Devin P. Sullivan

Unbiased Rare Event Sampling in Spatial Stochastic Systems Biology Models Using a Weighted Ensemble of Trajectories.

The long-term goal of connecting scales in biological simulation can be facilitated by scale-agnostic methods. We demonstrate that the weighted ensemble (WE) strategy, initially developed for molecular simulations, applies effectively to spatially resolved cell-scale simulations. The WE approach runs an ensemble of parallel trajectories with assigned weights and uses a statistical resampling strategy of replicating and pruning trajectories to focus computational effort on difficult-to-sample regions. The method can also generate unbiased estimates of non-equilibrium and equilibrium observables, sometimes with significantly less aggregate computing time than would be possible using standard parallelization. Here, we use WE to orchestrate particle-based kinetic Monte Carlo simulations, which include spatial geometry (e.g., of organelles, plasma membrane) and biochemical interactions among mobile molecular species. We study a series of models exhibiting spatial, temporal and biochemical complexity and show that although WE has important limitations, it can achieve performance significantly exceeding standard parallel simulation—by orders of magnitude for some observables.

Joint Modeling of Cell and Nuclear Shape Variation

It is shown for the first time that cell shape can be accurately predicted from nuclear shape (and vice versa) for three different cell lines. This correlation is reduced by altering protein C1QBP or various drugs. In addition, a generative model is given for the kinetics of shape change. The software is available in the open-source CellOrganizer system.

Active machine learning-driven experimentation to determine compound effects on protein patterns

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

Design Automation for Biological Models: A Pipeline that Incorporates Spatial and Molecular Complexity

Understanding the dynamics of biochemical networks is a major goal of systems biology. Due to the heterogeneity of cells and the low copy numbers of key molecules, spatially resolved approaches are required to fully understand and model these systems. Until recently, most spatial modeling was performed using geometries obtained either through manual segmentation or manual fabrication both of which are time-consuming and tedious. Similarly, the system of reactions associated with the model had to be manually defined, a process that is both tedious and error-prone for large networks. As a result, spatially resolved simulations have typically only been performed in a limited number of geometries, which are often highly simplified, and with small reaction networks.

Deep learning is combined with massive-scale citizen science to improve large-scale image classification

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.

Transcriptome profiling of the interconnection of pathways involved in malignant transformation and response to hypoxia

In tumor tissues, hypoxia is a commonly observed feature resulting from rapidly proliferating cancer cells outgrowing their surrounding vasculature network. Transformed cancer cells are known to exhibit phenotypic alterations, enabling continuous proliferation despite a limited oxygen supply. The four-step isogenic BJ cell model enables studies of defined steps of tumorigenesis: the normal, immortalized, transformed, and metastasizing stages. By transcriptome profiling under atmospheric and moderate hypoxic (3% O2) conditions, we observed that despite being highly similar, the four cell lines of the BJ model responded strikingly different to hypoxia. Besides corroborating many of the known responses to hypoxia, we demonstrate that the transcriptome adaptation to moderate hypoxia resembles the process of malignant transformation. The transformed cells displayed a distinct capability of metabolic switching, reflected in reversed gene expression patterns for several genes involved in oxidative phosphorylation and glycolytic pathways. By profiling the stage-specific responses to hypoxia, we identified ASS1 as a potential prognostic marker in hypoxic tumors. This study demonstrates the usefulness of the BJ cell model for highlighting the interconnection of pathways involved in malignant transformation and hypoxic response.