Biology subjects

Caicedo, J. C.

Publications and source records attributed to Caicedo, J. C..

11 recordsLinked to original sources

bioRxiv2026

mnDINO: Accurate and robust segmentation of micronuclei with vision transformer networks

Recent advances in cell segmentation successfully produce models that generalize across various cell-lines and imaging types. However, these methods still fail to recognize subcellular structures such as micronuclei (MN), which are rare and tiny DNA-containing structures found outside of the main nucleus and observable under the microscope. While they can be hard to recognize in images, studying MN formation is of great interest because of their relationship to chromosome instability, genotoxicity, and cancer progression. Here we present a segmentation model, mnDINO, to segment micronuclei in DNA stained images under diverse experimental conditions with very high efficiency and accuracy. To train this model, we collected a heterogeneous set of images with more than five thousand annotated micronuclei. Trained with this diverse resource, the mnDINO model improves the accuracy of MN segmentation, and exhibits strong generalization across microscopes and cell lines. The dataset, code, and pre-trained model are made publicly available to facilitate future research in MN biology.

bioinformatics↗

bioRxiv2025

Prediction of Piconewton Receptor Tension Images using Deep Learning

Piconewton (pN) receptor forces govern many biological processes, but measuring these forces remains challenging. Molecular tension probes (MTPs) provide a sensitive means to measure pN cellular forces via fluorescence microscopy; however, MTPs are challenging to use and only forces transmitted through the probes are reported, complicating their use in heterogenous environments. Here, we present Tension Deep Learning (TensionDL), which leverages convolutional neural networks and image-to-image translation to predict pN receptor tension maps from images of cell morphology and the force-transducing protein vinculin. We validate the accuracy of TensionDL at the subcellular and cellular scales, demonstrate model accuracy across different substrate stiffnesses and cell types, and leverage TensionDL to make semi-quantitative predictions of cell mechanical output. Finally, TensionDL enables long-term mapping of pN receptor tension and infers tension distributions in heterogeneous environments in which some forces are not transduced through MTPs.

bioengineering↗

bioRxiv2023

Unbiased single-cell morphology with self-supervised vision transformers

Accurately quantifying cellular morphology at scale could substantially empower existing single-cell approaches. However, measuring cell morphology remains an active field of research, which has inspired multiple computer vision algorithms over the years. Here, we show that DINO, a vision-transformer based, self-supervised algorithm, has a remarkable ability for learning rich representations of cellular morphology without manual annotations or any other type of supervision. We evaluate DINO on a wide variety of tasks across three publicly available imaging datasets of diverse specifications and biological focus. We find that DINO encodes meaningful features of cellular morphology at multiple scales, from subcellular and single-cell resolution, to multi-cellular and aggregated experimental groups. Importantly, DINO successfully uncovers a hierarchy of biological and technical factors of variation in imaging datasets. The results show that DINO can support the study of unknown biological variation, including single-cell heterogeneity and relationships between samples, making it an excellent tool for image-based biological discovery.

bioinformatics↗

bioRxiv2022

Learning representations for image-based profiling of perturbations

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 that highlight phenotypic outcomes. Here, we present an optimized strategy for learning representations of treatment effects from high-throughput imaging data, which follows a causal framework for interpreting results and guiding performance improvements. We use weakly supervised learning (WSL) 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 Cell Painting images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a WSL model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN-1. We conducted a comprehensive evaluation of our strategy on three publicly available Cell Painting datasets, discovering that representations obtained by the Cell Painting CNN-1 can improve performance in downstream analysis for biological matching up to 30% with respect to classical features, while also being more computationally efficient.

bioinformatics↗

bioRxiv2022

Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations

Identifying genetic and chemical perturbations with similar impacts on cell morphology can reveal compounds mechanisms of action or novel regulators of genetic pathways. Research on methods for identifying such similarities has lagged due to a lack of carefully designed and well-annotated image sets of cells treated with chemical and genetic perturbations. Here, we create such a Resource dataset, CPJUMP1, where each perturbed gene is a known target of at least two chemical compounds in the dataset. We systematically explore the directionality of correlations among perturbations that target the same gene, and we find that identifying matches between chemical perturbations and genetic perturbations is a challenging task. Our dataset and baseline analyses provide a benchmark for evaluating methods that measure perturbation similarities and impact, and more generally, learn effective representations of cellular state from microscopy images. Such advancements would accelerate the applications of image-based profiling, such as functional genomics and drug discovery.

