RT Conference Proceedings
T1 Reconstruction of Gene Regulatory Networks with Multi-objective Particle Swarm Optimisers
A1 Hurtado-Requena, Sandro José
A1 García-Nieto, José Manuel
A1 Navas-Delgado, Ismael
A1 Nebro-Urbaneja, Antonio Jesús
A1 Aldana-Montes, José Francisco
K1 Genética - Investigación - Congresos
K1 Bioinformática - Congresos
AB The computational reconstruction of GeneRegulatory Networks (GRNs) from gene expression data has beenmodelled as a complex optimisation problem, which enables the use ofsophisticated search methods to address it. Among these techniques,particle swarm optimisation based algorithms stand out as prominent techniques with fast convergence and accurate network inferences. A multi-objective approach for the inference of GRNs consistsof optimising a given network’s topology while tuning the kinetic order parameters in an S-System, thus preventing the use of unnecessary penalty weights and enables the adoption of Pareto optimalitybased algorithms. In this study, we empirically assess the behaviour ofa set of multi-objective particle swarm optimisers based on differentarchiving and leader selection strategies in the scope of the inferenceof GRNs. The main goal is to provide system biologists with experimental evidence about which optimisation technique performs withhigher success for the inference of consistent GRNs. The experimentsconducted involve time-series datasets of gene expression taken fromthe DREAM3/4 standard benchmarks, as well as in vivo datasets fromIRMA and Melanoma cancer samples. Our study shows that multiobjective particle swarm optimiser OMOPSO obtains the best overallperformance. Inferred networks show biological consistency in accordance with in vivo studies in the literature.
YR 2022
FD 2022-07-05
LK https://hdl.handle.net/10630/25134
UL https://hdl.handle.net/10630/25134
LA spa
NO Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026