Search

Session-based recommendation uses existing items in users’ interaction sessions to predict the next items with which users will interact. The existing items in sessions usually have different degrees of relevance with each other, and this item relevance also reflects users’ interests. Moreover, when sessions are represented in different structural forms, there will be different types of relevance between items, an aspect typically neglected by previous work. In this paper, we propose a novel Context-aware Item Attraction Model (CIAM) for session-based recommendation, which is capable of capturing different types of relevance between items in order to obtain users’ general and temporal interests and predict the next items in sessions. First, we convert sessions into local and global undirected graphs to mine the item adjacency relevance within and across sessions in order to better determine users’ general interests. Second, we retain the natural sequence structure of sessions, and model the transition relevance between items in sessions to get users’ temporal interests. Third, we design a context-aware item embedding method to obtain the embedding of each item; this method utilizes superposition and a weighted graph convolutional network to aggregate the context information from both the item’s features and the item’s neighborhood. Finally, based on users’ general and temporal interests, as well as the context-aware embeddings of items, we predict the next items with which users will interact during a session. The proposed model is then extensively evaluated on two real-world datasets. Experimental results show that our model outperforms the state-of-the-art baseline methods. Through the analysis of the experiments, we prove that our model can effectively capture the different types of relevance between items within and across sessions for accurately modeling user interests, therefore improving recommendation performance.

Personalized news recommendation systems aim to alleviate information overload and provide users with personalized reading suggestions. In general, each news has its own lifecycle that is depicted by a bell-shaped curve of clicks, which is highly likely to influence users’ choices. However, existing methods typically depend on capturing user preference to make recommendations while ignoring the importance of news lifecycle. To fill this gap, we propose a Deep Co-Attention Network DCAN by modeling user preference and news lifecycle for news recommendation. The core of DCAN is a Co-Attention Net that fuses the user preference attention and news lifecycle attention together to model the dual influence of users’ clicked news. In addition, in order to learn the comprehensive news representation, a Multi-Path CNN is proposed to extract multiple patterns from the news title, content and entities. Moreover, to better capture user preference and model news lifecycle, we present a User Preference LSTM and a News Lifecycle LSTM to extract sequential correlations from news representations and additional features. Extensive experimental results on two real-world news datasets demonstrate the significant superiority of our method and validate the effectiveness of our Co-Attention Net by means of visualization.

Question-answering sentiment analysis (QASA) is a novel but meaningful sentiment analysis task based on question-answering online reviews. Existing neural network-based models that conduct sentiment analysis of online reviews have already achieved great success. However, the syntax and implicitly semantic connection in the dependency tree have not been made full use of, especially for Chinese which has specific syntax. In this work, we propose a Residual-Duet Network leveraging textual and tree dependency information for Chinese question-answering sentiment analysis. In particular, we explore the synergies of graph embedding with structural dependency links to learn syntactic information. The transverse and longitudinal compression encoders are developed to capture sentiment evidence with disparate types of compression and different residual connections. We evaluate our model on three Chinese QASA datasets in different domains. Experimental results demonstrate the superiority of our proposed model in Chinese question-answering sentiment analysis.

Mainstream partial-denitrification with anammox (PD-anammox) process faced the challenge of complex organics involved in real sewage. Herein, PD-anammox coupled with in-situ fermentation was successfully achieved in a full biofilm system formed by three-stage anoxic/oxic reactor to treat real wastewater with low COD/N of 3.6. The total nitrogen (TN) removal efficiency was enhanced to 78.4% ± 3.6% with average TN and ammonium concentrations in effluent of 10.6 and 0.5 mg N/L, respectively. Batch tests confirmed that partial-denitrification was the major nitrite provider for anammox in the anoxic biofilm, while in-situ fermentation could decompose the complex organics to readily-biodegradable organics for full- or partial-denitrification. Additionally, a significant anammox bacteria (Candidatus Brocadia) population was detected in the second (3.53%) and third (4.46%) anoxic zones, while denitrifiers and fermentative bacteria were mainly enriched in the first anoxic zone. This study presents a feasible approach for PD-anammox process in practical application under mainstream condition.

Modeling the relevance matching between a query and a document is challenging in ad-hoc document retrieval due to diverse semantic matching aspects. Both explicit and implicit semantic matching aspects exist, corresponding to the query term occurrences in a document and the term transformations between queries and documents respectively. While most of existing neural retrieval models involve both explicit and implicit matching aspects, they do not clearly and effectively distinguish and couple explicit and implicit matching signals, resulting in either only capturing the local knowledge of query topics or lacking of in-depth understanding of user query need. In this work, we propose a deep relevance coupling model (DRC) for document retrieval to capture the diverse semantic matching aspects. DRC effectively learns and couples three aspects: explicit semantic learning, implicit semantic learning, and relevance coupling. The explicit semantic learning employs a frequency layer and a probability layer to obtain the exact term-level relevance signals between queries and documents. The implicit semantic learning adopts a transformation layer and a dependency layer to automatically capture the implicit term-level relevance signals between queries and documents. The relevance coupling transforms the term-level signals to the query-document matching signals by using a term weight layer and then integrates all the query-document matching signals into the final relevance scores between queries and documents. Experiments conducted on the TREC collections demonstrate that the DRC model delivers better retrieval accuracy and robustness than the baseline methods.

