Research Spotlight: Evolutionary Algorithms Designing Nanoparticle Cancer Treatments

Late last year some of the Evo Nano team from the University of Novi Sad and the University of the West of England, published their research on using evolutionary algorithms to look at the effect of ruggedness of the fitness landscape on the evolution of genome length of nanoparticles in a paper in IEEE Computational Intelligence. Using multiple types of nanoparticles is expected to provide better treatment of cancer tumours, so it’s important that genome length is not hindered by the landscape. Using an agent-based cell simulator, it was found that whilst ruggedness does affect the dynamics of the process, the evolution of genome length is not inhibited. This allowed for more than one type of nanoparticle. They used PhysiCell to simulate the interaction with the tumour. Evolution of a single nanoparticle led to only a 7% reduction in the tumour size, whereas the simultaneous evolution of multiple types led to a 50% decrease. To read more about the results, have a look at the paper here: Evolutionary Algorithms Designing Nanoparticle Cancer Treatments with Multiple Particle Types

Average and confidence levels (95%) results from 10 runs of EA with variable-length genome for the composition of the best solution.