Unbiased Complete Estimation of Chloroplast Number in Plant Cells Using Deep Learning Methods

Su, Q.; Liu, L.; Hu, Z.; Wang, T.; Wang, H.; Guo, Q.; Liao, X.; Dong, Z.; Yang, S.; Liu, N.; Zhao, Q.

doi:10.1101/2023.12.17.572064

Home/Archive/bioRxiv

bioRxiv · 10.1101/2023.12.17.572064

Unbiased Complete Estimation of Chloroplast Number in Plant Cells Using Deep Learning Methods

Su, Q.·Liu, L.·Hu, Z.·Wang, T.·Wang, H.·Guo, Q.·Liao, X.·Dong, Z.·Yang, S.·Liu, N.·Zhao, Q.

View original source ↗Export metadata ↓

Abstract

Chloroplasts are essential organelles in plants that are involved in plant development and photosynthesis. Accurate quantification of chloroplast numbers is important for understanding the status and type of plant cells, as well as assessing photosynthetic potential and efficiency. Traditional methods of counting chloroplasts using microscopy are time-consuming and face challenges such as the possibility of missing out-of-focus samples or double counting when adjusting the focal position. Here, we developed an innovative approach called Detecting- and-Counting-chloroplasts (D&Cchl) for automated detection and counting of chloroplasts. This approach utilizes a deep-learning-based object detection algorithm called You-Only-Look-Once (YOLO), along with the Intersection Over Union (IOU) strategy. The application of D&Cchl has shown excellent performance in accurately identifying and quantifying chloroplasts. This holds true when applied to both a single image and a three-dimensional (3D) structure composed of a series of images. Furthermore, by integrating Cellpose, a cell-segmentation tool, we were able to successfully perform single-cell 3D chloroplast counting. Compared to manual counting methods, this approach improved the accuracy of detection and counting to over 95%. Together, our work not only provides an efficient and reliable tool for accurately analyzing the status of chloroplasts, enhancing our understanding of plant photosynthetic cells and growth characteristics, but also makes a significant contribution to the convergence of botany and deep learning. One-sentence summaryThis deep learning-based approach enables the accurate complete detection and counting of chloroplasts in 3D single cells using microscopic image stacks, and showcases a successful example of utilizing deep learning methods to analyze subcellular spatial information in plant cells. The authors responsible for distribution of materials integral to the findings presented in this article in accordance with the policy described in the Instructions for Authors (https://academic.oup.com/plcell/) is: Zhao Dong (dongzhao@hebeu.edu.cn), Shaokai Yang, (shaokai1@ualberta.ca), Ningjing Liu (liuningjing1@yeah.net), and Qiong Zhao (qzhao@bio.ecnu.edu.cn).

Explore related subjects

cell biology Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Su, Q., Liu, L., Hu, Z., Wang, T., Wang, H., Guo, Q., Liao, X., Dong, Z., Yang, S., Liu, N., Zhao, Q.. 2023-12-18. Unbiased Complete Estimation of Chloroplast Number in Plant Cells Using Deep Learning Methods. https://doi.org/10.1101/2023.12.17.572064

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

OPN3 mediates retinal-dependent lipofuscin accumulation and its loss sensitizes keratinocytes to blue-light-induced proteomic remodeling

Lipofuscin is a blue-light-absorbing pigment that contributes to oxidative damage. Whether all-trans retinal (atRAL) contributes to its formation in response to light remains unclear. We asked whether blue-light photosensitization of atRAL promotes lipofuscin accumulation in human keratinocytes and whether this depends on Opsin 3 (OPN3). Blue-light excitation of atRAL reduced mitochondrial and lysosomal viability, impaired autophagic flux, and increased lipofuscin. OPN3 knockdown significantly reduced this accumulation. Label-free data-independent acquisition (DIA) proteomics showed that OPN3 acts at three levels. In the dark, OPN3 loss altered proteome networks associated with autophagy, apoptosis, and interferon-related responses. Under blue light, control cells activated a stress-adaptive program spanning inflammatory regulation, lipid metabolism, and mitochondrial function, which atRAL strongly amplified. This molecular signature, including induction of cellular respiration and ATP-production proteins, was largely absent when OPN3 was silenced. Respirometry showed that blue light suppressed oxygen consumption in both lines over the first 24 h, but a faster recovery in OPN3 knockdown cells at 48 and 72 h was observed. Together, these data define three functions of OPN3: maintaining the basal proteome in a blue-light-independent manner, enabling the adaptive blue-light response, and enabling retinal-dependent lipofuscin formation in keratinocytes.

cell biology↗

bioRxiv2026

Uncoupling microtubule lifetime, stability and post-translational modifications.

Microtubules (MTs) undergo continuous cycles of growth and disassembly. Because the transitions between these states are stochastic, MT age varies widely within a population. As MTs age, they are thought to accumulate post-translational modifications (PTMs) that, directly or indirectly, enhance their stability and thereby extend their lifetime. The rare MTs that withstand prolonged exposure to destabilizing drugs such as nocodazole (NZ) are indeed enriched in PTMs; yet the relationships between MT age, PTMs and stability remain unclear. Using microinjection of labelled tubulin, we measured microtubule network turnover in immortalized mouse embryonic fibroblasts. Half of the network was renewed within 3 minutes and 80% within 10 minutes, while approximately 5% of microtubules persisted for more than 20 minutes. These dynamics were comparable in quiescent and senescent cells, although the fraction of slowly renewing or non-renewing microtubules rose to 20% in senescent cells. Unexpectedly, neither the amount of PTMs (acetylation and detyrosination) nor resistance to NZ increased with MT age, and resistance to NZ was independent of these PTMs. Degrees of acetylation and detyrosination should therefore not be taken as readouts of MT age or stability. Because these PTMs do not accumulate on MTs over time, the chemical modification of polymerized tubulin is likely more reversible and dynamic than previously assumed.

cell biology↗

bioRxiv2026

Evidence of complete myofibril remodeling after severe damage in adult Drosophila.

Muscle function depends on the ability of myofibrils to withstand and repair mechanical damage, yet how adult muscles remodel damaged myofibrils remains poorly understood. Here, we establish a Drosophila model that allows the induction and longitudinal visualization of extensive myofibril damage and recovery in intact adult femur muscles. Sustained muscle depolarization caused extensive disruption of myofibrillar organization, with severe damage characterized by near-complete loss of Z-disc structures. Remarkably, myofibril architecture and muscle function were largely restored within days, revealing a substantial capacity for myofibril reconstruction in adult femur muscles. We identified two distinct states of myofibril damage, mild and severe, with mild damage appearing before severe damage during aging, suggesting a progressive process of myofibril deterioration and repair failure. We further show that filamins mechanosignaling is required for efficient myofibril remodeling. Following damage, wild-type filamin redistributes from the Z-disc and accumulates outside the myofibrils, whereas constitutively open filamin remains Z-disc-associated and constitutively closed filamin redistributes but results in increased damage and impaired recovery. These findings suggest that effective repair requires dynamic transitions between filamin conformational states and that filamin redistribution is an active component of the damage response rather than simply a consequence of muscle injury. During aging, filamin progressively redistributes from the Z-disc and muscle damage accumulates, with severe damage increasing after the appearance of mild damage. Together, our findings reveal a previously unappreciated capacity of adult muscle to reassemble damaged myofibrils and identify filamin mechanosignaling as a key component of this repair process, providing a framework for understanding how defective mechanosensing may contribute to age-related muscle decline and muscle disease.

cell biology↗