paper-with-me

홈 › Papers

Repurposing Protein Language Models for Latent Flow-Based Fitness Optimization

2026-02-02 · Amaru Caceres Arroyo, Lea Bogensperger, Ahmed Allam, Michael Krauthammer, Konrad Schindler, Dominik Narnhofer arxiv

Protein fitness optimization is challenged by a vast combinatorial landscape where high-fitness variants are extremely sparse. Many current methods either underperform or require computationally expensive gradient-based sampling. We present CHASE, a framework that repurposes the evolutionary knowledge of pretrained protein language models by compressing their embeddings into a compact latent space. By training a conditional flow-matching model with classifier-free guidance, we enable the direct generation of high-fitness variants without predictor-based guidance during the ODE sampling steps. CHASE achieves state-of-the-art performance on AAV and GFP protein design benchmarks. Finally, we show that bootstrapping with synthetic data can further enhance performance in data-constrained settings.

📄 PDF Abstract BibTeX arXiv:2602.02425

Code (0)

등록된 구현이 없습니다.

Tasks

Protein Design

Similar Papers 제목 키워드 기반

A Variational Perspective on Generative Protein Fitness Optimization

2025-01-31 · Lea Bogensperger, Dominik Narnhofer, Ahmed Allam, Konrad Schindler 외

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 pr…

Protein Design

Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space

2024-05-29 · Minji Lee, Luiz Felipe Vecchietti, Hyunkyu Jung, Hyun Joo Ro 외

Proteins are complex molecules responsible for different functions in nature. Enhancing the functionality of proteins and cellular fitness can significantly impact various industries. However, protein optimization using …

DecoderLanguage ModelingLanguage ModellingProtein Language Model

Binary Latent Protein Fitness Landscapes for Quantum Annealing Optimization

2026-03-18 · Truong-Son Hy arxiv

We propose Q-BIOLAT, a framework for modeling and optimizing protein fitness landscapes in binary latent spaces. Starting from protein sequences, we leverage pretrained protein language models to obtain continuous embedd…

Representation Learning

ReLSO: A Transformer-based Model for Latent Space Optimization and Generation of Proteins

2022-01-24 · Egbert Castro, Abhinav Godavarthi, Julian Rubinfien, Kevin B. Givechian 외

The development of powerful natural language models have increased the ability to learn meaningful representations of protein sequences. In addition, advances in high-throughput mutagenesis, directed evolution, and next-…

Q-BIOLAT: Binary Latent Protein Fitness Landscapes for QUBO-Based Optimization

2026-03-29 · Truong-Son Hy arxiv

Protein fitness optimization is inherently a discrete combinatorial problem, yet most learning-based approaches rely on continuous representations and are primarily evaluated through predictive accuracy. We introduce Q-B…

Protein Language Model