mlsanityData to 7 Oct 2026

A Variational Perspective on Generative Protein Fitness Optimization

arXiv 2501.19200 ↗First posted 31 Jan 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The goal of protein fitness optimization is to discover new protein variants with enhanced fitness for a given use. The vast search space and the sparsely populated fitness landscape, along with the discrete nature of protein sequences, pose significant challenges when trying to determine the gradient towards configurations with higher fitness. We introduce Variational Latent Generative Protein Optimization (VLGPO), a variational perspective on fitness optimization. Our method embeds protein sequences in a continuous latent space to enable efficient sampling from the fitness distribution and combines a (learned) flow matching prior over sequence mutations with a fitness predictor to guide optimization towards sequences with high fitness. VLGPO achieves state-of-the-art results on two different protein benchmarks of varying complexity. Moreover, the variational design with explicit prior and likelihood functions offers a flexible plug-and-play framework that can be easily customized to suit various protein design tasks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 31 Jan 2025.

Builds on

24 of 43 references.

References · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Flow Matching for Generative Modelingcited by 5,426
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  8. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  9. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  10. 2022Biological Sequence Design with GFlowNetscited by 172
  11. 2023Protein Design with Guided Discrete Diffusioncited by 154
  12. 2024D-Flow: Differentiating through Flows for Controlled Generationcited by 115
12 more
  1. 2019Conditioning by adaptive sampling for robust designcited by 110
  2. 2023Guided Flows for Generative Modeling and Decision Makingcited by 99
  3. 2021Oops I Took A Gradient: Scalable Sampling for Discrete Distributionscited by 92
  4. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 87
  5. 2018Taming VAEscited by 85
  6. 2022Tranception: protein fitness prediction with autoregressive transformers and inference-time retrievalcited by 78
  7. 2020AdaLead: A simple and robust adaptive greedy search algorithm for sequence designcited by 63
  8. 2017The reparameterization trick for acquisition functionscited by 61
  9. 2022Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMCcited by 17
  10. 2024Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Spacecited by 13
  11. 2020A primer on model-guided exploration of fitness landscapes for biological sequence designcited by 7
  12. 2024Closed-Form Test Functions for Biophysical Sequence Optimization Algorithmscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modelingcited by 25
  2. 2026Repurposing Protein Language Models for Latent Flow-Based Fitness Optimizationcited by 0
  3. 2026Feedback-Calibrated Protein Optimization with Batch-Aligned Tail Arbitrationcited by 0
  4. 2026Structure-aware Reinforcement Learning for Protein Directed Evolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Steering Generative Models with Experimental Data for Protein Fitness Optimization
  2. 2025Evolutionary Profiles for Protein Fitness Prediction
  3. 2026EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering
  4. 2025Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation
  5. 2026Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards
  6. 2024Reinforcement Learning for Sequence Design Leveraging Protein Language Models
  7. 2025Improving Protein Sequence Design through Designability Preference Optimization
  8. 2026Protein Counterfactuals via Diffusion-Guided Latent Optimization