您好,欢迎访问宁夏农林科学院 机构知识库!

Application of explainable machine learning in the production of pullulan by Aureobasidium pullulans CGMCCNO.7055

文献类型: 外文期刊

作者: Chen, Shiwei 1 ; Li, Wenmin 1 ; Zhao, Xiaowen 1 ; Li, Miaoxin 1 ; Zhao, Tingbin 4 ; Zheng, Guobao 5 ; Cao, Weifeng 1 ; Qiao, Changsheng 1 ;

作者机构: 1.Tianjin Univ Sci & Technol, State Key Lab Biobased Fiber Mat, Tianjin 300457, Peoples R China

2.Tianjin Univ Sci & Technol, Key Lab Ind Fermentat Microbiol, Minist Educ, Tianjin 300457, Peoples R China

3.Tianjin Univ Sci & Technol, Tianjin Engn Res Ctr Microbial Metab & Fermentat P, Sch Biotechnol, Tianjin 300457, Peoples R China

4.Tianjin Huizhi Biotrans Bioengn Co Ltd, Tianjin 300457, Peoples R China

5.Ningxia Acad Agr & Forestry Sci, Inst Forestry Sci Agr Biotechnol, Res Ctr, Yinchuan 750002, Peoples R China

关键词: Pullulan; Explainable machine learning; SHAP; NSGA-III

期刊名称:INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES ( 影响因子:8.5; 五年影响因子:8.7 )

ISSN: 0141-8130

年卷期: 2025 年 308 卷

页码:

收录情况: SCI

摘要: The application of machine learning in pullulan biofermentation has demonstrated significant potential. Explainable machine learning enhances model transparency and interpretability by revealing the relationships between variables. In this study, we compared the predictive performance of six machine learning models. The Categorical Boosting (CatBoost) model demonstrated the best fit for biomass and pullulan molecular weight, while eXtreme Gradient Boosting (XGBoost) excelled in predicting pullulan production. Additionally, feature importance and SHapley Additive exPlanations (SHAP) analyses visualized the complex relationships between medium conditions and objectives. Yeast extract emerged as the most influential factor for all three targets. Meanwhile, NaCl and initial pH showed potential in regulating pullulan production and molecular weight, respectively. Finally, optimal medium conditions for maximizing biomass, pullulan production, and molecular weight were determined using the Non-dominated Sorting Genetic Algorithm III (NSGA-III) algorithm, achieving a maximum integrated optimization rate of 275.08 % (calculated as the average of improvements across the three objectives). This study effectively expands the application of the NSGA-III algorithm in multi-objective optimization for pullulan production. These findings contribute to advancing the application of explainable machine learning and advanced intelligent algorithms in the field of pullulan production.

  • 相关文献
作者其他论文 更多>>