A Sparse Fireworks Algorithm for Gene Regulatory Network Reconstruction based on Fuzzy Cognitive Maps

Abstract

Gene regulatory networks (GRNs) denote the interrelation among genes in the genomic level. In reality, gene regulatory networks are presented as sparse networks, so using sparse models to represent GRNs is a meaningful task. Fuzzy cognitive maps (FCMs) have been used to reconstruct GRNs. However, the networks learned by automated derivate-free methods are much denser than those in practical applications. Moreover, the performance of current sparse FCM learning algorithms is worse than what we expect. The fireworks algorithm is an efficient and simple optimization algorithm. However, there are few fireworks algorithms currently used to solve the sparse optimization problem. To utilize the powerful learning ability of fireworks algorithms to learn sparse FCMs, we propose a sparse fireworks algorithm (SFWA-FCM). Compared with existing FCM learning algorithms, SFWA-FCM’s excellent numerical fitting ability and sparse modeling ability are illustrated. In addition, SFWA-FCM is used to solve the problem of GRN reconstruction. On the GRN reconstruction benchmark DREAM4, SFWA shows the high accuracy. The good performance in learning sparse FCMs illustrates the effectiveness of SFWA-FCM, and the simplicity and scalability of the framework ensure that it can be adapted to a wide range of needs.