Selection of molecular descriptors with artificial intelligence for the understanding of HIV-1 protease peptidomimetic inhibitors-activity

QSAR prediction of HIV-1 protease inhibitory activities using docking derived molecular descriptors

In this study, application of a new hybrid docking-quantitative structure activity relationship (QSAR) methodology to model and predict the HIV-1 protease inhibitory activities of a series of newly synthesized chemicals is reported. This hybrid docking-QSAR approach can provide valuable information about the most important chemical and structural features of the ligands that affect their inhibitory activities. Docking studies were used to find the actual conformations of chemicals in active site of HIV-1 protease. Then the molecular descriptors were calculated from these conformations. Multiple linear regression (MLR) and least square support vector machine (LS-SVM) were used as QSAR models, respectively. The obtained results reveal that statistical parameters of the LS-SVM model are better than the MLR model, which indicate that there are some non-linear relations between selected molecular descriptors and anti-HIV activities of interested chemicals. The correlation coefficient (R), root mean square error (RMSE) and average absolute error (AAE) for LS-SVM are: R=0.988, RMSE=0.207 and AAE=0.145 for the training set, and R=0.965, RMSE=0.403 and AAE=0.338 for the test set. Leave one out cross validation test was used for assessment of the predictive power and validity of models which led to cross-validation correlation coefficient QUOTE of 0.864 and 0.850 and standardized predicted relative error sum of squares (SPRESS) of 0.553 and 0.581 for LS-SVM and MLR models, respectively.

Ribonucleases of different origins with a wide spectrum of medicinal applications

Ribonucleases (RNases) are a type of nucleases that catalyze the degradation of RNA into smaller components. They exist in a wide range of life forms from prokaryotes to eukaryotes. RNase-controlled RNA degradation is a determining factor in the control of gene expression, maturation and turnover, which are further associated with the progression of cancers and infectious diseases. Over the years, RNases purified from multiple origins have drawn increasing attention from medical scientists due to their remarkable antitumor properties. In this review, we present a brief summary of the representative RNases of fungal, bacterial, plant, and animal origins and outline their potential medicinal value in the treatment of tumor and AIDS. Among them, the most clinically promising RNases are mushroom RNases, Binase and Barnase from bacteria, ginseng RNases, and Onconase from frog (Rana pipiens). Fast developing protein engineering of RNases, which display more potent cytotoxic activity on and greater selectivity for malignant cells, has also aroused the interest of researchers. The multiple anti-cancer mechanisms of RNases are also included. To sum up, these inspiring studies unveil a new perspective for RNases as potential therapeutic agents.

A new sequence representation as applied in better specificity elucidation for human immunodeficiency virus type 1 protease

Factor analysis scales of generalized amino acid information (FASGAI) involving hydrophobicity, alpha and turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties were derived from 516 property parameters of 20-coded amino acids, and was then employed to represent sequence structures of 746 peptides with 8 amino acid residues. Cleavage site prediction models for human immunodeficiency virus type 1 protease by linear discriminant analysis and support vector machine with radial basis function kernel were constructed to identify if they could be cleaved or not, and were further utilized to investigate the cleavage specificity. These diversified properties, including the bulky properties, secondary conformation characteristics, electronic properties, and hydrophobicity at the first, the second, the fourth, the fifth, and the sixth residue, are possibly important factors in determining HIV PR cleavage or not. Particularly, maximal positive and negative influences result from the bulky properties of different sites. Further results from analysis of variance also likely reflect that the HIV PR recognizes diversified key properties of various sites in the octameric sequences. Satisfactory results show that FASGAI can not only be used to represent sequence structures of various functional peptides, but alsoprovide a potential feasible measure for exploring relationship between protein motif sequences and their functions.