Resolving the spatial distribution of the human proteome at a subcellular level can greatly increase our understanding of human biology and disease. Here we present a comprehensive image-based map of subcellular protein distribution, the Cell Atlas, built by integrating transcriptomics and antibody-based immunofluorescence microscopy with validation by mass spectrometry. Mapping the in situ localization of 12,003 human proteins at a single-cell level to 30 subcellular structures enabled the definition of the proteomes of 13 major organelles. Exploration of the proteomes revealed single-cell variations in abundance or spatial distribution and localization of about half of the proteins to multiple compartments. This subcellular map can be used to refine existing protein-protein interaction networks and provides an important resource to deconvolute the highly complex architecture of the human cell.

The proteins secreted by human cells (collectively referred to as the secretome) are important not only for the basic understanding of human biology but also for the identification of potential targets for future diagnostics and therapies. Here, we present a comprehensive analysis of proteins predicted to be secreted in human cells, which provides information about their final localization in the human body, including the proteins actively secreted to peripheral blood. The analysis suggests that a large number of the proteins of the secretome are not secreted out of the cell, but instead are retained intracellularly, whereas another large group of proteins were identified that are predicted to be retained locally at the tissue of expression and not secreted into the blood. Proteins detected in the human blood by mass spectrometry–based proteomics and antibody-based immunoassays are also presented with estimates of their concentrations in the blood. The results are presented in an updated version 19 of the Human Protein Atlas in which each gene encoding a secretome protein is annotated to provide an open-access knowledge resource of the human secretome, including body-wide expression data, spatial localization data down to the single-cell and subcellular levels, and data about the presence of proteins that are detectable in the blood.

Systems biology has experienced dramatic growth in the number, size, and complexity of computational models. To reproduce simulation results and reuse models, researchers must exchange unambiguous model descriptions. We review the latest edition of the Systems Biology Markup Language (SBML), a format designed for this purpose. A community of modelers and software authors developed SBML Level 3 over the past decade. Its modular form consists of a core suited to representing reaction‐based models and packages that extend the core with features suited to other model types including constraint‐based models, reaction‐diffusion models, logical network models, and rule‐based models. The format leverages two decades of SBML and a rich software ecosystem that transformed how systems biologists build and interact with models. More recently, the rise of multiscale models of whole cells and organs, and new data sources such as single‐cell measurements and live imaging, has precipitated new ways of integrating data with models. We provide our perspectives on the challenges presented by these developments and how SBML Level 3 provides the foundation needed to support this evolution.

Pattern recognition and classification of images are key challenges throughout the life sciences. We combined two approaches for large-scale classification of fluorescence microscopy images. First, using the publicly available data set from the Cell Atlas of the Human Protein Atlas (HPA), we integrated an image-classification task into a mainstream video game (EVE Online) as a mini-game, named Project Discovery. Participation by 322,006 gamers over 1 year provided nearly 33 million classifications of subcellular localization patterns, including patterns that were not previously annotated by the HPA. Second, we used deep learning to build an automated Localization Cellular Annotation Tool (Loc-CAT). This tool classifies proteins into 29 subcellular localization patterns and can deal efficiently with multi-localization proteins, performing robustly across different cell types. Combining the annotations of gamers and deep learning, we applied transfer learning to create a boosted learner that can characterize subcellular protein distribution with F1 score of 0.72. We found that engaging players of commercial computer games provided data that augmented deep learning and enabled scalable and readily improved image classification.

No abstract

Pinpointing subcellular protein localizations from microscopy images is easy to the trained eye, but challenging to automate. Based on the Human Protein Atlas image collection, we held a competition to identify deep learning solutions to solve this task. Challenges included training on highly imbalanced classes and predicting multiple labels per image. Over 3 months, 2,172 teams participated. Despite convergence on popular networks and training techniques, there was considerable variety among the solutions. Participants applied strategies for modifying neural networks and loss functions, augmenting data and using pretrained networks. The winning models far outperformed our previous effort at multi-label classification of protein localization patterns by ~20%. These models can be used as classifiers to annotate new images, feature extractors to measure pattern similarity or pretrained networks for a wide range of biological applications.

Cellular division is a fundamental source of cell-to-cell variability, and studies of transcript and protein abundances have revealed several hundred genes that are regulated by the cell cycle 1-8 . However, none of these studies provide single-cell resolution of protein expression, leaving an incomplete understanding of cell-to-cell heterogeneity and the roles of cycling transcripts and proteins. Here, we present the first comprehensive map of spatiotemporal heterogeneity of the human proteome by integrating proteomics at subcellular resolution, single-cell transcriptomics, and pseudotime measurements of individual cells within the cell cycle. We identify that 17% of the human proteome displays cell-to-cell variability, of which 26% is correlated to cell cycle progression, and we present the first evidence of cell cycle association for 235 proteins. Only 15% of proteomic cell cycle regulation is due to transcriptomic cycling, which points to other means of regulation such as post-translational modifications. For proteins regulated at the transcript level, we observe a 7.7 hour delay between peak expression of transcript and protein on average. This spatially resolved proteomic map of the cell cycle has been integrated into the Human Protein Atlas and serves as a valuable resource for accelerating molecular studies of the human cell cycle and cell proliferation.

High throughput screening determines the effects of many conditions on a given biological target. Currently, to estimate the effects of those conditions on other targets requires either strong modeling assumptions (e.g. similarities among targets) or separate screens. Ideally, data-driven experimentation could be used to learn accurate models for many conditions and targets without doing all possible experiments. We have previously described an active machine learning algorithm that can iteratively choose small sets of experiments to learn models of multiple effects. We now show that, with no prior knowledge and with liquid handling robotics and automated microscopy under its control, this learner accurately learned the effects of 48 chemical compounds on the subcellular localization of 48 proteins while performing only 29% of all possible experiments. The results represent the first practical demonstration of the utility of active learning-driven biological experimentation in which the set of possible phenotypes is unknown in advance.DOI: http://dx.doi.org/10.7554/eLife.10047.001