Hierarchy cuckoo search algorithm for parameter estimation in biological systems

- A hybrid hierarchical cuckoo search as a new optimization approach is proposed.
- It successfully applied on a set of benchmark functions.
- It efficiently estimated parameters for isomerization of α-Pinene.
- For the inhibition of HIV proteinase it improved the best known solution in the literature.

Mathematical models play a critical role in describing behavior of biomedical and biological processes. These models have unknown parameters that cannot be measured directly and researchers need reliable tools to estimate them from available experimental data. We present a new modification of cuckoo search (CS) algorithm, named hybrid hierarchical cuckoo search (HHCS), as a powerful computational tool to help with this task. The proposed algorithm uses an information sharing mechanism which allows cuckoo eggs to share their best search information through a heterogeneous hierarchical structure. The HHCS takes advantage of the cooperation between cuckoo eggs to maintain the diversity of solutions and to avoid premature convergence. This approach is also hybridized with a local search method in order to reduce the computational time required for determining the optimal solution. First, the generalization properties of HHCS is evaluated against a set of benchmark functions. Thereafter, we investigate the application of HHCS on two highly non-linear parameter estimation problems of biological systems, namely isomerization of α-Pinene and inhibition of HIV proteinase. Statistical analysis of experimental results shows that the proposed algorithm provides very competitive results compared to CS and several state-of-the-art algorithms in terms of solution accuracy, convergence speed, and robustness. Notably, the HHCS improves the best known solution in the literature for the inhibition of HIV proteinase.