Deep learning-enhanced morphological profiling predicts cell fate dynamics in real-time in hPSCs

Ren, Edward; Kim, Sung-Min; Saad, Mohamad; Huguet, Samuel F; Shi, Yulin; Cohen, Andrew R.; Piddini, Eugenia; Carazo-Salas, Rafael E.

doi:10.1101/2021.07.31.454574

Cited by 8 publications

(7 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In conventional feature engineering approaches, prior knowledge is incorporated into a model by choosing features that represent the system, for example, by measuring image properties or adding relevant fluorescent cell signalling reporters. This has recently been used, with ML-enabled dimensionality reduction, to study transitions in human pluripotent stem cell populations [12]. However, choosing appropriate measurements becomes increasingly difficult with more complex features such as describing the local organization of tissues comprising multiple cell types and varying degrees of epithelialization.…”

Section: Introductionmentioning

confidence: 99%

Learning biophysical determinants of cell fate with deep neural networks

et al. 2022

View full text Add to dashboard Cite

Deep learning is now a powerful tool in microscopy data analysis, and is routinely used for image processing applications such as segmentation and denoising. However, it has rarely been used to directly learn mechanistic models of a biological system, owing to the complexity of the internal representations. Here, we develop an end-to-end machine learning approach capable of learning an explainable model of a complex biological phenomenon, cell competition, directly from a large corpus of time-lapse microscopy data. Cell competition is a quality control mechanism that eliminates unfit cells from a tissue and during which cell fate is thought to be determined by the local cellular neighborhood over time. To investigate this, we developed a new approach (τ -VAE) by coupling a probabilistic encoder to a temporal convolution network to predict the fate of each cell in an epithelium. Using the τ -VAE's latent representation of the local tissue organization and the flow of information in the network, we decode the physical parameters responsible for correct prediction of fate in cell competition. Remarkably, the model autonomously learns that cell density is the single most important factor in predicting cell fate -a conclusion that is in agreement with our current understanding from over a decade of scientific research. Finally, to test the learned internal representation, we challenge the network with experiments performed in the presence of drugs that block signalling pathways involved in competition. We present a novel discriminator network that, using the predictions of the τ -VAE, can identify conditions which deviate from the normal behaviour, paving the way for automated, mechanism-aware drug screening.

show abstract

Section: Introductionmentioning

confidence: 99%

Learning biophysical determinants of cell fate with deep neural networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…An emerging advance of morphological profiling is toward live-cell phenotyping, which can be performed by fluorescent or phase-contrast imaging, and by continuous imaging [ 27 , 121 ] or dynamic imaging [ 48 ]. Several advantages accompany this approach.…”

Section: Novel Applications Of Morphological Profiling In Drug Discoverymentioning

confidence: 99%

“…The morphological profile was generated from 24-h high-content imaging and can be used to accurately infer 41 of 83 testable MOAs [ 27 ]. Beyond this, live-cell imaging enables the characterization of cell-state transition dynamics, a critical feature in developmental biology [ 48 , 121 ]. Human pluripotent stem cells (hPSCs) coexpressing histone H2B and cell cycle reporters can be profiled in a multi-day, high-content manner at single-cell resolution.…”

Section: Novel Applications Of Morphological Profiling In Drug Discoverymentioning

confidence: 99%

Morphological profiling for drug discovery in the era of deep learning

Tang,

Ratnayake,

Seabra

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

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.

show abstract

“…Recent advancements in machine learning provide opportunities for predicting stem cell fate by utilizing large datasets of stem cell characteristics ( Fan et al, 2017 ; Ashraf et al, 2021 ; Zhu et al, 2021 ). Among these machine learning methods, deep learning techniques have emerged as powerful tools to predict and identify stem cell patterns and lineage relationships ( Kusumoto and Yuasa, 2019 ; Ren et al, 2021 ). These models can identify key features such as molecular signatures, cell morphology, and gene expression that influence stem cell fate, allowing for precise differentiation predictions.…”

Section: Introductionmentioning

confidence: 99%

Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)

Mai,

Luo,

Fasciano

et al. 2023

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

Human mesenchymal stem cells (hMSCs) are multipotent progenitor cells with the potential to differentiate into various cell types, including osteoblasts, chondrocytes, and adipocytes. These cells have been extensively employed in the field of cell-based therapies and regenerative medicine due to their inherent attributes of self-renewal and multipotency. Traditional approaches for assessing hMSCs differentiation capacity have relied heavily on labor-intensive techniques, such as RT-PCR, immunostaining, and Western blot, to identify specific biomarkers. However, these methods are not only time-consuming and economically demanding, but also require the fixation of cells, resulting in the loss of temporal data. Consequently, there is an emerging need for a more efficient and precise approach to predict hMSCs differentiation in live cells, particularly for osteogenic and adipogenic differentiation. In response to this need, we developed innovative approaches that combine live-cell imaging with cutting-edge deep learning techniques, specifically employing a convolutional neural network (CNN) to meticulously classify osteogenic and adipogenic differentiation. Specifically, four notable pre-trained CNN models, VGG 19, Inception V3, ResNet 18, and ResNet 50, were developed and tested for identifying adipogenic and osteogenic differentiated cells based on cell morphology changes. We rigorously evaluated the performance of these four models concerning binary and multi-class classification of differentiated cells at various time intervals, focusing on pivotal metrics such as accuracy, the area under the receiver operating characteristic curve (AUC), sensitivity, precision, and F1-score. Among these four different models, ResNet 50 has proven to be the most effective choice with the highest accuracy (0.9572 for binary, 0.9474 for multi-class) and AUC (0.9958 for binary, 0.9836 for multi-class) in both multi-class and binary classification tasks. Although VGG 19 matched the accuracy of ResNet 50 in both tasks, ResNet 50 consistently outperformed it in terms of AUC, underscoring its superior effectiveness in identifying differentiated cells. Overall, our study demonstrated the capability to use a CNN approach to predict stem cell fate based on morphology changes, which will potentially provide insights for the application of cell-based therapy and advance our understanding of regenerative medicine.

show abstract

Deep learning-enhanced morphological profiling predicts cell fate dynamics in real-time in hPSCs

Cited by 8 publications

References 73 publications

Learning biophysical determinants of cell fate with deep neural networks

Learning biophysical determinants of cell fate with deep neural networks

Morphological profiling for drug discovery in the era of deep learning

Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)

Contact Info

Product

Resources

About