PEP2D algorithm was developed using a random forest classifier approach. First RandomForest gives probabilites values of helix,sheet and coil. Next, these probabilites values were optimized using weight optimization and final probabilities for helix, sheet and coil were obtained. The secondary strcuture having the highest probabilite value i assigned. We have used Weka machine learning package, which consist of Random forest classifiers that we have used in our study.
Diagrammatic representation of PEP2D algorithm. |