Definition and Detection of Outliers in Chemical Space Export

@article{CasalegnoSB08, abstract = {Abstract: Detection of outliers is a complex and challenging area of research in chemical theory. Among current notions, that of outliers in the chemical spacedescriptorsis meaningful with multiple applications in the field of drug discovery and predictive modeling. Presented here is a new framework for outlier detection, relying on a discrete, fragment-based representation of the molecular structures. From this starting point, a recursive method is developed that quantifies the contribution of fragments to compound description and identifies outliers in chemical structure databases according to a novel definition. In contrast to existing detection routes, this approach avoids the use of thresholds usually required to quantify outlying behavior. Three chemical databases are investigated to demonstrate its generality and flexibility. The result reveals a new species of outliers, compounds with no specific structural features, rather than unique ones.}, address = {IRFMN, Mario Negri Institute for Pharmacological Research, Via La Masa, 19, 20156 Milano, Italy, and Dipartimento di Chimica Organica e Industriale, Universita� degli Studi di Milano, Via Venezian 21, 20133 Milano, Italy}, author = {Casalegno, Mose\&\#x300; and Sello, Guido and Benfenati, Emilio}, citeulike-article-id = {3147171}, citeulike-linkout-0 = {http://dx.doi.org/10.1021/ci7004065}, citeulike-linkout-1 = {http://pubs.acs.org/doi/abs/10.1021/ci7004065}, doi = {10.1021/ci7004065}, journal = {J. Chem. Inf. Model.}, keywords = {chemistry, space}, month = {July}, posted-at = {2008-08-22 08:23:32}, priority = {2}, title = {Definition and Detection of Outliers in Chemical Space}, url = {http://dx.doi.org/10.1021/ci7004065}, year = {2008} }

TY - JOUR ID - CasalegnoSB08 L3 - citeulike-article-id:3147171 N2 - Abstract: Detection of outliers is a complex and challenging area of research in chemical theory. Among current notions, that of outliers in the chemical spacedescriptorsis meaningful with multiple applications in the field of drug discovery and predictive modeling. Presented here is a new framework for outlier detection, relying on a discrete, fragment-based representation of the molecular structures. From this starting point, a recursive method is developed that quantifies the contribution of fragments to compound description and identifies outliers in chemical structure databases according to a novel definition. In contrast to existing detection routes, this approach avoids the use of thresholds usually required to quantify outlying behavior. Three chemical databases are investigated to demonstrate its generality and flexibility. The result reveals a new species of outliers, compounds with no specific structural features, rather than unique ones. JF - J. Chem. Inf. Model. AD - IRFMN, Mario Negri Institute for Pharmacological Research, Via La Masa, 19, 20156 Milano, Italy, and Dipartimento di Chimica Organica e Industriale, Universita� degli Studi di Milano, Via Venezian 21, 20133 Milano, Italy TI - Definition and Detection of Outliers in Chemical Space KW - chemistry KW - space AU - Casalegno, Mosè AU - Sello, Guido AU - Benfenati, Emilio PY - 2008/07/25/ UR - http://dx.doi.org/10.1021/ci7004065 ER -