基于CNN和Bi-LSTM模型的蛋白質(zhì)甲基化位點識別

打開文本圖片集

關(guān)鍵詞：甲基化；卷積神經(jīng)網(wǎng)絡(luò)；雙向長短時記憶網(wǎng)絡(luò)；特征融合；位點識別DOI：10.15938/j. jhust.2025.02.009中圖分類號：TP391.4 文獻標志碼：A 文章編號：1007-2683（2025）02-0082-09

Abstract：MethylationisaproteinPost-Translational Modification（PTM）thatregulatescellfunction，whichcanprovideguidance andhelpforresearchinthefieldsofgeneregulationanddiseaseprediction.Atpresent，therearesomeproblemsintheresearchof methylationsiterecogitin，suchasfewlabeleddtasets，nsuffcentpositivesmpledataandlowrecogitionaccracyofhylation research.Inordertosolvetheseproblems，thispaperproposesaproteinmethylationsiterecognitionmethodbasedonConvolutional NeuralNetwork（CNN）andBi-directionalLongShor-TermMemory（Bi-LSTM）model.Ourmodelisdividedintotwobranches.The CNNbranchusesadenseconnectionmethodtomakethefeatureinformationofachlayerfull transmitedandshared.ThestackedBiLSTMbranchesobtainbidirectionallong-termdependenciesinthesequence，andthenthetwobranchesperform featurefusionfor methylationrecognition.ExperimentsshowthattheAccuracy（ACC），F(xiàn)1Score（F1score）andMatthewsCorrelationCoficient （MCC）obtainedbyusingourmodeltoidentifymethylationsitesareO.8519，0.8494andO.7284，respectively.Compared with other methods，the model has better performance.

Keywords;methylation；convolutionalneuralnetwork；bi-directionallongshrt-termmemory；featurefusion；siterecogition

0 引言

甲基化是一種翻譯后修飾（post-translationalmodification，PTM），通過向蛋白質(zhì)結(jié)構(gòu)中添加甲基來修飾蛋白質(zhì)的功能和構(gòu)象，在表觀遺傳過程中發(fā)揮著重要的作用[]。（剩余15029字）