Biology subjects

McQuin, C.

Publications and source records attributed to McQuin, C..

4 recordsLinked to original sources

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↗

bioRxiv2018

Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images

Identifying nuclei is often a critical first step in analyzing microscopy images of cells, and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluation metrics for nucleus segmentation do not satisfactorily capture error modes that are relevant in cellular images. Besides, large image data sets with ground truth for evaluation have been limiting. We present an evaluation framework to measure accuracy, types of errors, and computational efficiency; and use it to compare two deep learning strategies (U-Net and DeepCell) alongside a classical approach implemented in CellProfiler. We publicly release a set of 23,165 manually annotated nuclei and source code to reproduce experiments. Our results show that U-Net outperforms both pixel-wise classification networks and classical algorithms. Also, our evaluation framework shows that deep learning improves accuracy and reduces the number of biologically relevant errors by half.

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↗

bioRxiv2018

Label-free assessment of red blood cell storage lesions by deep learning

Blood transfusion is a life-saving clinical procedure. With millions of units needed globally each year, it is a growing concern to improve product quality and recipient outcomes.\n\nStored red blood cells (RBCs) undergo continuous degradation, leading to structural and biochemical changes. To analyze RBC storage lesions, complex biochemical and biophysical assays are often employed.\n\nWe demonstrate that label-free imaging flow cytometry and deep learning can characterize RBC morphologies during 42-day storage, replacing the current practice of manually quantifying a blood smear from stored blood units. Based only on bright field and dark field images, our model achieved 90% accuracy in classifying six different RBC morphologies associated with storage lesions versus human-curated manual examination. A model fitted to the deep learning-extracted features revealed a pattern of morphological changes within the aging blood unit that allowed predicting the expiration date of stored blood using solely morphological assessment.\n\nDeep learning and label-free imaging flow cytometry could therefore be applied to reduce complex laboratory procedures and facilitate robust and objective characterization of blood samples.

bioinformatics↗