Genomic and transcriptomic analysis of genes involved in exopolysaccharide biosynthesis by Streptococcus thermophilus IMAU20561 grown on different sources of nitrogen.

Exopolysaccharides (EPSs), which are produced by lactic acid bacteria, have been found to improve the texture and functionality of fermented dairy products. In a previous study, four nitrogen sources were identified as affecting the yield, molecular weight and structure of EPSs produced by Streptococcus thermophilus IMAU20561 in M17 medium. In this genomic and transcriptomics study, a novel eps gene cluster responsible for assembly of repeating units of EPS is reported. This eps cluster (22.3 kb), consisting of 24 open reading frames, is located in the chromosomal DNA. To explore the biosynthetic mechanisms in EPS, we completed RNA-seq analysis of S. thermophilus IMAU20561 grown in four different nitrogen sources for 5 h (log phase) or 10 h (stationary phase). GO functional annotation showed that there was a significant enrichment of differentially expressed genes (DEGs) involved in: amino acid biosynthesis and metabolism; ribonucleotide biosynthesis and metabolism; IMP biosynthesis and metabolism; and phosphorus metabolism. KEGG functional annotation also indicated enrichment of DEGs involved in amino acid biosynthesis, glycolysis, phosphotransferase system, fructose, and mannose metabolism. Our findings provide a better understanding the genetic traits of S. thermophilus, the biosynthetic pathways needed for the production of EPS, and a theoretical basis for screening dairy starter cultures.

A general sample-weighted framework for epileptic seizure prediction.

OBJECTIVE: Effective epileptic seizure prediction can make the patients know the onset of the seizure in advance to take timely preventive measures. Many studies based on machine learning methods have been proposed to tackle this problem and achieve significant progress in recent years. However, most studies treat each EEG training sample's contribution to the model as equal, while different samples have different predictive effects on epileptic seizures (e.g., preictal samples from different times). To this end, in this paper, we propose a general sample-weighted framework for patient-specific epileptic seizure prediction. METHODS: Specifically, we define the mapping from the sample weights of training sets to the performance of the validation sets as the fitness function to be optimized. Then, the genetic algorithm is employed to optimize this fitness function and obtain the optimal sample weights. Finally, we obtain the final model by using the training sets with optimized sample weights. RESULTS: To evaluate the effectiveness of our framework, we conduct extensive experiments on both traditional machine learning methods and prevalent deep learning methods. Our framework can significantly improve performance based on these methods. Among them, our framework based on Transformer achieves an average sensitivity of 94.6%, an average false prediction rate of 0.06/h, and an average AUC of 0.939 in 12 pediatric patients from the CHB-MIT database with the leave-one-out method, which outperforms the state-of-the-art methods. CONCLUSION: This study provides new insights into the field of epileptic seizure prediction by considering the discrepancies between EEG samples. Moreover, we develop a general sample-weighted framework, which applies to almost all classical classification methods and can significantly improve performance based on these methods.

Interpreting Bottom-Up Decision-Making of CNNs via Hierarchical Inference.

With the great success of convolutional neural networks (CNNs), interpretation of their internal network mechanism has been increasingly critical, while the network decision-making logic is still an open issue. In the bottom-up hierarchical logic of neuroscience, the decision-making process can be deduced from a series of sub-decision-making processes from low to high levels. Inspired by this, we propose the Concept-harmonized HierArchical INference (CHAIN) interpretation scheme. In CHAIN, a network decision-making process from shallow to deep layers is interpreted by the hierarchical backward inference based on visual concepts from high to low semantic levels. Firstly, we learned a general hierarchical visual-concept representation in CNN layered feature space by concept harmonizing model on a large concept dataset. Secondly, for interpreting a specific network decision-making process, we conduct the concept-harmonized hierarchical inference backward from the highest to the lowest semantic level. Specifically, the network learning for a target concept at a deeper layer is disassembled into that for concepts at shallower layers. Finally, a specific network decision-making process is explained as a form of concept-harmonized hierarchical inference, which is intuitively comparable to the bottom-up hierarchical visual recognition way. Quantitative and qualitative experiments demonstrate the effectiveness of the proposed CHAIN at both instance and class levels.

CHIP: Channel-Wise Disentangled Interpretation of Deep Convolutional Neural Networks.

With the increasing popularity of deep convolutional neural networks (DCNNs), in addition to achieving high accuracy, it becomes increasingly important to explain how DCNNs make their decisions. In this article, we propose a CHannel-wise disentangled InterPretation (CHIP) model for visual interpretations of DCNN predictions. The proposed model distills the class-discriminative importance of channels in DCNN by utilizing sparse regularization. We first introduce network perturbation to learn the CHIP model. The proposed model is capable to not only distill the global perspective knowledge from networks but also present class-discriminative visual interpretations for the predictions of networks. It is noteworthy that the CHIP model is able to interpret different layers of networks without retraining. By combining the distilled interpretation knowledge at different layers, we further propose the Refined CHIP visual interpretation that is both high-resolution and class-discriminative. Based on qualitative and quantitative experiments on different data sets and networks, the proposed model provides promising visual interpretations for network predictions in an image classification task compared with the existing visual interpretation methods. The proposed model also outperforms the related approaches in the ILSVRC 2015 weakly supervised localization task.

Stabilization of ultrafine metal nanocatalysts on thin carbon sheets.

A novel strategy was proposed to anchor ultrafine metal nanoparticles (NPs) on thin carbon sheets for highly stable and efficient heterogeneous catalysts. In this facile approach, a dense monolayer of ultrafine AuNPs was sandwiched between a silica core and a resin shell, followed by carbonization of the shell at a high temperature and then selective removal of the silica core. The shrinkage of the shells during carbonization facilitates partial embedment of the AuNPs on the carbon shell surface and provides superior stability against particle sintering during high temperature/mechanical post-treatments and catalytic reactions. It was also found that diffusion of reactants to the surface of AuNPs could be maximized by reducing the thickness of the hollow shells or simply by cracking the shells into thin carbon sheets, both significantly benefiting the catalytic efficiency. The advantages of this ultra-stable architecture together with the densely dispersed catalytic sites were demonstrated by their high stability and superior catalytic activity in reducing hydrophilic 4-nitrophenol and hydrophobic nitrobenzene.