mlsanityData to 14 Oct 2026

Protein Discovery with Discrete Walk-Jump Sampling

arXiv 2306.12360 ↗First posted 8 Jun 2023q-bio.BM cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

We resolve difficulties in training and sampling from a discrete generative model by learning a smoothed energy function, sampling from the smoothed data manifold with Langevin Markov chain Monte Carlo (MCMC), and projecting back to the true data manifold with one-step denoising. Our Discrete Walk-Jump Sampling formalism combines the contrastive divergence training of an energy-based model and improved sample quality of a score-based model, while simplifying training and sampling by requiring only a single noise level. We evaluate the robustness of our approach on generative modeling of antibody proteins and introduce the distributional conformity score to benchmark protein generative models. By optimizing and sampling from our models for the proposed distributional conformity score, 97-100% of generated samples are successfully expressed and purified and 70% of functional designs show equal or improved binding affinity compared to known functional antibodies on the first attempt in a single round of laboratory experiments. We also report the first demonstration of long-run fast-mixing MCMC chains where diverse antibody protein classes are visited in a single MCMC chain.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 17 of its 55 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

17 of 55 references.

References · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  6. 2021Variational Diffusion Modelscited by 1,153
  7. 2021E(n) Equivariant Graph Neural Networkscited by 965
  8. 2023Protein Design with Guided Discrete Diffusioncited by 157
  9. 2022Concrete Score Matching: Generalized Score Matching for Discrete Datacited by 148
  10. 2021Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-designcited by 86
  11. 2022Conditional Antibody Design as 3D Equivariant Graph Translationcited by 75
  12. 2016Neural Machine Translation in Linear Timecited by 66
5 more
  1. 2019Neural Empirical Bayescited by 46
  2. 2016Criteria of efficiency for conformal predictioncited by 36
  3. 2018Deep Energy Estimator Networkscited by 34
  4. 2021Multimeasurement Generative Modelscited by 8
  5. 2022A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequencescited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 19; 2025: 14; 2026: 4.

38 papers.

Sort:

By area:

  1. 2024Unlocking Guidance for Discrete State-Space Diffusion and Flow Modelscited by 129
  2. 2024Dirichlet Flow Matching with Applications to DNA Sequence Designcited by 115
  3. 2024Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Reviewcited by 98
  4. 2025Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Reviewcited by 88
  5. 2024How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Frameworkcited by 48
  6. 2025Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithmscited by 47
  7. 2024Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generationcited by 36
  8. 2024Full-Atom Peptide Design based on Multi-modal Flow Matchingcited by 34
  9. 2023Improving Protein Optimization with Smoothed Fitness Landscapescited by 21
  10. 2024Structure-based drug design by denoising voxel gridscited by 19
  11. 2025α-Flow: A Unified Framework for Continuous-State Discrete Flow Matching Modelscited by 18
  12. 2024Concept Bottleneck Language Models For protein designcited by 15
26 more
  1. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 15
  2. 2024Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Spacecited by 13
  3. 2025UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Designcited by 12
  4. 2024Diffusion on language model encodings for protein sequence generationcited by 11
  5. 2024Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimizationcited by 9
  6. 2024Evolution Guided Generative Flow Networkscited by 4
  7. 2024Implicitly Guided Design with PropEn: Match your Data to Follow the Gradientcited by 4
  8. 2024JAMUN: Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensemblescited by 4
  9. 2025ProtFlow: Fast Protein Sequence Design via Flow Matching on Compressed Protein Language Model Embeddingscited by 4
  10. 2025DDPS: Discrete Diffusion Posterior Sampling for Paths in Layered Graphscited by 4
  11. 2024Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Designcited by 3
  12. 2024A noise-corrected Langevin algorithm and sampling by half-denoisingcited by 3
  13. 2025Overconfident Oracles: Limitations of In Silico Sequence Design Benchmarkingcited by 3
  14. 2025ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoodscited by 3
  15. 2025Guided Sequence-Structure Generative Modeling for Iterative Antibody Optimizationcited by 3
  16. 2024Reinforcement Learning for Sequence Design Leveraging Protein Language Modelscited by 1
  17. 2024GROOT: Effective Design of Biological Sequences with Limited Experimental Datacited by 1
  18. 2025AffinityFlow: Guided Flows for Antibody Affinity Maturationcited by 1
  19. 2024Decoupled Sequence and Structure Generation for Realistic Antibody Designcited by 0
  20. 2025Demystify Protein Generation with Hierarchical Conditional Diffusion Modelscited by 0
  21. 2025Data-Dependent Smoothing for Protein Discovery with Walk-Jump Samplingcited by 0
  22. 2025seqme: a Python library for evaluating biological sequence designcited by 0
  23. 2026Efficient Protein Optimization via Structure-aware Hamiltonian Dynamicscited by 0
  24. 2026Repurposing Protein Language Models for Latent Flow-Based Fitness Optimizationcited by 0
  25. 2026When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlowscited by 0
  26. 2026Structure-aware Reinforcement Learning for Protein Directed Evolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024On diffusion posterior sampling via sequential Monte Carlo for zero-shot scaffolding of protein motifs
  2. 2026Minimal-Action Discrete Schr"odinger Bridge Matching for Peptide Sequence Design
  3. 2025MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models
  4. 2025Learning conformational ensembles of proteins based on backbone geometry
  5. 2024Improving Antibody Design with Force-Guided Sampling in Diffusion Models
  6. 2026Conditional generation of antibody sequences with classifier-guided germline-absorbing discrete diffusion
  7. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generation
  8. 2026Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards