Explanation of KEYWORDS

Probability

The Platt’s posterior class probability ^{1; 2; 3} is employed for scoring the predicted functional families of a query protein. This probability has been used for scoring the machine learning classification of protein functional families ³, fold classes ⁴, transmembrane topology ⁵, secondary structures ⁶, and the effect of missense mutations on protein function ⁷. It has also been built into such popular machine learning software as LibSVM 8, in which the posterior probability takes the form of a sigmoid function Pr(y=1|f)=P_AB(f)=1/(1+exp(Af+B)), where f=f(x) is the output of the SVM and the parameters A and B are optimized via cross validation of the training sets.

1. Platt, J. (1999). Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in large margin classifiers 10, 61–74.
2. Lin, H. T., Lin, C. J. & Weng, R. C. (2007). A note on Platt’s probabilistic outputs for support vector machines. Machine learning 68, 267–276.
3. Minneci, F., Piovesan, D., Cozzetto, D. & Jones, D. T. (2013). FFPred 2.0: improved homology-independent prediction of gene ontology terms for eukaryotic protein sequences. PLoS One 8, e63754.
4. Grassmann, J., Reczko, M., Suhai, S. & Edler, L. (1999). Protein fold class prediction: new methods of statistical classification. Proc Int Conf Intell Syst Mol Biol, 106-12.
5. Reynolds, S. M., Kall, L., Riffle, M. E., Bilmes, J. A. & Noble, W. S. (2008). Transmembrane topology and signal peptide prediction using dynamic bayesian networks. PLoS Comput Biol 4, e1000213.
6. Guermeur, Y., Geourjon, C., Gallinari, P. & Deleage, G. (1999). Improved performance in protein secondary structure prediction by inhomogeneous score combination. Bioinformatics 15, 413-21.
7. Needham, C. J., Bradford, J. R., Bulpitt, A. J., Care, M. A. & Westhead, D. R. (2006). Predicting the effect of missense mutations on protein function: analysis with Bayesian networks. BMC Bioinformatics 7, 405.
8. Chang, C. C. & Lin, C. J. (2011). LIBSVM: A Library for Support Vector Machines. Acm Transactions on Intelligent Systems and Technology 2.