Robust classification of subcellular location patterns in high resolution 3D fluorescence microscope images

Profiling stem cell states in three-dimensional biomaterial niches using high content image informatics

A predictive framework for the evolution of stem cell biology in 3-D is currently lacking. In this study we propose deep image informatics of the nuclear biology of stem cells to elucidate how 3-D biomaterials steer stem cell lineage phenotypes. The approach is based on high content imaging informatics to capture minute variations in the 3-D spatial organization of splicing factor SC-35 in the nucleoplasm as a marker to classify emergent cell phenotypes of human mesenchymal stem cells (hMSCs). The cells were cultured in varied 3-D culture systems including hydrogels, electrospun mats and salt leached scaffolds. The approach encompasses high resolution 3-D imaging of SC-35 domains and high content image analysis (HCIA) to compute quantitative 3-D nuclear metrics for SC-35 organization in single cells in concert with machine learning approaches to construct a predictive cell-state classification model. Our findings indicate that hMSCs cultured in collagen hydrogels and induced to differentiate into osteogenic or adipogenic lineages could be classified into the three lineages (stem, adipogenic, osteogenic) with ⩾80% precision and sensitivity, within 72h. Using this framework, the augmentation of osteogenesis by scaffold design exerted by porogen leached scaffolds was also profiled within 72h with ∼80% high sensitivity. Furthermore, by employing 3-D SC-35 organizational metrics, differential osteogenesis induced by novel electrospun fibrous polymer mats incorporating decellularized matrix could also be elucidated and predictably modeled at just 3days with high precision. We demonstrate that 3-D SC-35 organizational metrics can be applied to model the stem cell state in 3-D scaffolds. We propose that this methodology can robustly discern minute changes in stem cell states within complex 3-D architectures and map single cell biological readouts that are critical to assessing population level cell heterogeneity.

STATEMENT OF SIGNIFICANCE

The sustained development and validation of bioactive materials relies on technologies that can sensitively discern cell response dynamics to biomaterials, while capturing cell-to-cell heterogeneity and preserving cellular native phenotypes. In this study, we illustrate the application of a novel high content image informatics platform to classify emergent human mesenchymal stem cell (hMSC) phenotypes in a diverse range of 3-D biomaterial scaffolds with high sensitivity and precision, and track cell responses to varied external stimuli. A major in silico innovation is the proposed image profiling technology based on unique three dimensional textural signatures of a mechanoreporter protein within the nuclei of stem cells cultured in 3-D scaffolds. This technology will accelerate the pace of high-fidelity biomaterial screening.

Mining biomedical images towards valuable information retrieval in biomedical and life sciences

Biomedical images are helpful sources for the scientists and practitioners in drawing significant hypotheses, exemplifying approaches and describing experimental results in published biomedical literature. In last decades, there has been an enormous increase in the amount of heterogeneous biomedical image production and publication, which results in a need for bioimaging platforms for feature extraction and analysis of text and content in biomedical images to take advantage in implementing effective information retrieval systems. In this review, we summarize technologies related to data mining of figures. We describe and compare the potential of different approaches in terms of their developmental aspects, used methodologies, produced results, achieved accuracies and limitations. Our comparative conclusions include current challenges for bioimaging software with selective image mining, embedded text extraction and processing of complex natural language queries.

Location proteomics: systematic determination of protein subcellular location

Proteomics seeks the systematic and comprehensive understanding of all aspects of proteins, and location proteomics is the relatively new subfield of proteomics concerned with the location of proteins within cells. This review provides a guide to the widening selection of methods for studying location proteomics and integrating the results into systems biology. Automated and objective methods for determining protein subcellular location have been described based on extracting numerical features from fluorescence microscope images and applying machine learning approaches to them. Systems to recognize all major protein subcellular location patterns in both two-dimensional and three-dimensional HeLa cell images with high accuracy (over 95% and 98%, respectively) have been built. The feasibility of objectively grouping proteins into subcellular location families, and in the process of discovering new subcellular patterns, has been demonstrated using cluster analysis of images from a library of randomly tagged protein clones. Generative models can be built to effectively capture and communicate the patterns in these families. While automated methods for high-resolution determination of subcellular location are now available, the task of applying these methods to all expressed proteins in many different cell types under many conditions represents a very significant challenge.

Automated interpretation of subcellular patterns in fluorescence microscope images for location proteomics

Proteomics, the large scale identification and characterization of many or all proteins expressed in a given cell type, has become a major area of biological research. In addition to information on protein sequence, structure and expression levels, knowledge of a protein's subcellular location is essential to a complete understanding of its functions. Currently, subcellular location patterns are routinely determined by visual inspection of fluorescence microscope images. We review here research aimed at creating systems for automated, systematic determination of location. These employ numerical feature extraction from images, feature reduction to identify the most useful features, and various supervised learning (classification) and unsupervised learning (clustering) methods. These methods have been shown to perform significantly better than human interpretation of the same images. When coupled with technologies for tagging large numbers of proteins and high-throughput microscope systems, the computational methods reviewed here enable the new subfield of location proteomics. This subfield will make critical contributions in two related areas. First, it will provide structured, high-resolution information on location to enable Systems Biology efforts to simulate cell behavior from the gene level on up. Second, it will provide tools for Cytomics projects aimed at characterizing the behaviors of all cell types before, during, and after the onset of various diseases.

