ScaleFExSM: a lightweight and scalable method to extract fixed features from single cells in high-content imaging screens DOI Creative Commons
Gabriel Comolet, N.K. Bose, Jeff Winchell

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: July 9, 2023

Abstract Leveraging artificial intelligence (AI) in image-based morphological profiling of cell populations is proving increasingly valuable for identifying diseased states and drug responses high-content imaging (HCI) screens. When the differences between (such as a healthy diseased) are completely unknown undistinguishable by human eye, it crucial that HCI screens large scale, allowing numerous replicates developing reliable models, well accounting confounding factors such individual (donor) intra-experimental variation. However, screen sizes increase, challenges arise including lack scalable solutions analyzing high-dimensional datasets processing results timely manner. For this purpose, many tools have been developed to reduce images into set features using unbiased methods, embedding vectors extracted from pre-trained neural networks or autoencoders. While these methods preserve most predictive power contained each image despite reducing dimensionality significantly, they do not provide easily interpretable information. Alternatively, techniques extract specific cellular data typically slow, difficult often produce redundant outputs, which can lead model learning irrelevant data, might distort future predictions. Here we present ScaleFEx℠, memory efficient open-source Python pipeline extracts biologically meaningful datasets. It requires only modest computational resources but also be deployed on high-powered cloud computing infrastructure. ScaleFEx℠ used conjunction with AI models cluster subsequently explore, identify, rank insights hallmarks phenotypic categories. We demonstrate performance tool dataset consisting control drug-treated cells cohort 20 donors, benchmarking against state-of-the-art tool, CellProfiler, analyze underlying shift induced chemical compounds. In addition, generalizability utility shown analysis publicly available Overall, constitutes robust compact effects drugs phenotypes defining leveraged disease discovery.

Language: Английский

Evolution and impact of high content imaging DOI Creative Commons
Gregory P. Way, Heba Sailem, Steven Shave

et al.

SLAS DISCOVERY, Journal Year: 2023, Volume and Issue: 28(7), P. 292 - 305

Published: Sept. 3, 2023

The field of high content imaging has steadily evolved and expanded substantially across many industry academic research institutions since it was first described in the early 1990's. High refers to automated acquisition analysis microscopic images from a variety biological sample types. Integration microscopes with multiwell plate handling robotics enables be performed at scale support medium- high-throughput screening pharmacological, genetic diverse environmental perturbations upon complex systems ranging 2D cell cultures 3D tissue organoids small model organisms. In this perspective article authors provide collective view on following key discussion points relevant evolution imaging:• Evolution impact imaging: An perspective• image analysis• data pipelines towards multiparametric phenotypic profiling applications• role integration multiomics• repositories sharing standards• Future hardware software • applications multiomics standards

Language: Английский

Citations

21
Cell Painting: a decade of discovery and innovation in cellular imaging DOI
Srijit Seal, Maria‐Anna Trapotsi, Ola Spjuth

et al.

Nature Methods, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 5, 2024

Language: Английский

Citations

4
Evaluating feature extraction in ovarian cancer cell line co-cultures using deep neural networks DOI Creative Commons

O. P. Sharma,

Greta Gudoitytė,

Rezan Minozada

et al.

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

Published: Feb. 25, 2025

Abstract Single-cell image analysis is crucial for studying drug effects on cellular morphology and phenotypic changes. Most studies focus single cell types, overlooking the complexity of interactions. Here, we establish an pipeline to extract features cancer cells cultured with fibroblasts. Using high-content imaging, analyze oncology library across five fibroblast line co-culture combinations, generating 61,440 images ∼170 million single-cell objects. Traditional phenotyping CellProfiler achieves average enrichment score 62.6% mechanisms action, while pre-trained neural networks (EfficientNetB0 MobileNetV2) reach 61.0% 62.0%, respectively. Variability in scores may reflect use multiple concentrations since not all induce significant morphological changes, as well genetic context treatment. Our study highlights nuanced drug-induced variations underscores heterogeneity ovarian lines their response complex environments.

