In the absence of experimentally determined three dimensional (3D) structures of proteins, the prediction of protein structures using computational methods is a standard alternative approach in bioinformatics. When using the predicted protein models to compute the native structure of an unknown target protein, estimating the actual quality of the protein models is important for selecting the best or near-best model. Moreover, estimates of the differences between the protein models and the native protein structure are obviously useful to end users who can then decide on the utility of the models for their specific problems. This article describes two new single-model quality assessment (QA) programs, pure single-model QA method (psQA) and a template based QA method (tbQA), that we developed. psQA is a pure single-model QA program that uses a neural network method to predict residue-residue distance matrices of the native protein structures. tbQA is a quasi-single-model QA program that mainly uses target-template sequence alignments and template structures. The performance of these two model QA programs was analyzed in a data set of 24022 models for 94 targets from the 10th critical assessment of protein structure prediction (CASP10) experiment.Key words model quality assessment; protein structure prediction; model accuracy; Critical Assessment of protein Structure Prediction When experimental three dimensional (3D) structures of proteins are not available, protein structure prediction using a computational method is widely used in biology and medical research, and has proven to be a useful tool. In the tenth community-wide Critical Assessment of Structure Prediction ( CASP10 1) ), various protein structure prediction methods, including the methods of 69 individual servers, were tested and showed significant progress over the past CASP experiments.2-4) Currently, protein structure prediction methods are still being developed and a significant progress has been made to improve their accuracy.In general, protein structure prediction methods consist of two steps: (1) generation of many candidate models from different alignments and templates, and (2) estimation of the quality of the candidate models to select the best or near best model. For protein structure prediction, the usefulness of a predicted protein model depends on its quality (i.e., similarity with the native protein structure); however, the quality of the model cannot be ascertained when the experimental protein structure is unknown. At present, many protein structure prediction methods can generate high quality models as candidates, but it remains difficult to identify the best or near best model. Therefore, computational biologists have developed various quality assessment (QA) methods to estimate the quality of predicted models when the experimental structure is not available. Accurate QA methods that are based on the coordinates of predicted models will contribute to the improvement of protein structure prediction strategies. Moreover, estimates of ...