DiGress: Discrete Denoising diffusion for graph generation

Vignac, Clément; Krawczuk, Igor; Siraudin, Antoine; Wang, Bohan; Cevher, Volkan; Frossard, Pascal

doi:10.48550/arxiv.2209.14734

Cited by 17 publications

(28 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the DPMs for continuous data, some works study discrete DPMs and achieve impressive results on generating texts (Austin et al, 2021;Li et al, 2022), graphs (Vignac et al, 2022) and images (Hoogeboom et al, 2021). Inspired by these progresses, DPMs have been adopted to solve problems in chemistry and biology domain, including molecule generation (Xu et al, 2022b;Hoogeboom et al, 2022;Wu et al, 2022c;Jing et al, 2022), molecular representation learning (Liu et al, 2022), protein structure prediction (Wu et al, 2022b), protein-ligand binding (Corso et al, 2022), protein design (Anand & Achim, 2022;Luo et al, 2022;Ingraham et al, 2022;Watson et al, 2022) and motif-scaffolding (Trippe et al, 2022).…”

Section: Related Workmentioning

confidence: 99%

Physics-Inspired Protein Encoder Pre-Training via Siamese Sequence-Structure Diffusion Trajectory Prediction

Zhang¹,

Xu²,

Lozano³

et al. 2023

Preprint

View full text Add to dashboard Cite

Pre-training methods on proteins are recently gaining interest, leveraging either protein sequences or structures, while modeling their joint energy landscape is largely unexplored. In this work, inspired by the success of denoising diffusion models, we propose the DiffPreT approach to pretrain a protein encoder by sequence-structure multimodal diffusion modeling. DiffPreT guides the encoder to recover the native protein sequences and structures from the perturbed ones along the multimodal diffusion trajectory, which acquires the joint distribution of sequences and structures. Considering the essential protein conformational variations, we enhance DiffPreT by a physicsinspired method called Siamese Diffusion Trajectory Prediction (SiamDiff) to capture the correlation between different conformers of a protein. SiamDiff attains this goal by maximizing the mutual information between representations of diffusion trajectories of structurally-correlated conformers. We study the effectiveness of DiffPreT and SiamDiff on both atom-and residue-level structure-based protein understanding tasks. Experimental results show that the performance of DiffPreT is consistently competitive on all tasks, and SiamDiff achieves new state-of-the-art performance, considering the mean ranks on all tasks. The source code will be released upon acceptance.

show abstract

Section: Related Workmentioning

confidence: 99%

Physics-Inspired Protein Encoder Pre-Training via Siamese Sequence-Structure Diffusion Trajectory Prediction

Zhang¹,

Xu²,

Lozano³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Then, attention weights are multiplied with V m1 to create the final representation of the annotation matrix. The new representation of the adjacency matrix is the concatenated version of the [45,46]. For our default model, output dimension size of the transformer is 128 for both the annotation and adjacency.…”

Section: Gan1 Generatormentioning

confidence: 99%

Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks

Ünlü¹,

Çevrim²,

Sarıgün³

et al. 2023

Preprint

View full text Add to dashboard Cite

Discovering novel drug candidate molecules is one of the most fundamental and critical steps in drug development. Generative deep learning models, which create synthetic data given a probability distribution, have been developed with the purpose of picking completely new samples from a partially known space. Generative models offer high potential for designing de novo molecules; however, in order for them to be useful in real-life drug development pipelines, these models should be able to design target-specific molecules, which is the next step in this field. In this study, we propose a novel generative system, DrugGEN, for the de novo design of drug candidate molecules that interact with selected target proteins. The proposed system represents compounds and protein structures as graphs and processes them via serially connected two generative adversarial networks comprising graph transformers. DrugGEN is implemented with five independent models, each with a unique sample generation routine. The system

show abstract

“…Baselines. We compare our HGGT with twelve deep graph generative models: GraphVAE [5], GraphRNN [18], GNF [37], GRAN [23], EDP-GNN [24], GraphGen [13], GraphAF [25], GraphDF [26], SPECTRE [35], GDSS [8], DiGress [9], and GDSM [36]. We provide a detailed description of the implementations in Appendix E.…”

Section: Generic Graph Generationmentioning

confidence: 99%

“…Baselines. We compare HGGT with eight deep graph generative models: EDP-GNN [24], MoFlow [39], GraphAF [25], GraphDF [26], GraphEBM [7], GDSS [8], DiGress [9], and GDSM [36]. We provide a detailed description of implementation in Appendix E. Results.…”

Section: Molecular Graph Generationmentioning

confidence: 99%

Finding Key Structures in MMORPG Graph with Hierarchical Graph Summarization

Jang

Park²,

Jang

et al. 2022

ACM Trans. Knowl. Discov. Data

View full text Add to dashboard Cite

What are the key structures existing in a large real-world MMORPG (Massively Multiplayer Online Role-Playing Game) graph? How can we compactly summarize an MMORPG graph with hierarchical node labels, considering substructures at different levels of hierarchy? Recent MMORPGs generate complex interactions between entities inducing a heterogeneous graph where each entity has hierarchical labels. Succinctly summarizing a heterogeneous MMORPG graph is crucial to better understand its structure; however it is a challenging task since it needs to handle complex interactions and hierarchical labels efficiently. Although there exist few methods to summarize a large-scale graph, they do not deal with heterogeneous graphs with hierarchical node labels. We propose GSHL , a novel method that summarizes a heterogeneous graph with hierarchical labels. We formulate the encoding cost of hierarchical labels using MDL (Minimum Description Length). GSHL exploits the formulation to identify and segment subgraphs, and discovers compact and consistent structures in the graph. Experiments on a large real-world MMORPG graph with multi-million edges show that GSHL is a useful and scalable tool for summarizing the graph, finding important structures in the graph, and finding similar users.

show abstract

DiGress: Discrete Denoising diffusion for graph generation

Cited by 17 publications

References 0 publications

Physics-Inspired Protein Encoder Pre-Training via Siamese Sequence-Structure Diffusion Trajectory Prediction

Physics-Inspired Protein Encoder Pre-Training via Siamese Sequence-Structure Diffusion Trajectory Prediction

Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks

Finding Key Structures in MMORPG Graph with Hierarchical Graph Summarization

Contact Info

Product

Resources

About