Despite the availabilty of imaging-based and mass-spectrometry-based methods for spatial proteomics, a key challenge remains connecting images with single-cell-resolution protein abundance measurements. Here, we introduce Deep Visual Proteomics (DVP), which combines artificial-intelligence-driven image analysis of cellular phenotypes with automated single-cell or single-nucleus laser microdissection and ultra-high-sensitivity mass spectrometry. DVP links protein abundance to complex cellular or subcellular phenotypes while preserving spatial context. By individually excising nuclei from cell culture, we classified distinct cell states with proteomic profiles defined by known and uncharacterized proteins. In an archived primary melanoma tissue, DVP identified spatially resolved proteome changes as normal melanocytes transition to fully invasive melanoma, revealing pathways that change in a spatial manner as cancer progresses, such as mRNA splicing dysregulation in metastatic vertical growth that coincides with reduced interferon signaling and antigen presentation. The ability of DVP to retain precise spatial proteomic information in the tissue context has implications for the molecular profiling of clinical samples.

Recent advancements in deep learning have revolutionized the way microscopy images of cells are processed. Deep learning network architectures have a large number of parameters, thus, in order to reach high accuracy, they require a massive amount of annotated data. A common way of improving accuracy builds on the artificial increase of the training set by using different augmentation techniques. A less common way relies on test-time augmentation (TTA) which yields transformed versions of the image for prediction and the results are merged. In this paper we describe how we have incorporated the test-time argumentation prediction method into two major segmentation approaches utilized in the single-cell analysis of microscopy images. These approaches are semantic segmentation based on the U-Net, and instance segmentation based on the Mask R-CNN models. Our findings show that even if only simple test-time augmentations (such as rotation or flipping and proper merging methods) are applied, TTA can significantly improve prediction accuracy. We have utilized images of tissue and cell cultures from the Data Science Bowl (DSB) 2018 nuclei segmentation competition and other sources. Additionally, boosting the highest-scoring method of the DSB with TTA, we could further improve prediction accuracy, and our method has reached an ever-best score at the DSB.

Single-cell segmentation is typically a crucial task of image-based cellular analysis. We present nucleAIzer, a deep-learning approach aiming toward a truly general method for localizing 2D cell nuclei across a diverse range of assays and light microscopy modalities. We outperform the 739 methods submitted to the 2018 Data Science Bowl on images representing a variety of realistic conditions, some of which were not represented in the training data. The key to our approach is that during training nucleAIzer automatically adapts its nucleus-style model to unseen and unlabeled data using image style transfer to automatically generate augmented training samples. This allows the model to recognize nuclei in new and different experiments efficiently without requiring expert annotations, making deep learning for nucleus segmentation fairly simple and labor free for most biological light microscopy experiments. It can also be used online, integrated into CellProfiler and freely downloaded at www.nucleaizer.org.

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.

To find objects on images automatically, first we must teach the computer how to recognize them by showing examples. The most robust of such methods use deep learning, needing a large annotated dataset to be efficient. We propose an ImageJ plugin, AnnotatorJ, a fast and easy-to-use annotation tool aiding manual hand-labeling with deep learning.