Semi-supervised Contrastive Learning for Bioactivity Prediction using Cell Painting Image Data DOI Open Access

David Bushiri Pwesombo,

Carsten Jörn Beese, Christopher Schmied

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 29, 2024

Abstract Morphological profiling has recently demonstrated remarkable potential for identifying the biological activities of small molecules. Alongside fully supervised and self-supervised machine learning methods proposed bioactivity prediction from Cell Painting image data, we introduce here a semi-supervised contrastive (SemiSupCon) approach. This approach combines strengths using annotations in leveraging large unannotated datasets with learning. SemiSupCon enhances downstream performance classifying MeSH pharmacological classifications PubChem, as well mode action target Drug Repurposing Hub across two publicly available datasets. Notably, our effectively predicted several compounds, these findings were validated through literature searches. demonstrates that can potentially expedite exploration activity based on data minimal human intervention.

Language: Английский

A Decade in a Systematic Review: The Evolution and Impact of Cell Painting DOI Creative Commons
Srijit Seal, Maria‐Anna Trapotsi, Ola Spjuth

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: May 7, 2024

ABSTRACT High-content image-based assays have fueled significant discoveries in the life sciences past decade (2013-2023), including novel insights into disease etiology, mechanism of action, new therapeutics, and toxicology predictions. Here, we systematically review substantial methodological advancements applications Cell Painting. Advancements include improvements Painting protocol, assay adaptations for different types perturbations applications, improved methodologies feature extraction, quality control, batch effect correction. Moreover, machine learning methods recently surpassed classical approaches their ability to extract biologically useful information from images. data been used alone or combination with other - omics decipher action a compound, its toxicity profile, many biological effects. Overall, key advances expanded Painting’s capture cellular responses various perturbations. Future will likely lie advancing computational experimental techniques, developing publicly available datasets, integrating them high-content types.

Language: Английский

Citations

12
Semisupervised Contrastive Learning for Bioactivity Prediction Using Cell Painting Image Data DOI Creative Commons

David Bushiri Pwesombo,

Carsten Jörn Beese, Christopher Schmied

et al.

Journal of Chemical Information and Modeling, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 6, 2025

Morphological profiling has recently demonstrated remarkable potential for identifying the biological activities of small molecules. Alongside fully supervised and self-supervised machine learning methods proposed bioactivity prediction from Cell Painting image data, we introduce here a semisupervised contrastive (SemiSupCon) approach. This approach combines strengths using annotations in leveraging large unannotated data sets with learning. SemiSupCon enhances downstream performance classifying MeSH pharmacological classifications PubChem, as well mode action target Drug Repurposing Hub across two publicly available sets. Notably, our effectively predicted several compounds, these findings were validated through literature searches. demonstrates that can potentially expedite exploration activity based on minimal human intervention.

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
Morphological Profiling Dataset of EU-OPENSCREEN Bioactive Compounds Over Multiple Imaging Sites and Cell Lines DOI Creative Commons
Christopher Wolff, Martin Neuenschwander, Carsten Jörn Beese

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 27, 2024

Abstract Morphological profiling with the Cell Painting assay has emerged as a promising method in drug discovery research. The captures morphological changes across various cellular compartments enabling rapid identification of effect compounds. We present comprehensive dataset using carefully curated and well-annotated EU-OPENSCREEN Bioactive Compound Set. Our was generated multiple imaging sites high-throughput confocal microscopes Hep G2 well U2 OS cell line. employed an extensive optimization process to achieve high data quality different sites. An analysis four replicates validates robustness data. compare features lines map profiles activity, toxicity, basic compound targets further describe demonstrate potential this be used for mechanism action exploration.

Language: Английский

Citations

3
Design, Synthesis, Antitumour Evaluation, and In Silico Studies of Pyrazolo-[1,5-c]quinazolinone Derivatives Targeting Potential Cyclin-Dependent Kinases DOI Creative Commons

Danyang Zheng,

Chenqi Yang,

Xiaogang Li

et al.

Molecules, Journal Year: 2023, Volume and Issue: 28(18), P. 6606 - 6606

Published: Sept. 13, 2023

An efficient, straightforward, and metal-free methodology to rapidly access functionalised pyrazolo-[1,5-c]quinazolinones via a [3 + 2] dipolar cycloaddition regioselective ring expansion process was developed. The synthesised compounds were characterised by methods such as NMR, HRMS, HPLC. in vitro antiproliferative activity against A549 cells (non-small cell lung cancer) significant for 4i, 4m, 4n with IC50 values of 17.0, 14.2, 18.1 μM, respectively. In particular, 4t showed inhibitory CDK9/2. Predicted biological target molecular modelling studies suggest that the compound may CDKs antitumour effects. derivatives considered have moderate drug-likeness sufficient safety silico. summary, series pyrazolo-[1,5-c]quinazolinone is reported first time. We provide not only simple efficient synthetic method but also helpful lead further development novel cyclin-dependent kinase (CDK) inhibitors.

