DNA Fingerprinting for Identification of Rice Varieties and Seed Genetic Purity Assessment

Vanisri, S.; Rani, Durga; Swathi, G.; Jamal,; Mulinti, Sreedhar; Nagireddy, Ranjit Kumar; Eruvuri, Ramprasad; Yanda, Raviteja

doi:10.1007/s40003-018-0324-8

Cited by 23 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Seed variety identification is an important issue for crop planting. Gene based techniques can be used to identify seed varieties accurately [2,3]. However, the sample preparation is complex for these methods, and workers with expert operation skill are also indispensable.…”

Section: Introductionmentioning

confidence: 99%

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

et al. 2019

View full text Add to dashboard Cite

Cotton seed purity is a critical factor influencing the cotton yield. In this study, near-infrared hyperspectral imaging was used to identify seven varieties of cotton seeds. Score images formed by pixel-wise principal component analysis (PCA) showed that there were differences among different varieties of cotton seeds. Effective wavelengths were selected according to PCA loadings. A self-design convolution neural network (CNN) and a Residual Network (ResNet) were used to establish classification models. Partial least squares discriminant analysis (PLS-DA), logistic regression (LR) and support vector machine (SVM) were used as direct classifiers based on full spectra and effective wavelengths for comparison. Furthermore, PLS-DA, LR and SVM models were used for cotton seeds classification based on deep features extracted by self-design CNN and ResNet models. LR and PLS-DA models using deep features as input performed slightly better than those using full spectra and effective wavelengths directly. Self-design CNN based models performed slightly better than ResNet based models. Classification models using full spectra performed better than those using effective wavelengths, with classification accuracy of calibration, validation and prediction sets all over 80% for most models. The overall results illustrated that near-infrared hyperspectral imaging with deep learning was feasible to identify cotton seed varieties.

show abstract

Section: Introductionmentioning

confidence: 99%

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Traditionally, the DUS tests of varieties depended on the field morphological descriptions observed during entire crop growth duration, which is time-consuming. In addition, the results of the DUS test are not exact because some descriptors rely on the experience, and the interaction between genotype and environment that may result in an unstable phenotype (Satturu et al, 2018). Furthermore, with the rapid development of the breeding program, some elite main parents are frequently used in breeding practice, which results in high genetic similarity among the developed varieties, so it is not suitable to distinguish them based on morphological traits.…”

Section: Discussionmentioning

confidence: 99%

“…The simple sequence repeat (SSR) markers are widely distributed in the genome and exhibit the advantages of codominance, better repeatability, higher polymorphism, stable amplification, ease of handling (McCouch et al, 1997;Cook et al, 2002). Thus, they are widely used in rice fingerprinting and genetic diversity analysis (Zhang et al, 2015;Meng et al, 2018;Mnasri et al, 2018;Satturu et al, 2018;Bhattacharjee et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Genetic Diversity Analysis of Hybrid Rice Parental Lines and Genetic Purity Assessment of Hybrid Seeds of China

Cai¹,

Lu²,

Liu³

et al. 2020

JAS

View full text Add to dashboard Cite

Thirty-five pairs of SSR primers were used for genetic diversity analysis and DNA fingerprinting of 31 hybrid rice core parental lines developed in central- and southern-China using one japonica rice line and three inbred rice lines as the check varieties. The average number of alleles (Na) per SSR locus was 4.02, with a range of two to eight, the effective number of alleles (Ne) was 83.16 with a mean of 2.38, ranging from 1.19 to 4.66. The polymorphic information content (PIC) ranged from 0.16 to 0.79, with an average number of 0.52. The results of the cluster analysis indicated that the check varieties viz., one japonica rice and three inbred rice, were clustered into two groups with similarity coefficients of 0.62 and 0.71 respectively indicating their relatedness. Thirty-one hybrid rice parental lines were clustered into 6 groups according to their different types, pedigrees and regions of development with similarity coefficients of approximately 0.76. The highest genetic similarity coefficient (0.94) was observed between Y58S and C815S, and the lowest (0.63) was observed between Quan9311A and Peiai64S. The purity of one hybrid rice cultivar was tested using characteristic marker and the field test, and it was demonstrated that the purities obtained using the two methods were similar. This research will be helpful for rice breeding, new cultivar registration and seed production.

show abstract

“…Genetic analysis and chemometrics-based technologies are known as powerful tools for the identification of accurate seed varieties [8,9,10,11]. However, these methods are only suitable for the laboratory environment, and adequate skills are also required for operational staff.…”

Section: Introductionmentioning

confidence: 99%

Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network

Zhu

Zhou

Zhang

et al. 2019

Sensors

View full text Add to dashboard Cite

Soybean variety is connected to stress resistance ability, as well as nutritional and commercial value. Near-infrared hyperspectral imaging was applied to classify three varieties of soybeans (Zhonghuang37, Zhonghuang41, and Zhonghuang55). Pixel-wise spectra were extracted and preprocessed, and average spectra were also obtained. Convolutional neural networks (CNN) using the average spectra and pixel-wise spectra of different numbers of soybeans were built. Pixel-wise CNN models obtained good performance predicting pixel-wise spectra and average spectra. With the increase of soybean numbers, performances were improved, with the classification accuracy of each variety over 90%. Traditionally, the number of samples used for modeling is large. It is time-consuming and requires labor to obtain hyperspectral data from large batches of samples. To explore the possibility of achieving decent identification results with few samples, a majority vote was also applied to the pixel-wise CNN models to identify a single soybean variety. Prediction maps were obtained to present the classification results intuitively. Models using pixel-wise spectra of 60 soybeans showed equivalent performance to those using the average spectra of 810 soybeans, illustrating the possibility of discriminating soybean varieties using few samples by acquiring pixel-wise spectra.

show abstract

DNA Fingerprinting for Identification of Rice Varieties and Seed Genetic Purity Assessment

Cited by 23 publications

References 16 publications

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

Genetic Diversity Analysis of Hybrid Rice Parental Lines and Genetic Purity Assessment of Hybrid Seeds of China

Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network

Contact Info

Product

Resources

About