Learn More
Currently most of state-of-the-art methods for Chinese word segmentation are based on supervised learning, whose features aremostly extracted from a local context. Thesemethods cannot utilize the long distance information which is also crucial for word segmentation. In this paper, we propose a novel neural network model for Chinese word segmentation, which(More)
BACKGROUND Deletion and the reciprocal duplication in 16p11.2 were recently associated with autism and developmental delay. METHOD We indentified 27 deletions and 18 duplications of 16p11.2 were identified in 0.6% of all samples submitted for clinical array-CGH (comparative genomic hybridisation) analysis. Detailed molecular and phenotypic(More)
During the last two decades, the importance of human genome copy number variation (CNV) in disease has become widely recognized. However, much is not understood about underlying mechanisms. We show how, although model organism research guides molecular understanding, important insights are gained from study of the wealth of information available in the(More)
Complex genomic rearrangements (CGRs) consisting of two or more breakpoint junctions have been observed in genomic disorders. Recently, a chromosome catastrophe phenomenon termed chromothripsis, in which numerous genomic rearrangements are apparently acquired in one single catastrophic event, was described in multiple cancers. Here, we show that(More)
CDK5RAP2 is a human microcephaly protein that contains a γ-tubulin complex (γ-TuC)-binding domain conserved in Drosophila melanogaster centrosomin and Schizosaccharomyces pombe Mto1p and Pcp1p, which are γ-TuC-tethering proteins. In this study, we show that this domain within CDK5RAP2 associates with the γ-tubulin ring complex (γ-TuRC) to stimulate its(More)
Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, in most previous works, the models are learned based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we use the multitask learning framework to jointly learn across multiple related(More)
-Tubulin plays a critical role in microtubule nucleation occurring at least at centrosomes, chromatins, and spindle microtubules. There are two differently sized -tubulin complexes (-TuCs): the -tubulin small complex (-TuSC) and the -tubulin ring complex (-TuRC; Wiese and Zheng, 2006; Lüders and Stearns, 2007; Raynaud-Messina and Merdes, 2007).(More)
The tasks in fine-grained opinion mining can be regarded as either a token-level sequence labeling problem or as a semantic compositional task. We propose a general class of discriminative models based on recurrent neural networks (RNNs) and word embeddings that can be successfully applied to such tasks without any taskspecific feature engineering effort.(More)
IMPORTANCE Clinical whole-exome sequencing is increasingly used for diagnostic evaluation of patients with suspected genetic disorders. OBJECTIVE To perform clinical whole-exome sequencing and report (1) the rate of molecular diagnosis among phenotypic groups, (2) the spectrum of genetic alterations contributing to disease, and (3) the prevalence of(More)
Duplication at the Xq28 band including the MECP2 gene is one of the most common genomic rearrangements identified in neurodevelopmentally delayed males. Such duplications are non-recurrent and can be generated by a non-homologous end joining (NHEJ) mechanism. We investigated the potential mechanisms for MECP2 duplication and examined whether genomic(More)