Boosting accuracy of automated classification of fluorescence microscope images for location proteomics

Background

Detailed knowledge of the subcellular location of each expressed protein is critical to a full understanding of its function. Fluorescence microscopy, in combination with methods for fluorescent tagging, is the most suitable current method for proteome-wide determination of subcellular location. Previous work has shown that neural network classifiers can distinguish all major protein subcellular location patterns in both 2D and 3D fluorescence microscope images. Building on these results, we evaluate here new classifiers and features to improve the recognition of protein subcellular location patterns in both 2D and 3D fluorescence microscope images.

Results

We report here a thorough comparison of the performance on this problem of eight different state-of-the-art classification methods, including neural networks, support vector machines with linear, polynomial, radial basis, and exponential radial basis kernel functions, and ensemble methods such as AdaBoost, Bagging, and Mixtures-of-Experts. Ten-fold cross validation was used to evaluate each classifier with various parameters on different Subcellular Location Feature sets representing both 2D and 3D fluorescence microscope images, including new feature sets incorporating features derived from Gabor and Daubechies wavelet transforms. After optimal parameters were chosen for each of the eight classifiers, optimal majority-voting ensemble classifiers were formed for each feature set. Comparison of results for each image for all eight classifiers permits estimation of the lower bound classification error rate for each subcellular pattern, which we interpret to reflect the fraction of cells whose patterns are distorted by mitosis, cell death or acquisition errors. Overall, we obtained statistically significant improvements in classification accuracy over the best previously published results, with the overall error rate being reduced by one-third to one-half and with the average accuracy for single 2D images being higher than 90% for the first time. In particular, the classification accuracy for the easily confused endomembrane compartments (endoplasmic reticulum, Golgi, endosomes, lysosomes) was improved by 5–15%. We achieved further improvements when classification was conducted on image sets rather than on individual cell images.

Conclusions

The availability of accurate, fast, automated classification systems for protein location patterns in conjunction with high throughput fluorescence microscope imaging techniques enables a new subfield of proteomics, location proteomics. The accuracy and sensitivity of this approach represents an important alternative to low-resolution assignments by curation or sequence-based prediction.

     

A framework for the automated analysis of subcellular patterns in human protein atlas images

The systematic study of subcellular location patterns is required to fully characterize the human proteome, as subcellular location provides critical context necessary for understanding a protein's function. The analysis of tens of thousands of expressed proteins for the many cell types and cellular conditions under which they may be found creates a need for automated subcellular pattern analysis. We therefore describe the application of automated methods, previously developed and validated by our laboratory on fluorescence micrographs of cultured cell lines, to analyze subcellular patterns in tissue images from the Human Protein Atlas. The Atlas currently contains images of over 3000 protein patterns in various human tissues obtained using immunohistochemistry. We chose a 16 protein subset from the Atlas that reflects the major classes of subcellular location. We then separated DNA and protein staining in the images, extracted various features from each image, and trained a support vector machine classifier to recognize the protein patterns. Our results show that our system can distinguish the patterns with 83% accuracy in 45 different tissues, and when only the most confident classifications are considered, this rises to 97%. These results are encouraging given that the tissues contain many different cell types organized in different manners, and that the Atlas images are of moderate resolution. The approach described is an important starting point for automatically assigning subcellular locations on a proteome-wide basis for collections of tissue images such as the Atlas.     

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.     

Automated image analysis of protein localization in budding yeast

MOTIVATION: The yeast Saccharomyces cerevisiae is the first eukaryotic organism to have its genome completely sequenced. Since then, several large-scale analyses of the yeast genome have provided extensive functional annotations of individual genes and proteins. One fundamental property of a protein is its subcellular localization, which provides critical information about how this protein works in a cell. An important project therefore was the creation of the yeast GFP fusion localization database by the University of California, San Francisco, USA (UCSF). This database provides localization data for 75% of the proteins believed to be encoded by the yeast genome. These proteins were classified into 22 distinct subcellular location categories by visual examination. Based on our past success at building automated systems to classify subcellular location patterns in mammalian cells, we sought to create a similar system for yeast. RESULTS: We developed computational methods to automatically analyze the images created by the UCSF yeast GFP fusion localization project. The system was trained to recognize the same location categories that were used in that study. We applied the system to 2640 images, and the system gave the same label as the previous assignments to 2139 images (81%). When only the highest confidence assignments were considered, 94.7% agreement was observed. Visual examination of the proteins for which the two approaches disagree suggests that at least some of the automated assignments may be more accurate. The automated method provides an objective, quantitative and repeatable assignment of protein locations that can be applied to new collections of yeast images (e.g. for different strains or the same strain under different conditions). It is also important to note that this performance could be achieved without requiring colocalization with any marker proteins. AVAILABILITY: The original images analyzed in this article are available at http://yeastgfp.ucsf.edu, and source code and results are available at http://murphylab.web.cmu.edu/software.     

