SUMMARY: The next-generation sequencing brought opportunities for the diagnosis of genetic disorders due to its high-throughput capabilities. However, the majority of existing methods were limited to only sequencing candidate variants, and the process of linking these variants to a diagnosis of genetic disorders still required medical professionals to consult databases. Therefore, we introduce diseaseGPS, an integrated platform for the diagnosis of genetic disorders that combines both phenotype and genotype data for analysis. It offers not only a user-friendly GUI web application for those without a programming background but also scripts that can be executed in batch mode for bioinformatics professionals. The genetic and phenotypic data are integrated using the ACMG-Bayes method and a novel phenotypic similarity method, to prioritize the results of genetic disorders. diseaseGPS was evaluated on 6085 cases from Deciphering Developmental Disorders project and 187 cases from Shanghai Children's hospital. The results demonstrated that diseaseGPS performed better than other commonly used methods. AVAILABILITY AND IMPLEMENTATION: diseaseGPS is available to freely accessed at https://diseasegps.sjtu.edu.cn with source code at https://github.com/BioHuangDY/diseaseGPS.

In recent researches, binarized neural network (BNN) has been proposed to address the massive computations and large memory footprint problem of the convolutional neural network (CNN). Several works have designed specific BNN accelerators and showed very promising results. Nevertheless, only part of the neural network is binarized in their architecture and the benefits of binary operations were not fully exploited. In this work, we propose the first fully binarized convolutional neural network accelerator (FBNA) architecture, in which all convolutional operations are binarized and unified, even including the first layer and padding. The fully unified architecture provides more resource, parallelism and scalability optimization opportunities. Compared with the state-of-the-art BNN accelerator, our evaluation results show 3.1x performance, 5.4x resource efficiency and 4.9x power efficiency on CIFAR-10.

Deep convolutional neural networks (ConvNets) have achieved the state-of-the-art performance on many real-world applications. However, significant computation and storage demands are required by ConvNets. Spiking neural networks (SNNs), with sparsely activated neurons and event-driven computations, show great potential to take advantage of the ultra- low power spike-based hardware architectures. Yet, training SNN with similar accuracy as ConvNets is difficult. Recent researchers have demonstrated the work of converting ConvNets to SNNs (CNN-SNN conversion) with similar accuracy. However, the energy-efficiency of the converted SNNs is impaired by the increased classification latency. In this paper, we focus on optimizing the classification latency of the converted SNNs. First, we propose a restricted output training method to normalize the converted weights dynamically in the CNN-SNN training phase. Second, false spikes are identified and the false spike inhibition theory is derived to speedup the convergence of the classification process. Third, we propose a temporal max pooling method to approximate the max pooling operation in ConvNets without accuracy loss. The evaluation shows that the converted SNNs converge in about 30 time-steps and achieve the best classification accuracy of 94% on CIFAR -10 dataset.

Deep convolutional neural networks (CNNs) have shown state-of-the-art accuracy for various computer vision and speech tasks. However, CNNs are computation-intensive and energy-inefficient which are difficult to be deployed in real-time systems. Event-driven Spiking Neural Networks (SNNs) are extremely power efficient, which provides an alternative for ultra-low power applications. But effective training methods for SNN are still lacking. Due to its spatio-temporal feature of SNN, conventional training method for CNN can not be employed in SNN. To address this problem, some researchers proposed to convert the corresponding weights of trained CNNs into the synapse weights of SNNs (CNNs-SNNs). Nevertheless, limited by the [0, 1] constraints on the SNN neuron outputs, the accuracy of the converted SNNs is impaired. Besides, as the SNN network becomes deeper, the convergence speed of SNN inference are unacceptably slow. In this work, we proposed an innovative deep multi-strength SNN (M-SNN) structure which relaxes the restriction of the neuron output spike strength while the event-driven feature for low-power implementations is maintained. Using this architecture, large scale SNN can be converted from CNN with comparable accuracy and fast inference speed. The evaluation results show 3.7 × convergence speedup. Moreover, with multi-strength spike, aggressive pruning strategies can be applied to reduce the computational operations by almost 85% while maintaining the same accuracy.