Competition for nutrients contained in diverse types of plant cell wall-associated polysaccharides may explain the evolution of substrate-specific catabolic gene modules in common bacterial members of the human gut microbiota.

Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items. The matching stage retrieves candidate items relevant to user interests, while the ranking stage sorts candidate items by user interests. Thus, the most critical ability is to model and represent user interests for either stage. Most of the existing deep learning-based models represent one user as a single vector which is insufficient to capture the varying nature of user's interests. In this paper, we approach this problem from a different view, to represent one user with multiple vectors encoding the different aspects of the user's interests. We propose the Multi-Interest Network with Dynamic routing (MIND) for dealing with user's diverse interests in the matching stage. Specifically, we design a multi-interest extractor layer based on capsule routing mechanism, which is applicable for clustering historical behaviors and extracting diverse interests. Furthermore, we develop a technique named label-aware attention to help learn a user representation with multiple vectors. Through extensive experiments on several public benchmarks and one largescale industrial dataset from Tmall, we demonstrate that MIND can achieve superior performance than state-of-the-art methods for recommendation. Currently, MIND has been deployed for handling major online traffic at the homepage on Mobile Tmall App.

Understanding the catalytic mechanism of bimetallic nanocatalysts remains challenging. Here, we adopt an adsorbate mediated thermal reduction approach to yield monodispersed AuPd catalysts with continuous change of the Pd-Au coordination numbers embedded in a mesoporous carbonaceous matrix. The structure of nanoalloys is well-defined, allowing for a direct determination of the structure-property relationship. The results show that the Pd single atom and dimer are the active sites for the base-free oxidation of primary alcohols. Remarkably, the d -orbital charge on the surface of Pd serves as a descriptor to the adsorbate states and hence the catalytic performance. The maximum d -charge gain occurred in a composition with 33–50 at% Pd corresponds to up to 9 times enhancement in the reaction rate compared to the neat Pd. The findings not only open an avenue towards the rational design of catalysts but also enable the identification of key steps involved in the catalytic reactions.

No abstract

BackgroundPrecise identification of three-dimensional genome organization, especially enhancer-promoter interactions (EPIs), is important to deciphering gene regulation, cell differentiation and disease mechanisms. Currently, it is a challenging task to distinguish true interactions from other nearby non-interacting ones since the power of traditional experimental methods is limited due to low resolution or low throughput.ResultsWe propose a novel computational framework EP2vec to assay three-dimensional genomic interactions. We first extract sequence embedding features, defined as fixed-length vector representations learned from variable-length sequences using an unsupervised deep learning method in natural language processing. Then, we train a classifier to predict EPIs using the learned representations in supervised way. Experimental results demonstrate that EP2vec obtains F1 scores ranging from 0.841~ 0.933 on different datasets, which outperforms existing methods. We prove the robustness of sequence embedding features by carrying out sensitivity analysis. Besides, we identify motifs that represent cell line-specific information through analysis of the learned sequence embedding features by adopting attention mechanism. Last, we show that even superior performance with F1 scores 0.889~ 0.940 can be achieved by combining sequence embedding features and experimental features.ConclusionsEP2vec sheds light on feature extraction for DNA sequences of arbitrary lengths and provides a powerful approach for EPIs identification.Electronic supplementary materialThe online version of this article (10.1186/s12864-018-4459-6) contains supplementary material, which is available to authorized users.