Department of Clinical Biological Resource Bank, Guangzhou Institute of Pediatrics, Guangzhou Women and Children's Medical Center Guangzhou Medical University Guangzhou Guangdong China
Auto-generated profile, based on publicly available information
Lei Pi
Department of Clinical Biological Resource Bank, Guangzhou Institute of Pediatrics, Guangzhou Women and Children's Medical Center Guangzhou Medical University Guangzhou Guangdong China
Background: Accumulating evidence suggests that several microRNA (miRNA) polymorphisms are closely associated with disease susceptibility or progression, such as in Kawasaki disease (KD). Our previous studies revealed the association of miR‐149 rs2292832 T>C and miR‐196a2 rs11614913 C>T polymorphisms with KD susceptibility. The present study further focused on the relationship between three miRNA polymorphisms (miR‐149 rs2292832 T>C, miR‐196a2 rs11614913 C>T and miR‐499a rs3746444 A>G) and the risk of coronary artery aneurysm (CAA) in southern Chinese KD patients.Methods: We evaluated 318 KD patients with CAAs and 784 patients without CAAs. TaqMan assays were used to estimate genotyping and analyze the relationship between miRNA polymorphisms (miR‐149 rs2292832 T>C, miR‐196a2 rs11614913 C>T and miR‐499a rs3746444 A>G) and risk associations of CAA by odds ratios (ORs) and 95% confidence intervals (CIs).Results: We found that the miR‐149 rs2292832 TC/CC genotype increased the CAA risk (adjusted OR = 1.53, 95% CI = 1.15–2.03, p = 0.003 for TC, adjusted OR = 1.63, 95% CI = 1.08–2.47, p = 0.021 for CC), whereas the miR‐499a rs3746444 AG genotype decreased the CAA risk in KD patients (adjusted OR = 0.33, 95% CI = 0.25–0.45 p ≤ 0.001). Moreover, patients carrying two or three of these single nucleotide polymorphism (SNP) genotypes (rs2292832 TC/CC and rs11614913 TT and rs3746444 AA) had a higher risk for CAA than those who harbored only zero or one of these SNP genotypes.Conclusions: Our results demonstrated that the miR‐149 rs2292832 T>C polymorphism increased the risk of CAA in KD patients and that the miR‐499a rs3746444 A>G polymorphism decreased the risk of CAA in KD patients. Further studies with larger sample sizes and different centers are needed to confirm the findings of the present study.
Dual-Path RNN(DPRNN) has achieved great progress in single-channel speech separation. However, RNN-based model needs to pass information through intermediate states and it does not allow parallel computing. Meanwhile, inter-chunk modeling of DPRNN only modeled between multiples of the chunk length, which means the underutilization of contextual information. To address these problems, we propose a multi-scale dual-path temporal convolutional network, DPTCN-ATPP. DPTCN-ATPP utilizes a stacked of one-dimensional dilated convolutions (1-D CNNs) instead of RNN to learn local and global information. Besides, DPTCN-ATPP applies parallel encoders to extract multi-scale input features. Finally, DPTCN-ATPP introduces the ATPP block to summarize multi-scale deep features. The experiment results show that DPTCN-ATPP achieves 19.6dB and 19.8dB on the metrics of scale-invariant source-to-noise ratio(SI-SNR) and source-to-distortion (SDR) respectively, outperforming baseline DPRNN and single-scale TCN (Conv-TasNet).