NDLI: Toward generalizable phenotype prediction from single-cell morphology representations

Please wait, while we are loading the content...

Mosquito Tissue Ultrastructure-Expansion Microscopy (MoTissU-ExM) enables ultrastructural and anatomical analysis of malaria parasites and their mosquito

Microfluidic platform for microbial spore germination studies in multiple growth conditions

Gap-repair recombineering for efficient retrieval of large DNA fragments from BAC clones and manipulation of large high-copy number plasmids

Advances in medical imaging techniques

Scalable isolation of surface-engineered extracellular vesicles and separation of free proteins via tangential flow filtration and size exclusion chromatography (TFF-SEC)

An end-to-end workflow to study newly synthesized mRNA following rapid protein depletion in Saccharomyces cerevisiae

Confirming size-exclusion chromatography as a clinically relevant extracellular vesicles separation method from 1mL plasma through a comprehensive comparison of methods

Magnetic procedure for sentinel lymph node detection and evaluation of metastases: design and rationale of the Lowmag trial

Mini-MEndR: a miniaturized 96-well predictive assay to evaluate muscle stem cell-mediated repair

Artificial intelligence for omics data analysis

Biomaterials and scaffolds for tissue engineering and regenerative medicine

Plant genome editing to achieve food and nutrient security

Empowering scientific progress: the vital role of open-access, peer-reviewed methods and protocols

Toward generalizable phenotype prediction from single-cell morphology representations

Content Provider	Springer Nature : BioMed Central
Author	Tomkinson, Jenna Kern, Roshan Mattson, Cameron Way, Gregory P.
Abstract	Background Functional cell processes (e.g., molecular signaling, response to stimuli, mitosis, etc.) impact cell phenotypes, which scientists can measure with cell morphology. However, linking these measurements with phenotypes remains challenging because it requires manually annotated labels. We propose that nuclear morphology can be a predictive marker for cell phenotypes that are generalizable across contexts. Methods We reanalyzed a pre-labeled, publicly-available nucleus microscopy dataset from the MitoCheck consortium. We extracted single-cell morphology features using CellProfiler and DeepProfiler, which provide robust processing pipelines. We trained multinomial, multi-class elastic-net logistic regression models to classify nuclei into one of 15 phenotypes such as ‘Anaphase,’ ‘Apoptosis’, and ‘Binuclear’. We rigorously assessed performance using F1 scores, precision-recall curves, and a leave-one-image-out (LOIO) cross-validation analysis. In LOIO, we retrained models using cells from every image except one and predicted phenotype in the held-out image, repeating this procedure for all images. We evaluated each morphology feature space, a concatenated feature space, and several feature space subsets (e.g., nuclei AreaShape features only). We applied models to the Joint Undertaking in Morphological Profiling (JUMP) data to assess performance using a different dataset. Results In a held-out test set, we observed an overall F1 score of 0.84. Individual phenotype scores ranged from 0.64 (moderate performance) to 0.99 (high performance). Phenotypes such as ‘Elongated’, ‘Metaphase’, and ‘Apoptosis’ showed high performance. While CellProfiler and DeepProfiler features were generally equally effective, concatenation yielded the best results for 9/15 phenotypes. LOIO showed a performance decline, indicating our model could not reliably predict phenotypes in new images. Poor performance was unrelated to illumination correction or model selection. Applied to the JUMP data, models trained using nuclear AreaShape features only increased alignment with the annotated MitoCheck data (based on UMAP space). This approach implicated many chemical and genetic perturbations known to be associated with specific phenotypes. Discussion Poor LOIO performance demonstrates challenges of single-cell phenotype prediction in new datasets. We propose several strategies that could pave the way for more generalizable methods in single-cell phenotype prediction, which is a step toward morphology representation ontologies that would aid in cross-dataset interpretability.
Related Links	https://bmcmethods.biomedcentral.com/counter/pdf/10.1186/s44330-024-00014-3.pdf
Ending Page	14
Page Count	14
Starting Page	1
File Format	HTM / HTML
ISSN	30048729
DOI	10.1186/s44330-024-00014-3
Journal	BMC Methods
Issue Number	1
Volume Number	1
Language	English
Publisher	BioMed Central
Publisher Date	2024-12-09
Access Restriction	Open
Subject Keyword	Biomedicine Medicine Public Health Life Sciences High content microscopy Single-cell phenotype Image-based profiling Machine learning CellProfiler analysis Medicine/Public Health
Content Type	Text
Resource Type	Article
Subject	Biomedical Engineering Applied Microbiology and Biotechnology

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Toward generalizable phenotype prediction from single-cell morphology representations

Discovery of optimal cell type classification marker genes from single cell RNA sequencing data

Implementation and calibration of spectroscopic single-molecule localization microscopy

iPAR: a new reporter for eukaryotic cytoplasmic protein aggregation

PSSR2: a user-friendly Python package for democratizing deep learning-based point-scanning super-resolution microscopy

Advances in medical imaging techniques

Autophagy profiling in single cells with open source CellProfiler-based image analysis.

High-content single-cell combinatorial indexing.

Artificial intelligence for omics data analysis

Toward generalizable phenotype prediction from single-cell morphology representations

Similar Documents

Toward generalizable phenotype prediction from single-cell morphology representations

Discovery of optimal cell type classification marker genes from single cell RNA sequencing data

Implementation and calibration of spectroscopic single-molecule localization microscopy

iPAR: a new reporter for eukaryotic cytoplasmic protein aggregation

PSSR2: a user-friendly Python package for democratizing deep learning-based point-scanning super-resolution microscopy

Advances in medical imaging techniques

Autophagy profiling in single cells with open source CellProfiler-based image analysis.

High-content single-cell combinatorial indexing.

Artificial intelligence for omics data analysis

Toward generalizable phenotype prediction from single-cell morphology representations