Concise Cascade Methods for Transgenic Rice Seed Discrimination using Spectral Phenotyping
作者机构：Department of Agricultural and Biological EngineeringPurdue UniversityWest LafayetteIN 47907USA College of Biosystems Engineering and Food ScienceZhejiang UniversityHangzhouChina Huzhou Institute of Zhejiang UniversityHuzhouChina
出 版 物：《Plant Phenomics》 (植物表型组学（英文）)
年 卷 期：2023年第5卷第3期
页 面：564-580页
核心收录：
学科分类：0402[教育学-心理学(可授教育学、理学学位）] 0303[法学-社会学] 0710[理学-生物学] 0832[工学-食品科学与工程（可授工学、农学学位）] 1002[医学-临床医学] 1001[医学-基础医学(可授医学、理学学位)] 09[农学] 0837[工学-安全科学与工程] 0901[农学-作物学] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：supported by the National Key Research and Development Program of China(2021ZD0113601) Key Research and Development Projects of Huzhou City(2021ZD2037).
主 题：fir simplicity consuming
摘 要：Currently,the presence of genetically modified(GM)organisms in agro-food markets is strictly regulated by enacted legislation worldwide.It is essential to ensure the traceability of these transgenic products for food safety,consumer choice,environmental monitoring,market integrity,and scientific research.However,detecting the existence of GM organisms involves a combination of complex,time-consuming,and labor-intensive techniques requiring high-level professional skills.In this paper,a concise and rapid pipeline method to identify transgenic rice seeds was proposed on the basis of spectral imaging technologies and the deep learning approach.The composition of metabolome across 3 rice seed lines containing the cry1Ab/cry1Ac gene was compared and studied,substantiating the intrinsic variability induced by these GM traits.Results showed that near-infrared and terahertz spectra from different genotypes could reveal the regularity of GM metabolic variation.The established cascade deep learning model divided GM discrimination into 2 phases including variety classification and GM status identification.It could be found that terahertz absorption spectra contained more valuable features and achieved the highest accuracy of 97.04%for variety classification and 99.71%for GM status identification.Moreover,a modified guided backpropagation algorithm was proposed to select the task-specific characteristic wavelengths for further reducing the redundancy of the original spectra.The experimental validation of the cascade discriminant method in conjunction with spectroscopy confirmed its viability,simplicity,and effectiveness as a valuable tool for the detection of GM rice seeds.This approach also demonstrated its great potential in distilling crucial features for expedited transgenic risk assessment.
维普期刊数据库