mlsanityData to 7 Oct 2026

Preference optimization of protein language models as a multi-objective binder design paradigm

arXiv 2403.04187 ↗First posted 7 Mar 2024physics.bio-ph cs.AI cs.CEcited by 4

On the map: LLM alignment / RLHF / preference optimisation → Preference optimization for molecular design

Abstract (arXiv)

We present a multi-objective binder design paradigm based on instruction fine-tuning and direct preference optimization (DPO) of autoregressive protein language models (pLMs). Multiple design objectives are encoded in the language model through direct optimization on expert curated preference sequence datasets comprising preferred and dispreferred distributions. We show the proposed alignment strategy enables ProtGPT2 to effectively design binders conditioned on specified receptors and a drug developability criterion. Generated binder samples demonstrate median isoelectric point (pI) improvements by 17%-60%.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Preference optimization for molecular design, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 13 of its 34 references that are in the map. First posted on arXiv 7 Mar 2024.

Builds on

13 of 34 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Preference Optimization for Molecular Language Models18 Oct

Other references · 12

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2017Deep reinforcement learning from human preferencescited by 3,846
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  6. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  7. 2018Hierarchical Neural Story Generationcited by 1,182
  8. 2022ProGen2: Exploring the Boundaries of Protein Language Modelscited by 156
  9. 2023Protein Design with Guided Discrete Diffusioncited by 154
  10. 2023A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generationcited by 10
  11. 2023Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Modelcited by 5
  12. 2023Pairing interacting protein sequences using masked language modelingcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactionscited by 5
  2. 2024Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimizationcited by 5
  3. 2025Protein Inverse Folding From Structure Feedbackcited by 5
  4. 2025g-DPO: Scalable Preference Optimization for Protein Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
  2. 2025Improving Protein Sequence Design through Designability Preference Optimization
  3. 2026Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment
  4. 2026Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization
  5. 2025Controllable Protein Sequence Generation with LLM Preference Optimization
  6. 2024Reinforcement Learning for Sequence Design Leveraging Protein Language Models
  7. 2025From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning?
  8. 2026Scaffold-Conditioned Preference Triplets for Controllable Molecular Optimization with Large Language Models