Dual oxidases (DUOXs) were originally identified as NADPH oxidases (NOXs), found to be associated with the reactive oxygen species (ROS) hydrogen peroxide (H2O2) production at the plasma membrane and crucial in host biological processes. In this study, SpDUOX1 and SpDUOX2 of mud crab (Scylla paramamosain) were identified and studied. Both SpDUOX1 and SpDUOX2 are transmembrane proteins, including an N-signal peptide region and a peroxidase homology domain in the extracellular region, transmembrane regions, and three EF (calcium-binding region) domains, a FAD-binding domain, and a NAD binding domain in the intracellular region. The SpDUOXs were expressed in all tissues examined, but mainly in hepatopancreas, heart, and mid-intestine. The expression of the SpDUOXs in the hemolymph of mud crabs was up-regulated after challenge with Vibrio parahemolyticus or LPS. RNA interference (RNAi) of the SpDUOXs resulted in reduced ROS production in hemolymph. The bacterial count increased in the hemolymph of mud crabs injected with SpDUOX1 or SpDUOX2-RNAi, while the bacterial clearance ability of hemolymph significantly reduced. At the phylum level, the phyla Bacteroidetes and Actinobacteria were significantly increased, while Proteobacteria were significantly reduced following SpDUOX2 knockdown. There was a significant increase in the relative abundance of the genera Marinomonas, Pseudoalteromonas, Shewanella, and Hydrogenoph in SpDUOX2 depleted mud crabs compared with the controls. Our current findings therefore indicated that SpDUOXs might play important roles in maintaining the homeostasis in the hemolymph microbiota of mud crab.

α-Synuclein is a major component of Lewy bodies in Parkinson's disease. Although no signal sequence is apparent, α-synuclein expressed in Escherichia coli is mostly located in the periplasm. The possibilities that α-synuclein translocated into the periplasm across the inner membrane by the SecA or the Tat targeting route identified in bacteria and that α-synuclein was released through MscL were excluded. The signal recognition particle-dependent pathway is involved in the translocation of α-synuclein. The C-terminal 99-to-140 portion of the α-synuclein molecule plays a signal-like role for its translocation into the periplasm, cooperating with the central 61-to-95 section. The N-terminal 1-to-60 region is not required for this translocation.

CheA-short interacts with CheZ to localize CheZ to cell poles. The fifth helical region (residues 112 to 133) from the phosphotransfer domain of CheA interacts with CheZ and becomes ordered and helical, although it lacks a stable fold in the CheA fragment comprising residues 98 to 150 alone. One CheA molecule binds to one CheZ dimer.

alpha-Synuclein (AS) is a main component of Lewy bodies in midbrain dopamine neurons pathologically characteristic of Parkinson's disease. We show that heat shock protein (Hsp) 70 inhibits AS fibril formation via preventing the formation of prefibrillar AS (PreAS), binding with PreAS to impede nuclei formation, and binding with nuclei to retard fibril elongation. Also, Hsp70 suppresses the PreAS-induced permeabilization of vesicular membrane through interactions with PreAS. The substrate-binding domain alone is sufficient for Hsp70 to inhibit AS fibril formation. The binding of Hsp70 with PreAS only requires the substrate-binding subdomain, and the binding with AS nuclei requires the C-terminal lid subdomain as well. The results may form the molecular basis for elucidating the mechanism of AS fibril formation and the crucial roles of chaperones in protecting proteins from toxic conversion in many conformational diseases.

The effects of applying nitrogen fertilizer in ploughed furrow at different stages on dry matter production and yield of rice were studied in a field experiment in 1999. The results showed that applying N fertilizer at booting stage (BS) had better effects on dry weight (2.9 g.hill-1) of leaf, stem and whole plant than at panicle primordia formation stage (PPFS), tillering stage (TS) and regular N fertilization (RF). Meanwhile, the dry weight of leaf and sheath as well as the leaf area index (LAI, 8.9) could be maintained at a high level for a relative long time in BS treatment, compared with PPFS, TS and RF treatments. Similar phenomenon was observed in the growth velocity (0.73 g.d-1.hill-1) of stem and whole plant, and the dry weight (10434 kg.hm-2) of seed. The grain yield of rice followed the sequence of BSor = PPFSTSor = RF. Thus, the optimum stage of applying N fertilizer in ploughed furrow was the booting stage.

The hydantoinase-producing conditions from strain Arthrobacter K1108 were investigated. It is shown that the hydantoinase in the strain is intracellular and inducible. Its optimal inducer is 5-benzylhydantoin, while 5-indolylmethylhydantoin and 5-phenylhydantoin cannot induce the production of hydantoinase in K1108. A gratuitous inducer was designed, with which the hydantoinase production is 343% as much as that with 5-benzylhydantoin. The media for culturing the bacteria were screened and optimized. Under optimal conditions, the specific activity of K1108 cells reached 10.8 U/mL.