TY - DATA T1 - OCEAN: Optimized Cross rEActivity estimatioN PY - 2016/09/26 AU - Paul Czodrowski AU - Wolf-Guido Bolick UR - https://acs.figshare.com/articles/journal_contribution/OCEAN_Optimized_Cross_rEActivity_estimatioN/3859521 DO - 10.1021/acs.jcim.6b00067.s001 L4 - https://ndownloader.figshare.com/files/6054630 KW - success rate KW - OCEAN performance check KW - success rates KW - Optimized Cross rEActivity estimatioN KW - ChEMBL 20 compounds KW - ChEMBL data KW - phenotypic screens KW - source code KW - ChEMBL 21 compounds KW - drug discovery process KW - heuristics approach KW - New ChEMBL data KW - TOP 10 ranks KW - off-target elucidation KW - target prediction tool KW - polypharmacological compounds KW - ChEMBL 20 N2 - The prediction of molecular targets is highly beneficial during the drug discovery process, be it for off-target elucidation or deconvolution of phenotypic screens. Here, we present OCEAN, a target prediction tool exclusively utilizing publically available ChEMBL data. OCEAN uses a heuristics approach based on a validation set containing almost 1000 drug ← → target relationships. New ChEMBL data (ChEMBL20 as well as ChEMBL21) released after the validation was used for a prospective OCEAN performance check. The success rates of OCEAN to predict correctly the targets within the TOP10 ranks are 77% for recently marketed drugs and 62% for all new ChEMBL20 compounds and 51% for all new ChEMBL21 compounds. OCEAN is also capable of identifying polypharmacological compounds; the success rate for molecules simultaneously hitting at least two targets is 64% to be correctly predicted within the TOP10 ranks. The source code of OCEAN can be found at http://www.github.com/rdkit/OCEAN ER -