Single Seed Identification in Three Medicago Species via Multispectral Imaging Combined with Stacking Ensemble Learning.

Multispectral imaging (MSI) has become a new fast and non-destructive detection method in seed identification. Previous research has usually focused on single models in MSI data analysis, which always employed all features and increased the risk to efficiency and that of system cost. In this study, we developed a stacking ensemble learning (SEL) model for successfully identifying a single seed of sickle alfalfa (Medicago falcata), hybrid alfalfa (M. varia), and alfalfa (M. sativa). SEL adopted a three-layer structure, i.e., level 0 with principal component analysis (PCA), linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) as models of dimensionality reduction and feature extraction (DRFE); level 1 with support vector machine (SVM), multiple logistic regression (MLR), generalized linear models with elastic net regularization (GLMNET), and eXtreme Gradient Boosting (XGBoost) as basic learners; and level 3 with XGBoost as meta-learner. We confirmed that the values of overall accuracy, kappa, precision, sensitivity, specificity, and sensitivity in the SEL model were all significantly higher than those in basic models alone, based on both spectral features and a combination of morphological and spectral features. Furthermore, we also developed a feature filtering process and successfully selected 5 optimal features out of 33 ones, which corresponded to the contents of chlorophyll, anthocyanin, fat, and moisture in seeds. Our SEL model in MSI data analysis provided a new way for seed identification, and the feature filter process potentially could be used widely for development of a low-cost and narrow-channel sensor.

Uncovering a Phenomenon of Active Hormone Transcriptional Regulation during Early Somatic Embryogenesis in Medicago sativa.

Somatic embryogenesis (SE) is a developmental process in which somatic cells undergo dedifferentiation to become plant stem cells, and redifferentiation to become a whole embryo. SE is a prerequisite for molecular breeding and is an excellent platform to study cell development in the majority of plant species. However, the molecular mechanism involved in M. sativa somatic embryonic induction, embryonic and maturation is unclear. This study was designed to examine the differentially expressed genes (DEGs) and miRNA roles during somatic embryonic induction, embryonic and maturation. The cut cotyledon (ICE), non-embryogenic callus (NEC), embryogenic callus (EC) and cotyledon embryo (CE) were selected for transcriptome and small RNA sequencing. The results showed that 17,251 DEGs, and 177 known and 110 novel miRNAs families were involved in embryonic induction (ICE to NEC), embryonic (NEC to EC), and maturation (EC to CE). Expression patterns and functional classification analysis showed several novel genes and miRNAs involved in SE. Moreover, embryonic induction is an active process of molecular regulation, and hormonal signal transduction related to pathways involved in the whole SE. Finally, a miRNA-target interaction network was proposed during M. sativa SE. This study provides novel perspectives to comprehend the molecular mechanisms in M. sativa SE.

Karyotypic evolution of the Medicago complex: sativa-caerulea-falcata inferred from comparative cytogenetic analysis.

BACKGROUND: Polyploidy plays an important role in the adaptation and speciation of plants. The alteration of karyotype is a significant event during polyploidy formation. The Medicago sativa complex includes both diploid (2n = 2× = 16) and tetraploid (2n = 2× = 32) subspecies. The tetraploid M. ssp. sativa was regarded as having a simple autopolyploid origin from diploid ssp. caerulea, whereas the autopolyploid origin of tetraploid ssp. falcata from diploid form ssp. falcata is still in doubt. In this study, detailed comparative cytogenetic analysis between diploid to tetraploid species, as well as genomic affinity across different species in the M. sativa complex, were conducted based on comparative mapping of 11 repeated DNA sequences and two rDNA sequences by a fluorescence in situ hybridization (FISH) technique. RESULTS: FISH patterns of the repeats in diploid subspecies caerulea were highly similar to those in tetraploid subspecies sativa. Distinctly different FISH patterns were first observed in diploid ssp. falcata, with only centromeric hybridizations using centromeric and multiple region repeats and a few subtelomeric hybridizations using subtelomeric repeats. Tetraploid subspecies falcata was unexpectedly found to possess a highly variable karyotype, which agreed with neither diploid ssp. falcata nor ssp. sativa. Reconstruction of chromosome-doubling process of diploid ssp. caerulea showed that chromosome changes have occurred during polyploidization process. CONCLUSIONS: The comparative cytogenetic results provide reliable evidence that diploid subspecies caerulea is the direct progenitor of tetraploid subspecies sativa. And autotetraploid ssp. sativa has been suggested to undergo a partial diploidization by the progressive accumulation of chromosome structural rearrangements during evolution. However, the tetraploid subspecies falcata is far from a simple autopolyploid from diploid subspecies falcata although no obvious morphological change was observed between these two subspecies.

KI effects on corrosion inhibition for 1018 steel in acid media using Medicago sativa.

Medicago sativa (M. sativa) extract is a safe and eco-friendly corrosion inhibitor of 1018 steel in acid media. The inhibitor reached a maximum efficiency of 85% by using 500 ppm. In this work, we study the use of KI as an add-on to increase the inhibition efficiency of M. sativa, as well as making the natural inhibitor competitive with the commercial ones. We evaluated the effect of halide ions through the variation of different concentrations of KI and its synergy with the extract of M. sativa as a corrosion inhibitor of carbon steel in 0.5 M sulfuric acid and at different temperatures. The results were obtained through electrochemical techniques such as electrochemical impedance spectroscopy (EIS), potentiodynamic polarization (PDP) curves, and weight loss gravimetric technique. It was found that halide ions increase the inhibition efficiency of M. sativa from 85 to 95% when 5 mM concentration of KI was used. The efficiency of the inhibition increases proportionally with the immersion time but reduces when the temperature increases. The addition of iodide ions (I-) revealed that it exerts a synergistic effect on the inhibition of corrosion with the extract of M. sativa. However, when studying the metal surface using a scanning electron microscope, pitting corrosion was found.

Overexpression of GsZFP1 enhances salt and drought tolerance in transgenic alfalfa (Medicago sativa L.).

GsZFP1 encodes a Cys2/His2-type zinc-finger protein. In our previous study, when GsZFP1 was heterologously expressed in Arabidopsis, the transgenic Arabidopsis plants exhibited enhanced drought and cold tolerance. However, it is still unknown whether GsZFP1 is also involved in salt stress. GsZFP1 is from the wild legume Glycine soja. Therefore, the aims of this study were to further elucidate the functions of the GsZFP1 gene under salt and drought stress in the forage legume alfalfa and to investigate its biochemical and physiological functions under these stress conditions. Our data showed that overexpression of GsZFP1 in alfalfa resulted in enhanced salt tolerance. Under high salinity stress, greater relative membrane permeability and malondialdehyde (MDA) content were observed and more free proline and soluble sugars accumulated in transgenic alfalfa than in the wild-type (WT) plants; in addition, the transgenic lines accumulated less Na(+) and more K(+) in both the shoots and roots. Overexpression of GsZFP1 also enhanced the drought tolerance of alfalfa. The fold-inductions of stress-responsive marker gene expression, including MtCOR47, MtRAB18, MtP5CS, and MtRD2, were greater in transgenic alfalfa than those of WT under drought stress conditions. In conclusion, the transgenic alfalfa plants generated in this study could be used for farming in salt-affected as well as arid and semi-arid areas.