Click-Through Rate (CTR) prediction plays an important role in many industrial applications, such as online advertising and recommender systems. How to capture users' dynamic and evolving interests from their behavior sequences remains a continuous research topic in the CTR prediction. However, most existing studies overlook the intrinsic structure of the sequences: the sequences are composed of sessions, where sessions are user behaviors separated by their occurring time. We observe that user behaviors are highly homogeneous in each session, and heterogeneous cross sessions. Based on this observation, we propose a novel CTR model named Deep Session Interest Network (DSIN) that leverages users' multiple historical sessions in their behavior sequences. We first use self-attention mechanism with bias encoding to extract users' interests in each session. Then we apply Bi-LSTM to model how users' interests evolve and interact among sessions. Finally, we employ the local activation unit to adaptively learn the influences of various session interests on the target item. Experiments are conducted on both advertising and production recommender datasets and DSIN outperforms other stateof-the-art models on both datasets.

We conducted a genome-wide scan of SNPs to identify variants associated with length of survival in 1,331 individuals with esophageal squamous-cell carcinoma (ESCC), with associations validated in 2 independent sets including 1,962 individuals with this cancer. We identified rs1050631 in SLC39A6 as associated with the survival times of affected individuals, with the hazard ratio for death from ESCC in the combined sample being 1.30 (95% confidence interval (CI) = 1.19-1.43; P = 3.77 × 10(-8)). rs7242481, located in the 5' UTR of SLC39A6, disturbs a transcriptional repressor binding site and results in upregulation of SLC39A6 expression. Immunohistochemical staining of ESCC tissues showed that higher expression of SLC39A6 protein was correlated with shorter length of survival in individuals with advanced ESCC (P = 0.013). Knockdown of SLC39A6 expression suppressed proliferation and invasion in ESCC cells. These results suggest that SLC39A6 has an important role in the prognosis of ESCC and may be a potential therapeutic target.

Network assisted full-duplex (NAFD) is a spatial-division duplex technique for future wireless networks with cellfree massive multiple-input multiple-output (CF massive MIMO) network, where a large number of remote antenna units (RAUs), either using half-duplex or full-duplex, jointly support truly flexible duplex including time-division duplex, frequency-division duplex and full duplex on demand of uplink and downlink traffic by using network MIMO methods. With NAFD, bi-directional data rates of the wireless network could be increased and end-to-end delay could be reduced. In this paper, the spectral efficiency of NAFD communications in CF massive MIMO network with imperfect channel state information (CSI) is investigated under spatial correlated channels. Based on large dimensional random matrix theory, the deterministic equivalents for the uplink sum-rate with minimum-mean-square-error (MMSE) receiver as well as the downlink sum-rate with zero-forcing (ZF) and regularized zero-forcing (RZF) beamforming are derived. Numerical results show that under various environmental settings, the deterministic equivalents are accurate in both a large-scale system and system with a finite number of antennas. It is also shown that with the downlink-touplink interference cancellation, the uplink spectral efficiency of CF massive MIMO with NAFD could be improved.The spectral efficiencies of NAFD with different duplex configurations such as in-band full-duplex, and half-duplex are compared. With the same total numbers of transmit and receive antennas, NAFD with half-duplex RAUs offers a higher spectral efficiency. To alleviate the uplink-to-downlink interference, a novel genetic algorithm based user scheduling strategy (GAS) is proposed. Simulation results show that the achievable downlink sum-rate by using the GAS is greatly improved compared to that by using the random user scheduling. Index TermsNetwork-assisted full-duplex, cell-free massive MIMO, full-duplex, spectral efficiency, deterministic equivalent, scheduling Recently, a novel concept called cell-free (CF) massive multiple-input multiple-output (MIMO) was proposed to overcome the inter-cell interference by innovating the cellular architecture [18], [19]. Compared to small-cell network, CF massive MIMO potentially has a large spectral efficiency [19]. From the point of view of baseband transmission, the performance gain of CF massive MIMO comes from the joint processing of a large number of geographically distributed RAUs [20]. Our recent prototyping system in large-scale distributed MIMO has demonstrated that the data rate of 10Gbps could be achieved by a 128x128 large-scale distributed MIMO (or CF massive MIMO) with 100MHz bandwidth [21]. Different from the existing works, in this paper, we propose a network-assisted full duplex (NAFD) to unify the flexible duplex, hybrid-duplex, full-duplex, and other duplex methods [7], [14], [15], [22] under the CF massive MIMO network, and solve the CLI problem to achieve truly flexible duplex, which is essential in the 5G NR [...

Chronic obstructive pulmonary disease (COPD) is a major cause of morbidity and mortality. Cigarette smoke (CS) drives disease development and progression. The epithelial barrier is damaged by CS with increased monolayer permeability. However, the molecular changes that cause this barrier disruption and the interaction between adhesion proteins and the cytoskeleton are not well defined. We hypothesized that CS alters monolayer integrity by increasing cell contractility and decreasing cell adhesion in epithelia. Normal human airway epithelial cells and primary COPD epithelial cells were exposed to air or CS, and changes measured in protein levels. We measured the cortical tension of individual cells and the stiffness of cells in a monolayer. We confirmed that the changes in acute and subacute in vitro smoke exposure reflect protein changes seen in cell monolayers and tissue sections from COPD patients. Epithelial cells exposed to repetitive CS and those derived from COPD patients have increased monolayer permeability. E-cadherin and β-catenin were reduced in smoke exposed cells as well as in lung tissue sections from patients with COPD. Moreover, repetitive CS caused increased tension in individual cells and cells in a monolayer, which corresponded with increased polymerized actin without changes in myosin IIA and IIB total abundance. Repetitive CS exposure impacts the adhesive intercellular junctions and the tension of epithelial cells by increased actin polymer levels, to further destabilize cell adhesion. Similar changes are seen in epithelial cells from COPD patients indicating that these findings likely contribute to COPD pathology.