Pattern Recogn Lett 27:861–874įerrer-Costa C, Orozco M, de la Cruz X (2002) Characterization of disease-associated single amino acid polymorphisms in terms of sequence and structure properties. J Med Chem 38(14):2705–2713Įisenberg D, Schwarz E, Komaromy M, Wall R (1984) Analysis of membrane and surface protein sequences with the hydrophobic moment plot. doi: 10.1002/prot.20810Ĭollantes ER, Dunn WJ 3rd (1995) Amino acid side chain descriptors for quantitative structure-activity relationship studies of peptide analogues. doi: 10.1145/1961189.1961199Ĭheng J, Randall A, Baldi P (2006) Prediction of protein stability changes for single-site mutations using support vector machines. doi: 10.1093/nar/gki375Ĭhang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. Nucleic Acids Res 33(Web Server issue):W306–W310. doi: 10.1093/bioinformatics/bti1109Ĭapriotti E, Fariselli P, Casadio R (2005b) I-Mutant2.0: predicting stability changes upon mutation from the protein sequence or structure. doi: 10.1093/bioinformatics/bth92820/suppl_1/i63Ĭapriotti E, Fariselli P, Calabrese R, Casadio R (2005a) Predicting protein stability changes from sequences using support vector machines. Data Min Knowl Disc 2:121–167Ĭapriotti E, Fariselli P, Casadio R (2004) A neural-network-based method for predicting protein stability changes upon single point mutations. doi: 101093/nar/gkh08232/suppl_1/D120īurges CJC (1998) A tutorial on support vector machines for pattern recognition. Nucleic Acids Res 32(Database issue):D120–D121. The performance of the M47 classifier on all six tested contingency table evaluation parameters is better than that of existing machine learning-based models or energy function-based protein stability classifiers.īava KA, Gromiha MM, Uedaira H, Kitajima K, Sarai A (2004) ProTherm, version 4.0: thermodynamic database for proteins and mutants. M47 predicted the stability of variant proteins with an accuracy of 87 % and a Matthews correlation coefficient of 0.68 for a large dataset of 1925 variants, whereas M8 performed better when a relatively small dataset of 388 variants was used for 20-fold cross-validation. Based on the structural properties including contact energy (CE) and further physicochemical properties of the amino acids as input features, we developed two support vector machine classifiers. To decrease the number of model parameters and to improve the generalization potential, we calculated the amino acid contact energy change for point variations using a structure-based coarse-grained model. However, models trained using limited data have performance problems and many model parameters tend to be over-fitted. Several methods have been proposed for this task including machine learning-based approaches. To understand the effects of substitutions, computational models are preferred to time-consuming and expensive experimental methods. Predicting the effects of amino acid substitutions on protein stability provides invaluable information for protein design, the assignment of biological function, and for understanding disease-associated variations.
0 kommentar(er)
