mlsanityData to 7 Oct 2026

Biological Sequence Design with GFlowNets

arXiv 2203.04115 ↗First posted 2 Mar 2022q-bio.BM cs.LGcited by 172

Not on the map. Why?

Abstract (arXiv)

Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several rounds of molecule ideation and expensive wet-lab evaluations. These experiments can consist of multiple stages, with increasing levels of precision and cost of evaluation, where candidates are filtered. This makes the diversity of proposed candidates a key consideration in the ideation phase. In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candidate solutions, with the objective to obtain a diverse batch of useful (as defined by some utility function, for example, the predicted anti-microbial activity of a peptide) and informative candidates after each round. We also propose a scheme to incorporate existing labeled datasets of candidates, in addition to a reward function, to speed up learning in GFlowNets. We present empirical results on several biological sequence design tasks, and we find that our method generates more diverse and novel batches with high scoring candidates compared to existing approaches.

Key facts. Cited by 172 papers in the map (data through 7 Oct 2026). Builds on 21 of its 50 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

21 of 50 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  6. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  7. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  8. 2019Evaluating Protein Transfer Learning with TAPEcited by 229
  9. 2017Bridging the Gap Between Value and Policy Based Reinforcement Learningcited by 178
  10. 2020ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computingcited by 162
  11. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  12. 2019Conditioning by adaptive sampling for robust designcited by 110
9 more
  1. 2022Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimizationcited by 96
  2. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 87
  3. 2019Model Inversion Networks for Model-Based Optimizationcited by 83
  4. 2020AdaLead: A simple and robust adaptive greedy search algorithm for sequence designcited by 63
  5. 2017The reparameterization trick for acquisition functionscited by 61
  6. 2020Optimizing Molecules using Efficient Queries from Property Evaluationscited by 50
  7. 2021Benchmarking deep generative models for diverse antibody sequence designcited by 9
  8. 2019Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functionscited by 6
  9. 2022Fourier Representations for Black-Box Optimization over Categorical Variablescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 12; 2023: 49; 2024: 46; 2025: 40; 2026: 25.

172 papers.

Sort:

By area:

  1. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 129
  2. 2022GFlowNets and variational inferencecited by 103
  3. 2022Multi-Objective GFlowNetscited by 100
  4. 2023A theory of continuous generative flow networkscited by 98
  5. 2023Amortizing intractable inference in large language modelscited by 94
  6. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 83
  7. 2023Towards Understanding and Improving GFlowNet Trainingcited by 74
  8. 2023Robust Scheduling with GFlowNetscited by 67
  9. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  10. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  11. 2024Learning diverse attacks on large language models for robust red-teaming and safety tuningcited by 54
  12. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
38 more
  1. 2022Generative Augmented Flow Networkscited by 48
  2. 2023Sample-efficient Multi-objective Molecular Optimization with GFlowNetscited by 48
  3. 2024Improved off-policy training of diffusion samplerscited by 47
  4. 2023Local Search GFlowNetscited by 45
  5. 2023GFlowNet-EM for learning compositional latent variable modelscited by 40
  6. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  7. 2024Discrete Probabilistic Inference as Control in Multi-path Environmentscited by 40
  8. 2022A Variational Perspective on Generative Flow Networkscited by 39
  9. 2025FlowRL: Matching Reward Distributions for LLM Reasoningcited by 38
  10. 2024Genetic-guided GFlowNets for Sample Efficient Molecular Optimizationcited by 36
  11. 2024Full-Atom Peptide Design based on Multi-modal Flow Matchingcited by 34
  12. 2023Stochastic Generative Flow Networkscited by 32
  13. 2023Thompson sampling for improved exploration in GFlowNetscited by 31
  14. 2024Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNetscited by 30
  15. 2023Crystal-GFN: sampling crystals with desirable properties and constraintscited by 29
  16. 2023Distributional GFlowNets with Quantile Flowscited by 28
  17. 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
  18. 2024Improving GFlowNets for Text-to-Image Diffusion Alignmentcited by 27
  19. 2023Learning to Scale Logits for Temperature-Conditional GFlowNetscited by 26
  20. 2025Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modelingcited by 25
  21. 2022Unifying Generative Models with GFlowNets and Beyondcited by 24
  22. 2023Learning Energy Decompositions for Partial Inference of GFlowNetscited by 24
  23. 2023Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequencescited by 23
  24. 2024Adaptive teachers for amortized samplerscited by 23
  25. 2022GFlowOut: Dropout with Generative Flow Networkscited by 22
  26. 2024GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learningcited by 22
  27. 2023Improving Protein Optimization with Smoothed Fitness Landscapescited by 20
  28. 2023PhyloGFN: Phylogenetic inference with generative flow networkscited by 20
  29. 2024MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximationcited by 20
  30. 2024Generative Flows on Synthetic Pathway for Drug Designcited by 20
  31. 2023CFlowNets: Continuous Control with Generative Flow Networkscited by 19
  32. 2024QGFN: Controllable Greediness with Action Valuescited by 18
  33. 2022Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMCcited by 17
  34. 2023Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Designcited by 17
  35. 2023Pre-Training and Fine-Tuning Generative Flow Networkscited by 16
  36. 2022Accelerating Material Design with the Generative Toolkit for Scientific Discoverycited by 15
  37. 2023Multi-Fidelity Active Learning with GFlowNetscited by 15
  38. 2024SurfPro: Functional Protein Design Based on Continuous Surfacecited by 14

50 most cited of 172 All 172 (JSON)