ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2017, Vol. 54 ›› Issue (12): 2660-2673.doi: 10.7544/issn1000-1239.2017.20170644

所属专题: 2017人工智能应用专题

• 人工智能 • 上一篇    下一篇



  1. 1(西南大学计算机与信息科学学院 重庆 400715); 2(广东工业大学计算机学院 广州 510006) (
  • 出版日期: 2017-12-01
  • 基金资助: 

Protein Function Prediction Based on Multiple Networks Collaborative Matrix Factorization

Yu Guoxian1, Wang Keyao1, Fu Guangyuan1, Wang Jun1, Zeng An2   

  1. 1(College of Computer and Information Science, Southwest University, Chongqing 400715); 2(School of Computers, Guangdong University of Technology, Guangzhou 510006)
  • Online: 2017-12-01

摘要: 准确预测蛋白质功能是生物信息学的核心任务之一,也是人工智能在生物数据分析中的重要应用点之一.高通量技术的广泛应用产生了大量的生物分子功能关联网络,整合这些网络可更为全面地分析理解蛋白质功能机理,提升蛋白质功能预测精度.已有多种基于数据整合的蛋白质功能预测方法,但它们通常难以应用到较大功能标签空间,未利用标签间关联性和差异性整合多个网络.提出一种基于多网络数据协同矩阵分解的蛋白质功能预测方法(ProCMF).该方法首先利用非负矩阵分解将蛋白质-功能标签关联矩阵分解为2个低秩矩阵,挖掘蛋白质与标签之间的潜在关联.其次,为利用标签间关联关系和多种蛋白质特征数据,ProCMF分别基于上述2个低秩矩阵定义平滑正则性,约束指导低秩矩阵的协同分解.为了差异性地集成多个网络,ProCMF对不同的网络设置不同的权重.最后ProCMF将上述目标统一到一个目标方程中,并用一种交替迭代的方法分别优化求解低秩矩阵和网络权重.在酵母菌、人类和老鼠3个模式物种的多网络数据集上的实验结果表明:ProCMF获得了较其他相关算法更好的预测性能,ProCMF能有效地处理大量的功能标签和区分性地整合多个网络.

关键词: 蛋白质功能预测, 功能关联网络, 网络集成, 非负矩阵分解, 协同分解

Abstract: Accurately and automatically predicting biological functions of proteins is one of the fundamental tasks in bioinformatics, and it is also one of the key applications of artificial intelligence in biological data analysis. The wide application of high throughput technologies produces various functional association networks of molecules. Integrating these networks contributes to more comprehensive view for understanding the functional mechanism of proteins and to improve the performance of protein function prediction. However, existing network integration based solutions cannot apply to a large number of functional labels, ignore the correlation between labels, or cannot differentially integrate multiple networks. This paper proposes a protein function prediction approach based on multiple networks collaborative matrix factorization (ProCMF). To explore the latent relationship between proteins and between labels, ProCMF firstly applies nonnegative matrix factorization to factorize the protein-label association matrix into two low-rank matrices. To employ the correlation between labels and to guide the collaborative factorization with proteomic data, it defines two smoothness terms on these two low-rank matrices. To differentially integrate these networks, ProCMF sets different weights to them. In the end, ProCMF combines these goals into a unified objective function and introduces an alternative optimization technique to jointly optimize the low-rank matrices and weights. Experimental results on three model species (yeast, human and mouse) with multiple functional networks show that ProCMF outperforms other related competitive methods. ProCMF can effectively and efficiently handle massive labels and differentially integrate multiple networks.

Key words: protein function prediction, functional association network, network integration, nonnegative matrix factorization, collaborative factorization