Zero-Shot 3D Drug Design by Sketching and Generating

  title={Zero-Shot 3D Drug Design by Sketching and Generating},
  author={Siyu Long and Yi Zhou and Xinyu Dai and Hao Zhou},
Drug design is a crucial step in the drug discovery cycle. Recently, various deep learning-based methods design drugs by generating novel molecules from scratch, avoiding traversing large-scale drug libraries. However, they depend on scarce experimental data or time-consuming docking simulation, leading to overfitting issues with limited training data and slow generation speed. In this study, we propose the zero-shot drug design method D ESERT ( D rug d E sign by S k E tching and gene R a T ing… 
1 Citations

3CLpro inhibitors: DEL-based molecular generation

This study generated molecules using the structure-affinity data for 3C-like protease from its own-built DEL platform, and molecular docking and affinity model based on DEL data were applied to explore the enhanced impact of transfer learning on molecule generation.



The Curious Case of Neural Text Degeneration

By sampling text from the dynamic nucleus of the probability distribution, which allows for diversity while effectively truncating the less reliable tail of the distribution, the resulting text better demonstrates the quality of human text, yielding enhanced diversity without sacrificing fluency and coherence.

Conditional molecular design with deep generative models

A conditional molecular design method that facilitates generating new molecules with desired properties is presented, built as a semisupervised variational autoencoder trained on a set of existing molecules with only a partial annotation.

A 3D Generative Model for Structure-Based Drug Design

A 3D generative model that generates molecules given a designated 3D protein binding site that exhibits high binding to specific targets and good drug properties such as drug-likeness even if the model is not explicitly optimized for them is proposed.

Highly accurate protein structure prediction with AlphaFold

This work validated an entirely redesigned version of the neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experiment in a majority of cases and greatly outperforming other methods.

Extended-Connectivity Fingerprints

A description of their implementation has not previously been presented in the literature, and ECFPs can be very rapidly calculated and can represent an essentially infinite number of different molecular features.

Pocket-Based Drug Design: Exploring Pocket Space

This review will attempt to summarize the current status of this pocket issue and will present some prospective avenues of further inquiry.

Structure-aware generation of drug-like molecules

This work proposes a novel supervised model that generates molecular graphs jointly with 3D pose in a discretised molecular space and proposes molecules with binding scores exceeding some known ligands, which could be useful in future wet-lab studies.

AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings

This work implemented Python bindings to facilitate scripting and the development of docking workflows in AutoDock Vina 1.2.0, an effort toward the unification of the features of the AutoD dock4 and AutoD Dock Vina programs.

Molecule Optimization by Explainable Evolution

Lean-Docking: Exploiting Ligands' Predicted Docking Scores to Accelerate Molecular Docking

It is shown that quality regressors can be trained to predict docking scores from molecular fingerprints and it is also clear that significant progress in the virtual screening power of docking scores is desirable.