1.Depression recognition based on frequency-space domain fusion and 3D-CNN-Attention
Jianshang WANG ; Bingtao ZHANG ; Xiaomin WANG ; Dachuan YAN
Chinese Journal of Medical Physics 2024;41(10):1307-1314
A three-dimensional feature construction method based on spectral information is presented,in which the power values of each channel are arranged into two-dimensional feature vectors based on electrode positions.The different frequency band features are arranged into a three-dimensional integral feature tensor to extract the information in frequency domain.Meanwhile,in order to reduce the influence of volume conductor effect,functional connectivity is utilized to map the temporal electroencephalogram data to the spatial brain functional network for extracting the spatial information.By analyzing the relationship between features and target classes,a 3D-CNN-Attention network model is proposed to incorporate an Attention mechanism in 3D-CNN network to enhance the electroencephalogram feature learning capability.A series of comparative experiments on publicly available datasets show that 3D-CNN-Attention network framework outperforms other methods in depression detection,obtaining an accuracy rate of up to 96.32%.The proposed method provides an effective solution for depression detection.
2.Effect of MLCK knockout on apoptosis in FaDu cells
Lei Xiong ; Jianshang Huang ; Qing Zhou ; Yuan Wang ; Li Zuo
Acta Universitatis Medicinalis Anhui 2023;58(5):748-752,759
Objective:
To construct a myosin light chain kinase ( MLCK) knockout hypopharyngeal carcinoma FaDu cell line and discuss the knockout effect of MLCK on apoptosis of FaDu cells.
Methods:
MLCK knockout FaDu cell lines were constructed by liposome transfection of sgRNA and Cas9 2NLS Nuclease , and the knockout cell lines were identified by DNA sequencing and divided into control group , MLCK KO 1 group and MLCK KO 2 group. The knockout efficiency of MLCK was assessed by RT⁃qPCR and Western blot , and the effect of MLCK knockout on cell cycle and apoptosis was detected by flow cytometry while Western bolt was conducted to detect the effect of MLCK knockout on cell apoptosis.
Results:
DNA sequencing showed that MLCK base sequences were missing or substituted at the sgRNA sequence recognition , and RT⁃qPCR and Western blot showed lower mRNA and protein levels in MLCK knockout cell lines than those in the control group(P < 0. 000 1) . Furthermore , the flow cytometry assay showed that MLCK knockout did not significantly change the cycle of FaDu cells , but the rate of apoptosis increased (P < 0. 000 1) . Western blot showed that Bax/Bcl⁃2 (P < 0. 000 1) and Cleaved Caspase⁃3/Caspase⁃3 (P = 0. 000 7) ratios raised in the MLCK knockout group.
Conclusion
The knockout of MLCK induced apoptosis in FaDu cells , but the exact mechanism needs further study.