Graph-learning-based machine learning improves prediction and cultivation of commercial-grade marine microalgae Porphyridium.

Journal: Bioresource technology
PMID:

Abstract

A graph learning [Binarized Attributed Network Embedding (BANE)] model enhances the single-target and multi-target prediction performances of random forest and eXtreme Gradient Boosting (XGBoost) by learning complex interrelationships between cultivation parameters of Porphyridium. The BANE-XGBoost has the best prediction performance (train R > 0.96 and test R > 0.87). Based on Shapley Additive Explanation (SHAP) model, illumination intensity, culture time, and KHPO are the most critical factors for Porphyridium growth. The combined facilitating roles of cultivation parameters are found using the SHAP value-based heat map and group. To reach high biomass and daily production rate concurrently, one-way and two-way partial dependent plots models find the optimal conditions. The top 2 critical parameters (illumination intensity and KHPO) were selected to verify using the graphical user interface website based on the optimized model and lab experiments, respectively. This study shows thegraph-learning-based model can improve prediction performance and optimize intricate low-carbon microalgal cultivation.

Authors

  • Huankai Li
    State Key Laboratory of Environmental and Biological Analysis, Department of Chemistry, Hong Kong Baptist University, Hong Kong SAR China.
  • Leijian Chen
    State Key Laboratory of Environmental and Biological Analysis, Department of Chemistry, Hong Kong Baptist University, Hong Kong SAR China.
  • Feng Zhang
    Institute of Food Safety, Chinese Academy of Inspection and Quarantine, Beijing 100176, China; Key Laboratory of Food Quality and Safety for State Market Regulation, Beijing 100176, China. Electronic address: fengzhang@126.com.
  • Zongwei Cai
    State Key Laboratory of Environmental and Biological Analysis, Department of Chemistry, Hong Kong Baptist University, Hong Kong 999077, China. Electronic address: zwcai@hkbu.edu.hk.