Premium
From Virtual to Real Screening for D 3 Dopamine Receptor Ligands
Author(s) -
Byvatov Evgeny,
Sasse Britta C.,
Stark Holger,
Schneider Gisbert
Publication year - 2005
Publication title -
chembiochem
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.05
H-Index - 126
eISSN - 1439-7633
pISSN - 1439-4227
DOI - 10.1002/cbic.200400400
Subject(s) - virtual screening , support vector machine , receptor , computer science , similarity (geometry) , computational biology , value (mathematics) , predictive value , information retrieval , ligand (biochemistry) , small molecule , chemistry , combinatorial chemistry , artificial intelligence , bioinformatics , machine learning , biology , biochemistry , drug discovery , medicine , image (mathematics)
Even in the absence of receptor‐structure information, iterative virtual screening cycles with support vector machines (SVM) offer a rapid way to identify novel leads with minimal experimental effort. First, an SVM is trained for prediction of D 3 receptor‐selective ligands. Based on the prediction of this virtual filter, compounds are tested for binding affinity at D 2 and D 3 receptors. Second, a similarity search is performed with the most promising candidate from round one. Four out of five compounds from the final hit list exhibited nanomolar affinity at the D 3 receptor including a novel scaffold structure. The K i value of the best molecule ( 1 ) was 40±6 n M .