Robust Numerical Features for Description and Classification of Subcellular Location Patterns in Fluorescence Microscope Images

Abstract

Abstract. The ongoing biotechnology revolution promises a complete understanding of the mechanisms by which cells and tissues carry out their functions. Central to that goal is the determination of the function of each protein that is present in a given cell type, and determining a protein's location within cells is critical to understanding its function. As large amounts of data become available from genome-wide determination of protein subcellular location, automated approaches to categorizing and comparing location patterns are urgently needed. Since subcellular location is most often determined using fluorescence microscopy, we have developed automated systems for interpreting the resulting images. We report here improved numeric features for describing such images that are fairly robust to image intensity binning and spatial resolution. We validate these features by using them to train neural networks that accurately recognize all major subcellular patterns with an accuracy higher than any previously reported. Having validated the features by using them for classification, we also demonstrate using them to create Subcellular Location Trees that group similar proteins and provide a systematic framework for describing subcellular location.

Cell microarrays and RNA interference chip away at gene function

“…Excellent work has been done in this field in recent years [46][47][48] . Some researchers write custom software or macros for non-high-throughput image analysis programs, but their general applicability is limited 8,13,24,40,42,[49][50][51][52][53][54][55][56][57] .…”

Principles of Bioimage Informatics: Focus on Machine Learning of Cell Patterns

“…The results of one such experiment are shown in Figure 2, where the computer achieves 92% accuracy classifying ten location classes [23], while the human interpreter can only achieve 83% [24]. In another classification study, on the problem of cell detection, it was observed that computers perform comparably to a medium-quality expert, but were still outperformed by an experienced expert.…”

Automated proteome-wide determination of subcellular location using high throughput microscopy

“…However, we have previously proposed that unsupervised methods are more appropriate to the analysis of protein subcellular location patterns [4]. We have used the retroviral CD-tagging technology developed by Jarvik, Berget and colleagues [12] to collect increasing numbers of images of mouse 3T3 cells expressing proteins randomly-tagged with GFP and then cluster them into Subcellular Location Trees [6,13,14].…”

“…The large volume of images generated by high throughput systems requires automated systems for interpretation. Automated systems not only can recognize all major subcellular patterns [1][2][3], but they can perform as well or better than visual inspection [4][5][6]. Examples of major patterns used for development and testing of these systems are shown in Figure 1.…”