Deep learning detection of dynamic exocytosis events in fluorescence TIRF microscopy DOI Creative Commons
Hugo Lachuer, Emmanuel Moebel, Anne‐Sophie Macé

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 12, 2024

Abstract Segmentation and detection of biological objects in fluorescence microscopy is paramount importance cell imaging. Deep learning approaches have recently shown promise to advance, automatize accelerate analysis. However, most the interest has been given segmentation static 2D/3D images whereas dynamic processes obtained from time-lapse acquisitions less explored. Here we adapted DeepFinder, a U-net originally designed for 3D noisy cryo-electron tomography (cryo-ET) data, rare exocytosis events (termed ExoDeepFinder) observed temporal series 2D Total Internal Reflection Fluorescent Microscopy (TIRFM) images. ExoDeepFinder achieved good absolute performances with relatively small training dataset 60 cells/∼12000 events. We rigorously compared deep unsupervised conventional methods literature. outcompeted tested methods, but also exhibited greater plasticity experimental conditions when under drug treatments after changes line or imaged reporter. This robustness unseen did not require re-training demonstrating generalization capability ExoDeepFinder. ExoDeepFinder, as well annotated datasets, were made transparent available through an open-source software Napari plugin can directly be applied custom user data. The apparent detect open new opportunities future deep-learning guided analysis live-cell

Language: Английский

Novel high-content and open-source image analysis tools for profiling mitochondrial morphology in neurological cell models DOI Creative Commons
Marcus Y. Chin, David Joy, Madhuja Samaddar

et al.

SLAS DISCOVERY, Journal Year: 2025, Volume and Issue: unknown, P. 100208 - 100208

Published: Jan. 1, 2025

Language: Английский

Citations

1
Artificial intelligence for life sciences: A comprehensive guide and future trends DOI

Ming Luo,

Wenyu Yang, Long Bai

et al.

The Innovation Life, Journal Year: 2024, Volume and Issue: unknown, P. 100105 - 100105

Published: Jan. 1, 2024

<p>Artificial intelligence has had a profound impact on life sciences. This review discusses the application, challenges, and future development directions of artificial in various branches sciences, including zoology, plant science, microbiology, biochemistry, molecular biology, cell developmental genetics, neuroscience, psychology, pharmacology, clinical medicine, biomaterials, ecology, environmental science. It elaborates important roles aspects such as behavior monitoring, population dynamic prediction, microorganism identification, disease detection. At same time, it points out challenges faced by application data quality, black-box problems, ethical concerns. The are prospected from technological innovation interdisciplinary cooperation. integration Bio-Technologies (BT) Information-Technologies (IT) will transform biomedical research into AI for Science paradigm.</p>

Language: Английский

Citations

7
DeepKymoTracker: A tool for accurate construction of cell lineage trees for highly motile cells DOI Creative Commons
Khelina Fedorchuk, Sarah M. Russell, Kajal Zibaei

et al.

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(2), P. e0315947 - e0315947

Published: Feb. 10, 2025

Time-lapse microscopy has long been used to record cell lineage trees. Successful construction of a tree requires tracking and preserving the identity multiple cells across many images. If single is misidentified all its progeny will be corrupted inferences about heritability may incorrect. Successfully avoiding such errors challenging, however, when studying highly-motile as T lymphocytes which readily change shape from one image next. To address this problem, we developed DeepKymoTracker, pipeline for combined segmentation. Central DeepKymoTracker use seed, marker each transmits information position between sets images during tracking, well segmentation steps. The seed allows 3D convolutional neural network (CNN) detect associate several consecutive in an integrated way, reducing risk poor corrupting identity. was trained extensively on synthetic experimental lymphocyte It benchmarked against five publicly available, automatic analysis tools outperformed them almost respects. software written pure Python freely available. We suggest tool particularly suited suspension, whose fast motion makes assembly difficult.

Language: Английский

Citations

0
Nellie: automated organelle segmentation, tracking and hierarchical feature extraction in 2D/3D live-cell microscopy DOI Creative Commons
Austin E.Y.T. Lefebvre,

Gabriel Sturm,

Ting‐Yu Lin

et al.

Nature Methods, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 27, 2025

Abstract Cellular organelles undergo constant morphological changes and dynamic interactions that are fundamental to cell homeostasis, stress responses disease progression. Despite their importance, quantifying organelle morphology motility remains challenging due complex architectures, rapid movements the technical limitations of existing analysis tools. Here we introduce Nellie, an automated unbiased pipeline for segmentation, tracking feature extraction diverse intracellular structures. Nellie adapts image metadata employs hierarchical segmentation resolve sub-organellar regions, while its radius-adaptive pattern matching enables precise motion tracking. Through a user-friendly Napari-based interface, comprehensive without coding expertise. We demonstrate Nellie’s versatility by unmixing multiple from single-channel data, mitochondrial ionomycin via graph autoencoders characterizing endoplasmic reticulum networks across types time points. This tool addresses critical need in biology providing accessible, dynamics.

