An official website of the United States government
Screening mutant libraries (MLs) of bacteria for strains with specific phenotypes is often a slow and laborious process that requires assessment of tens of thousands of individual cell colonies after plating and culturing on solid media. In this report, we develop a three-dimensional, photodegradable hydrogel interface designed to dramatically improve the throughput of ML screening by combining high-density cell culture with precision extraction and the recovery of individual, microscale colonies for follow-up genetic and phenotypic characterization. ML populations are first added to a hydrogel precursor solution consisting of polyethylene glycol (PEG) o-nitrobenzyl diacrylate and PEG-tetrathiol macromers, where they become encapsulated into 13 μm thick hydrogel layers at a density of 90 cells/mm^2, enabling parallel monitoring of 2.8 × 10^4 mutants per hydrogel. Encapsulated cells remain confined within the elastic matrix during culture, allowing one to track individual cells that grow into small, stable microcolonies (45 ± 4 μm in diameter) over the course of 72 h. Colonies with rare growth profiles can then be identified, extracted, and recovered from the hydrogel in a sequential manner and with minimal damage using a high-resolution, 365 nm patterned light source. The light pattern can be varied to release motile cells, cellular aggregates, or microcolonies encapsulated in protective PEG coatings. To access the benefits of this approach for ML screening, an Agrobacterium tumefaciens C58 transposon ML was screened for rare, resistant mutants able to grow in the presence of cell free culture media from Rhizobium rhizogenes K84, a well-known inhibitor of C58 cell growth. Subsequent genomic analysis of rare cells (9/28,000) that developed into microcolonies identified that seven of the resistant strains had mutations in the acc locus of the Ti plasmid. These observations are consistent with past research demonstrating that the disruption of this locus confers resistance to agrocin 84, an inhibitory molecule produced by K84. The high-throughput nature of the screen allows the A. tumefaciens genome (approximately 5.6 Mbps) to be screened to saturation in a single experimental trial, compared to hundreds of platings required by conventional plating approaches. As a miniaturized version of the gold-standard plating assay, this materials-based approach offers a simple, inexpensive, and highly translational screening technique that does not require microfluidic devices or complex liquid handling steps. The approach is readily adaptable to other applications that require isolation and study of rare or phenotypically pure cell populations.
more »
« less
This content will become publicly available on February 1, 2026
Machine learning models for segmentation and classification of cyanobacterial cells
Abstract Timelapse microscopy has recently been employed to study the metabolism and physiology of cyanobacteria at the single-cell level. However, the identification of individual cells in brightfield images remains a significant challenge. Traditional intensity-based segmentation algorithms perform poorly when identifying individual cells in dense colonies due to a lack of contrast between neighboring cells. Here, we describe a newly developed software package called Cypose which uses machine learning (ML) models to solve two specific tasks: segmentation of individual cyanobacterial cells, and classification of cellular phenotypes. The segmentation models are based on the Cellpose framework, while classification is performed using a convolutional neural network named Cyclass. To our knowledge, these are the first developed ML-based models for cyanobacteria segmentation and classification. When compared to other methods, our segmentation models showed improved performance and were able to segment cells with varied morphological phenotypes, as well as differentiate between live and lysed cells. We also found that our models were robust to imaging artifacts, such as dust and cell debris. Additionally, the classification model was able to identify different cellular phenotypes using only images as input. Together, these models improve cell segmentation accuracy and enable high-throughput analysis of dense cyanobacterial colonies and filamentous cyanobacteria.
