A paper co-authored by two IIGB faculty members, Tao Jiang and Thomas Girke, and CEPCEB IGERT graduate student Yiqun Cao appearing in the April 2010 issue of Bioinformatics has been selected for the Faculty of 1000 Biology site.  Faculty of 1000 Biology is an award-winning online service that highlights and evaluates the most interesting papers published in the biological sciences, based on the recommendations of over 2000 of the world’s top researchers. It was launched in January 2002 and already over 90% of the world’s top institutions subscribe (e.g., NIH, Johns Hopkins and all Max Planck Institutes). Papers are highlighted on the basis of their scientific merit rather than the journal in which they appear.

The paper, titled “Accelerated similarity searching and clustering of large compoung sets by geometric embedding and locality sensitive hashing,” was evaluated by Yi-Kuo Yu who states:

This article describes an indexing scheme for datasets of chemical compounds based on combining two complementary approaches (embedding and locality sensitive hashing), resulting in substantial improvements in retrieval times and a novel clustering algorithm. The findings of this article are useful to the chemical-compound community as well as to other fields having large datasets with complex similarity measures.

Citation:
Cao Y, Jiang T, Girke T (2010) Accelerated similarity searching and clustering of large compound sets by geometric embedding and locality sensitive hashing. Bioinformatics 26(7):953-9.