Automated Image Analysis of Fluorescence Microscopic Images to Identify Protein-protein Interactions

Sankar Venkataraman; Jennifer Morrell-Falvey; Mitchel Doktycz; Hairong Qi

doi:10.1109/IEMBS.2005.1616535

Automated Image Analysis of Fluorescence Microscopic Images to Identify Protein-protein Interactions

Conf Proc IEEE Eng Med Biol Soc. 2005:2006:797-800. doi: 10.1109/IEMBS.2005.1616535.

Authors

Sankar Venkataraman¹, Jennifer Morrell-Falvey, Mitchel Doktycz, Hairong Qi

Affiliation

¹ Electrical Engineering Department at The university of Tennessee, Knoxville TN-37996. (Phone: 865-335-7726; e-mail: sankar@utk.edu); University of Tennessee, Knoxville TN - 37996 (e-mail: hqi@utk.edu).

PMID: 17282304
DOI: 10.1109/IEMBS.2005.1616535

Abstract

The identification of protein-protein interactions along with their spatial and temporal localization is vital data for assigning functional information to proteins. Historically, these data sets obtained from fluorescence microscopy, have been analyzed manually, a process that is both time consuming and tedious. The development of an automated system that can measure the location dynamics of the interaction between two proteins inside a live cell is a high priority. This paper describes an automated image analysis system used to identify the interactions between two proteins of interest fused to either GFP or DIV IVA, a bacterial cell division protein that localizes to the cell poles [1]. Upon the induction of DIV IVA fusion protein expression, the GFP-fusion protein will be recruited to the cell poles if a positive interaction occurs. Advanced image processing and feature extraction algorithms are discussed in detail and a statistical feature set used to quantify the image-based information is developed.