more »
« less
- Award ID(s):
- 2054085
- PAR ID:
- 10599426
- Publisher / Repository:
- Springer
- Date Published:
- Journal Name:
- Photosynthesis Research
- Volume:
- 163
- Issue:
- 1
- ISSN:
- 0166-8595
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Cellular biomechanics plays a critical role in cancer metastasis and tumor progression. Existing studies on cancer cell biomechanics are mostly conducted in flat 2D conditions, where cells’ behavior can differ considerably from those in 3D physiological environments. Despite great advances in developing 3D in vitro models, probing cellular elasticity in 3D conditions remains a major challenge for existing technologies. In this work, optical Brillouin microscopy is utilized to longitudinally acquire mechanical images of growing cancerous spheroids over the period of 8 days. The dense mechanical mapping from Brillouin microscopy enables us to extract spatially resolved and temporally evolving mechanical features that were previously inaccessible. Using an established machine learning algorithm, it is demonstrated that incorporating these extracted mechanical features significantly improves the classification accuracy of cancer cells, from 74% to 95%. Building on this finding, a deep learning pipeline capable of accurately differentiating cancerous spheroids from normal ones solely using Brillouin images have been developed, suggesting the mechanical features of cancer cells can potentially serve as a new biomarker in cancer classification and detection.more » « less
-
We present a new annotated microscopic cellular image dataset to improve the effectiveness of machine learning methods for cellular image analysis. Cell counting is an important step in cell analysis. Typically, domain experts manually count cells in a microscopic image. Automated cell counting can potentially eliminate this tedious, time-consuming process. However, a good, labeled dataset is required for training an accurate machine learning model. Our dataset includes microscopic images of cells, and for each image, the cell count and the location of individual cells. The data were collected as part of an ongoing study investigating the potential of electrical stimulation to modulate stem cell differentiation and possible applications for neural repair. Compared to existing publicly available datasets, our dataset has more images of cells stained with more variety of antibodies (protein components of immune responses against invaders) typically used for cell analysis. The experimental results on this dataset indicate that none of the five existing models under this study are able to achieve sufficiently accurate count to replace the manual methods. The dataset is available at https://figshare.com/articles/dataset/Dataset/21970604.more » « less
-
Xu, Jinbo (Ed.)Abstract Motivation Motions of transmembrane receptors on cancer cell surfaces can reveal biophysical features of the cancer cells, thus providing a method for characterizing cancer cell phenotypes. While conventional analysis of receptor motions in the cell membrane mostly relies on the mean-squared displacement plots, much information is lost when producing these plots from the trajectories. Here we employ deep learning to classify breast cancer cell types based on the trajectories of epidermal growth factor receptor (EGFR). Our model is an artificial neural network trained on the EGFR motions acquired from six breast cancer cell lines of varying invasiveness and receptor status: MCF7 (hormone receptor positive), BT474 (HER2-positive), SKBR3 (HER2-positive), MDA-MB-468 (triple negative, TN), MDA-MB-231 (TN) and BT549 (TN). Results The model successfully classified the trajectories within individual cell lines with 83% accuracy and predicted receptor status with 85% accuracy. To further validate the method, epithelial–mesenchymal transition (EMT) was induced in benign MCF10A cells, noninvasive MCF7 cancer cells and highly invasive MDA-MB-231 cancer cells, and EGFR trajectories from these cells were tested. As expected, after EMT induction, both MCF10A and MCF7 cells showed higher rates of classification as TN cells, but not the MDA-MB-231 cells. Whereas deep learning-based cancer cell classifications are primarily based on the optical transmission images of cell morphology and the fluorescence images of cell organelles or cytoskeletal structures, here we demonstrated an alternative way to classify cancer cells using a dynamic, biophysical feature that is readily accessible. Availability and implementation A python implementation of deep learning-based classification can be found at https://github.com/soonwoohong/Deep-learning-for-EGFR-trajectory-classification. Supplementary information Supplementary data are available at Bioinformatics online.more » « less
-
Abstract This paper presents a method for time-lapse 3D cell analysis. Specifically, we consider the problem of accurately localizing and quantitatively analyzing sub-cellular features, and for tracking individual cells from time-lapse 3D confocal cell image stacks. The heterogeneity of cells and the volume of multi-dimensional images presents a major challenge for fully automated analysis of morphogenesis and development of cells. This paper is motivated by the pavement cell growth process, and building a quantitative morphogenesis model. We propose a deep feature based segmentation method to accurately detect and label each cell region. An adjacency graph based method is used to extract sub-cellular features of the segmented cells. Finally, the robust graph based tracking algorithm using multiple cell features is proposed for associating cells at different time instances. We also demonstrate the generality of our tracking method on C. elegans fluorescent nuclei imagery. Extensive experiment results are provided and demonstrate the robustness of the proposed method. The code is available on and the method is available as a service through the BisQue portal.more » « less
