Torsional Diffusion for Molecular Conformer Generation

By Bowen Jing, Gabriele Corso, Jeffrey Chang, Regina Barzilay, Tommi S. Jaakkola. 2022

391 citations recorded by the source corpus.

Molecular conformer generation is a fundamental task in computational chemistry. Several machine learning approaches have been developed, but none have outperformed state-of-the-art cheminformatics methods. We propose torsional diffusion, a novel diffusion framework that operates on the space of torsion angles via a diffusion process on the hypertorus and an extrinsic-to-intrinsic score model. On a standard benchmark of drug-like molecules, torsional diffusion generates superior conformer ensembles compared to machine learning and cheminformatics methods in terms of both RMSD and chemical properties, and is orders of magnitude faster than previous diffusion-based models. Moreover, our model provides exact likelihoods, which we employ to build the first generalizable Boltzmann generator. Code is available at https://github.com/gcorso/torsional-diffusion.

Subfields: Modeling and Simulation, Molecular Biology, Generative Models, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Modeling and Simulation

Arnaud Doucet

In Molecular Biology

In Generative Models

In Computational Chemistry & Drug Discovery

Citations in the corpus

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (2022, methodology): “To circumvent this issue, at training time we predict c with RDKit and replace x ⋆ with arg min x † ∈M c RMSD( x ⋆ , x † ) using the conformer matching procedure described in [6].”
Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models (2022, background): “To address such limitations, recent work has extended the diffusion framework to compact Riemannian manifolds [11], which has been in turn adapted to modeling rotational diffusion as the repeated application of a heat kernel on a torus [22].”
Equivariant 3D-conditional diffusion model for molecular linker design (2022, neutral): “More details on datasets, baselines and metrics can be found in Methods.”
TabDDPM: Modelling Tabular Data with Diffusion Models (2022, background): “…fields, such as NLP (Austin et al., 2021; Li et al., 2022), waveform signal processing (Kong et al., 2020; Chen et al., 2020b), molecular graphs (Jing et al., 2022; Hooge-boom et al., 2022), time series (Tashiro et al., 2021), testifying the universality of diffusion models across a wide range…”
DiffusionDet: Diffusion Model for Object Detection (2022, background): “…models have recently demonstrated remarkable results in fields including computer vision [4,21,33,35,39,68,71,75,76,82,104,108], nature language processing [3,30,52], audio processing [41,48,50,70, 91,100,103], graph-related topics [42], interdisciplinary applications [2,40,44,78,94,99,102], etc.”
DDGR: Continual Learning with Deep Diffusion-based Generative Replay (2023, background): “…have shown their exquisite potential in the field of computer vision (Dhariwal & Nichol, 2021; Ho et al., 2022b; Li et al., 2022; Luo & Hu, 2021), audio processing (Chen et al., 2021; Popov et al., 2021; Kim et al., 2022), and AI for science (Luo et al., 2021; Xu et al., 2022; Jing et al., 2022).”
SE(3) diffusion model with application to protein backbone generation (2023, background): “In particular, Jing et al. (2022) consider the product of tori for molecular conformer generation, Corso et al. (2022) on the product space R3 × SO(3) × SO(2)m for protein docking applications and Leach et al. (2022) on SO(3) for rotational alignment.”
Structure-based drug design with equivariant diffusion models (2022, neutral): “Torsional Diffusion [73] focuses on a conditional setting where molecular conformations (atomic coordinates) are generated from molecular graphs (atom types and bonds).”
Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, background): “Torsional diffusion [107] presents a new diffusion framework that makes operations on the space of torsion angles with a diffusion process on the hyperspace and an extrinsic-to-intrinsic scoring model.”
Protein structure generation via folding diffusion (2022, methodology): “, modelling the angles that specify a small molecule, to sample from the space of energetically favorable molecular conformations (Jing et al., 2022).”