Lineage tracing involves the identification of all ancestors and descendants of a given cell, and is an important tool for studying biological processes such as development and disease progression. However, in many settings, controlled time-course experiments are not feasible, for example when working with tissue samples from patients. Here we present Ima-geAEOT, a computational pipeline based on autoencoders and optimal transport for predicting the lineages of cells using time-labeled datasets from different stages of a cellular process. Given a single-cell image from one of the stages, ImageAEOT generates an artificial lineage of this cell based on the population characteristics of the other stages. These lineages can be used to connect subpopulations of cells through the different stages and identify image-based features and biomarkers underlying the biological process. To validate our method, we apply ImageAEOT to a benchmark task based on nuclear and chromatin images during the activation of fibroblasts by tumor cells in engineered 3D tissues. We further validate ImageAEOT on chromatin images of various breast cancer cell lines and human tissue samples, thereby linking alterations in chromatin condensation patterns to different stages of tumor progression. Our results demonstrate the promise of computational methods based on autoencoding and optimal transport principles for lineage tracing in settings where existing experimental strategies cannot be used.
Current cancer diagnosis employs various nuclear morphometric measures. While these have allowed accurate late-stage prognosis, early diagnosis is still a major challenge. Recent evidence highlights the importance of alterations in mechanical properties of single cells and their nuclei as critical drivers for the onset of cancer. We here present a method to detect subtle changes in nuclear morphometrics at single-cell resolution by combining fluorescence imaging and deep learning. This assay includes a convolutional neural net pipeline and allows us to discriminate between normal and human breast cancer cell lines (fibrocystic and metastatic states) as well as normal and cancer cells in tissue slices with high accuracy. Further, we establish the sensitivity of our pipeline by detecting subtle alterations in normal cells when subjected to small mechano-chemical perturbations that mimic tumor microenvironments. In addition, our assay provides interpretable features that could aid pathological inspections. This pipeline opens new avenues for early disease diagnostics and drug discovery.
Although we can increasingly image and measure biological processes at single-cell resolution, most assays can only take snapshots from a population of cells in time. Here we describe ImageAEOT, which combines an AutoEncoder, to map single-cell Images from different cell populations to a common latent space, with the framework of Optimal Transport to infer cellular trajectories. As a proof-of-concept, we apply ImageAEOT to nuclear and chromatin images during the activation of fibroblasts by tumor cells in engineered 3D tissues. We further validate ImageAEOT on chromatin images of various breast cancer cell lines and human tissue samples, thereby linking alterations in chromatin condensation patterns to different stages of tumor progression. Importantly, ImageAEOT can infer the trajectory of a particular cell from one snapshot in time and identify the changing features to provide early biomarkers for developmental and disease progression. Lineage tracing during differentiation, development and disease progression is critical for studying the underlying biological mechanisms. Current experimental methodologies often only provide snapshots of these cellular processes in time and from different cells. Although advances in machine learning in the past decade have prompted new computational methods (1-3), these are primarily aimed at the classification of cells and tissues based on training samples (4-6). This calls for computational methods that infer lineages based on single-cell snapshots in time and identify relevant features of the underlying biological process. Here we present ImageAEOT, which takes advantage of single-cell images, uses an autoencoder to embed them into a common latent space in order to perform optimal transport for predicting cellular trajectories from snapshots in time. Such modeling of cellular trajectories allows the identification of functional features and biomarkers underlying a biological process.The distribution of single-cell chromatin images occupies a low-dimensional manifold in a highdimensional space (7-8). ImageAEOT models cell trajectories from a source (blue) state to a target (red) state, given examples of images from both populations (Figure 1a). To do this, ImageAEOT first embeds the images into a low-dimensional latent space, which exhibits a simpler geometry than the original data manifold and is learned using a variational autoencoder (9-12). Within the latent space, ImageAEOT subsequently learns a model for predicting cell trajectories based on the principle of optimal transport (13-16). Finally, ImageAEOT decodes these trajectories back to the image space. Importantly, ImageAEOT does not merely interpolate between the training images, but given an image it infers and generates images of earlier and later cell states. In 17. Kalluri R. The biology and function of fibroblasts in cancer.
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.