This dataset contains a total of 781 Phase databases in 20 subfolders, created from Enamine REAL lead-like library downloaded in March 2021 (1.56 billion compounds). The compound order in the library was randomized and each Phase database was created from two million SMILES with Schrödinger version 2021-1 using the following commands:  ligprep -kp -retain -lab -epik -W e,-ph,7.0,-pht,1.5,-ms,16 -i 2 -t 8 -s 4 -NSTRUCT 2000 phase_database splice -new -fmt int phase_database revise -confs auto -max 1 -sample rapid Phase databases are divided into 20 subfolders named Enamine_REAL_lead-like_part_xx where xx is a number of the subfolder.Inside each folder, the individual Phase databases (2M cpds each) can be found, named as Enamine_xx_partyy_phasedb.tar.gz where xx denotes the number of the subfolder and yy is the number of the Phase database ranging from 00 to 38, except for subfolder 00, which has 40 parts.

2023