Language: Английский

Citations

0
Search for chromosomal instability aiding variants reveal naturally occurring kinetochore gene variants that perturb chromosome segregation DOI Creative Commons
Asifa Islam,

Janeth Catalina Manjarrez-González,

Xinhong Song

et al.

iScience, Journal Year: 2024, Volume and Issue: 27(3), P. 109007 - 109007

Published: Jan. 26, 2024

Chromosomal instability (CIN) is a hallmark of cancers, and CIN-promoting mutations are not fully understood. Here, we report 141 chromosomal aiding variant (CIVa) candidates by assessing the prevalence loss-of-function (LoF) variants in 135 chromosome segregation genes from over 150,000 humans. Unexpectedly, observe both heterozygous homozygous CIVa Astrin SKA3, two evolutionarily conserved kinetochore microtubule-associated proteins essential for segregation. To stratify harmful versus harmless variants, combine live-cell microscopy controlled protein expression. We find naturally occurring p.Q1012∗ as it fails to localize normally induces misalignment missegregation, dominant negative manner. In contrast, p.L7Qfs∗21 generates shorter isoform that localizes functions normally, SKA3 p.Q70Kfs∗7 allows wild-type SKA complex localisation function, revealing distinct resilience mechanisms render these harmless. Thus, present scalable framework predict CIVa, provide insight into compensate CIVa.

Language: Английский

Citations

3
Multi-SpinX: An advanced framework for automated tracking of mitotic spindles and kinetochores in multicellular environments DOI Creative Commons
Binghao Chai, Christoforos Efstathiou, Muhammad Choudhury

et al.

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 186, P. 109626 - 109626

Published: Jan. 22, 2025

Language: Английский

Citations

0
Advancing antibiotic discovery with bacterial cytological profiling: a high-throughput solution to antimicrobial resistance DOI Creative Commons

Jhonatan Salgado,

James Rayner,

Nikola Ojkic

et al.

Frontiers in Microbiology, Journal Year: 2025, Volume and Issue: 16

Published: Feb. 13, 2025

Developing new antibiotics poses a significant challenge in the fight against antimicrobial resistance (AMR), critical global health threat responsible for approximately 5 million deaths annually. Finding classes of that are safe, have acceptable pharmacokinetic properties, and appropriately active pathogens is lengthy expensive process. Therefore, high-throughput platforms needed to screen large libraries synthetic natural compounds. In this review, we present bacterial cytological profiling (BCP) as rapid, scalable, cost-effective method identifying antibiotic mechanisms action. Notably, BCP has proven its potential drug discovery, demonstrated by identification cellular target spirohexenolide A methicillin-resistant Staphylococcus aureus . We application different organisms discuss BCP’s advantages, limitations, improvements. Furthermore, highlight studies utilized investigate listed Bacterial Priority Pathogens List 2024 identify whose profiles missing. also explore most recent artificial intelligence deep learning techniques could enhance analysis data generated BCP, potentially advancing our understanding discovery novel druggable pathways.

Language: Английский

Citations

0
Intelligent microscopic imaging system based on microwell array chip for high-throughput analysis of single-cell heterogeneity DOI

Lingzhi Ye,

Rui Deng,

Aiping Zhi

et al.

Microchemical Journal, Journal Year: 2025, Volume and Issue: unknown, P. 113136 - 113136

Published: Feb. 1, 2025

Language: Английский

Citations

0
Data stewardship and curation practices in AI-based genomics and automated microscopy image analysis for high-throughput screening studies: promoting robust and ethical AI applications DOI Creative Commons

Asefa Adimasu Taddese,

Assefa Chekole Addis,

Bjorn T. Tam

et al.

Human Genomics, Journal Year: 2025, Volume and Issue: 19(1)

Published: Feb. 23, 2025

Language: Английский

Citations

0
Deep learning image analysis for continuous single-cell imaging of dynamic processes in Plasmodium falciparum-infected erythrocytes DOI Creative Commons

Sophia M. Frangos,

Sebastian Damrich,

Daniele Gueiber

et al.

Communications Biology, Journal Year: 2025, Volume and Issue: 8(1)

Published: March 25, 2025

Abstract Continuous high-resolution imaging of the disease-mediating blood stages human malaria parasite Plasmodium falciparum faces challenges due to photosensitivity, small size, and anisotropy large refractive index host erythrocytes. Previous studies often relied on snapshot galleries from multiple cells, limiting investigation dynamic cellular processes. We present a workflow enabling continuous, single-cell monitoring live parasites throughout 48-hour intraerythrocytic life cycle with high spatial temporal resolution. This approach integrates label-free, three-dimensional differential interference contrast fluorescence using an Airyscan microscope, automated cell segmentation through pre-trained deep-learning algorithms, 3D rendering for visualization time-resolved analyses. As proof concept, we applied this study knob-associated histidine-rich protein (KAHRP) export into erythrocyte compartment its clustering beneath plasma membrane. Our methodology opens avenues in-depth exploration processes in parasites, providing valuable tool further investigations.

Language: Английский

Citations

0