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

Abstract

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.

Figure 1

Illustration of morphological features extracted from images of two subcellular patterns. Objects are defined using an automated threshold selection method. The size and distance features are measured in pixels.

Figure 2

Typical images from the 10-class 2DHELA image dataset. Red color represents DNA staining and green color represents target protein fluorescence.

Figure 3

Typical images from 11-class 3DHeLa image dataset. The eleventh (cytoplasmic) pattern is represented by the blue color. Red, blue and green colors represent DNA staining, total protein staining and target protein fluorescence. Projections on the X-Y (top) and the X-Z (bottom) planes are shown. Image © Carnegie Mellon University; used with permission.

Figure 4

A consensus subcellular location tree generated on the 3D3T3 image dataset. The rows show the name of the tagged protein (where known), the description assigned from visual inspection, and the subcellular location inferred from annotations in the Gene Ontology (GO) database. Names of proteins whose location from visual inspection differs significantly from that inferred from GO annotation are preceeded with **. The sum of length of vertical edges connecting two proteins represents the distance between them. From reference (26).