In_house_machine_learning_score/Maestro/GOLD
Maestro_Schrodinger Suite_2016-2/CCDC_Gold Suite_2016/R
Use PH values listed in Data_set_fxr_crystallization_conditions.csv, use other default parameters in Ligprep of Schrodinger
Gold suite with autoscale = 0.2 and goldscore as a scoring function
RandomForest with number of trees = 550, using a total of number of features
Method: The training set is from PDBbind refined sets v2015. Gold docking software is used to get decoy sets, and the top poses are selected by our in-house software. All features of the training and test sets are generated by our in house machine learning tool. RandomForst is used to get predicted values.
Maestro/Gold/FRI-Score
Maestro Schrodinger Suite_2016-2/CCDC Gold Suite 2016
(prepwizard) -propka_pH # Use PH values listed in Data_set_fxr_crystallization_conditions.csv
(prepwizard) -fillsidechains -s # fillsidechains for target protein
(ligprep) -adjust_itc -ph # pH given in Data_set_fxr_crystallization_conditions.csv
Maestro's prepwizard was used to optimize the protein with PH value and fillsidechains option.
Maestro's ligprep was used to generate optimized 3d structure of ligands from 2d structure. Sample ligand was manually filled into the binding pocket as the reference ligand. Position of the reference ligand was set as binding site.
autoscale = 0.2
floodfill_center = cavity_from_ligand 8 atoms
gold_fitfunc_path = goldscore # use goldscore as scoring function to generate poses
num_poses = 500 # generate 500 poses as pose_pool for each complex
Use Gold to get top 50 poses. The top 5 candidates are selected by our in house machine learning.