Insights into Drug Cardiotoxicity from Biological and Chemical Data: The First Public Classifiers for FDA Drug-Induced Cardiotoxicity Rank

Journal of Chemical Information and Modeling, Год журнала: 2024, Номер 64(4), С. 1172 - 1186

Опубликована: Фев. 1, 2024

Drug-induced cardiotoxicity (DICT) is a major concern in drug development, accounting for 10-14% of postmarket withdrawals. In this study, we explored the capabilities chemical and biological data to predict cardiotoxicity, using recently released DICTrank set from United States FDA. We found that such data, including protein targets, especially those related ion channels (e.g., hERG), physicochemical properties electrotopological state), peak concentration plasma offer strong predictive ability DICT. Compounds annotated with mechanisms action as cyclooxygenase inhibition could distinguish between most-concern no-concern Cell Painting features ER stress discerned cardiotoxic nontoxic compounds. Models based on provided substantial accuracy (AUCPR = 0.93). With availability omics future, promises enhanced predictability deeper mechanistic insights, paving way safer development. All models study are available at https://broad.io/DICTrank_Predictor.

Язык: Английский

---

A Decade in a Systematic Review: The Evolution and Impact of Cell Painting

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Май 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.

Язык: Английский

---

Artificial intelligence for high content imaging in drug discovery

Current Opinion in Structural Biology, Год журнала: 2024, Номер 87, С. 102842 - 102842

Опубликована: Май 25, 2024

Artificial intelligence (AI) and high-content imaging (HCI) are contributing to advancements in drug discovery, propelled by the recent progress deep neural networks. This review highlights AI's role analysis of HCI data from fixed live-cell imaging, enabling novel label-free multi-channel fluorescent screening methods, improving compound profiling. experiments rapid cost-effective, facilitating large set accumulation for AI model training. However, success discovery also depends on high-quality data, reproducible experiments, robust validation ensure performance. Despite challenges like need annotated compounds managing vast image potential phenotypic profiling is significant. Future improvements AI, including increased interpretability integration multiple modalities, expected solidify HCI's discovery.

Язык: Английский

---

Metabolic and phenotypic changes induced by PFAS exposure in two human hepatocyte cell models

Environment International, Год журнала: 2024, Номер 190, С. 108820 - 108820

Опубликована: Июнь 17, 2024

PFAS are ubiquitous industrial chemicals with known adverse health effects, particularly on the liver. The liver, being a vital metabolic organ, is susceptible to PFAS-induced dysregulation, leading conditions such as hepatotoxicity and disturbances. In this study, we investigated phenotypic responses of exposure using two hepatocyte models, HepG2 (male cell line) HepaRG (female line), aiming define alterations, disturbances at metabolite pathway levels. mixture composition was selected based epidemiological data, covering broad concentration spectrum observed in diverse human populations. Phenotypic profiling by Cell Painting assay disclosed predominant effects mitochondrial structure function both models well F-actin, Golgi apparatus, plasma membrane-associated measures. We employed comprehensive characterization liquid chromatography combined high-resolution mass spectrometry (LC-HRMS). dose-dependent changes profiles, lipid, steroid, amino acid sugar carbohydrate metabolism cells media, line showing stronger response. cells, most bile acids, acylcarnitines free fatty acids showed downregulation, while medium-chain carnosine were upregulated, media different response especially relation media. Importantly, also nonmonotonic for several features metabolites. On level, associated pathways indicating oxidative stress inflammatory responses. Taken together, our findings disruptions hepatocytes shed light potential mechanisms contributing broader comprehension PFAS-related risks.

