Chaotic Lévy and adaptive restart enhance the Manta Ray foraging optimizer for gene feature selection

8.0

来源： Nature 关键字： computational biology

发布时间： 2025-11-26 04:08

摘要：

CLA-MRFO, an enhanced Manta Ray Foraging Optimization algorithm, integrates chaotic Lévy flight and adaptive strategies to improve gene feature selection for leukemia classification. The method demonstrated significant performance improvements on benchmark tests, achieving the lowest mean error on 23 out of 29 functions. In practical applications, CLA-MRFO effectively identified compact gene subsets with established roles in leukemia, yielding high F1-scores across multiple classifiers. This innovation not only addresses optimization challenges in high-dimensional spaces but also holds substantial promise for biomedical applications, particularly in cancer diagnostics.

原文：查看原文

价值分投票

评分标准

新闻价值分采用0-10分制，综合考虑新闻的真实性、重要性、时效性、影响力等多个维度。评分越高，表示该新闻的价值越大，越值得关注。

价值维度分析

domain_focus

1.0分+1.0分+符合医疗健康领域

business_impact

1.0分+具有商业影响力

scientific_rigor

1.5分+有具体实验数据支持

timeliness_innovation

1.5分+具有创新性和时效性

investment_perspective

2.5分+早期研发阶段

market_value_relevance

1.0分+与高发疾病相关

team_institution_background

0.5分+团队背景强

technical_barrier_competition

1.0分+技术壁垒高

关键证据

CLA-MRFO achieved the lowest mean error on 23 of 29 functions.

The method identified ultra-compact subsets of biologically coherent genes.

Statistical validation confirmed the significance of the results.

真实性检查

否

AI评分总结

CLA-MRFO, an enhanced Manta Ray Foraging Optimization algorithm, integrates chaotic Lévy flight and adaptive strategies to improve gene feature selection for leukemia classification. The method demonstrated significant performance improvements on benchmark tests, achieving the lowest mean error on 23 out of 29 functions. In practical applications, CLA-MRFO effectively identified compact gene subsets with established roles in leukemia, yielding high F1-scores across multiple classifiers. This innovation not only addresses optimization challenges in high-dimensional spaces but also holds substantial promise for biomedical applications, particularly in cancer diagnostics.