Language: Английский

Citations

5
Profiling Cellular Morphological Changes Induced by Dual‐targeting PROTACs of Aurora Kinase and RNA‐binding Protein YTHDF2 DOI Creative Commons

Georg L. Goebel,

Nicole Giannino,

Philipp Lampe

et al.

ChemBioChem, Journal Year: 2024, Volume and Issue: unknown

Published: June 5, 2024

Proteolysis targeting chimeras (PROTACs) are new chemical modalities that degrade proteins of interest, including established kinase targets and emerging RNA-binding (RBPs). Whereas diverse sets biochemical, biophysical cellular assays available for the evaluation optimizations PROTACs in understanding involved ubiquitin-proteasome-mediated degradation mechanism structure-degradation relationship, a phenotypic method profiling morphological changes is rarely used. In this study, first, we reported only examples degrading mRNA-binding protein YTHDF2 via screening multikinase PROTACs. Second, dual kinase- RBP-targeting using unbiased cell painting assay (CPA). The CPA analysis revealed high biosimilarity with aurora cluster annotated inhibitors, which reflected association between signaling network. Broadly, results demonstrated can be straightforward powerful approach to evaluate Complementary existing assays, provided perspective characterizing at morphology.

Language: Английский

Citations

1
Collective Synthesis of Sarpagine and Macroline Alkaloid‐Inspired Compounds DOI Creative Commons

Hikaru Aoyama,

Caitlin Davies, Jie Liu

et al.

Chemistry - A European Journal, Journal Year: 2023, Volume and Issue: 30(5)

Published: Sept. 27, 2023

Design strategies that can access natural-product-like chemical space in an efficient manner may facilitate the discovery of biologically relevant compounds. We have employed a divergent intermediate strategy to construct indole alkaloid-inspired compound collection derived from two different molecular design principles, i.e. biology-oriented synthesis and pseudo-natural products. The was subjected acid-catalyzed or newly discovered Sn-mediated conditions selectively promote intramolecular C- N-acylation, respectively. After further derivatization, totalling 84 compounds representing four classes obtained. Morphological profiling via cell painting assay coupled with subprofile analysis showed principles bioactivity profiles. suggested product class is enriched modulators tubulin, subsequent assays led identification suppress vitro tubulin polymerization mitotic progression.

Language: Английский

Citations

2
Direct synthesis of spirooxindoles enabled by palladium-catalyzed allylic alkylation and DBU-mediated cyclization: concept, scope and applications DOI

Fen Tan,

Xiaoyu He,

Qiao-Qiao Zhou

et al.

Organic Chemistry Frontiers, Journal Year: 2024, Volume and Issue: 11(19), P. 5443 - 5453

Published: Jan. 1, 2024

A concise construction of spiro[indoline-3,2′-pyrrol]-2-one skeletons is reported. This reaction proceeded through a palladium-catalyzed decarboxylative allylic alkylation followed by DBU-mediated intramolecular cyclization.

Language: Английский

Citations

0
Synthesis of C–N or C–C Spiroindolines via Rearrangement Coupling Reaction DOI
Xiao‐Ling Liu,

Panpan Qiao,

Hui Chen

et al.

Organic Letters, Journal Year: 2024, Volume and Issue: 26(45), P. 9759 - 9763

Published: Oct. 31, 2024

Herein, we report a general approach to effectively construct C–N or C–C spiroindolines using tetrahydro-β-carbolines as starting materials via rearrangement coupling reaction. This method is characterized by its operational simplicity and mild conditions. Notably, wide range of anilines indoles are suitable for this intermolecular coupling, yielding the corresponding in good excellent yields.

Language: Английский

Citations

0
Semi-supervised Contrastive Learning for Bioactivity Prediction using Cell Painting Image Data DOI Open Access

David Bushiri Pwesombo,

Carsten Jörn Beese, Christopher Schmied

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 29, 2024

Abstract Morphological profiling has recently demonstrated remarkable potential for identifying the biological activities of small molecules. Alongside fully supervised and self-supervised machine learning methods proposed bioactivity prediction from Cell Painting image data, we introduce here a semi-supervised contrastive (SemiSupCon) approach. This approach combines strengths using annotations in leveraging large unannotated datasets with learning. SemiSupCon enhances downstream performance classifying MeSH pharmacological classifications PubChem, as well mode action target Drug Repurposing Hub across two publicly available datasets. Notably, our effectively predicted several compounds, these findings were validated through literature searches. demonstrates that can potentially expedite exploration activity based on data minimal human intervention.

Language: Английский

Citations

0