SeedQuant: a deep learning-based tool for assessing stimulant and inhibitor activity on root parasitic seeds

Abstract

Witchweeds (Striga spp.) and broomrapes (Orobanchaceae and Phelipanche spp.) are root parasitic plants that infest many crops in warm and temperate zones, causing enormous yield losses and endangering global food security. Seeds of these obligate parasites require rhizospheric, host-released stimulants to germinate, which opens up possibilities for controlling them by applying specific germination inhibitors or synthetic stimulants that induce lethal germination in host’s absence. To determine their effect on germination, root exudates or synthetic stimulants/inhibitors are usually applied to parasitic seeds in in vitro bioassays, followed by assessment of germination ratios. Although these protocols are very sensitive, the germination recording process is laborious, representing a challenge for researchers and impeding high-throughput screens. Here, we developed an automatic seed census tool to count and discriminate germinated from non-germinated seeds. We combined deep learning, a powerful data-driven framework that can accelerate the procedure and increase its accuracy, for object detection with computer vision latest development based on the Faster R-CNN algorithm. Our method showed an accuracy of 94% in counting seeds of Striga hermonthica and reduced the required time from ˜5 minutes to 5 seconds per image. Our proposed software, SeedQuant, will be of great help for seed germination bioassays and enable high-throughput screening for germination stimulants/inhibitors. ​SeedQuant is an open-source software that can be further trained to count different types of seeds for research purposes.

MultipleXLab: A high-throughput portable live-imaging root phenotyping platform using deep learning and computer vision

“…In addition, we implemented an image segmentation pipeline powered by deep learning to facilitate and accelerate the analysis of numerous multidomain images. This approach has recently received much attention because it provides an attractive solution for fast detection and measurement tasks in complex applications [ 41 – 45 ], providing a basis for automatically measuring phenotypic traits. These tools can perform supervised and unsupervised root segmentation using convolutional neural networks based on classical deep learning architectures.…”

A New Formulation for Strigolactone Suicidal Germination Agents, towards Successful Striga Management

“…On the 11th day, the discs were dried in a laminar flow cabinet and the SL analogs (50 μL) were applied on each disc with various concentrations ranging from 10 −5 M to 10 −11 M. After application, the Striga seeds were induced to germinate in the dark for 24 h at 30 °C. The discs were scanned under a binocular microscope and germinated, and non-germinated seeds were counted by SeedQuant [ 43 ] and germination rate (in %) was calculated.…”

“…Then, 10 mL of MP3 or Nijmegen with EC- and AG formulations at 1.0 μM concentration were added in each Petri plate and sealed with parafilm to incubate in the dark at 30 °C for two-week intervals for up to 12 weeks. On the final week, five glass fiber filter paper discs, containing 50–100 pre-conditioned Striga seeds were added in each plate and incubated at 30 °C for 24 h. The discs were scanned under a binocular microscope and germinated and non-germinated seeds were counted by SeedQuant [ 43 ] and germination rate (in %) was calculated.…”

Protocol for characterizing strigolactones released by plant roots

“…However, SLs are released at extremely low concentrations (∼picoMolar per liter of root exudate), even under phosphate starvation, and are relatively unstable, which makes their quantification difficult ( Boutet-Mercey et al., 2018 ). The protocol below describes specifically and in a stepwise manner: the SL extraction from root exudates of rice ( Wang et al., 2019 , 2020 ) and pearl millet - when cultured in hydroponic and sand system - and their subsequent analysis using (1) the detection and quantification of SLs by LC-MS, as well as (2) the evaluation of their efficacy as seed germination stimulant of the root parasitic plant Striga hermonthica, using SeedQuant ( Braguy et al., 2021 ). Our protocol is also suitable for many other plant species, such as Arabidopsis ( Ablazov et al., 2020 ) and tomato; however, it may need some modifications with respect to the parameters of the MS analysis.…”

“…For complete details on the use and execution of this protocol, please refer to Wang et al. (2019) and Braguy et al. (2021) .…”