• DocumentCode
    534462
  • Title

    Application of protein Hasse matrix image to predict protein structural classes

  • Author

    Xiao, Xuan ; Xu, Pei-Jie

  • Author_Institution
    Comput. Dept., Jing-De-Zhen Ceramic Inst., Jing-De-Zhen, China
  • Volume
    6
  • fYear
    2010
  • fDate
    16-18 Oct. 2010
  • Firstpage
    2285
  • Lastpage
    2288
  • Abstract
    A novel approach was developed for predicting the structural classes of proteins based on their sequences. It was assumed that proteins belonging to a same structural class must bear some sort of similar texture on the protein Hasse matrix images generated by partial ordering. Based on this, three geometric invariant moment factors derived from the image functions were used as the pseudo amino acid components to formulate the protein samples for statistical prediction. The success rates thus obtained on a previously constructed benchmark dataset are quite promising, implying that the protein Hasse matrix image can help to reveal some inherent and subtle features deeply hidden in a pile of long and complicated amino acid sequences.
  • Keywords
    bioinformatics; molecular biophysics; molecular configurations; prediction theory; proteins; amino acid sequences; geometric invariant moment factors; partial ordering; protein Hasse matrix image; protein structural class prediction; pseudo amino acid components; statistical prediction; Amino acids; Classification algorithms; Feature extraction; Nearest neighbor searches; Protein engineering; Protein sequence; Fuzzy K nearest neighbor algorithm; Geometric moments; Protein Hasse matrix image; Pseudo amino acid composition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on
  • Conference_Location
    Yantai
  • Print_ISBN
    978-1-4244-6495-1
  • Type

    conf

  • DOI
    10.1109/BMEI.2010.5639329
  • Filename
    5639329