GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation

Xu, Minkai; Yu, Lantao; Yang, Song; Shi, Chence; Ermon, Stefano; Tang, J.

doi:10.48550/arxiv.2203.02923

Cited by 57 publications

(92 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposition ensures that the probability of a structure is invariant to any rigid transform [51]. In other word, if two structures are the same up to rigid transform, they have an equal probability of being sampled from the distribution of our model.…”

Section: Methodsmentioning

confidence: 99%

“…Diffusion probabilistic models learn to generate data via denoising samples from a prior distribution [44, 17, 45]. Recently, progress has been made in developing equivariant diffusion models for molecular 3D structures [51, 19, 42]. Atoms in a molecule do not have natural orientations so the generation process is different from generating protein structures.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures

Luo

Peng

et al. 2022

Preprint

103

View full text Add to dashboard Cite

Antibodies are immune system proteins that protect the host by binding to specific antigens such as viruses and bacteria. The binding between antibodies and antigens are mainly determined by the complementarity-determining regions (CDR) on the antibodies. In this work, we develop a deep generative model that jointly models sequences and structures of CDRs based on diffusion processes and equivariant neural networks. Our method is the first deep learning-based method that can explicitly target specific antigen structures and generate antibodies at atomic resolution. The model is a ''Swiss Army Knife'' which is capable of sequence-structure co-design, sequence design for given backbone structures, and antibody optimization. For antibody optimization, we propose a special sampling scheme that first perturbs the given antibody and then denoises it. As the number of available antibody structures is relatively scarce, we curate a new dataset that contains antibody-like proteins as a complement to the original antibody dataset for training. We conduct extensive experiments to evaluate the quality of both sequences and structures of designed antibodies. We find that our model could yield highly competitive results in terms of binding affinity measured by biophysical energy functions and other protein design metrics.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures

Luo

Peng

et al. 2022

Preprint

103

View full text Add to dashboard Cite

show abstract

“…Diffusion Models for Image Synthesis. Starting with the seminal works of Sohl-Dickstein et al [52] and Ho et al [21], diffusion-based generative models have improved generative modeling of artificial visual systems [11,31,61,23,64,46] and other data [32,24,62] by sequentially removing noise from a random signal to generate an image. Being likelihood-based models, they achieve high data distribution coverage with well-behaved optimization properties while producing high resolution images at unprecedented quality.…”

Section: Related Workmentioning

confidence: 99%

Retrieval-Augmented Diffusion Models

Blattmann¹,

Rombach²,

Oktay³

et al. 2022

Preprint

View full text Add to dashboard Cite

Generative image synthesis with diffusion models has recently achieved excellent visual quality in several tasks such as text-based or class-conditional image synthesis. Much of this success is due to a dramatic increase in the computational capacity invested in training these models. This work presents an alternative approach: inspired by its successful application in natural language processing, we propose to complement the diffusion model with a retrieval-based approach and to introduce an explicit memory in the form of an external database. During training, our diffusion model is trained with similar visual features retrieved via CLIP and from the neighborhood of each training instance. By leveraging CLIP's joint image-text embedding space, our model achieves highly competitive performance on tasks for which it has not been explicitly trained, such as class-conditional or text-image synthesis, and can be conditioned on both text and image embeddings. Moreover, we can apply our approach to unconditional generation, where it achieves state-of-the-art performance. Our approach incurs low computational and memory overheads and is easy to implement. We discuss its relationship to concurrent work and will publish code and pretrained models soon.

show abstract

“…Latterly, diffusion models become a favored choice in conformation generation [78]. Xu et al [97] introduces a GeoDiff by progressively injecting and eliminating small noises. However, its perturbations evolve over discrete times.…”

Section: Related Workmentioning

confidence: 99%

DiffMD: A Geometric Diffusion Model for Molecular Dynamics Simulations

Wu¹,

Zhang²,

Jin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Molecular dynamics (MD) has long been the de facto choice for modeling complex atomistic systems from first principles, and recently deep learning become a popular way to accelerate it. Notwithstanding, preceding approaches depend on intermediate variables such as the potential energy or force fields to update atomic positions, which requires additional computations to perform back-propagation. To waive this requirement, we propose a novel model called ScoreMD by directly estimating the gradient of the log density of molecular conformations. Moreover, we analyze that diffusion processes highly accord with the principle of enhanced sampling in MD simulations, and is therefore a perfect match to our sequential conformation generation task. That is, ScoreMD perturbs the molecular structure with a conditional noise depending on atomic accelerations and employs conformations at previous timeframes as the prior distribution for sampling. Another challenge of modeling such a conformation generation process is that the molecule is kinetic instead of static, which no prior studies strictly consider. To solve this challenge, we introduce a equivariant geometric Transformer as a score function in the diffusion process to calculate the corresponding gradient. It incorporates the directions and velocities of atomic motions via 3D spherical Fourier-Bessel representations. With multiple architectural improvements, we outperforms state-of-the-art baselines on MD17 and isomers of C7O2H10. This research provides new insights into the acceleration of new material and drug discovery. IntroductionsMolecular dynamics (MD) [18,33,86], an in silico tool that simulates complex atomic systems based on first principles, has exerted dramatic impacts in scientific research. Instead of yielding an average structure by experimental approaches including X-ray crystallography and cryo-EM, MD simulations can capture the sequential behavior of molecules in full atomic details at very fine temporal resolution, and thus allows researchers to quantify how much various regions of the molecule move at equilibrium and what types of structural fluctuations they undergo. In the areas of molecular biology and drug discovery [26], the most basic and intuitive application of MD is to assess the mobility or flexibility * Equal contributions.† The corresponding author.Preprint. Under review.

show abstract

GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation

Cited by 57 publications

References 15 publications

Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures

Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures

Retrieval-Augmented Diffusion Models

DiffMD: A Geometric Diffusion Model for Molecular Dynamics Simulations

Contact Info

Product

Resources

About