Vebjorn Ljosa is a computational biologist in the Imaging Platform of the Broad Institute. The goal of his research is to characterize chemical compounds and genes by using high-throughput microscopy to study their effects on cultured cells.
Ljosa develops machine-learning and data-analysis techniques to take hundreds of measurements from the CellProfiler software, developed by the Imaging Platform, and identify subtle phenotypes, profile compounds or genes with respect to those phenotypes, and group compounds or genes that have similar effects.
Ljosa joined the Broad in 2007 with experience in the world of databases and the development of index structures for complex, non-traditional datatypes. He earned his Ph.D. in computer science from the University of California, Santa Barbara, where his thesis work focused on querying and mining microscopy images, in particular the probabilistic, or uncertain, values that result from analyzing such images.Select Publications
Kamentsky L, et al. Improved structure, function, and compatibility for CellProfiler: modular high-throughput image analysis software. Bioinformatics 2011; 27 (8): 1179-1180.
Riklin-Raviv, et al. Morphology-Guided Graph Search for Untangling Objects: C. elegans Analysis. Proceedings of the 13th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). 2010; p. 634-641.
Wählby C, et al. Resolving clustered worms via probabilistic shape models. Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI). April 2010; p. 552–555.