Gene function prediction is a complicated and challenging hierarchical multi-label classification\n(HMC) task, in which genes may have many functions at the same time and these functions are organized\nin a hierarchy. This paper proposed a novel HMC algorithm for solving this problem based on the\nGene Ontology (GO), the hierarchy of which is a directed acyclic graph (DAG) and is more difficult\nto tackle. In the proposed algorithm, the HMC task is firstly changed into a set of binary classification\ntasks. Then, two measures are implemented in the algorithm to enhance the HMC performance by\nconsidering the hierarchy structure during the learning procedures. Firstly, negative instances selecting\npolicy associated with the SMOTE approach are proposed to alleviate the imbalanced data set problem.\nSecondly, a nodes interaction method is introduced to combine the results of binary classifiers. It can\nguarantee that the predictions are consistent with the hierarchy constraint. The experiments on eight\nbenchmark yeast data sets annotated by the Gene Ontology show the promising performance of the\nproposed algorithm compared with other state-of-the-art algorithms
Loading....