bioinformatics↗

bioRxiv2021

Cell Painting predicts impact of lung cancer variants

Most variants in most genes across most organisms have an unknown impact on the function of the corresponding gene. This gap in knowledge is especially acute in cancer, where clinical sequencing of tumors now routinely reveals patient-specific variants whose functional impact on the corresponding gene is unknown, impeding clinical utility. Transcriptional profiling was able to systematically distinguish these variants of unknown significance (VUS) as impactful vs. neutral in an approach called expression-based variant-impact phenotyping (eVIP). We profiled a set of lung adenocarcinoma-associated somatic variants using Cell Painting, a morphological profiling assay that captures features of cells based on microscopy using six stains of cell and organelle components. Using deep-learning-extracted features from each cells image, we found that cell morphological profiling (cmVIP) can predict variants functional impact and, particularly at the single-cell level, reveals biological insights into variants which can be explored in our public online portal. Given its low cost, convenient implementation, and single-cell resolution, cmVIP profiling therefore seems promising as an avenue for using non-gene-specific assays to systematically assess the impact of variants, including disease-associated alleles, on gene function.

cancer biology↗

bioRxiv2021

High-Dimensional Gene Expression and Morphology Profiles of Cells across 28,000 Genetic and Chemical Perturbations

Cells can be perturbed by various chemical and genetic treatments and the impact on the cells gene expression (transcription, i.e. mRNA levels) and morphology (in an image-based assay) can be measured. The patterns observed in this high-dimensional profile data can power a dozen applications in drug discovery and basic biology research, but both types of profiles are rarely available for large-scale experiments. Here, we provide a collection of four datasets with both gene expression and morphological profile data useful for developing and testing multi-modal methodologies. Roughly a thousand features are measured for each of the two data types, across more than 28,000 thousand chemical and genetic perturbations. We define biological problems that use the shared and complementary information in these two data modalities, provide baseline analysis and evaluation metrics for multi-omic applications, and make the data resource publicly available (http://broad.io/rosetta).

systems biology↗

bioRxiv2020

Predicting compound activity from phenotypic profiles and chemical structures

Recent advances in deep learning enable using chemical structures and phenotypic profiles to accurately predict assay results for compounds virtually, reducing the time and cost of screens in the drug-discovery process. We evaluate the relative strength of three high-throughput data sources--chemical structures, images (Cell Painting), and gene-expression profiles (L1000)--to predict compound activity using a sparse 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 with high accuracy in 6-10% of assays tested; replacing million-compound physical screens with computationally prioritized smaller screens throughout the pharmaceutical industry could yield major savings. Furthermore, the three profiling modalities are complementary, and in combination they can predict 21% of assays with high accuracy, and 64% if lower accuracy is acceptable. Our study shows that, for many assays, predicting compound activity from phenotypic profiles and chemical structures might accelerate the early stages of the drug-discovery process.

bioinformatics↗

bioRxiv2018

Weakly supervised learning of single-cell feature embeddings

We study the problem of learning representations for single cells in microscopy images to discover biological relationships between their experimental conditions. Many new applications in drug discovery and functional genomics require capturing the morphology of individual cells as comprehensively as possible. Deep convolutional neural networks (CNNs) can learn powerful visual representations, but require ground truth for training; this is rarely available in biomedical profiling experiments. While we do not know which experimental treatments produce cells that look alike, we do know that cells exposed to the same experimental treatment should generally look similar. Thus, we explore training CNNs using a weakly supervised approach that uses this information for feature learning. In addition, the training stage is regularized to control for unwanted variations using mixup or RNNs. We conduct experiments on two different datasets; the proposed approach yields single-cell embeddings that are more accurate than the widely adopted classical features, and are competitive with previously proposed transfer learning approaches.

bioinformatics↗

bioRxiv2017

CytoGAN: Generative Modeling of Cell Images

We explore the application of Generative Adversarial Networks to the domain of morphological profiling of human cultured cells imaged by fluorescence microscopy. When evaluated for their ability to group cell images responding to treatment by chemicals of known classes, we find that adversarially learned representations are superior to autoencoder-based approaches. While currently inferior to classical computer vision and transfer learning, the adversarial framework enables useful visualization of the variation of cellular images due to their generative capabilities.

bioinformatics↗

bioRxiv2016

Automating Morphological Profiling with Generic Deep Convolutional Networks

Morphological profiling aims to create signatures of genes, chemicals and diseases from microscopy images. Current approaches use classical computer vision-based segmentation and feature extraction. Deep learning models achieve state-of-the-art performance in many computer vision tasks such as classification and segmentation. We propose to transfer activation features of generic deep convolutional networks to extract features for morphological profiling. Our approach surpasses currently used methods in terms of accuracy and processing speed. Furthermore, it enables fully automated processing of microscopy images without need for single cell identification.

bioinformatics↗