Wen Yujing, Liu Xing, He Feng, Shi Yanli, Chen Fanghui, Li Wenfei, Song Youhong, Li Lin, Jiang Haiyang, Zhou Liang, Wu Leiming
The National Engineering Laboratory of Crop Resistance Breeding, School of Life Sciences, Anhui Agricultural University, Hefei 230036, China.
School of Materials and Chemistry, Anhui Agricultural University, Hefei, Anhui 230036, China.
Int J Biol Macromol. 2024 Nov;280(Pt 4):136140. doi: 10.1016/j.ijbiomac.2024.136140. Epub 2024 Sep 28.
Lignin has been recognized as a major factor contributing to lignocellulosic recalcitrance in biofuel production and attracted attentions as a high-value product in the biorefinery field. As the traditional wet chemical methods for detecting lignin content are labor-intensive, time-consuming and environment-toxic, it is an urgent need to develop high-throughput and environment-friendly techniques for large-scale crop germplasms screening. In this study, we conducted a Fourier transform infrared (FTIR) assay on 150 maize germplasms with a diverse lignin composition to build predictive models for lignin content in maize stalk. Principal component analysis (PCA) was applied to the FTIR spectra for use as model inputs. Classification and advanced gradient boosting machine (GBM) algorithms demonstrated higher predictive accuracy (0.82-0.96) compared to traditional linear and regularization algorithms (0.03-0.04) in the training set. Notably, two optimal models, built using the extreme gradient boosting (XGBoost) and light gradient boosting machine (LightGBM) algorithms, achieved R values of over 0.91 in the training set and over 0.82 in the test set. Overall, the combination of FTIR and machine learning (ML) algorithms offers a high-throughput and efficient method for predicting lignin content. This approach holds significant potential for genetic breeding and the effective utilization of maize in industrial production.
木质素被认为是生物燃料生产中导致木质纤维素难降解的主要因素，并作为生物炼制领域的高价值产品受到关注。由于传统的检测木质素含量的湿化学方法劳动强度大、耗时且对环境有毒，因此迫切需要开发高通量且环境友好的技术用于大规模作物种质筛选。在本研究中，我们对150份具有不同木质素组成的玉米种质进行了傅里叶变换红外光谱（FTIR）分析，以建立玉米秸秆中木质素含量的预测模型。主成分分析（PCA）应用于FTIR光谱用作模型输入。与训练集中的传统线性和正则化算法（0.03 - 0.04）相比，分类和高级梯度提升机（GBM）算法显示出更高的预测准确性（0.82 - 0.96）。值得注意的是，使用极端梯度提升（XGBoost）和轻量级梯度提升机（LightGBM）算法构建的两个最优模型在训练集中的R值超过0.91，在测试集中超过0.82。总体而言，FTIR和机器学习（ML）算法的结合为预测木质素含量提供了一种高通量且高效的方法。这种方法在遗传育种和玉米在工业生产中的有效利用方面具有巨大潜力。
