辨識不同種類之稻米以及研究其基因型與表現型之關聯

Identifying Rice Grains of Various Varieties and Studying the Genotype-Phenotype Association of Rice Grains

郭子毅(Tzu-Yi Kuo)

指導教授 ： 周楚洋

共同指導教授 ： 郭彥甫(Yan-Fu Kuo)

國立臺灣大學/生物資源暨農學院/生物產業機電工程學研究所/碩士(2016年)

https://doi.org/10.6342/NTU201610260

摘要

水稻是全世界許多人的主食,每年在國際市場上交易的數量十分龐大。不同的品種 的水稻在外觀上存在著差異,這些外觀差異可以藉由分析其與水稻基因型的關聯 來了解造成外觀差異的原因。本研究利用影像處理以及稀疏表達分類器等非破壞 性檢測分辨 30 種不同的水稻,同時也對於 255 種水稻的外觀以及基因型做出其關 聯性的分析。稀疏表達分類器則可以利用過度充分基底來捕捉具有代表性的外觀 特徵。在實驗中,種子取自於 Genetic Stocks Oryza,基因資訊取自於公開資料庫, 利用顯微鏡與高解析度數位相機提高影像畫質。量化的外觀特徵大致上被分為水 稻種子以及護穎的形態、顏色以及紋理等特徵。接下來利用線性模型對上述特徵分 析其與基因型的關係。稀疏表達分類器藉著輸入量化的外觀特徵來辨識其中 30 種 水稻品種,稀疏表達分類器對於 30 種品種的辨識準確率可達到 89.1%。

關鍵字

水稻辨識 ； 稀疏編碼 ； 影像處理 ； 機器視覺 ； 數量性狀基因座

並列摘要

Rice (Oryza sativa L.) is a major staple food and is traded globally in considerable amount. Rice shows remarkable variation in grains. The phenotypic information of the rice grains need to be quantified as the first step to investigate the association between the phenotypes and genotypes. This study proposed to distinguish the rice grains of 30 varieties nondestructively using image processing, sparse representation based classification (SRC) and a procedure to phenotype rice grains of 255 varieties in high precision. SRC is a method that uses over-complete bases to capture the representative traits of rice grains. In the experiments, rice seeds were acquired from Genetic Stocks Oryza germplasm collection. The genotypic information (i.e., SNPs) of these seeds are publicly available. The images of the grains were acquired in high resolution using microscopy (approximately 2413 dots per inch). Morphological, color, and textural traits of the grain body, sterile lemmas, and brush were quantified. The traits were subsequently fit into a unified mixed linear model for investigating the association between the phenotypic and genotypic variations of the varieties. An SRC classifier was developed to identify the varieties of the grains using the traits as the inputs. The proposed approach could discriminate the varieties of the rice grains with an accuracy of 89.1%.

並列關鍵字

Variety identification ； sparse coding ； locality constraint ； machine vision ； machine learning ； image processing ； phenotyping

參考文獻

Arlot, S., Celisse, A., 2010. A survey of cross-validation procedures for model selection. Statistics surveys 4, 40-79.

Becerra, V., Paredes, M., Gutierrez, E., Rojo, C., 2015. Genetic diversity, identification, and certification of Chilean rice varieties using molecular markers. Chilean journal of agricultural research 75, 267-274.

Bradbury, P.J., Zhang, Z., Kroon, D.E., Casstevens, T.M., Ramdoss, Y., Buckler, E.S., 2007. TASSEL: software for association mapping of complex traits in diverse samples. Bioinformatics 23, 2633-2635.

Bush, W.S., Moore, J.H., 2012. Chapter 11: Genome-wide association studies. PLoS Comput Biol 8, e1002822.

Chen, H., Xie, W., He, H., Yu, H., Chen, W., Li, J., Yu, R., Yao, Y., Zhang, W., He, Y., 2014. A high-density SNP genotyping array for rice biology and molecular breeding. Molecular plant 7, 541-553.