Proceedings of the 2022 6th International Conference on Computational Biology and Bioinformatics最新文献

筛选

英文中文

Prediction of Protein Interactions Based on Cnn-Lstm 基于Cnn-Lstm的蛋白质相互作用预测

Proceedings of the 2022 6th International Conference on Computational Biology and Bioinformatics Pub Date : 2022-12-26 DOI: 10.1145/3589437.3589439

Jihong Wang, Xiaodan Wang, Junwei Wu

{"title":"Prediction of Protein Interactions Based on Cnn-Lstm","authors":"Jihong Wang, Xiaodan Wang, Junwei Wu","doi":"10.1145/3589437.3589439","DOIUrl":"https://doi.org/10.1145/3589437.3589439","url":null,"abstract":"Protein is the material basis and the only form of all life activities, and it is also the material basis or drug for diagnosing and treating diseases. The number of human proteins not only far exceeds the number of genes, but also due to the variability and diversity of proteins, protein research techniques are far more complex and difficult than nucleic acid techniques. Protein-protein interactions (PPIs) play key roles in many cellular biological processes and underlie the entire molecular machinery of living cells, which can be used to aid in drug target detection and therapeutic design. Deep learning methods have produced many research results in the field of bioinformatics. Convolutional neural network (CNN) methods and LSTM methods have strong spatial and sequence feature representation learning capabilities, and have achieved outstanding results in the fields of images and text. In-depth research can be done in the field of PPI. In this paper, we propose a CNN-LSTM method to predict PPI. Taking the protein sequence as the research basis, the protein sequence is encoded in hexadecimal, and the protein interaction relationship pair is constructed, and the CNN method and the LSTM method are introduced for fusion learning. A 3-layer convolutional network is used for representation learning, and then connected to the LSTM layer. The prediction performance of the model is improved by adjusting different parameters such as learning rate and activation function. On the test set, Auc is 0.9212 and F1 is 0.9206, and compared with other commonly used models, it proves that CNN-LSTM has good learning and generalization capabilities, and can be effectively used for PPI prediction.","PeriodicalId":119590,"journal":{"name":"Proceedings of the 2022 6th International Conference on Computational Biology and Bioinformatics","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129019680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identification of Splice Junctions Across Species Using BLSTM Model 利用BLSTM模型鉴定跨物种剪接连接

Proceedings of the 2022 6th International Conference on Computational Biology and Bioinformatics Pub Date : 2022-12-26 DOI: 10.1145/3589437.3589438

Aparajita Dutta, K. Singh, A. Anand

引用次数: 0

Proceedings of the 2022 6th International Conference on Computational Biology and Bioinformatics 2022年第六届计算生物学与生物信息学国际会议论文集

Proceedings of the 2022 6th International Conference on Computational Biology and Bioinformatics Pub Date : 1900-01-01 DOI: 10.1145/3589437

引用次数: 0

首页上一页