Identify High-Quality Protein Structural Models by Enhanced -Means

One critical issue in protein three-dimensional structure prediction using either ab initio or comparative modeling involves identification of high-quality protein structural models from generated decoys. Currently, clustering algorithms are widely used to identify near-native models; however, their performance is dependent upon different conformational decoys, and, for some algorithms, the accuracy declines when the decoy population increases. Here, we proposed two enhanced -means clustering algorithms capable of robustly identifying high-quality protein structural models. The first one employs the clustering algorithm SPICKER to determine the initial centroids for basic -means clustering (-means), whereas the other employs squared distance to optimize the initial centroids (-means++). Our results showed that -means and -means++ were more robust as compared with SPICKER alone, detecting 33 (59%) and 42 (75%) of 56 targets, respectively, with template modeling scores better than or equal to those of SPICKER. We observed that the classic -means algorithm showed a similar performance to that of SPICKER, which is a widely used algorithm for protein-structure identification. Both -means and -means++ demonstrated substantial improvements relative to results from SPICKER and classical -means.