded by the gene. However, there exists another kind of RNA, which consists of the 3’UTR alone, without all other elements in mRNA such as 5’UTR and coding region. The importance of independent 3’UTR RNA (referred as I3’UTR) was prompted by results of artificially introducing such RNA species into malignant mammalian cells. Since 1991, we found that the middle part of the 3’UTR of the human nuclear factor for interleukin-6 (NF-IL6) or C/EBP gene exerted tumor suppression effect in vivo. Our subsequent studies showed that transfection of C/EBP 3’UTR led to down-regulation of several genes favorable for malignancy and to up-regulation of some genes favorable for phenotypic reversion. Also, it was shown that the sequences near the termini of the C/EBP 3’UTR were important for its tumor suppression activity. Then, the C/EBP 3’UTR was found to directly inhibit the phosphorylation activity of protein kinase CPKC in SMMC-7721, a hepatocarcinoma cell line. Recently, an AU-rich region in the C/EBP 3’UTR was found also to be responsible for its tumor suppression. Recently we have also found evidence that the independent C/EBP 3’UTR RNA is actually exists in human tissues, such as fetal liver and heart, pregnant uterus, senescent fibroblasts etc. Through 1990’s to 2000’s, world scientists found several 3’UTR RNAs that functioned as artificial independent RNAs in cancer cells and resulted in tumor suppression. Interestingly, majority of genes for these RNAs have promoter-like structures in their 3’UTR regions, although the existence of their transcribed products as independent 3’UTR RNAs is still to be confirmed. Our studies indicate that the independent 3’UTR RNA is a novel non-coding RNA species whose function should be the regulation not of the expression of their original mRNA, but of some essential life activities of the cell as a whole.
    PPT Version | PDF Version
  • Shigeomi Horito
    Reconstruction of a transmembrane protein tetraspanin (CD9) into lipid bilayer by interaction of ganglioside GM3 and tetraspanin
    PPT Version | PDF Version
  • Kevin R. Anderson
    Kevin-Anderson-California-State-Polytechnic-University-USA-Fluid-Structure-interaction-(FSI)-analysis-of-a-solar-powered-UAV
    PPT Version | PDF Version

Recommended Conferences

Peer Reviewed Journals
 
Make the best use of Scientific Research and information from our 700 + peer reviewed, Open Access Journals
International Conferences 2017-18
 
Meet Inspiring Speakers and Experts at our 3000+ Global Annual Meetings

Contact Us

 
© 2008-2017 OMICS International - Open Access Publisher. Best viewed in Mozilla Firefox | Google Chrome | Above IE 7.0 version
adwords