Factor Analysis Scales of Generalized Amino Acid Information as Applied in Predicting Interactions between the Human Amphiphysin-1 SH3 Domains and Their Peptide Ligands

College of Bioengineering, Chongqing University, Chongqing 400030, PR China.
Chemical Biology &amp Drug Design (Impact Factor: 2.51). 05/2008; 71(4):345-51. DOI: 10.1111/j.1747-0285.2008.00641.x
Source: PubMed

ABSTRACT Factor analysis scales of generalized amino acid information (FASGAI) involving hydrophobicity, alpha-helix and beta-turn propensities, bulky properties, compositional characteristics, local flexibility, and electronic properties, was proposed to represent the structures of the decapeptides binding the human amphiphysin-1 SH3 domains. Parameters being responsible for the binding affinities were selected by genetic algorithm, and a quantitative structure-affinity relationship (QSAR) model by partial least square was established to predict the peptide-SH3 domain interactions. Diversified properties of the residues between P(2) and P(-3) (including P(2) and P(-3)) of the decapeptide (P(4)P(3)P(2)P(1)P(0)P(-1)P(-2)P(-3)P(-4)P(-5)) may contribute remarkable effect to the interactions between the SH3 domain and the decapeptide. Particularly, electronic properties of P(2) may provide relatively large positive contributions to the interactions, and reversely, hydrophobicity of P(2) may be largely negative to the interactions. These results showed that FASGAI vectors can well represent the structural characteristics of the decapeptides. Furthermore, the model obtained, which showed low computational complexity, correlated FASGAI descriptors with the binding affinities as well as that FASGAI vectors may also be applied in QSAR studies of peptides.

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this article, we discuss the application of the Gaussian process (GP) and other statistical methods (PLS, ANN, and SVM) for the modeling and prediction of binding affinities between the human amphiphysin SH3 domain and its peptide ligands. Divided physicochemical property scores of amino acids, involving significant hydrogen bond, electronic, hydrophobic, and steric properties, was used to characterize the peptide structures, and quantitative structure-affinity relationship models were then constructed by PLS, ANN, SVM, and GP coupled with genetic algorithm-variable selection. The results show that: (i) since the significant flexibility and high complexity possessed in polypeptide structures, linear PLS method was incapable of fulfilling a satisfying behavior on SH3 domain binding peptide dataset; (ii) the overfitting involved in training process has decreased the predictive power of ANN model to some extent; (iii) both SVM and GP have a good performance for SH3 domain binding peptide dataset. Moreover, by combining linear and nonlinear terms in the covariance function, the GP is capable of handling linear and nonlinear-hybrid relationship, and which thus obtained a more stable and predictable model than SVM. Analyses of GP models showed that diversified properties contribute remarkable effect to the interactions between the SH3 domain and the peptides. Particularly, steric property and hydrophobicity of P(2), electronic property of P(0), and electronic property and hydrogen bond property of P(-3) in decapeptide (P(4)P(3)P(2)P(1)P(0)P(-1)P(-2)P(-3)P(-4)P(-5)) significantly contribute to the binding affinities of SH3 domain-peptide interactions.
    Biopolymers 01/2008; 90(6):792-802. DOI:10.1002/bip.21091 · 2.29 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A genetic algorithm was developed and assessed in order to select pairs of proper structural descriptors able to estimate and predict octanol-water partition coefficients of polychlorinated biphenyls (PCBs). The molecular descriptors family was calculated for a sample of 206 PCBs. The problem of searching for the proper descriptors in order to identify structure-activity relationships was translated in genetic terms. The following parameters were imposed in the genetic algorithm (GA) search: sample size - 12, number of variables in multivariate linear regression - 4, imposed adaptation requirements - 3 criteria, maximum number of generations - 50,000, selection strategy - tournament, probability of parent/child mutation - 0.05, number of genes implied in the mutation - 2, optimization parameter - determination coefficient, optimization score - minimum in the sample, and optimization objective - maximum. The highest determination coefficient was obtained in the generation 17,277. Twenty-one evolutions were studied until the optimum solution was obtained. The model identified by the implemented genetic algorithm proved not to be statistically different from the model identified through complete search (Z(Steiger) = 1.37, p = 0.0861). According to this GA model, the relationship between the structure of PCBs and octanol-water partition coefficients was of geometric and topological nature as previously revealed by the complete search. The genetic algorithm proved its ability to identify two pairs of molecular descriptors able to characterize the relationship between the structure of PCBs and the octanol-water partition coefficient.
    Journal of Molecular Modeling 08/2009; 16(2):377-86. DOI:10.1007/s00894-009-0540-z · 1.87 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A new structure-based approach was proposed to quantitatively characterize the binding profile of human amphiphysin-1 (hAmph1) SH3 domain-peptide complexes. In this protocol, the protein/peptide atoms were classified into 16 types in terms of their physicochemical meaning and biological function, and then a 16 x 16 atom-pair interaction matrix was constructed to describe 256 atom-pair types between the SH3 domain and the peptide ligand, with atoms from peptide and SH3 domain served as the matrix columns and rows, respectively. Three non-covalent effects dominating SH3 domain-peptide binding as electrostatic, van der Waals (steric) and hydrophobic interactions were separately calculated for the 256 atom-pair types. As a result, 768 descriptors coding detailed information about SH3 domain-peptide interactions were yielded for further statistical modeling and analysis. Based on a culled data set consisting of 592 samples with known affinities, we employed this approach, coupled with partial least square (PLS) regression and genetic algorithm (GA), to predict and to interpret the peptide-binding behavior to SH3 domain. In comparison with the previous works, our method is more capable of capturing important factors in the SH3 domain-peptide binding, thus, yielding models with better statistical performance. Furthermore, the optimal GA/PLS model indicates that the electrostatic effect plays a crucial role in SH3 domain-peptide complexes, and steric contact and hydrophobic force also contribute significantly to the binding.
    Amino Acids 09/2009; 38(4):1209-18. DOI:10.1007/s00726-009-0332-x · 3.65 Impact Factor