# Improving Protein Sequence Design through Designability Preference Optimization

arXiv: https://arxiv.org/abs/2506.00297 · HTML: https://mlsanity.com/paper/2506.00297/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [Learning from Protein Structure with Geometric Vector Perceptrons](https://mlsanity.com/paper/2009.01411/) (2020)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [Biological Sequence Design with GFlowNets](https://mlsanity.com/paper/2203.04115/) (2022)
- [Provably Robust DPO: Aligning Language Models with Noisy Feedback](https://mlsanity.com/paper/2403.00409/) (2024)
- [LiPO: Listwise Preference Optimization through Learning-to-Rank](https://mlsanity.com/paper/2402.01878/) (2024)
- [Noise Contrastive Alignment of Language Models with Explicit Rewards](https://mlsanity.com/paper/2402.05369/) (2024)
- [PiFold: Toward effective and efficient protein inverse folding](https://mlsanity.com/paper/2209.12643/) (2022)
- [Structure-informed Language Models Are Protein Designers](https://mlsanity.com/paper/2302.01649/) (2023)
- [ProteinBench: A Holistic Evaluation of Protein Foundation Models](https://mlsanity.com/paper/2409.06744/) (2024)
- [Generative De Novo Protein Design with Global Context](https://mlsanity.com/paper/2204.10673/) (2022)
- [UniIF: Unified Molecule Inverse Folding](https://mlsanity.com/paper/2405.18968/) (2024)
- [Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization](https://mlsanity.com/paper/2410.19471/) (2024)

## Built on by (most cited first, 6 of 6)

- [ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning](https://mlsanity.com/paper/2506.07459/) (2025)
- [Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment](https://mlsanity.com/paper/2603.06748/) (2026)
- [g-DPO: Scalable Preference Optimization for Protein Language Models](https://mlsanity.com/paper/2510.19474/) (2025)
- [PepEDiff: Zero-Shot Peptide Binder Design via Protein Embedding Diffusion](https://mlsanity.com/paper/2601.13327/) (2026)
- [RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design](https://mlsanity.com/paper/2604.17175/) (2026)
- [Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision](https://mlsanity.com/paper/2607.16263/) (2026)

## Abstract (arXiv)

Protein sequence design methods have demonstrated strong performance in sequence generation for de novo protein design. However, as the training objective was sequence recovery, it does not guarantee designability--the likelihood that a designed sequence folds into the desired structure. To bridge this gap, we redefine the training objective by steering sequence generation toward high designability. To do this, we integrate Direct Preference Optimization (DPO), using AlphaFold pLDDT scores as the preference signal, which significantly improves the in silico design success rate. To further refine sequence generation at a finer, residue-level granularity, we introduce Residue-level Designability Preference Optimization (ResiDPO), which applies residue-level structural rewards and decouples optimization across residues. This enables direct improvement in designability while preserving regions that already perform well. Using a curated dataset with residue-level annotations, we fine-tune LigandMPNN with ResiDPO to obtain EnhancedMPNN, which achieves a nearly 3-fold increase in in silico design success rate (from 6.56% to 17.57%) on a challenging enzyme design benchmark.