Artificial neural network model for predicting HIV protease cleavage sites in protein

Knowledge of the polyprotein cleavage sites by HIV protease will refine our understanding of its specificity, and the information thus acquired will be useful for designing specific and efficient HIV protease inhibitors. The search for inhibitors of HIV protease will be greatly expedited if one can find an accurate, robust, and rapid method for predicting the cleavage sites in proteins by HIV protease. In this paper, Kohonen's self-organization model, which uses typical artificial neural networks, is applied to predict the cleavability of oligopeptides by proteases with multiple and extended specificity subsites. We selected HIV-1 protease as the subject of study. We chose 299 oligopeptides for the training set, and another 63 oligopeptides for the test set. Because of its high rate of correct prediction (58/63 = 92.06%) and stronger fault-tolerant ability, the neural network method should be a useful technique for finding effective inhibitors of HIV protease, which is one of the targets in designing potential drugs against AIDS. The principle of the artificial neural network method can also be applied to analyzing the specificity of any multisubsite enzyme.

[1]  T. Miyata,et al.  Retroviral gag and DNA endonuclease coding sequences in IgE-binding factor gene , 1985, Nature.

[2]  K. Chou Prediction of human immunodeficiency virus protease cleavage sites in proteins. , 1996, Analytical biochemistry.

[3]  B. Haynes,et al.  Frequent detection and isolation of cytopathic retroviruses (HTLV-III) from patients with AIDS and at risk for AIDS. , 1984, Science.

[4]  A Wlodawer,et al.  Structure of complex of synthetic HIV-1 protease with a substrate-based inhibitor at 2.3 A resolution. , 1989, Science.

[5]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[6]  H. Mitsuya,et al.  Molecular targets for AIDS therapy. , 1990, Science.

[7]  T. Miyata,et al.  Retroviral protease-like sequence in the yeast transposon Ty 1 , 1985, Nature.

[8]  S. Putney,et al.  How antibodies block HIV infection: paths to an AIDS vaccine. , 1992, Trends in biochemical sciences.

[9]  K. Chou,et al.  Studies on the specificity of HIV protease: An application of Markov chain theory , 1993, Journal of protein chemistry.

[10]  William R. Taylor,et al.  A structural model for the retroviral proteases , 1987, Nature.

[11]  K. Chou,et al.  A vector projection approach to predicting HIV protease cleavage sites in proteins , 1993, Proteins.

[12]  Brian W. Metcalf,et al.  Inhibition of HIV-1 protease in infected T-lymphocytes by synthetic peptide analogues , 1990, Nature.

[13]  V. Turk,et al.  Human immunodeficiency virus has an aspartic-type protease that can be inhibited by pepstatin A. , 1988, Proceedings of the National Academy of Sciences of the United States of America.

[14]  J. Chou,et al.  Predicting cleavability of peptide sequences by HIV protease via correlation-angle approach , 1993, Journal of protein chemistry.

[15]  Tomi K. Sawyer,et al.  A synthetic HIV-1 protease inhibitor with antiviral activity arrests HIV-like particle maturation. , 1990, Disease markers.

[16]  B. Moss,et al.  An inhibitor of the protease blocks maturation of human and simian immunodeficiency viruses and spread of infection. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[18]  T. Copeland,et al.  Molecular characterization of gag proteins from simian immunodeficiency virus (SIVMne) , 1988, Journal of virology.

[19]  John P. Overington,et al.  X-ray analysis of HIV-1 proteinase at 2.7 Å resolution confirms structural homology among retroviral enzymes , 1989, Nature.

[20]  T K Sawyer,et al.  The evaluation of non-viral substrates of the HIV protease as leads in the design of inhibitors for AIDS therapy. , 1991, Advances in experimental medicine and biology.

[21]  L J Davis,et al.  Active human immunodeficiency virus protease is required for viral infectivity. , 1988, Proceedings of the National Academy of Sciences of the United States of America.

[22]  J. Chermann,et al.  Isolation of a T-lymphotropic retrovirus from a patient at risk for acquired immune deficiency syndrome (AIDS). , 1983, Science.

[23]  K. Chou,et al.  Predicting human immunodeficiency virus protease cleavage sites in proteins by a discriminant function method , 1996, Proteins.

[24]  K. Chou,et al.  A vectorized sequence-coupling model for predicting HIV protease cleavage sites in proteins. , 1993, The Journal of biological chemistry.

[25]  I B Duncan,et al.  Rational design of peptide-based HIV proteinase inhibitors. , 1990, Science.

[26]  A. Tomasselli,et al.  A cumulative specificity model for proteases from human immunodeficiency virus types 1 and 2, inferred from statistical analysis of an extended substrate data base. , 1991, The Journal of biological chemistry.

[27]  C. Zhang,et al.  An alternate-subsite-coupled model for predicting HIV protease cleavage sites in proteins. , 1994, Protein engineering.

[28]  C M Cook,et al.  The three-dimensional x-ray crystal structure of HIV-1 protease complexed with a hydroxyethylene inhibitor. , 1991, Advances in experimental medicine and biology.

[29]  A. Wlodawer,et al.  Structure-based inhibitors of HIV-1 protease. , 1993, Annual review of biochemistry.

[30]  E. Wimmer,et al.  Proteolytic processing of polyproteins in the replication of RNA viruses. , 1989, Biochemistry.