A graphical model approach to automated classification of protein subcellular location patterns in multi-cell images

Background

Knowledge of the subcellular location of a protein is critical to understanding how that protein works in a cell. This location is frequently determined by the interpretation of fluorescence microscope images. In recent years, automated systems have been developed for consistent and objective interpretation of such images so that the protein pattern in a single cell can be assigned to a known location category. While these systems perform with nearly perfect accuracy for single cell images of all major subcellular structures, their ability to distinguish subpatterns of an organelle (such as two Golgi proteins) is not perfect. Our goal in the work described here was to improve the ability of an automated system to decide which of two similar patterns is present in a field of cells by considering more than one cell at a time. Since cells displaying the same location pattern are often clustered together, considering multiple cells may be expected to improve discrimination between similar patterns.

Results

We describe how to take advantage of information on experimental conditions to construct a graphical representation for multiple cells in a field. Assuming that a field is composed of a small number of classes, the classification accuracy can be improved by allowing the computed probability of each pattern for each cell to be influenced by the probabilities of its neighboring cells in the model. We describe a novel way to allow this influence to occur, in which we adjust the prior probabilities of each class to reflect the patterns that are present. When this graphical model approach is used on synthetic multi-cell images in which the true class of each cell is known, we observe that the ability to distinguish similar classes is improved without suffering any degradation in ability to distinguish dissimilar classes. The computational complexity of the method is sufficiently low that improved assignments of classes can be obtained for fields of twelve cells in under 0.04 second on a 1600 megahertz processor.

Conclusion

We demonstrate that graphical models can be used to improve the accuracy of classification of subcellular patterns in multi-cell fluorescence microscope images. We also describe a novel algorithm for inferring classes from a graphical model. The performance and speed suggest that the method will be particularly valuable for analysis of images from high-throughput microscopy. We also anticipate that it will be useful for analyzing the mixtures of cell types typically present in images of tissues. Lastly, we anticipate that the method can be generalized to other problems.

An adaptive multirate algorithm for acquisition of fluorescence microscopy data sets

We propose an algorithm for adaptive efficient acquisition of fluorescence microscopy data sets using a multirate (MR) approach. We simulate acquisition as part of a larger system for protein classification based on their subcellular location patterns and, thus, strive to maintain the achieved level of classification accuracy as much as possible. This problem is similar to image compression but unique due to additional restrictions, namely causality; we have access only to the information scanned up to that point. While we do want to acquire fewer samples with as low distortion as possible to achieve compression, our goal is to do so while affecting the overall classification accuracy as little as possible. We achieve this by using an adaptive MR scanning scheme which samples the regions of the image area that hold the most pertinent information. Our results show that we can achieve significant compression which we can then use to aquire faster or to increase space resolution of our data set, all while minimally affecting the classification accuracy of the entire system.

Object type recognition for automated analysis of protein subcellular location

The new field of location proteomics seeks to provide a comprehensive, objective characterization of the subcellular locations of all proteins expressed in a given cell type. Previous work has demonstrated that automated classifiers can recognize the patterns of all major subcellular organelles and structures in fluorescence microscope images with high accuracy. However, since some proteins may be present in more than one organelle, this paper addresses a more difficult task: recognizing a pattern that is a mixture of two or more fundamental patterns. The approach utilizes an object-based image model, in which each image of a location pattern is represented by a set of objects of distinct, learned types. Using a two-stage approach in which object types are learned and then cell-level features are calculated based on the object types, the basic location patterns were well recognized. Given the object types, a multinomial mixture model was built to recognize mixture patterns. Under appropriate conditions, synthetic mixture patterns can be decomposed with over 80% accuracy, which, for the first time, shows that the problem of computationally decomposing subcellular patterns into fundamental organelle patterns can be solved.

Objective clustering of proteins based on subcellular location patterns

The goal of proteomics is the complete characterization of all proteins. Efforts to characterize subcellular location have been limited to assigning proteins to general categories of organelles. We have previously designed numerical features to describe location patterns in microscope images and developed automated classifiers that distinguish major subcellular patterns with high accuracy (including patterns not distinguishable by visual examination). The results suggest the feasibility of automatically determining which proteins share a single location pattern in a given cell type. We describe an automated method that selects the best feature set to describe images for a given collection of proteins and constructs an effective partitioning of the proteins by location. An example for a limited protein set is presented. As additional data become available, this approach can produce for the first time an objective systematics for protein location and provide an important starting point for discovering sequence motifs that determine localization.

Location proteomics: a systems approach to subcellular location

Systems Biology requires comprehensive systematic data on all aspects and levels of biological organization and function. In addition to information on the sequence, structure, activities and binding interactions of all biological macromolecules, the creation of accurate predictive models of cell behaviour will require detailed information on the distribution of those molecules within cells and the ways in which those distributions change over the cell cycle and in response to mutations or external stimuli. Current information on subcellular location in protein databases is limited to unstructured text descriptions or sets of terms assigned by human curators. These entries do not permit basic operations that are common to other biological databases, such as measurement of the degree of similarity between the distributions of two proteins, and they are not able to fully capture the complexity of protein patterns that can be observed. The field of location proteomics seeks to provide automated, objective high-resolution descriptions of protein location patterns within cells. Methods have been developed to group proteins into statistically indistinguishable location patterns using automated analysis of fluorescence microscope images. The resulting clusters, or location families, are analogous to clusters found for other domains, such as protein sequence families. Preliminary work suggests the feasibility of expressing each unique pattern as a generative model that can be incorporated into comprehensive models of cell behaviour.