首页|基于Transformer的蛋白质相互作用预测研究

基于Transformer的蛋白质相互作用预测研究

扫码查看
研究蛋白质相互作用(PPIs)在生物学中具有非常重要的意义,蛋白质相互作用及其相互作用类型的研究对于理解正常和疾病状态下的细胞生物学过程至关重要,从而有助于治疗靶点的识别和新药物的设计.针对传统蛋白质相互作用预测模型预测精度不够高的问题,提出了一种基于Transformer的模型TPPI对蛋白质进行相互作用的预测.五倍交叉验证实验结果表明,该模型在人类蛋白质数据集上预测的准确率为0.944,表现出了较好的预测准确性.
Transformer-based protein interaction prediction research
The study of protein interactions(PPIs)is of great significance in biology,and the study of protein interactions and their interaction types is essential for understanding cell biological processes in normal and disease states,thereby aiding the iden-tification of therapeutic targets and the design of new drugs.In this paper,aiming at the problem that the prediction accuracy of tra-ditional protein interaction prediction models is not high enough,a Transformer-based model TPPI is proposed to predict protein in-teractions.The results of the five-fold cross-validation experiment show that the prediction accuracy of the model on the human pro-tein dataset is 0.944,showing good prediction accuracy.

Transformerproteininteractionforecast

靳晓宏、韦文山

展开 >

广西民族大学电子信息学院,南宁 530000

Transformer 蛋白质 相互作用 预测

2024

现代计算机
中大控股

现代计算机

影响因子:0.292
ISSN:1007-1423
年,卷(期):2024.30(6)
  • 11