查看文章

To overcome the problem of exponentially increasing protein data, drug discoverers need efficient machine learning techniques to predict the functions of proteins which are responsible for various diseases in human body. The existing decision tree induction methodology C4. 5 uses the entropy calculation for best attribute selection. The proposed method develops a new decision tree induction technique in which uncertainty measure is used for best attribute selection. This is based on the study of priority based packages of SDFs (Sequence Derived Features). The present research work results the creation of better decision tree in terms of depth than the existing C4. 5 technique. The tree with greater depth ensures more number of tests before functional class assignment and thus results in more accurate predictions than the existing prediction technique. For the same test data, the percentage accuracy of the new HPF (Human Protein Function) predictor is 72% and that of the existing prediction technique is 44%.