skip to main content

Explore Research Products in the NSF-PAR

Title: A deep learning approach to track Arabidopsis seedlings’ circumnutation from time-lapse videos
Abstract Background

Circumnutation (Darwin et al., Sci Rep 10(1):1–13, 2000) is the side-to-side movement common among growing plant appendages but the purpose of circumnutation is not always clear. Accurately tracking and quantifying circumnutation can help researchers to better study its underlying purpose.

 Results

In this paper, a deep learning-based model is proposed to track the circumnutating flowering apices in the plant Arabidopsis thaliana from time-lapse videos. By utilizing U-Net to segment the apex, and combining it with the model update mechanism, pre- and post- processing steps, the proposed model significantly improves the tracking time and accuracy over other baseline tracking methods. Additionally, we evaluate the computational complexity of the proposed model and further develop a method to accelerate the inference speed of the model. The fast algorithm can track the apices in real-time on a computer without a dedicated GPU.

 Conclusion

We demonstrate that the accuracy of tracking the flowering apices in the plant Arabidopsis thaliana can be improved with our proposed deep learning-based model in terms of both the racking success rate and the tracking error. We also show that the improvement in the tracking accuracy is statistically significant. The time-lapse video dataset of Arabidopsis is also provided which can be used for future studies on Arabidopsis in various takes.

  more » « less
NSF-PAR ID:
10399159
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
Springer Science + Business Media
Date Published:
Journal Name:
Plant Methods
Volume:
19
Issue:
1
ISSN:
1746-4811
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ( , Plant Methods)
    Abstract Background

    The plant hormone auxin plays a central role in regulation of plant growth and response to environmental stimuli. Multiple pathways have been proposed for biosynthesis of indole-3-acetic acid (IAA), the primary auxin in a number of plant species. However, utilization of these different pathways under various environmental conditions and developmental time points remains largely unknown.

     Results

    Monitoring incorporation of stable isotopes from labeled precursors into proposed intermediates provides a method to trace pathway utilization and characterize new biosynthetic routes to auxin. These techniques can be aided by addition of chemical inhibitors to target specific steps or entire pathways of auxin synthesis.

     Conclusions

    Here we describe techniques for pathway analysis inArabidopsis thalianaseedlings using multiple stable isotope-labeled precursors and chemical inhibitors coupled with highly sensitive liquid chromatography-mass spectrometry (LC–MS) methods. These methods should prove to be useful to researchers studying routes of IAA biosynthesis in vivo in a variety of plant tissues.

     
    more » « less
  2. ; ; ; ( , Rapid Prototyping Journal)
    Purpose

    The purpose of this study is to develop a deep learning framework for additive manufacturing (AM), that can detect different defect types without being trained on specific defect data sets and can be applied for real-time process control.

     Design/methodology/approach

    This study develops an explainable artificial intelligence (AI) framework, a zero-bias deep neural network (DNN) model for real-time defect detection during the AM process. In this method, the last dense layer of the DNN is replaced by two consecutive parts, a regular dense layer denoted (L1) for dimensional reduction, and a similarity matching layer (L2) for equal weight and non-biased cosine similarity matching. Grayscale images of 3D printed samples acquired during printing were used as the input to the zero-bias DNN.

     Findings

    This study demonstrates that the approach is capable of successfully detecting multiple types of defects such as cracks, stringing and warping with high accuracy without any prior training on defective data sets, with an accuracy of 99.5%.

     Practical implications

    Once the model is set up, the computational time for anomaly detection is lower than the speed of image acquisition indicating the potential for real-time process control. It can also be used to minimize manual processing in AI-enabled AM.

