MAGCNSE: predicting lncRNA-disease associations using multi-view attention graph convolutional network and stacking ensemble model.

BACKGROUND: Many long non-coding RNAs (lncRNAs) have key roles in different human biologic processes and are closely linked to numerous human diseases, according to cumulative evidence. Predicting potential lncRNA-disease associations can help to detect disease biomarkers and perform disease analysis and prevention. Establishing effective computational methods for lncRNA-disease association prediction is critical. RESULTS: In this paper, we propose a novel model named MAGCNSE to predict underlying lncRNA-disease associations. We first obtain multiple feature matrices from the multi-view similarity graphs of lncRNAs and diseases utilizing graph convolutional network. Then, the weights are adaptively assigned to different feature matrices of lncRNAs and diseases using the attention mechanism. Next, the final representations of lncRNAs and diseases is acquired by further extracting features from the multi-channel feature matrices of lncRNAs and diseases using convolutional neural network. Finally, we employ a stacking ensemble classifier, consisting of multiple traditional machine learning classifiers, to make the final prediction. The results of ablation studies in both representation learning methods and classification methods demonstrate the validity of each module. Furthermore, we compare the overall performance of MAGCNSE with that of six other state-of-the-art models, the results show that it outperforms the other methods. Moreover, we verify the effectiveness of using multi-view data of lncRNAs and diseases. Case studies further reveal the outstanding ability of MAGCNSE in the identification of potential lncRNA-disease associations. CONCLUSIONS: The experimental results indicate that MAGCNSE is a useful approach for predicting potential lncRNA-disease associations.

Enhancement effects of flat-mirror reflection on plasma radiation.

Laser-induced breakdown spectroscopy quality can be improved by using a nanosecond Nd:YAG laser pulse to excite soil samples. To investigate how flat-mirror reflection affects the radiation characteristics of laser-induced plasma, emission spectra of sample elements were recorded using a grating spectrometer and photoelectric detection system. Placing a planar mirror vertically on the sample surface (10 mm mirror to plasma-center axis distance) for flat-mirror reflection increased spectral line intensities of Mg, Al, Fe, and Ba by 93.06%, 159.63%, 93.43%, and 94.61%, respectively. Signal-to-noise ratio increased by 17.56%, 40.21%, 31.29%, and 30%. The radiation enhancement mechanism was clarified using measured plasma parameters.

[Effects of laser shot frequency on plasma radiation characteristics].

To improve the quality of laser-induced breakdown spectroscopy, nanosecond pulse laser generated by Nd:YAG laser was used to excite soil sample. The intensity and signal-to-background ratio of A1 I 394.401 nm, Ba I 455.403 nm, Fe I 430.791 nm and Ti I 498.173 nm were observed using a grating spectrometer and a photoelectric detection system. The effects of laser shot frequency (5, 10 and 15 Hz)on the radiation characteristics of laser-induced plasma was studied. The experimental results show that as compared with the laser shot frequency of 5 Hz, the spectral line intensity of A1, Ba, Fe and Ti increased by about 50.94%, 112.7%, 107.46%, and 99.38% at 15 Hz respectively under the same laser energy, while the spectral signal-to-background ratio increased by about 15.16%, 24.08%, 40.26% and 72.06% respectively. The effects mechanism of the laser shot frequency on radiation characteristics of plasma is explained by measuring plasma parameters.