TY - JOUR AU - Wu, Qingyao AU - Ye, Yunming AU - Ng, Michael K. AU - Ho, Shen-Shyang AU - Shi, Ruichao PY - 2014 DA - 2014/01/24 TI - Collective prediction of protein functions from protein-protein interaction networks JO - BMC Bioinformatics SP - S9 VL - 15 IS - 2 AB - Automated assignment of functions to unknown proteins is one of the most important task in computational biology. The development of experimental methods for genome scale analysis of molecular interaction networks offers new ways to infer protein function from protein-protein interaction (PPI) network data. Existing techniques for collective classification (CC) usually increase accuracy for network data, wherein instances are interlinked with each other, using a large amount of labeled data for training. However, the labeled data are time-consuming and expensive to obtain. On the other hand, one can easily obtain large amount of unlabeled data. Thus, more sophisticated methods are needed to exploit the unlabeled data to increase prediction accuracy for protein function prediction. SN - 1471-2105 UR - https://doi.org/10.1186/1471-2105-15-S2-S9 DO - 10.1186/1471-2105-15-S2-S9 ID - Wu2014 ER -