     Originality/value

    To the best of the authors’ knowledge, this is the first study to use zero-bias DNN, an explainable AI approach for defect detection in AM.

     
    more » « less
  3. ; ; ; ; ; ( , Current Protocols)
    Abstract

    The localization of a protein provides important information about its biological functions. The visualization of proteins by immunofluorescence has become an essential approach in cell biology. Here, we describe an easy‐to‐follow immunofluorescence protocol to localize proteins in whole‐mount tissues of maize (Zea mays) and Arabidopsis. We present the whole‐mount immunofluorescence procedure using maize ear primordia and Arabidopsis inflorescence apices as examples, followed by tips and suggestions for each step. In addition, we provide a supporting protocol to describe the use of an ImageJ plug‐in to analyze colocalization. This protocol has been optimized to observe proteins in 2‐5 mm maize ear primordia or in developing Arabidopsis inflorescence apices; however, it can be used as a reference to perform whole‐mount immunofluorescence in other plant tissues and species. © 2021 Wiley Periodicals LLC.

    Basic Protocol: Whole‐mount immunofluorescence for maize and Arabidopsis shoot apices

    Support Protocol: Measure colocalization by JACoP plugin in ImageJ

     
    more » « less
  4. ; ; ; ( , Theoretical and Applied Genetics)
    Abstract Key message

    A population of lettuce that segregated for photoperiod sensitivity was planted under long-day and short-day conditions. Genetic mapping revealed two distinct sets of QTLs controlling daylength-independent and photoperiod-sensitive flowering time.

     Abstract

    The molecular mechanism of flowering time regulation in lettuce is of interest to both geneticists and breeders because of the extensive impact of this trait on agricultural production. Lettuce is a facultative long-day plant which changes in flowering time in response to photoperiod. Variations exist in both flowering time and the degree of photoperiod sensitivity among accessions of wild (Lactuca serriola) and cultivated (L. sativa) lettuce. An F6population of 236 recombinant inbred lines (RILs) was previously developed from a cross between a late-flowering, photoperiod-sensitiveL. serriolaaccession and an early-flowering, photoperiod-insensitiveL. sativaaccession. This population was planted under long-day (LD) and short-day (SD) conditions in a total of four field and screenhouse trials; the developmental phenotype was scored weekly in each trial. Using genotyping-by-sequencing (GBS) data of the RILs, quantitative trait loci (QTL) mapping revealed five flowering time QTLs that together explained more than 20% of the variation in flowering time under LD conditions. Using two independent statistical models to extract the photoperiod sensitivity phenotype from the LD and SD flowering time data, we identified an additional five QTLs that together explained more than 30% of the variation in photoperiod sensitivity in the population. Orthology and sequence analysis of genes within the nine QTLs revealed potential functional equivalents in the lettuce genome to the key regulators of flowering time and photoperiodism,FDandCONSTANS, respectively, in Arabidopsis.

     
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al ( , Plant Direct)
    Abstract

    Plant responses to the environment are shaped by external stimuli and internal signaling pathways. In both the model plantArabidopsis thaliana(Arabidopsis) and crop species, circadian clock factors are critical for growth, flowering, and circadian rhythms. Outside ofArabidopsis,however, little is known about the molecular function of clock gene products. Therefore, we sought to compare the function ofBrachypodium distachyon(Brachypodium) andSetaria viridis(Setaria) orthologs ofEARLY FLOWERING3,a key clock gene inArabidopsis. To identify both cycling genes and putativeELF3functional orthologs inSetaria, a circadianRNA‐seq dataset and online query tool (Diel Explorer) were generated to explore expression profiles ofSetariagenes under circadian conditions. The function ofELF3orthologs fromArabidopsis, Brachypodium,andSetariawas tested for complementation of anelf3mutation inArabidopsis. We find that both monocot orthologs were capable of rescuing hypocotyl elongation, flowering time, and arrhythmic clock phenotypes. Using affinity purification and mass spectrometry, our data indicate that BdELF3 and SvELF3 could be integrated into similar complexesin vivoas AtELF3. Thus, we find that, despite 180 million years of separation,BdELF3andSvELF3can functionally complement loss ofELF3at the molecular and physiological level.

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email