scholarly journals Label-free prediction of Cell Painting from brightfield images

2021 ◽  
Author(s):  
Jan Oscar Cross-Zamirski ◽  
Elizabeth Mouchet ◽  
Guy Williams ◽  
Carola-Bibiane Schönlieb ◽  
Riku Turkki ◽  
...  
Keyword(s):  
Pearson Correlation ◽  
Ground Truth ◽  
Free Cell ◽  
Label Free ◽  
Biological Interest ◽  
Genetic Perturbations ◽  
Toxicity Analysis ◽  
Model Training ◽  
Downstream Analysis ◽  
Cellular Components

Cell Painting is a high-content image-based assay which can reveal rich cellular morphology and is applied in drug discovery to predict bioactivity, assess toxicity and understand diverse mechanisms of action of chemical and genetic perturbations. In this study, we investigate label-free Cell Painting by predicting the five fluorescent Cell Painting channels from paired brightfield z-stacks using deep learning models. We train and validate the models with a dataset representing 1000s of pan-assay interference compounds sampled from 17 unique batches. The model predictions are evaluated using a test set from two additional batches, treated with compounds comprised from a publicly available phenotypic set. In addition to pixel-level evaluation, we process the label-free Cell Painting images with a segmentation-based feature-extraction pipeline to understand whether the generated images are useful in downstream analysis. The mean Pearson correlation coefficient (PCC) of the images across all five channels is 0.84. Without actually incorporating these features into the model training we achieved a mean correlation of 0.45 from the features extracted from the images. Additionally we identified 30 features which correlated greater than 0.8 to the ground truth. Toxicity analysis on the label-free Cell Painting resulted a sensitivity of 62.5% and specificity of 99.3% on images from unseen batches. Additionally, we provide a breakdown of the feature profiles by channel and feature type to understand the potential and limitation of the approach in morphological profiling. Our findings demonstrate that label-free Cell Painting has potential above the improved visualization of cellular components, and it can be used for downstream analysis. The findings also suggest that label-free Cell Painting could allow for repurposing the imaging channels for other non-generic fluorescent stains of more targeted biological interest, thus increasing the information content of the assay.

Label-free, mass-sensitive single-molecule imaging using interferometric scattering microscopy

2020 ◽  
Author(s):  
Nikolas Hundt
Keyword(s):  
Single Molecule ◽  
Cellular Systems ◽  
Single Molecule Imaging ◽  
Label Free ◽  
Measurement Sensitivity ◽  
Mass Distributions ◽  
Quantitative Measurements ◽  
Contrast Mechanism ◽  
Cellular Components ◽  
Scattering Signal

Abstract Single-molecule imaging has mostly been restricted to the use of fluorescence labelling as a contrast mechanism due to its superior ability to visualise molecules of interest on top of an overwhelming background of other molecules. Recently, interferometric scattering (iSCAT) microscopy has demonstrated the detection and imaging of single biomolecules based on light scattering without the need for fluorescent labels. Significant improvements in measurement sensitivity combined with a dependence of scattering signal on object size have led to the development of mass photometry, a technique that measures the mass of individual molecules and thereby determines mass distributions of biomolecule samples in solution. The experimental simplicity of mass photometry makes it a powerful tool to analyse biomolecular equilibria quantitatively with low sample consumption within minutes. When used for label-free imaging of reconstituted or cellular systems, the strict size-dependence of the iSCAT signal enables quantitative measurements of processes at size scales reaching from single-molecule observations during complex assembly up to mesoscopic dynamics of cellular components and extracellular protrusions. In this review, I would like to introduce the principles of this emerging imaging technology and discuss examples that show how mass-sensitive iSCAT can be used as a strong complement to other routine techniques in biochemistry.

Label-free cell phenotypic study of opioid receptors and discovery of novel mu opioid ligands from natural products

2021 ◽  
Vol 270 ◽  
pp. 113872
Author(s):  
Tao Hou ◽  
Fangfang Xu ◽  
Xingrong Peng ◽  
Han Zhou ◽  
Xiuli Zhang ◽  
...  
Keyword(s):  
Natural Products ◽  
Opioid Receptors ◽  
Free Cell ◽  
Label Free ◽  
Mu Opioid ◽  
Opioid Ligands

Raman spectroscopy-based label-free cell identification using wavelet transform and support vector machine

RSC Advances ◽  
2016 ◽  
Vol 6 (55) ◽  
pp. 50027-50033 ◽  
Author(s):  
S. Bakhtiaridoost ◽  
H. Habibiyan ◽  
S. Muhammadnejad ◽  
M. Haddadi ◽  
H. Ghafoorifard ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Raman Spectroscopy ◽  
Wavelet Transform ◽  
Raman Spectra ◽  
Free Cell ◽  
Support Vector ◽  
Label Free ◽  
Cell Identification ◽  
Rare Cells

Wavelet transform and SVM applied to Raman spectra makes a powerful and accurate tool for identification of rare cells such as CTCs.

