A computational approach for the classification of protein tyrosine kinases

Article · September 2009with7 Reads
DOI: 10.1007/s10059-009-0122-z · Source: PubMed
Protein tyrosine kinases (PTKs) play a central role in the modulation of a wide variety of cellular events such as differentiation, proliferation and metabolism, and their unregulated activation can lead to various diseases including cancer and diabetes. PTKs represent a diverse family of proteins including both receptor tyrosine kinases (RTKs) and non-receptor tyrosine kinases (NRTKs). Due to the diversity and important cellular roles of PTKs, accurate classification methods are required to better understand and differentiate different PTKs. In addition, PTKs have become important targets for drugs, providing a further need to develop novel methods to accurately classify this set of important biological molecules. Here, we introduce a novel statistical model for the classification of PTKs that is based on their structural features. The approach allows for both the recognition of PTKs and the classification of RTKs into their subfamilies. This novel approach had an overall accuracy of 98.5% for the identification of PTKs, and 99.3% for the classification of RTKs.
  • [Show abstract] [Hide abstract] ABSTRACT: This chapter discusses the hidden Markov models (HMM) for biological sequences. A hidden Markov model (HMM) is a statistical model, which is very well suited for many tasks in molecular biology, although they have been mostly developed for speech recognition. The most popular use of the HMM in molecular biology is as a probabilistic profile of a protein family, which is called a profile HMM. From a family of proteins (or DNA), a profile HMM can be made for searching a database for other members of the family. These profile HMMs resemble the profile and weight matrix methods, and the main contribution is that the profile HMM treats gaps in a systematic way. The HMM is particularly well suited for problems with a simple grammatical structure, such as gene finding. In gene finding several signals must be recognized and combined into a prediction of exons and introns and the prediction must conform to various rules to make it a reasonable gene prediction. An HMM can combine recognition of the signals and it can be made such that the predictions always follow the rules of a gene.
    Article · Dec 1998
  • [Show abstract] [Hide abstract] ABSTRACT: Mutations in receptor tyrosine kinases (RTKs) have been linked to an increasing number of inherited human disease syndromes, including dwarfism, craniosynostosis, heritable cancer susceptibility, venous malformation and Piebaldism. Both gain-of-function mutations resulting in constitutive receptor activation, and loss-of-function mutations resulting in non-functional or dominant negative receptors, have been observed. This review summarizes RTK families that are involved in inherited syndromes, describes the molecular consequences of the disease mutations, and predicts that many novel mutations remain to be identified.
    Article · Jun 2000
  • Chapter · Jan 1998 · Pharmaceutical Research
  • [Show abstract] [Hide abstract] ABSTRACT: We have deduced the entire 1,370-amino-acid sequence of the human insulin receptor precursor from a single complementary DNA clone. The precursor starts with a 27-amino-acid signal sequence, followed by the receptor α-subunit, a precursor processing enzyme cleavage site, then the β-subunit containing a single 23-amino-acid transmembrane sequence. There are sequence homologies to human epidermal growth factor receptor and the members of the src family of oncogene products.
    Article · Feb 1985
  • [Show abstract] [Hide abstract] ABSTRACT: Protein kinases and phosphatases are likely targets for the development of therapeutic drugs since they are involved in specific signaling pathways which regulate cell functions such as metabolism, cell cycle progression, cell adhesion, vascular function and angiogenesis. Protein phosphorylation and dephosphorylation serve as molecular switches for modulating these processes and the level and duration of each is a highly regulated process in normal cells. Several compounds that inhibit the activity of tyrosine kinases are being evaluated as cancer therapeutic agents in clinical trials. Diabetes and complications of diabetes also involve deregulated levels of protein kinases. New approaches for regulating kinase gene expression include specific antisense oligonucleotides for inhibiting post-transcriptional processing of the messenger RNA, naturally occurring products and their chemical derivatives to inhibit kinase activity, and monoclonal antibodies to inhibit receptor linked kinases. Inhibition of phosphatases also serves to alter the duration of phosphorylation by kinases. Considerations for development of effective inhibitors include non-specific actions of compounds, cellular uptake, multiple intracellular targets that can dilute the effective cellular concentration of an agent, and tissue specificity. Kinase inhibitors may allow other therapeutic agents additional time to become effective and they may act synergistically with current treatments.
    Article · Nov 2000
  • [Show abstract] [Hide abstract] ABSTRACT: G-protein coupled receptors (GPCRs) are a class of pharmacologically relevant transmembrane proteins with specific characteristics. They play a key role in different biological process and are very important for understanding human diseases. However, ligand specificity of many receptors remains unknown and only one crystal structure solved to date. It is highly desirable to predict receptor’s type using only sequence information. In this paper, Support Vector Machine is introduced to predict receptor’s type based on its amino acid composition. The prediction is performed to the amine-binding classes of the rhodopsin-like family. The overall predictive accuracy about 94% has been achieved in a ten-fold cross-validation.
    Conference Paper · Aug 2004
Show more