A multiresolution approach to automated classification of protein subcellular location images

Background  

Fluorescence microscopy is widely used to determine the subcellular location of proteins. Efforts to determine location on a proteome-wide basis create a need for automated methods to analyze the resulting images. Over the past ten years, the feasibility of using machine learning methods to recognize all major subcellular location patterns has been convincingly demonstrated, using diverse feature sets and classifiers. On a well-studied data set of 2D HeLa single-cell images, the best performance to date, 91.5%, was obtained by including a set of multiresolution features. This demonstrates the value of multiresolution approaches to this important problem.     

Automated analysis of high‐content microscopy data with deep learning

Existing computational pipelines for quantitative analysis of high‐content microscopy data rely on traditional machine learning approaches that fail to accurately classify more than a single dataset without substantial tuning and training, requiring extensive analysis. Here, we demonstrate that the application of deep learning to biological image data can overcome the pitfalls associated with conventional machine learning classifiers. Using a deep convolutional neural network (DeepLoc) to analyze yeast cell images, we show improved performance over traditional approaches in the automated classification of protein subcellular localization. We also demonstrate the ability of DeepLoc to classify highly divergent image sets, including images of pheromone‐arrested cells with abnormal cellular morphology, as well as images generated in different genetic backgrounds and in different laboratories. We offer an open‐source implementation that enables updating DeepLoc on new microscopy datasets. This study highlights deep learning as an important tool for the expedited analysis of high‐content microscopy data.     

Automated Learning of Subcellular Variation among Punctate Protein Patterns and a Generative Model of Their Relation to Microtubules

Characterizing the spatial distribution of proteins directly from microscopy images is a difficult problem with numerous applications in cell biology (e.g. identifying motor-related proteins) and clinical research (e.g. identification of cancer biomarkers). Here we describe the design of a system that provides automated analysis of punctate protein patterns in microscope images, including quantification of their relationships to microtubules. We constructed the system using confocal immunofluorescence microscopy images from the Human Protein Atlas project for 11 punctate proteins in three cultured cell lines. These proteins have previously been characterized as being primarily located in punctate structures, but their images had all been annotated by visual examination as being simply “vesicular”. We were able to show that these patterns could be distinguished from each other with high accuracy, and we were able to assign to one of these subclasses hundreds of proteins whose subcellular localization had not previously been well defined. In addition to providing these novel annotations, we built a generative approach to modeling of punctate distributions that captures the essential characteristics of the distinct patterns. Such models are expected to be valuable for representing and summarizing each pattern and for constructing systems biology simulations of cell behaviors.     

Context based mixture model for cell phase identification in automated fluorescence microscopy

Background  

Automated identification of cell cycle phases of individual live cells in a large population captured via automated fluorescence microscopy technique is important for cancer drug discovery and cell cycle studies. Time-lapse fluorescence microscopy images provide an important method to study the cell cycle process under different conditions of perturbation. Existing methods are limited in dealing with such time-lapse data sets while manual analysis is not feasible. This paper presents statistical data analysis and statistical pattern recognition to perform this task.     

The Yeast Resource Center Public Image Repository: A large database of fluorescence microscopy images

Background  

There is increasing interest in the development of computational methods to analyze fluorescent microscopy images and enable automated large-scale analysis of the subcellular localization of proteins. Determining the subcellular localization is an integral part of identifying a protein's function, and the application of bioinformatics to this problem provides a valuable tool for the annotation of proteomes. Training and validating algorithms used in image analysis research typically rely on large sets of image data, and would benefit from a large, well-annotated and highly-available database of images and associated metadata.     