Language: Английский

Citations

0
Evaluation of DNA encoded library and machine learning model combinations for hit discovery DOI Creative Commons
Sumaiya Iqbal, Wei Jiang, Eric R. Hansen

et al.

npj Drug Discovery., Journal Year: 2025, Volume and Issue: 2(1)

Published: April 2, 2025

Language: Английский

Citations

0
Phenotypic drug discovery DOI
Sonja Sievers, Herbert Waldmann, Slava Ziegler

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Assay Development and Automation in High Content Screening DOI
Sakshi Garg,

Charles-Hugues Lardeau,

Elizabeth Mouchet

et al.

Royal Society of Chemistry eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 26 - 74

Published: April 30, 2025

High-content screening (HCS), which involves imaging at scale, relies on the use of appropriate cell models and automation systems, effective statistical assessment assay quality high-quality execution culture plate preparation steps. The success an HCS campaign will very much lie in rigour applied planning development phases, robust most system parameters to implementation systems enable large-scale screens would not be feasible otherwise. In this chapter, we discuss key decisions that need made when developing for considering deploy screen.

Language: Английский

Citations

0
DEL+ML paradigm for actionable hit discovery – a cross DEL and cross ML model assessment. DOI Creative Commons
Sumaiya Iqbal, Wei Jiang, Eric R. Hansen

et al.

Published: July 24, 2024

DNA-Encoded Library (DEL) technology allows the screening of millions, or even billions, encoded compounds in a pooled fashion which is faster and cheaper than traditional approaches. These massive amounts data related to DEL binders not-binders target interest enable Machine Learning (ML) model development large, readily accessible, drug-like libraries an ultra-high-throughput fashion. Here, we report comparative assessment DEL+ML pipeline for hit discovery using three DELs five ML models (fifteen combinations two different feature representations). Each was used screen diverse set compound collections identify orthosteric therapeutic targets, Casein kinase 1𝛼/δ (CK1𝛼/δ). Overall, 10% 94% predicted were confirmed biophysical assays, including nanomolar (187 69.6 nM affinity CK1𝛼 CK1δ, respectively). Our study provides insights into paradigm discovery: importance ensemble approach identifying binders, usefulness large training chemical diversity DEL, significance generalizability over accuracy. We shared our results via open-source repository further use similar efforts.

Language: Английский

Citations

2
Hit me with your best shot: Integrated hit discovery for the next generation of drug targets DOI

Sajda Ashraf,

J. Henry Blackwell, Geoffrey A. Holdgate

et al.

Drug Discovery Today, Journal Year: 2024, Volume and Issue: 29(10), P. 104143 - 104143

Published: Aug. 23, 2024

Language: Английский

Citations

2
Low concentration cell painting images enable the identification of highly potent compounds DOI Creative Commons

Son V. Ha,

Steffen Jaensch, Lorena G. A. Freitas

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 17, 2024

Language: Английский

Citations

0
Phenotypic approaches for CNS drugs DOI Creative Commons

Rakesh Sharma,

Caitlin R. M. Oyagawa, Hamid Abbasi

et al.

Trends in Pharmacological Sciences, Journal Year: 2024, Volume and Issue: 45(11), P. 997 - 1017

Published: Oct. 21, 2024

Central nervous system (CNS) drug development is plagued by high clinical failure rate. Phenotypic assays promote translation of drugs reducing complex brain diseases to measurable, clinically valid phenotypes. We critique recent platforms integrating patient-derived cells, which most accurately recapitulate CNS disease phenotypes, with higher throughput models, including immortalized balance validity and scalability. These were screened conventional commercial chemogenomic compound libraries. explore emerging library curation strategies improve hit rate quality, screening novel fragment libraries as alternatives, for more tractable target deconvolution. The relevant models used in these could harbor important, unidentified targets, so we review evolving agnostic deconvolution approaches, chemical proteomics artificial intelligence (AI), aid phenotypic mechanism elucidation, thereby facilitating rational hit-to-drug optimization.

Language: Английский

Citations

0