A ‘smart’ aptamer-functionalized continuous label-free cell catch-transport-release system

2021 ◽  
Author(s):  
Bozhen Zhang ◽  
Canran Wang ◽  
Yingjie Du ◽  
Rebecca Paxton ◽  
Ximin He
Keyword(s):  
Biomedical Research ◽  
Cell Sorting ◽  
Free Cell ◽  
Label Free ◽  
Clinical Therapeutics ◽  
Release System ◽  
System P

Label-free cell sorting devices are of great significance for biomedical research and clinical therapeutics. However, current platforms for label-free cell sorting cannot achieve continuity and selectivity simultaneously, resulting in complex...

scholarly journals Pinhole microLED Array as Point Source Illumination for Miniaturized Lensless Cell Monitoring Systems

Proceedings ◽  
2018 ◽  
Vol 2 (13) ◽  
pp. 866 ◽  
Author(s):  
Shinta Mariana ◽  
Gregor Scholz ◽  
Feng Yu ◽  
Agus Budi Dharmawan ◽  
Iqbal Syamsu ◽  
...  
Keyword(s):  
Image Quality ◽  
Light Emitting Diode ◽  
Free Cell ◽  
Monitoring Systems ◽  
Label Free ◽  
Light Emitting ◽  
Non Invasive ◽  
Cell Monitoring ◽  
Blue Spectral Region ◽  
Led Arrays

Pinhole‐shaped light‐emitting diode (LED) arrays with dimension ranging from 100 μm down to 5 μm have been developed as point illumination sources. The proposed microLED arrays, which are based on gallium nitride (GaN) technology and emitting in the blue spectral region (λ = 465 nm), are integrated into a compact lensless holographic microscope for a non‐invasive, label‐free cell sensing and imaging. From the experimental results using single pinhole LEDs having a diameter of 90 μm, the reconstructed images display better resolution and enhanced image quality compared to those captured using a commercial surface‐mount device (SMD)‐based LED.

scholarly journals DeepMAsED: evaluating the quality of metagenomic assemblies

2020 ◽  
Vol 36 (10) ◽  
pp. 3011-3017 ◽  
Author(s):  
Olga Mineeva ◽  
Mateo Rojas-Carulla ◽  
Ruth E Ley ◽  
Bernhard Schölkopf ◽  
Nicholas D Youngblut
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Ground Truth ◽  
Supplementary Information ◽  
Learning Approach ◽  
Wide Range ◽  
Metagenome Assembly ◽  
Model Training ◽  
Reference Genomes

Abstract Motivation Methodological advances in metagenome assembly are rapidly increasing in the number of published metagenome assemblies. However, identifying misassemblies is challenging due to a lack of closely related reference genomes that can act as pseudo ground truth. Existing reference-free methods are no longer maintained, can make strong assumptions that may not hold across a diversity of research projects, and have not been validated on large-scale metagenome assemblies. Results We present DeepMAsED, a deep learning approach for identifying misassembled contigs without the need for reference genomes. Moreover, we provide an in silico pipeline for generating large-scale, realistic metagenome assemblies for comprehensive model training and testing. DeepMAsED accuracy substantially exceeds the state-of-the-art when applied to large and complex metagenome assemblies. Our model estimates a 1% contig misassembly rate in two recent large-scale metagenome assembly publications. Conclusions DeepMAsED accurately identifies misassemblies in metagenome-assembled contigs from a broad diversity of bacteria and archaea without the need for reference genomes or strong modeling assumptions. Running DeepMAsED is straight-forward, as well as is model re-training with our dataset generation pipeline. Therefore, DeepMAsED is a flexible misassembly classifier that can be applied to a wide range of metagenome assembly projects. Availability and implementation DeepMAsED is available from GitHub at https://github.com/leylabmpi/DeepMAsED. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Label-free cell based impedance measurements of ZnO nanoparticles—human lung cell interaction: a comparison with MTT, NR, Trypan blue and cloning efficiency assays

2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Giuseppina Bozzuto ◽  
Giuseppe D’Avenio ◽  
Maria Condello ◽  
Simona Sennato ◽  
Ezio Battaglione ◽  
...  
Keyword(s):  
Trypan Blue ◽  
A549 Cells ◽  
Cell Interaction ◽  
Neutral Red ◽  
Free Cell ◽  
Mitogenic Activity ◽  
Label Free ◽  
Cloning Efficiency ◽  
Zno Nps ◽  
Experimental Conditions

Abstract Background There is a huge body of literature data on ZnOnanoparticles (ZnO NPs) toxicity. However, the reported results are seen to be increasingly discrepant, and deep comprehension of the ZnO NPs behaviour in relation to the different experimental conditions is still lacking. A recent literature overview emphasizes the screening of the ZnO NPs toxicity with more than one assay, checking the experimental reproducibility also versus time, which is a key factor for the robustness of the results. In this paper we compared high-throughput real-time measurements through Electric Cell-substrate Impedance-Sensing (ECIS®) with endpoint measurements of multiple independent assays. Results ECIS-measurements were compared with traditional cytotoxicity tests such as MTT, Neutral red, Trypan blue, and cloning efficiency assays. ECIS could follow the cell behavior continuously and noninvasively for days, so that certain long-term characteristics of cell proliferation under treatment with ZnO NPs were accessible. This was particularly important in the case of pro-mitogenic activity exerted by low-dose ZnO NPs, an effect not revealed by endpoint independent assays. This result opens new worrisome questions about the potential mitogenic activity exerted by ZnO NPs, or more generally by NPs, on transformed cells. Of importance, impedance curve trends (morphology) allowed to discriminate between different cell death mechanisms (apoptosis vs autophagy) in the absence of specific reagents, as confirmed by cell structural and functional studies by high-resolution microscopy. This could be advantageous in terms of costs and time spent. ZnO NPs-exposed A549 cells showed an unusual pattern of actin and tubulin distribution which might trigger mitotic aberrations leading to genomic instability. Conclusions ZnO NPs toxicity can be determined not only by the intrinsic NPs characteristics, but also by the external conditions like the experimental setting, and this could account for discrepant data from different assays. ECIS has the potential to recapitulate the needs required in the evaluation of nanomaterials by contributing to the reliability of cytotoxicity tests. Moreover, it can overcome some false results and discrepancies in the results obtained by endpoint measurements. Finally, we strongly recommend the comparison of cytotoxicity tests (ECIS, MTT, Trypan Blue, Cloning efficiency) with the ultrastructural cell pathology studies. Graphic Abstract

Sign in / Sign up

Export Citation Format

Share Document