Predicting protein subcellular locations using hierarchical ensemble of Bayesian classifiers based on Markov chains

Background  

The subcellular location of a protein is closely related to its function. It would be worthwhile to develop a method to predict the subcellular location for a given protein when only the amino acid sequence of the protein is known. Although many efforts have been made to predict subcellular location from sequence information only, there is the need for further research to improve the accuracy of prediction.     

Automated evaluation of autoantibodies on human epithelial-2 cells as an approach to standardize cell-based immunofluorescence tests

Introduction  

Analysis of autoantibodies (AAB) by indirect immunofluorescence (IIF) is a basic tool for the serological diagnosis of systemic rheumatic disorders. Automation of autoantibody IIF reading including pattern recognition may improve intra- and inter-laboratory variability and meet the demand for cost-effective assessment of large numbers of samples. Comparing automated and visual interpretation, the usefulness for routine laboratory diagnostics was investigated.     

Boosting multiclass learning with repeating codes and weak detectors for protein subcellular localization

MOTIVATION: Determining locations of protein expression is essential to understand protein function. Advances in green fluorescence protein (GFP) fusion proteins and automated fluorescence microscopy allow for rapid acquisition of large collections of protein localization images. Recognition of these cell images requires an automated image analysis system. Approaches taken by previous work concentrated on designing a set of optimal features and then applying standard machine-learning algorithms. In fact, trends of recent advances in machine learning and computer vision can be applied to improve the performance. One trend is the advances in multiclass learning with error-correcting output codes (ECOC). Another trend is the use of a large number of weak detectors with boosting for detecting objects in images of real-world scenes. RESULTS: We take advantage of these advances to propose a new learning algorithm, AdaBoost.ERC, coupled with weak and strong detectors, to improve the performance of automatic recognition of protein subcellular locations in cell images. We prepared two image data sets of CHO and Vero cells and downloaded a HeLa cell image data set in the public domain to evaluate our new method. We show that AdaBoost.ERC outperforms other AdaBoost extensions. We demonstrate the benefit of weak detectors by showing significant performance improvements over classifiers using only strong detectors. We also empirically test our method's capability of generalizing to heterogeneous image collections. Compared with previous work, our method performs reasonably well for the HeLa cell images. AVAILABILITY: CHO and Vero cell images, their corresponding feature sets (SSLF and WSLF), our new learning algorithm, AdaBoost.ERC, and Supplementary Material are available at http://aiia.iis.sinica.edu.tw/     

Automated Protein Subcellular Localization Based on Local Invariant Features

To understand the function of the encoded proteins, we need to be able to know the subcellular location of a protein. The most common method used for determining subcellular location is fluorescence microscopy which allows subcellular localizations to be imaged in high throughput. Image feature calculation has proven invaluable in the automated analysis of cellular images. This article proposes a novel method named LDPs for feature extraction based on invariant of translation and rotation from given images, the nature which is to count the local difference features of images, and the difference features are given by calculating the D-value between the gray value of the central pixel c and the gray values of eight pixels in the neighborhood. The novel method is tested on two image sets, the first set is which fluorescently tagged protein was endogenously expressed in 10 sebcellular locations, and the second set is which protein was transfected in 11 locations. A SVM was trained and tested for each image set and classification accuracies of 96.7 and 92.3 % were obtained on the endogenous and transfected sets respectively.     

Impact of image segmentation on high-content screening data quality for SK-BR-3 cells

Background  

High content screening (HCS) is a powerful method for the exploration of cellular signalling and morphology that is rapidly being adopted in cancer research. HCS uses automated microscopy to collect images of cultured cells. The images are subjected to segmentation algorithms to identify cellular structures and quantitate their morphology, for hundreds to millions of individual cells. However, image analysis may be imperfect, especially for "HCS-unfriendly" cell lines whose morphology is not well handled by current image segmentation algorithms. We asked if segmentation errors were common for a clinically relevant cell line, if such errors had measurable effects on the data, and if HCS data could be improved by automated identification of well-segmented cells.     

