Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+

TL;DR

Uni-Mol+ is a novel deep learning framework that iteratively refines 3D molecular conformations to accurately predict quantum chemical properties, outperforming previous methods that relied on less precise data representations.

Contribution

The paper introduces Uni-Mol+, a two-track Transformer model that iteratively updates molecular conformations to improve quantum property predictions, bridging the gap between raw conformations and electronic structure methods.

Findings

Significant accuracy improvements on multiple datasets.

Effective iterative conformation refinement process.

Open-source code and models available.

Abstract

Recent developments in deep learning have made remarkable progress in speeding up the prediction of quantum chemical (QC) properties by removing the need for expensive electronic structure calculations like density functional theory. However, previous methods learned from 1D SMILES sequences or 2D molecular graphs failed to achieve high accuracy as QC properties primarily depend on the 3D equilibrium conformations optimized by electronic structure methods, far different from the sequence-type and graph-type data. In this paper, we propose a novel approach called Uni-Mol+ to tackle this challenge. Uni-Mol+ first generates a raw 3D molecule conformation from inexpensive methods such as RDKit. Then, the raw conformation is iteratively updated to its target DFT equilibrium conformation using neural networks, and the learned conformation will be used to predict the QC properties. To effectively learn this update process towards the equilibrium conformation, we introduce a two-track Transformer model backbone and train it with the QC property prediction task. We also design a novel approach to guide the model's training process. Our extensive benchmarking results demonstrate that the proposed Uni-Mol+ significantly improves the accuracy of QC property prediction in various datasets. We have made the code and model publicly available at \url{https://github.com/dptech-corp/Uni-Mol}.