Advances in high-throughput microscopy have enabled the rapid acquisition of large numbers of high-content microscopy images. Next, whether by deep learning or classical algorithms, image analysis pipelines commonly produce single-cell features. To process these single cells for downstream applications, we present Pycytominer, a user-friendly, open-source Python package that implements the bioinformatics steps key to image-based profiling. We demonstrate Pycytominer's usefulness in a machine-learning project to predict nuisance compounds that cause undesirable cell injuries.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1038/s41592-025-02611-8 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
STExplore: An Integrated Online Platform for Comprehensive Analysis and Visualization of Spatial Transcriptomics Data.
Small Methods
March 2025
School of Computer Science, Northwestern Polytechnical University, No.1 Dongxiang Road, Xi'an, Shaanxi, 710129, China.
Spatial transcriptomics revolutionizes the understanding of tissue organization and cellular interactions by combining high-resolution spatial information with gene expression profiles. Existing spatial transcriptomics analysis platforms face challenges in accommodating diverse techniques, integrating multi-omics data, and providing comprehensive analytical workflows. STExplore, an advanced online platform, is developed to address these limitations.
View Article and Find Full Text PDFRECIP 1.0 + PSA for response assessment in mCRPC patients treated with Ac / Lu PSMA combination therapy.
EJNMMI Res
March 2025
Department of Nuclear Medicine, LMU University Hospital, LMU Munich, Munich, Germany.
Background: Targeted alpha therapy (TAT) with Ac has shown promising results in metastatic castration-resistant prostate cancer (mCRPC) patients pre-treated with [Lu]Lu-PSMA radioligand therapy (RLT). A combination treatment regimen adding Lu to decreased Ac activities may improve toxicity profile while maintaining sufficient anti-tumor effect. We therefore evaluated clinical and image-based response parameters in patients treated with Ac-/Lu-PSMA combination therapies (ALCT).
View Article and Find Full Text PDFReproducible image-based profiling with Pycytominer.
Nat Methods
March 2025
Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, USA.
Advances in high-throughput microscopy have enabled the rapid acquisition of large numbers of high-content microscopy images. Next, whether by deep learning or classical algorithms, image analysis pipelines commonly produce single-cell features. To process these single cells for downstream applications, we present Pycytominer, a user-friendly, open-source Python package that implements the bioinformatics steps key to image-based profiling.
View Article and Find Full Text PDFSystematic inference of super-resolution cell spatial profiles from histology images.
Nat Commun
February 2025
Institute of TCM-X/MOE Key Laboratory of Bioinformatics, Bioinformatics Division, BNRist/Department of Automation, Tsinghua University, Beijing, China.
Inferring cell spatial profiles from histology images is critical for cancer diagnosis and treatment in clinical settings. In this study, we report a weakly-supervised deep-learning method, HistoCell, to directly infer super-resolution cell spatial profiles consisting of cell types, cell states and their spatial network from histology images at the single-nucleus-level. Benchmark analysis demonstrates that HistoCell robustly achieves state-of-the-art performance in terms of cell type/states prediction solely from histology images across multiple cancer tissues.
View Article and Find Full Text PDFSelf-supervision advances morphological profiling by unlocking powerful image representations.
Sci Rep
February 2025
Machine Learning Research, Bayer AG, Berlin, Germany.
Cell Painting is an image-based assay that offers valuable insights into drug mechanisms of action and off-target effects. However, traditional feature extraction tools such as CellProfiler are computationally intensive and require frequent parameter adjustments. Inspired by recent advances in AI, we trained self-supervised learning (SSL) models DINO, MAE, and SimCLR on a subset of the JUMP Cell Painting dataset to obtain powerful representations for Cell Painting images.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!