Autism is a complex neuropsychiatric disorder with high heritability and an unclear etiology. The identification of key genes related to autism may elucidate its etiology. The current study provides an approach to predicting autism susceptibility genes. Genes are first extracted from the biomedical literature, and some autism susceptibility genes are then recognized as seeds by the prior knowledge. As candidates, the remaining genes are predicted by creating association rules between the seeds and candidates. In an evaluated data set, 27 autism susceptibility genes (type "Y") are extracted and 43 possible autism susceptibility genes (type "P") are predicted. The sum of "Y" and "P" genes accounts for 93.3% of the data set that are not contained in the typical database of autism susceptibility genes. Our approach can effectively extract and predict autism susceptibility genes from the biomedical literature. These predicted results complement the typical database of autism susceptibility genes. The web portal for the predicted results, which is freely available at http://biolab.hyit.edu.cn/ar, can be a valuable resource in studies of diseases related to genes.

No abstract

In this article, we propose a novel model to overcome the drawbacks of the modified Chan–Vese (MCV) model. Our model is devoted to find an optimal partition of inhomogeneous regions accurately and computationally efficient. MCV model was proposed on the concept of using one level‐set function for one region. It needs fewer numbers of iterations and improves the efficiency of image segmentation in contrast to the multiphase Chan–Vese model. The MCV model, however, is highly dependent on initial curves placement and often leads to erroneous segmentations on images with intensity inhomogeneity. In our model, to eliminate the affection of background information on the curve evolution and speed up the curve evolution, we first use the k‐means algorithm to presegment the image to get the initial curves and then add the local image information to the total energy functional of MCV model to deal with the intensity inhomogeneity. Finally, extensive experiments are done and the segmentation results on homogeneous multiphase images verify that the proposed method has the better accuracy and efficiency comparing to MCV model. Moreover, we show results on challenging multiphase inhomogeneous image to illustrate the robust and accurate segmentation that are possible with this novel model. © 2012 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 22, 103–113, 2012

No abstract