Abstract
Fluorescence microscopy is common in bacteria-plant interaction studies. However, strong autofluorescence from plant tissues impedes in vivo studies on endophytes tagged with fluorescent proteins. To solve this problem, we developed a deep-learning-based approach to eliminate plant autofluorescence from fluorescence microscopy images, tested for the model endophyte Azoarcus olearius BH72 colonizing Oryza sativa roots. Micrographs from three channels (tdTomato for gene expression, green fluorescent protein (GFP) and AutoFluorescence (AF)) were processed by a neural network based approach, generating images that simulate the background autofluorescence in the tdTomato channel. After subtracting the model-generated signals from each pixel in the genuine channel, the autofluorescence in the tdTomato channel was greatly reduced or even removed. The deep-learning-based approach can be applied for fluorescence detection and quantification, exemplified by a weakly expressed, a cell-density modulated and a nitrogen-fixation gene in A. olearius. A transcriptional nifH::tdTomato fusion demonstrated stronger induction of nif genes inside roots than outside, suggesting extension of the rhizosphere effect for diazotrophs into the endorhizosphere. The pre-trained convolutional neural network model is easily applied to process other images of the same plant tissues with the same settings. This study showed the high potential of deep-learning-based approaches in image processing. With proper training data and strategies, autofluorescence in other tissues or materials can be removed for broad applications.
Abstract from the paper’s OpenAlex record; open copy licensed other-oa. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 4
Claim · model-written summary
The approach greatly reduced or removed tdTomato-channel autofluorescence in rice-root images.
- Taxon
- Oryza sativa
Oryza sativae1 - Interactor
- Azoarcus olearius BH72Azoarcus oleariuse1symbiont
- Outcome
- autofluorescence in the tdTomato channele0
- Direction
- greatly reduced or even removede0
Not reportedComparatorValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the autofluorescence in the tdTomato channel was greatly reduced or even removed”
e1“Azoarcus olearius BH72 colonizing Oryza sativa roots”
Claim · model-written summary
The approach enabled fluorescence detection and quantification for three bacterial gene expression examples.
- Taxon
- Oryza sativaOryza sativae1
- Interactor
- A. oleariusAzoarcus oleariuse0symbiont
- Outcome
- fluorescence detection and quantificatione0
Not reportedComparatorValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The deep-learning-based approach can be applied for fluorescence detection and quantification, exemplified by a weakly expressed, a cell-density modulated and a nitrogen-fixation gene in A. olearius.”
e1“Azoarcus olearius BH72 colonizing Oryza sativa roots”
Claim · model-written summary
nif genes were induced more strongly inside rice roots than outside.
- Taxon
- Oryza sativaOryza sativae1
- Organ / stage
- rootse0
- Interactor
- Azoarcus olearius BH72Azoarcus oleariuse1symbiont
- Gene
- nif genese0
- Outcome
- induction of nif genese0
- Direction
- strongere0
- Comparator
- outsidee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“A transcriptional nifH::tdTomato fusion demonstrated stronger induction of nif genes inside roots than outside”
e1“Azoarcus olearius BH72 colonizing Oryza sativa roots”
Claim · model-written summary
The pretrained model can process other images of the same tissues under the same settings.
- Taxon
- Oryza sativaOryza sativae1
- Outcome
- process other images of the same plant tissuese0
- Qualifier
- with the same settingse0
Not reportedComparatorValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The pre-trained convolutional neural network model is easily applied to process other images of the same plant tissues with the same settings”
e1“Azoarcus olearius BH72 colonizing Oryza sativa roots”