Язык: Английский

---

Deciphering the phenotypic, inflammatory, and endocrine disrupting impacts of e-waste plastic-associated chemicals

Environmental Research, Год журнала: 2025, Номер unknown, С. 120929 - 120929

Опубликована: Янв. 1, 2025

Язык: Английский

---

Exploring NLRP3-related phenotypic fingerprints in human macrophages using Cell Painting assay

iScience, Год журнала: 2025, Номер 28(3), С. 111961 - 111961

Опубликована: Фев. 6, 2025

Existing research has proven difficult to understand the interplay between upstream signaling events during NLRP3 inflammasome activation. Additionally, downstream of complex formation such as cytokine release and pyroptosis can exhibit variation, further complicating matters. Cell Painting emerged a prominent tool for unbiased evaluation effect perturbations on cell morphological phenotypes. Using this technique, phenotypic fingerprints be generated that reveal connections phenotypes possible modes action. To best our knowledge, was first study utilized human THP-1 macrophages generate in response different endogenous exogenous triggers identify features specific formation. Our results demonstrated not only are trigger-specific but it also cellular associated with

Язык: Английский

---

Toward generalizable phenotype prediction from single-cell morphology representations

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Март 13, 2024

Abstract Functional cell processes (e.g., molecular signaling, response to environmental stimuli, mitosis, etc.) impact phenotypes, which scientists can easily and robustly measure with morphology. However, linking these morphology measurements phenotypes remains challenging because biologically interpretable require manually annotated labels. Automatic phenotype annotation from would link biological their phenotypic outcomes deepen understanding of function. We propose that nuclear be a predictive marker for is generalizable across types. Nucleus commonly accessible microscopy, but annotating specific information requires Therefore, we reanalyzed pre-labeled, publicly-available nucleus microscopy dataset the MitoCheck consortium predict single-cell phenotypes. extracted features using CellProfiler DeepProfiler, provide fast, robust, data processing pipelines. trained multinomial, multi-class elastic net logistic regression models classify nuclei into one 15 such as ‘Anaphase,’ ‘Apoptosis’, ‘Binuclear’. In held-out test set, observed an overall F1 score 0.84, where individual scores ranged 0.64 (indicating moderate performance) 0.99 high performance). Notably, ‘Elongated’, ‘Metaphase’, ‘Apoptosis’ showed performance. While DeepProfiler were generally equally effective, combining feature spaces yielded best results 9 leave-one-image-out (LOIO) cross-validation analysis significant performance decline, indicating our model could not reliably in new single images. Poor performance, show was unrelated factors like illumination correction or selection, limits generalizability datasets highlights challenges annotation. Nevertheless, modified applied approach JUMP Cell Painting pilot data. Our improved alignment highlighted many perturbations are known associated several strategies pave way more methods prediction, step toward representation ontologies aid cross-dataset interpretability.

Язык: Английский

---

Cell Painting: a decade of discovery and innovation in cellular imaging

Nature Methods, Год журнала: 2024, Номер unknown

Опубликована: Дек. 5, 2024

Язык: Английский

---

Insights into Drug Cardiotoxicity from Biological and Chemical Data: The First Public Classifiers for FDA DICTrank

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Окт. 18, 2023

Abstract Drug-induced cardiotoxicity (DICT) is a major concern in drug development, accounting for 10-14% of postmarket withdrawals. In this study, we explored the capabilities various chemical and biological data to predict cardiotoxicity, using recently released Drug-Induced Cardiotoxicity Rank (DICTrank) dataset from United States FDA. We analyzed diverse set sources, including physicochemical properties, annotated mechanisms action (MOA), Cell Painting, Gene Expression, more, identify indications cardiotoxicity. found that such data, protein targets, especially those related ion channels (such as hERG), properties electrotopological state) well peak concentration plasma offer strong predictive ability valuable insights into DICT. also compounds with particular action, cyclooxygenase inhibition, could distinguish between most-concern no-concern DICT compounds. Painting features ER stress discern cardiotoxic non-toxic While models based on currently provide substantial accuracy (AUCPR = 0.93), study underscores potential benefits incorporating more comprehensive future models. With availability - omics future, promises enhanced predictability delivers deeper mechanistic insights, paving way safer therapeutic development. All used are publicly at https://broad.io/DICTrank_Predictor

Язык: Английский

---

A scalable, data analytics workflow for image-based morphological profiles

Chemometrics and Intelligent Laboratory Systems, Год журнала: 2024, Номер unknown, С. 105232 - 105232

Опубликована: Сен. 1, 2024

Язык: Английский

---