RÉSUMÉ
In today's fast-paced and ever-changing environment, the need for algorithms with enhanced global optimization capability has become increasingly crucial due to the emergence of a wide range of optimization problems. To tackle this issue, we present a new algorithm called Random Particle Swarm Optimization (RPSO) based on cosine similarity. RPSO is evaluated using both the IEEE Congress on Evolutionary Computation (CEC) 2022 test dataset and Convolutional Neural Network (CNN) classification experiments. The RPSO algorithm builds upon the traditional PSO algorithm by incorporating several key enhancements. Firstly, the parameter selection is adapted and a mechanism called Random Contrastive Interaction (RCI) is introduced. This mechanism fosters information exchange among particles, thereby improving the ability of the algorithm to explore the search space more effectively. Secondly, quadratic interpolation (QI) is incorporated to boost the local search efficiency of the algorithm. RPSO utilizes cosine similarity for the selection of both QI and RCI, dynamically updating population information to steer the algorithm towards optimal solutions. In the evaluation using the CEC 2022 test dataset, RPSO is compared with recent variations of Particle Swarm Optimization (PSO) and top algorithms in the CEC community. The results highlight the strong competitiveness and advantages of RPSO, validating its effectiveness in tackling global optimization tasks. Additionally, in the classification experiments with optimizing CNNs for medical images, RPSO demonstrated stability and accuracy comparable to other algorithms and variants. This further confirms the value and utility of RPSO in improving the performance of CNN classification tasks.
RÉSUMÉ
DNA computing is a very efficient way to calculate, but it relies on high-quality DNA sequences, but it is difficult to design high-quality DNA sequences. The sequence it is looking for must meet multiple conflicting constraints at the same time to meet the requirements of DNA calculation. Therefore, we propose an improved arithmetic optimization algorithm of billiard algorithm to optimize the DNA sequence. This paper contributes as follows. The introduction to the good point set initialization to obtain high-quality solutions improves the optimization efficiency. The billiard hitting strategy was used to change the position of the population to enhance the global search scope. The use of a stochastic lens opposites learning mechanism can increase the capacity of the algorithm to get rid of locally optimal. The harmonic search algorithm is introduced to clarify some unqualified secondary structures and improve the quality of the solution. 12 benchmark functions and six other algorithms are used for comparison and ablation experiments to ensure the effectiveness of the algorithms. Finally, the DNA sequences we designed are of higher quality compared to other advanced algorithms.
Sujet(s)
Algorithmes , Séquence nucléotidiqueRÉSUMÉ
OBJECTIVE: RET (rearranged during transfection) kinase, as a transmembrane receptor tyrosine kinase, is a therapeutic target for several human cancer such as non-small cell lung cancer (NSCLC) and thyroid cancer. Pralsetinib is a recently approved drug for the treatment of RET-driven NSCLC and thyroid cancers. A single point mutation G810C at the C-lobe of the RET kinase causes pralsetinib resistance to this non-gatekeeper variant. However, the detailed mechanism remains poorly understood. METHODS: Here, multiple microsecond molecular dynamics (MD) simulations, molecular mechanics/generalized born surface area (MM/GBSA) binding free energy calculations, and community network analysis were performed to reveal the mechanism of pralsetinib resistance to the RET G810C mutant. RESULTS: The simulations showed that the G810C mutation had a minor effect on the overall conformational dynamics of the RET kinase domain. Energetic analysis suggested that the G810C mutation reduced the binding affinity of pralsetinib to the mutant. Per-residue energy contribution and structural analyses revealed that the hydrogen bonding interactions between pralsetinib and the hinge residues Glu805 and Ala807 were disrupted in the G810C mutant, which were responsible for the decreased binding affinity of pralsetinib to the mutant. CONCLUSIONS: The obtained results may provide understanding of the mechanism of pralsetinib resistance to the non-gatekeeper RET G810C mutant.