Rapid assessment of heavy metal accumulation capability of Sedum alfredii using hyperspectral imaging and deep learning.

Hyperaccumulators are the material basis and key to the phytoremediation of heavy metal contaminated soils. Conventional methods for screening hyperaccumulators are highly dependent on the time- and labor-consuming sampling and chemical analysis. In this study, a novel spectral approach assisted with multi-task deep learning was proposed to streamline accumulating ecotype screening, heavy metal stress discrimination, and heavy metals quantification in plants. The significant Cd/Zn co-hyperaccumulator Sedum alfredii and its non-accumulating ecotype were stressed by Cd, Zn, and Pb. Spectral images of leaves were rapidly acquired by hyperspectral imaging. The self-designed deep learning architecture was composed of a shallow network (ENet) for accumulating ecotype identification, and a multi-task network (HMNet) for heavy metal stress type and accumulation prediction simultaneously. To further assess the robustness of the networks, they were compared with conventional machine learning models (i.e., partial least squares (PLS) and support vector machine (SVM)) on a series of evaluation metrics of classification, multi-label classification, and regression. S. alfredii with heavy metals accumulation capability was identified by ENet with 100 % accuracy. HMNet reduced overfitting and outperformed machine learning models with the average exact match ratio (EMR) of heavy metal stress discrimination increased by 7.46 %, and residual prediction deviations (RPD) of heavy metal concentrations prediction increased by 53.59 %. The method succeeded in rapidly and accurately discriminating heavy metal stress with EMRs over 91 % and accuracies over 96 %, and in predicting heavy metals accumulation with an average RPD of 3.29 for Zn, 2.57 for Cd, and 2.53 for Pb, indicating the satisfactory practicability and potential for sensing heavy metals accumulation. This study provides a relatively novel spectral method to facilitate hyperaccumulator screening and heavy metals accumulation prediction in the phytoremediation process.

Potentiation effect of the AI-2 signaling molecule on postharvest disease control of pear and loquat by Bacillus amyloliquefaciens and its mechanism.

An autoinducer-2 (AI-2) signaling molecule from Bacillus was synthesized, and its mechanism on the biofilm formation and biocontrol ability of B. amyloliquefaciens was verified in vitro and in vivo. The 16S/ITS amplicon sequencing was used to analyze the effect of B. amyloliquefaciens B4 with or without AI-2 on the microflora of pears during storage. The results showed that B. amyloliquefaciens B4 secreted AI-2, which promoted biofilm formation. Additionally, AI-2 at a concentration of 40 µmol/L enhanced the biocontrol ability of B. amyloliquefaciens B4 on postharvest pear and loquat fruits. Finally, amplicon sequencing demonstrated that the addition of AI-2 increased the abundance of B. amyloliquefaciens B4 in fruit by stimulating the growth and biofilm formation of this bacterium.

Biofilm: New insights in the biological control of fruits with Bacillus amyloliquefaciens B4.

Biofilms are sessile microbial communities growing on surfaces, which are encased in some self-produced extracellular material. Beneficial biofilm could be widely used in agriculture, food, medicine, environment and other fields. As an ideal biocontrol agent, Bacillus amyloliquefaciens B4 can form a strong biofilm under static conditions. In this study, we screened out metal compounds that enhanced or inhibited the biofilm formation ability of B4, established the relationship between the biofilm of B4 strain and its postharvest biocontrol effect, and explored the regulation of metal compounds on the biofilm formation. The results showed 0.5 mmol L-1 ferric chloride could enhance the biofilm formation and strengthen the antifungal effect of B4, indicating that there was a positive relationship between the growth of biofilm and its biocontrol effect. The enhanced biofilm had a certain biocontrol effect on different fruit, including peach, loquat, Kyoho grape and cherry tomato. Furthermore, the expression of degU and tasA was affected by metal ion treatment, which meant the genes might be essential for the biofilm formation of B4. Our findings suggested that biofilm of B. amyloliquefaciens played an essential role in the process of biocontrol and it might be a novel strategy for managing postharvest fruit decay.