De Novo Molecule Design Through the Molecular Generative Model Conditioned by 3D Information of Protein Binding Sites

De novo molecule design through molecular generative model is gaining increasing attention in recent years. Here a novel generative model was proposed by integrating the 3D structural information of the protein binding pocket into the conditional RNN (cRNN) model to control the generation of drug-like molecules. In this model, the composition of protein binding pocket is effectively characterized through a coarse-grain strategy and the three-dimensional information of the pocket can be represented by the sorted eigenvalues of the coulomb matrix (EGCM) of the coarse-grained atoms composing the binding pocket. In current work, we used our EGCM method and a previously reported binding pocket descriptor DeeplyTough to train cRNN models and compared their performance. It has been shown that the molecules generated with the control of protein environment information have a clear tendency on generating compounds with higher similarity to the original X-ray bound ligand than normal RNN model and also achieving better performance in terms of docking scores. Our results demonstrate the potential application of EGCM controlled generative model for the targeted molecule generation and guided exploration on the drug-like chemical space.

Download Full-text

De Novo Molecule Design Through Molecular Generative Model Conditioned by 3D Information of Protein Binding Sites

10.26434/chemrxiv.13498332 ◽

2020 ◽

Author(s):

Mingyuan Xu ◽

Ting Ran ◽

Hongming Chen

Keyword(s):

Protein Binding ◽

De Novo ◽

Structural Information ◽

Chemical Space ◽

Three Dimensional ◽

Binding Pocket ◽

Generative Model ◽

Coarse Grained ◽

Molecule Design ◽

3D Information

De novo molecule design through molecular generative model is gaining increasing attention in recent years. Here a novel generative model was proposed by integrating the 3D structural information of the protein binding pocket into the conditional RNN (cRNN) model to control the generation of drug-like molecules. In this model, the composition of protein binding pocket is effectively characterized through a coarse-grain strategy and the three-dimensional information of the pocket can be represented by the sorted eigenvalues of the coulomb matrix (EGCM) of the coarse-grained atoms composing the binding pocket. In current work, we used our EGCM method and a previously reported binding pocket descriptor DeeplyTough to train cRNN models and compared their performance. It has been shown that the molecules generated with the control of protein environment information have a clear tendency on generating compounds with higher similarity to the original X-ray bound ligand than normal RNN model and also achieving better performance in terms of docking scores. Our results demonstrate the potential application of EGCM controlled generative model for the targeted molecule generation and guided exploration on the drug-like chemical space.

Download Full-text

EVALUATION OF TISSUE STEROID BINDING IN VITRO

Acta Endocrinologica ◽

10.1530/acta.0.068s223 ◽

1971 ◽

Vol 68 (1_Suppl) ◽

pp. S223-S246 ◽

Cited By ~ 2

Author(s):

C. R. Wira ◽

H. Rochefort ◽

E. E. Baulieu

Keyword(s):

Protein Binding ◽

Binding Sites ◽

Experimental System ◽

Specific Protein ◽

Coupling Mechanism ◽

Target Tissue ◽

Protein Binding Sites ◽

Definition Of ◽

Hormone Specificity

ABSTRACT The definition of a RECEPTOR* in terms of a receptive site, an executive site and a coupling mechanism, is followed by a general consideration of four binding criteria, which include hormone specificity, tissue specificity, high affinity and saturation, essential for distinguishing between specific and nonspecific binding. Experimental approaches are proposed for choosing an experimental system (either organized or soluble) and detecting the presence of protein binding sites. Techniques are then presented for evaluating the specific protein binding sites (receptors) in terms of the four criteria. This is followed by a brief consideration of how receptors may be located in cells and characterized when extracted. Finally various examples of oestrogen, androgen, progestagen, glucocorticoid and mineralocorticoid binding to their respective target tissues are presented, to illustrate how researchers have identified specific corticoid and mineralocorticoid binding in their respective target tissue receptors.

Download Full-text