By a News Reporter-Staff News Editor at Information Technology Newsweekly -- Researchers detail new data in Bioinformatics. According to news reporting originating in Pittsburgh, Pennsylvania, by VerticalNews journalists, research stated, "Evaluation of previous systems for automated determination of subcellular location from microscope images has been done using datasets in which each location class consisted of multiple images of the same representative protein. Here, we frame a more challenging and useful problem where previously unseen proteins are to be classified."
The news reporters obtained a quote from the research from Carnegie Mellon University, "Using CD-tagging, we generated two new image datasets for evaluation of this problem, which contain several different proteins for each location class. Evaluation of previous methods on these new datasets showed that it is much harder to train a classifier that generalizes across different proteins than one that simply recognizes a protein it was trained on. We therefore developed and evaluated additional approaches, incorporating novel modifications of local features techniques. These extended the notion of local features to exploit both the protein image and any reference markers that were imaged in parallel. With these, we obtained a large accuracy improvement in our new datasets over existing methods."
According to the news reporters, the research concluded: "Additionally, these features help achieve classification improvements for other previously studied datasets."
For more information on this research see: Determining the subcellular location of new proteins from microscope images using local features. Bioinformatics, 2013;29(18):2343-2349. Bioinformatics can be contacted at: Oxford Univ Press, Great Clarendon St, Oxford OX2 6DP, England. (Oxford University Press - www.oup.com/; Bioinformatics - bioinformatics.oxfordjournals.org)
Our news correspondents report that additional information may be obtained by contacting L.P. Coelho, Carnegie Mellon University, Dept. of Machine Learning, Pittsburgh, PA 15213, United States. Additional authors for this research include J.D. Kangas, A.W. Naik, E. Osuna-Highley, E. Glory-Afshar, M. Fuhrman, R. Simha, P.B. Berget, J.W. Jarvik and R.F. Murphy.
Keywords for this news article include: Peptides, Proteins, Pittsburgh, Amino Acids, Pennsylvania, United States, Bioinformatics, North and Central America
Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2013, NewsRx LLC