No abstract

No abstract

<abstract><p>Long non-coding RNAs (lncRNAs) play a regulatory role in many biological cells, and the recognition of lncRNA-protein interactions is helpful to reveal the functional mechanism of lncRNAs. Identification of lncRNA-protein interaction by biological techniques is costly and time-consuming. Here, an ensemble learning framework, RLF-LPI is proposed, to predict lncRNA-protein interactions. The RLF-LPI of the residual LSTM autoencoder module with fusion attention mechanism can extract the potential representation of features and capture the dependencies between sequences and structures by k-mer method. Finally, the relationship between lncRNA and protein is learned through the method of fuzzy decision. The experimental results show that the ACC of RLF-LPI is 0.912 on ATH948 dataset and 0.921 on ZEA22133 dataset. Thus, it is demonstrated that our proposed method performed better in predicting lncRNA-protein interaction than other methods.</p></abstract>

No abstract

Adverse drug reactions (ADR) include adverse reactions which are caused by drug quality problems or improper medication. In order to solve the issues which are triggered by the lack of research on local adverse drug reactions in Xinjiang and the shortcomings of traditional models in dealing with irregular sentences, this paper proposes a method for adverse drug identification in Xinjiang. The method is combined with BiLSTM-CNN hybrid network which is based on attention mechanism. The method analyzes deeply on the network text context feature and the attention pooling mechanism. These measures can reduce the information loss while acquiring the local convolution feature. The integration of attention mechanism, the addition of weight information make it becomes more sensitive to capture the importance of features which brings improvement of the ability to express features. Finally, the experiment was carried out in the Xinjiang Adverse Drug Reaction Data Set. The accuracy rate of this model in Xinjiang local drug adverse reaction identification was 87.27%, the recall rate was 88.87%, and the F value was 87.65%. Compared with the common convolutional neural network and BiLSTM, it achieves better classification results, and has obvious advantages for irregular grammar and long sentence recognition. Experiments showed that the ATT-BiLSTM-CNN model can rapidly improve the recognition performance of local adverse drug reactions in Xinjiang.