Quantitative Protein Localization Signatures Reveal an Association between Spatial and Functional Divergences of Proteins

Protein subcellular localization is a major determinant of protein function. However, this important protein feature is often described in terms of discrete and qualitative categories of subcellular compartments, and therefore it has limited applications in quantitative protein function analyses. Here, we present Protein Localization Analysis and Search Tools (PLAST), an automated analysis framework for constructing and comparing quantitative signatures of protein subcellular localization patterns based on microscopy images. PLAST produces human-interpretable protein localization maps that quantitatively describe the similarities in the localization patterns of proteins and major subcellular compartments, without requiring manual assignment or supervised learning of these compartments. Using the budding yeast Saccharomyces cerevisiae as a model system, we show that PLAST is more accurate than existing, qualitative protein localization annotations in identifying known co-localized proteins. Furthermore, we demonstrate that PLAST can reveal protein localization-function relationships that are not obvious from these annotations. First, we identified proteins that have similar localization patterns and participate in closely-related biological processes, but do not necessarily form stable complexes with each other or localize at the same organelles. Second, we found an association between spatial and functional divergences of proteins during evolution. Surprisingly, as proteins with common ancestors evolve, they tend to develop more diverged subcellular localization patterns, but still occupy similar numbers of compartments. This suggests that divergence of protein localization might be more frequently due to the development of more specific localization patterns over ancestral compartments than the occupation of new compartments. PLAST enables systematic and quantitative analyses of protein localization-function relationships, and will be useful to elucidate protein functions and how these functions were acquired in cells from different organisms or species. A public web interface of PLAST is available at http://plast.bii.a-star.edu.sg.     

Predicting Viral Protein Subcellular Localization with Chou's Pseudo Amino Acid Composition and Imbalance-Weighted Multi-Label K-Nearest Neighbor Algorithm

Machine learning is a kind of reliable technology for automated subcellular localization of viral proteins within a host cell or virus-infected cell. One challenge is that the viral protein samples are not only with multiple location sites, but also class-imbalanced. The imbalanced dataset often decreases the prediction performance. In order to accomplish this challenge, this paper proposes a novel approach named imbalance-weighted multi-label K-nearest neighbor to predict viral protein subcellular location with multiple sites. The experimental results by jackknife test indicate that the presented algorithm achieves a better performance than the existing methods and has great potentials in protein science.     

Unsupervised Clustering of Subcellular Protein Expression Patterns in High-Throughput Microscopy Images Reveals Protein Complexes and Functional Relationships between Proteins

Protein subcellular localization has been systematically characterized in budding yeast using fluorescently tagged proteins. Based on the fluorescence microscopy images, subcellular localization of many proteins can be classified automatically using supervised machine learning approaches that have been trained to recognize predefined image classes based on statistical features. Here, we present an unsupervised analysis of protein expression patterns in a set of high-resolution, high-throughput microscope images. Our analysis is based on 7 biologically interpretable features which are evaluated on automatically identified cells, and whose cell-stage dependency is captured by a continuous model for cell growth. We show that it is possible to identify most previously identified localization patterns in a cluster analysis based on these features and that similarities between the inferred expression patterns contain more information about protein function than can be explained by a previous manual categorization of subcellular localization. Furthermore, the inferred cell-stage associated to each fluorescence measurement allows us to visualize large groups of proteins entering the bud at specific stages of bud growth. These correspond to proteins localized to organelles, revealing that the organelles must be entering the bud in a stereotypical order. We also identify and organize a smaller group of proteins that show subtle differences in the way they move around the bud during growth. Our results suggest that biologically interpretable features based on explicit models of cell morphology will yield unprecedented power for pattern discovery in high-resolution, high-throughput microscopy images.     

Distinguishing between linear and exponential cell growth during the division cycle: Single-cell studies, cell-culture studies, and the object of cell-cycle research

Background  

Two approaches to understanding growth during the cell cycle are single-cell studies, where growth during the cell cycle of a single cell is measured, and cell-culture studies, where growth during the cell cycle of a large number of cells as an aggregate is analyzed. Mitchison has proposed that single-cell studies, because they show variations in cell growth patterns, are more suitable for understanding cell growth during the cell cycle, and should be preferred over culture studies. Specifically, Mitchison argues that one can glean the cellular growth pattern by microscopically observing single cells during the division cycle. In contrast to Mitchison's viewpoint, it is argued here that the biological laws underlying cell growth are not to be found in single-cell studies. The cellular growth law can and should be understood by studying cells as an aggregate.