1479-1-f7zzt-PosePredictionProtocol_Stage2.txt

Name

A hierarchical docking method: XDZ_1

Software

Maestro/OpenEye/ShaEP/MGLTools/AutoDock Vina

System Preparation Parameters

Gasteiger charges

System Preparation Method

All the released crystal structures of human BACE1
protein-small molecule complexes were collected from the Protein Data Bank.
In addition, the complex structures of BACE_1 to BACE_20 released after Stage 1b were also used.
Ligand structure was prepared using the program Maestro or Omega2 in OpenEye.
Preparation for docking with Vina was done using MGLTools.

Pose Prediction Parameters

Exhaustiveness=30 #exhaustiveness of global search (default=8)
Vina scoring funtion (empirical + knowledge-based function)
Num_modes=100 #max number of poses to generate

Pose Prediction Method

For a query ligand, the OEChem TK in OpenEye was employed to calcualte ligand similarities
to the small molecules in the released BACE1 structures.The PDB entry that has the best similarity score with
the query ligand was used the template. The program Maestro or ShaEP were employed to build a complex structure,
which was then used as the initial structure for Vina docking.

Answer 1

Yes

Answer 2

Yes

1479-2-zdgqn-LigandScoringProtocol_CNNScore-PL.txt

Name

CNNScore-PL

Software

Tensorflow

Parameters

grid = 32 * 32 * 32

Method

A convolutional neural networks scoring function, PL_CNNScore,
was used to evaluate these binding models. The model was originally developed
using a training set of nearly 4000 protein-ligand structures and their corresponding binding affinities.

Answer 1

Yes

Answer 2

Yes