Mining Image Date to Support Pharmaceutical Research

Wednesday, October 18, 2006 - 17:30
TH 331
Robert E. Dunkle, President A.B.E.S
GlaxoSmithKline reported that of the experiments performed in pharmaceutical research, up to 70% result in an image as the experimental result. These images are generated in nearly every phase of pharmaceutical research including target identification, genomics, proteomics, cell biology, pathology, autoradiography and more. Although an interpretation of the experimental image result is made at the time of the experiment, mining the image data to do comparative assessments has proven problematic. This presentation will discuss the architecture and practice of managing image data to enable mining. Mining is enabled from image content (visual features of the image) and image context (metadata about the image.) A web based system built on Oracle was developed to enable access and operation of the system from any java enabled browser. This provides pharmaceutical companies the ability to share data within departments, within project teams, across sites and with collaborators to review experimental results. Further, image data can be related to other experiment data to uncover relationship in say, toxicity, as a function of the properties of candidate drug compounds. An application to extract visual features from an image to deduce protein expression relative to a control will also be discussed. Difficulty of the algorithmic approach to this problem will be reviewed along with a method to resolve historical problems with spot detection and alignment of multiple 2D electrophoresis gel images.

Robert E. Dunkle, has more than 20 years’ experience in general management, business development and marketing strategy in life science informatics and process monitoring and control. Life science informatics experience has covered diverse fields such as bioinformatics, cheminformatics, image informatics, electronic laboratory notebooks and specialty applications in biology. Dunkle served as CEO of a start-up company – Scimaigx – that pioneered how information within and about images can be used facilitate the understanding of biology and decision-making. Prior to Scimagix he was president and CEO of from the National Center for Genome Resources charged with developing a mission and strategic plan for the five-year-old provider of bioinformatics and computational biology products. Formerly, Dunkle served as vice president at MDL Information Systems, Inc., where he managed the successful penetration of the company’s ISIS™ cheminformatics software platform and played an integral role in increasing the company’s valuation prior to its acquisition by Reed Elsevier in 1997. He has also served as vice president at Sierra Monitor, a start-up software and instrumentation provider. Presently, he is president of A.B.E.S., a management consulting company focusing on corporate strategy and M&A for life science and software companies.