ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design

• URL: http://arxiv.org/abs/2605.10189v1
• Date: Mon, 11 May 2026 08:38:51 GMT
• Title: ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
• Abstract summary: Designer proteins with desired functions or properties represents a core goal in synthetic biology and drug discovery.<n>Recent advances in protein language models (PLMs) have enabled the generation of highly designable protein sequences.<n>PLMs often trigger catastrophic forgetting of pretrained knowledge.<n>We propose ProteinOPD, a multi-objective preference alignment framework.
• Score: 30.966423183343206
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Designing proteins with desired functions or properties represents a core goal in synthetic biology and drug discovery. Recent advances in protein language models (PLMs) have enabled the generation of highly designable protein sequences, while preference alignment provides a promising way to steer designs toward desired functions and properties. Nevertheless, they often trigger catastrophic forgetting of pretrained knowledge, degrading basic designability and failing to balance multiple competing objectives. To address these issues, we draw inspiration from On-Policy Distillation (OPD), an advanced post-training method renowned for mitigating catastrophic forgetting through its mode-seeking nature. In this work, we propose ProteinOPD, a multi-objective preference alignment framework that can effectively balance multiple preference objectives while maintaining the inherent designability of PLMs. ProteinOPD adapts a pretrained PLM into preference-specific teachers and distills their knowledge into a shared student via token-level OPD on the student's own trajectories. During this process, the student is aligned to a unique normalized geometric consensus of weighted teachers while ensuring bounded optimization under conflicts. This bridges the gap for OPD in multi-objective/teacher alignment. Extensive experiments show that ProteinOPD achieves substantial gains on target preference objectives without compromising the designability, with an 8x training speedup over RL-based alignment competitors.

Related papers

• Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization [85.4863852505905]
  We introduce unsupervised reward optimization of protein language models (PLMs)<n>Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with semantic consistency informed by protein representation models, exhibit strong correlation with controllability measures across base models and temperature regimes.<n>Our framework provides a scalable pathway toward controllable biomolecular design in settings where labeled preferences or experimental feedback are scarce or unavailable.
  arXiv  Detail & Related papers  (2026-06-17T11:42:01Z)
• Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment [19.34182674159143]
  Protein sequence design must balance designability, defined as the ability to recover a target backbone.<n>Existing approaches address these properties through post hoc mutation, inference-time biasing, or retraining on property-specific subsets.<n>We introduce ProtAlign, a multi-objective preference alignment framework that fine-tunes inverse folding models to satisfy diverse developability objectives.
  arXiv  Detail & Related papers  (2026-03-06T10:57:51Z)
• Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles [74.32932832937618]
  We introduce $textbfRigidSSL$ ($textitRigidity-Aware Self-Supervised Learning$), a geometric pretraining framework that front-loads geometry learning prior to finetuning.<n>Phase I (RigidSSL-Perturb) learns geometric priors from 432K structures from the AlphaFold Protein Structure Database with simulated perturbations.<n>Phase II (RigidSSL-MD) refines these representations on 1.3K molecular dynamics trajectories to capture physically realistic transitions.
  arXiv  Detail & Related papers  (2026-03-02T21:32:30Z)
• Self Distillation Fine-Tuning of Protein Language Models Improves Versatility in Protein Design [61.2846583160056]
  Supervised fine-tuning (SFT) is a standard approach for adapting large language models to specialized domains.<n>This is in part because high-quality annotated data are far more difficult to obtain for proteins than for natural language.<n>We present a simple and general recipe for fast SFT of PLMs, designed to improve the fidelity, reliability, and novelty of generated protein sequences.
  arXiv  Detail & Related papers  (2025-12-10T05:34:47Z)
• Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation [0.9332987715848714]
  Large language model (LLM) agents operate in parallel, each assigned to a specific residue position.<n>This position-wise, decentralized coordination enables emergent design of diverse, well-defined sequences.<n>Our method achieves efficient, objective-directed designs within a few GPU-hours and operates entirely without fine-tuning or specialized training.
  arXiv  Detail & Related papers  (2025-11-27T10:42:52Z)
• ProteinAE: Protein Diffusion Autoencoders for Structure Encoding [64.77182442408254]
  We introduce ProteinAE, a novel and streamlined protein diffusion autoencoder.<n>ProteinAE directly maps protein backbone coordinates from E(3) into a continuous, compact latent space.<n>We demonstrate that ProteinAE achieves state-of-the-art reconstruction quality, outperforming existing autoencoders.
  arXiv  Detail & Related papers  (2025-10-12T14:30:32Z)
• Learning from B Cell Evolution: Adaptive Multi-Expert Diffusion for Antibody Design via Online Optimization [4.4987897173449]
  We propose the first biologically-motivated framework that leverages physics-based domain knowledge within an online meta-learning system.<n>Our method employs multiple specialized experts (van der Waals, molecular recognition, energy balance, and interface geometry) whose parameters evolve during generation based on iterative feedback.
  arXiv  Detail & Related papers  (2025-07-25T03:14:34Z)
• BInD: Bond and Interaction-generating Diffusion Model for Multi-objective Structure-based Drug Design [0.0]
  We present BInD, a diffusion model with knowledge-based guidance for multi-objective drug design.<n>BInD is designed to co-generate molecules and their interactions with a target protein to consider all key objectives equally well.<n> Comprehensive evaluations show that BInD achieves robust performance for all objectives while outperforming or matching state-of-the-art methods for each.
  arXiv  Detail & Related papers  (2024-05-27T06:26:55Z)
• xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein [74.64101864289572]
  We propose a unified protein language model, xTrimoPGLM, to address protein understanding and generation tasks simultaneously.<n>xTrimoPGLM significantly outperforms other advanced baselines in 18 protein understanding benchmarks across four categories.<n>It can also generate de novo protein sequences following the principles of natural ones, and can perform programmable generation after supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-01-11T15:03:17Z)
• A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design [54.30457372514873]
  We propose a hierarchical training paradigm (HTP) for the antibody sequence-structure co-design. HTP consists of four levels of training stages, each corresponding to a specific protein modality. Empirical experiments show that HTP sets the new state-of-the-art performance in the co-design problem.
  arXiv  Detail & Related papers  (2023-10-30T02:39:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.