Ensemble multi-objective evolutionary algorithm for gene regulatory network reconstruction based on fuzzy cognitive maps

• Published in: CAAI Transactions on Intelligence Technology Vol. 4; no. 1; pp. 24 - 36
• Main Authors: Liu, Jing, Chi, Yaxiong, Liu, Zongdong, He, Shan
• Format: Journal Article
• Language: English
• Published: Beijing The Institution of Engineering and Technology 01.03.2019; John Wiley & Sons, Inc; Wiley
• Subjects: A0210 Algebra, set theory, and graph theory; A0250 Probability theory, stochastic processes, and statistics; A8715B Biomolecular structure, configuration, conformation, and active sites; A8725F Physics of subcellular structures; A8780S Genomic techniques; Approximation; Artificial intelligence; automated methods; biology computing; Boolean; C1140Z Other topics in statistics; C1160 Combinatorial mathematics; C1180 Optimisation techniques; C4130 Interpolation and function approximation (numerical analysis); C6130 Data handling techniques; C6170K Knowledge engineering techniques; C7330 Biology and medical computing; called fuzzy cognitive maps; Cognitive maps; Cognitive models; complicated regulatory relationships; distinct optimal local information; efficient ensemble strategy; EMOEA; ensemble multiobjective evolutionary algorithm; Error analysis; Evolutionary algorithms; evolutionary computation; FCM -GRN; FCM learning problem; final network; fuzzy set theory; Gene expression; gene regulatory network reconstruction; gene regulatory networks; Genetic algorithms; genetics; genomic methods; genomics; GRNs; historical data; Historical structures; learning (artificial intelligence); Machine learning; MOEA; network structure information; Networks; Neural networks; Objectives; observed time sequence data; optimisation; Random variables; Research Article; Reverse engineering; selected networks; simple but powerful tool; synthetic FCMs; target network; training FCMs; fuzzy set theory; network structure information; final network; gene regulatory network reconstruction; training FCMs; FCM learning problem; optimisation; genetics; gene regulatory networks; biology computing; target network; observed time sequence data; genomics; simple but powerful tool; MOEA; efficient ensemble strategy; synthetic FCMs; learning (artificial intelligence); automated methods; called fuzzy cognitive maps; evolutionary computation; GRNs; ensemble multiobjective evolutionary algorithm; historical data; selected networks; EMOEA; genomic methods; FCM -GRN; distinct optimal local information; complicated regulatory relationships; gene expression
• ISSN: 2468-2322; 2468-2322
• DOI: 10.1049/trit.2018.1059

Many methods aim to use data, especially data about gene expression based on high throughput genomic methods, to identify complicated regulatory relationships between genes. The authors employ a simple but powerful tool, called fuzzy cognitive maps (FCMs), to accurately reconstruct gene regulatory networks (GRNs). Many automated methods have been carried out for training FCMs from data. These methods focus on simulating the observed time sequence data, but neglect the optimisation of network structure. In fact, the FCM learning problem is multi-objective which contains network structure information, thus, the authors propose a new algorithm combining ensemble strategy and multi-objective evolutionary algorithm (MOEA), called EMOEAFCM-GRN, to reconstruct GRNs based on FCMs. In EMOEAFCM-GRN, the MOEA first learns a series of networks with different structures by analysing historical data simultaneously, which is helpful in finding the target network with distinct optimal local information. Then, the networks which receive small simulation error on the training set are selected from the Pareto front and an efficient ensemble strategy is provided to combine these selected networks to the final network. The experiments on the DREAM4 challenge and synthetic FCMs illustrate that EMOEAFCM-GRN is efficient and able to reconstruct GRNs accurately.