融合蛋白质语言模型与深度神经网络的植物蛋白质相互作用预测研究  

Prediction of plant protein-protein interaction based on fusion of protein language model and deep neural network

作　　者：古海博 王成凤 金远 池方爱 李颜娥 Gu Haibo;Wang Chengfeng;Jin Yuan;Chi Fangai;Li Yan′e(College of Mathematics and Computer Science,Zhejiang A&F University,Hangzhou 311300,China)

机构地区：[1]浙江农林大学数学与计算机科学学院,浙江杭州311300

出　　处：《电子技术应用》2024年第4期22-28,共7页Application of Electronic Technique

基　　金：浙江省公益基金(LQ21H180001);浙江农林大学科研发展基金(2019RF065);浙江省软科学研究项目(2023C3509)。

摘　　要：预测植物中的蛋白质-蛋白质相互作用(PPI)具有重要的生物学意义。同时采用了4种编码方法及深度神经网络构建了蛋白质相互作用预测模型。结果表明,提出的融合蛋白质语言模型Ankh与深度神经网络的方法构建的PPI预测模型性能在3种植物数据集上均获得了最优的AUPR和AUC值,Sen及MCC值也均优于其他4种蛋白质相互作用预测模型。当模型在水稻、大豆的植物PPI数据集上进行测试时,所提出的模型AUPR值分别为0.8025、0.7301,AUC值分别为0.9562、0.9507。这些优异的结果表明,融合蛋白质语言模型Ankh的PPI模型可以作为植物蛋白质相互作用预测的一个有前途的工具。Predicting protein-protein interaction(PPI)in plants holds significant biological implications.This study has employed four encoding methods and a deep neural network to construct a model for predicting protein interactions.The results show that the developed PPI prediction model using the integrated approach of the protein language model Ankh with a deep neural network has achieved optimal AUPR and AUC values across three plant datasets,with its Sen and MCC values also outperforming those of four other models designed for protein interaction predictions.When tested on plant PPI datasets for rice and soybean,the proposed model has yielded AUPR scores of 0.8025 and 0.7301 respectively,and AUC scores of 0.9562 and 0.9507 respectively.These outstanding results indicate that the PPI model incorporating the protein language model Ankh can serve as a promising tool for predicting protein-protein interactions in plants.

关 键 词：植物蛋白质相关性 蛋白质语言模型 深度神经网络 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]