An official website of the United States government
Abstract Measuring the phenotypic effect of treatments on cells through imaging assays is an efficient and powerful way of studying cell biology, and requires computational methods for transforming images into quantitative data. Here, we present an improved strategy for learning representations of treatment effects from high-throughput imaging, following a causal interpretation. We use weakly supervised learning for modeling associations between images and treatments, and show that it encodes both confounding factors and phenotypic features in the learned representation. To facilitate their separation, we constructed a large training dataset with images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN. We evaluated our strategy on three publicly available Cell Painting datasets, and observed that the Cell Painting CNN improves performance in downstream analysis up to 30% with respect to classical features, while also being more computationally efficient.
more »
« less
This content will become publicly available on May 23, 2025
Morphological profiling for drug discovery in the era of deep learning
Abstract Morphological profiling is a valuable tool in phenotypic drug discovery. The advent of high-throughput automated imaging has enabled the capturing of a wide range of morphological features of cells or organisms in response to perturbations at the single-cell resolution. Concurrently, significant advances in machine learning and deep learning, especially in computer vision, have led to substantial improvements in analyzing large-scale high-content images at high throughput. These efforts have facilitated understanding of compound mechanism of action, drug repurposing, characterization of cell morphodynamics under perturbation, and ultimately contributing to the development of novel therapeutics. In this review, we provide a comprehensive overview of the recent advances in the field of morphological profiling. We summarize the image profiling analysis workflow, survey a broad spectrum of analysis strategies encompassing feature engineering– and deep learning–based approaches, and introduce publicly available benchmark datasets. We place a particular emphasis on the application of deep learning in this pipeline, covering cell segmentation, image representation learning, and multimodal learning. Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.
more »
« less
- Award ID(s):
- 2111679
- PAR ID:
- 10546368
- Publisher / Repository:
- Oxford Academic
- Date Published:
- Journal Name:
- Briefings in Bioinformatics
- Volume:
- 25
- Issue:
- 4
- ISSN:
- 1467-5463
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Predicting assay results for compounds virtually using chemical structures and phenotypic profiles has the potential to reduce the time and resources of screens for drug discovery. Here, we evaluate the relative strength of three high-throughput data sources—chemical structures, imaging (Cell Painting), and gene-expression profiles (L1000)—to predict compound bioactivity using a historical collection of 16,170 compounds tested in 270 assays for a total of 585,439 readouts. All three data modalities can predict compound activity for 6–10% of assays, and in combination they predict 21% of assays with high accuracy, which is a 2 to 3 times higher success rate than using a single modality alone. In practice, the accuracy of predictors could be lower and still be useful, increasing the assays that can be predicted from 37% with chemical structures alone up to 64% when combined with phenotypic data. Our study shows that unbiased phenotypic profiling can be leveraged to enhance compound bioactivity prediction to accelerate the early stages of the drug-discovery process.more » « less
-
null (Ed.)The advancements of information technology and related processing techniques have created a fertile base for progress in many scientific fields and industries. In the fields of drug discovery and development, machine learning techniques have been used for the development of novel drug candidates. The methods for designing drug targets and novel drug discovery now routinely combine machine learning and deep learning algorithms to enhance the efficiency, efficacy, and quality of developed outputs. The generation and incorporation of big data, through technologies such as high-throughput screening and high through-put computational analysis of databases used for both lead and target discovery, has increased the reliability of the machine learning and deep learning incorporated techniques. The use of these virtual screening and encompassing online information has also been highlighted in developing lead synthesis pathways. In this review, machine learning and deep learning algorithms utilized in drug discovery and associated techniques will be discussed. The applications that produce promising results and methods will be reviewed.more » « less
-
Three-dimensional (3D) tumor spheroid models have gained increased recognition as important tools in cancer research and anti-cancer drug development. However, currently available imaging approaches employed in high-throughput screening drug discovery platforms e.g. bright field, phase contrast, and fluorescence microscopies, are unable to resolve 3D structures deep inside (>50 μm) tumor spheroids. In this study, we established a label-free, non-invasive optical coherence tomography (OCT) imaging platform to characterize 3D morphological and physiological information of multicellular tumor spheroids (MCTS) growing from ~250 μm up to ~600 μm in height over 21 days. In particular, tumor spheroids of two cell lines glioblastoma (U-87 MG) and colorectal carcinoma (HCT 116) exhibited distinctive evolutions in their geometric shapes at late growth stages. Volumes of MCTS were accurately quantified using a voxel-based approach without presumptions of their geometries. In contrast, conventional diameter-based volume calculations assuming perfect spherical shape resulted in large quantification errors. Furthermore, we successfully detected necrotic regions within these tumor spheroids based on increased intrinsic optical attenuation, suggesting a promising alternative of label-free viability tests in tumor spheroids. Therefore, OCT can serve as a promising imaging modality to characterize morphological and physiological features of MCTS, showing great potential for high-throughput drug screening.more » « less
-
153 Background: Conventional monolayer cell cultures and xenograft models, while useful and economical in early drug discovery, cannot predict clinical efficacy. Further, preclinical screening assays that rely on differential metabolic activity between separate control and treated wells are incapable of capturing phenotypic response and could overstate efficacy for cells with high rates of proliferation. Consequently, over 95% of anticancer agents that show efficacy in preclinical studies, fail in clinical trials. Recently, patient-derived organoid (PDO) models have been utilized in developing platforms to predict clinical efficacy of preclinical formulations. If successful, such predictive ex vivo technologies could revolutionize cancer treatment by reducing cost and time-to-market for new, more effective therapeutics. Objective: Characterize a novel bioprinted organoid tumor (BOT) high-throughput screening ex vivo platform for drug response prediction (DRP) with known proteosome and survivn inhibitors in colorectal cancer. Methods: Bioink for 3D printing BOTs was prepared with HT-29 cells, an established NCI-60 human colorectal adenocarcinoma cell line with known sensitivity to proteosome and survivin inhibitors. Bioink was deposited layer-by-layer on multiple substrates, in various geometrical configurations, and cured in stages to allow cells and matrix to self-assemble with limited degrees of freedom. BOTs were screened 24h and 48h after printing with proteosome inhibitor Bortezomib and survivin inhibitor YM-155. BOTs were evaluated 48h and 72h after treatment using immunofluorescence live/dead assay. Morphological phenotypic changes resulting from treatment were also recorded. Results: Proteasome and survivin inhibitors have been reported to inhibit proliferation and induce cell death in colorectal cancer cells. A dose dependent response was observed for both agents in our novel BOT HTS thereby validating the platform. In addition, characteristic self-assembly of HT-29 cells was observed to be disrupted at effective doses and at certain concentrations below the effective dose. Traditional ATP assays are incapable of recording such phenotypic modulation. Further, a higher proliferation profile was observed in untreated BOTs suggesting that use of independent control wells in traditional assays could overstate efficacy of treatment. Conclusions: Functional high-throughput ex vivo DRP technologies have the potential to transform cancer treatment – from bench to bedside – along the drug discovery to market roadmap for much needed novel anticancer agents.more » « less
