How good are current pocket based 3D generative models? : The benchmark set and evaluation on protein pocket based 3D molecular generative models

12 August 2024, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

The development of three-dimensional (3D) molecular generative model based on protein pockets has recently attracted a lot of attentions. This type of model aims to achieve the simultaneous generation of molecular graph and 3D binding conformation under the constraint of protein binding. Various pocket based generative models have been proposed, however, currently there is a lack of systematic and objective evaluation metrics for these models. To address this issue, a comprehensive benchmark dataset, named as POKMOL-3D, is proposed to evaluate protein pocket based 3D molecular generative models. It includes 32 protein targets together with their known active compounds as a test set to evaluate the versatility of generation models to mimick the real-world scenario. Additionally, a series of 2D and 3D evaluation metrics was integrated to assess the quality of generated molecular structures and their binding conformations. It is expected that this work can enhance our comprehension of the effectiveness and weakness of current 3D generative models, and stimulate the discussion on challenges and useful guidance for developing next wave of molecular generative models.

Keywords

Molecular generative model
Structure-based drug design
Protein pocket
Benchmark

Supplementary materials

Title
Description
Actions
Title
POKMOL-3D: A Comprehensive Benchmark Set on Protein Pocket Based 3D Molecular Generative Models
Description
In current study, a novel benchmark dataset, named POKMOL-3D, was compiled specifically for evaluating pocket based 3D generative models, including a set of comprehensive metrics for measuring model quality from various perspectives. Nine recently published 3D models were selected for carrying out a benchmark study on the 32 protein pockets included in the dataset, along with the SMILES based REINVENT model as baseline. Through this study, it is our hope that the proposed evaluation framework can be useful in facilitating the future advancement of pocket based 3D generative model.
Actions

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.