Biology subjects

Claassen, M.

Publications and source records attributed to Claassen, M..

5 recordsLinked to original sources

bioRxiv2018

Dynamic Distribution Decomposition for Single-Cell Snapshot Time Series Identifies Subpopulations and Trajectories during iPSC Differentiation

Recent high-dimensional single-cell technologies such as mass cytometry are enabling time series experiments to monitor the temporal evolution of cell state distributions and to identify dynamically important cell states, such as fate decision states in differentiation. However, these technologies are destructive, and require analysis approaches that temporally map between cell state distributions across time points. Current approaches to approximate the single-cell time series as a dynamical system suffer from too restrictive assumptions about the type of kinetics, or link together pairs of sequential measurements in a discontinuous fashion.\n\nWe propose Dynamic Distribution Decomposition (DDD), an operator approximation approach to infer a continuous distribution map between time points. On the basis of single-cell snapshot time series data, DDD approximates the continuous time Perron-Frobenius operator by means of a finite set of basis functions. This procedure can be interpreted as a continuous time Markov chain over a continuum of states. By only assuming a memoryless Markov (autonomous) process, the types of dynamics represented are more general than those represented by other common models, e.g., chemical reaction networks, stochastic differential equations. Additionally, the continuity assumption ensures that the same dynamical system maps between all time points, not arbitrarily changing at each time point. We demonstrate the ability of DDD to reconstruct dynamically important cell states and their transitions both on synthetic data, as well as on mass cytometry time series of iPSC reprogramming of a fibroblast system. We use DDD to find previously identified subpopulations of cells and to visualize differentiation trajectories.\n\nDynamic Distribution Decomposition allows interpreting high-dimensional snapshot time series data as a low-dimensional Markov process, thereby enabling an interpretable dynamics analysis for a variety of biological processes by means of identifying their dynamically important cell states.\n\nAuthor summaryHigh-dimensional single-cell snapshot measurements are now increasingly utilized to study dynamic processes. Such measurements enable us to evaluate cell population distributions and their evolution over time. However, it is not trivial to map these distribution across time and to identify dynamically important cell states, i.e. bottleneck regions of state space exhibiting a high degree of change. We present Dynamic Distribution Decomposition (DDD) achieving this task by encoding single-cell measurements as linear combination of basis function distributions and evolving these as a linear system. We demonstrate reconstruction of dynamically important states for synthetic data of a bifurcated diffusion process and mass cytometry data for iPSC reprogramming.

systems biology↗

bioRxiv2018

Supervised learning on synthetic data for reverse engineering gene regulatory networks from experimental time-series

The reconstruction of gene regulatory networks from time resolved gene expression measurements is a key challenge in systems biology with applications in health and disease. While the most popular network inference methods are based on unsupervised learning approaches, supervised learning methods have proven their potential for superior reconstruction performance. However, obtaining the appropriate volume of informative training data constitutes a key limitation for the success of such methods.\n\nHere, we introduce a supervised learning approach to detect gene-gene regulation based on exclusively synthetic training data, termed surrogate learning, and show its performance for synthetic and experimental time-series. We systematically investigate different simulation configurations of biologically representative time-series of transcripts and augmentation of the data with a measurement model. We compare the resulting synthetic datasets to experimental data, and evaluate classifiers trained on them for detection of gene-gene regulation from experimental time-series. For classifiers, we consider hybrid convolutional recurrent neural networks, random forests and logistic regression, and evaluate the reconstruction performance of different simulation settings, data pre-processing and classifiers.\n\nWhen training and test time-courses are generated from the same distribution, we find that the largest tested neural network architecture achieves the best performance of 0.448 {+/-} 0.047 (mean {+/-} std) in maximally achievable F1 score over all datasets outperforming random forests by 32.4 % {+/-} 14 % (mean {+/-} std). Reconstruction performance is sensitive to discrepancies between synthetic training and test data, highlighting the importance of matching training and test data domains. For an experimental gene expression dataset from E.coli, we find that training data generated with measurement model, multi-gene perturbations, but without data standardization is best suited for training classifiers for network reconstruction from the experimental test data. We further demonstrate superiority to multiple unsupervised, state-of-the-art methods for networks comprising 20 genes of the experimental data from E.coli (average AUPR best supervised = 0.22 vs best unsupervised = 0.07).\n\nWe expect the proposed surrogate learning approach to be broadly applicable. It alleviates the requirement for large, difficult to attain volumes of experimental training data and instead relies on easily accessible synthetic data. Successful application for new experimental conditions and other data types is only limited by the automatable and scalable process of designing simulations which generate suitable synthetic data.

systems biology↗

bioRxiv2018

Adult-specific pheromones differently influence malthusian escape strategies of younger generations

Many animal and plant species respond to high or low population densities by phenotypic plasticity. To investigate if specific age classes and/or cross-generational signaling affect(s) phenotypic plasticity, we developed a dye-based method to differentiate co-occurring nematode age classes. We applied this method to Pristionchus pacificus, which develops a predatory mouth form to exploit alternative resources and kill competitors in response to high population densities. Remarkably, only adult, but not juvenile, crowding induces the predatory morph in other juveniles. Profiling of secreted metabolites throughout development with HPLC-MS combined with genetic mutants traced this result to the production of adult-specific pheromones. Specifically, the P. pacificus-specific di-ascaroside#1 that induces the predatory morph exhibits a binary induction in adults, even though mouth form is no longer plastic in adults. This cross-generational signaling between adults and juveniles may serve as an indication of rapidly increasing population size. Thus, phenotypic plasticity depends on critical age classes.

ecology↗

bioRxiv2018

Automated Gleason grading of prostate cancer tissue microarrays via deep learning

The Gleason grading system remains the most powerful prognostic predictor for patients with prostate cancer since the 1960s. Its application requires highly-trained pathologists, is tedious and yet suffers from limited inter-pathologist reproducibility, especially for the intermediate Gleason score 7. Automated annotation procedures constitute a viable solution to remedy these limitations.\n\nIn this study, we present a deep learning approach for automated Gleason grading of prostate cancer tissue microarrays with Hematoxylin and Eosin (H&E) staining. Our system was trained using detailed Gleason annotations on a discovery cohort of 641 patients and was then evaluated on an independent test cohort of 245 patients annotated by two pathologists. On the test cohort, the inter-annotator agreements between the model and each pathologist, quantified via Cohens quadratic kappa statistic, were 0.75 and 0.71 respectively, comparable with the inter-pathologist agreement (kappa=0.71). Furthermore, the models Gleason score assignments achieved pathology expert-level stratification of patients into prognostically distinct groups, on the basis of disease-specific survival data available for the test cohort.\n\nOverall, our study shows promising results regarding the applicability of deep learning-based solutions towards more objective and reproducible prostate cancer grading, especially for cases with heterogeneous Gleason patterns.

bioinformatics↗

bioRxiv2017

Tree-ensemble analysis tests for presence of multifurcations in single cell data

We introduce TreeTop, an algorithm for single-cell data analysis to identify and assess statistical significance of branch points in biological processes with possibly multi-level branching hierarchies. We demonstrate branch point identification for processes with varying topologies, including T cell maturation, B cell differentiation and hematopoiesis. Our analyses are consistent with recent experimental studies suggesting a shallow hierarchy of differentiation events in hematopoiesis, rather than the classical multi-level hierarchy.

systems biology↗