Q-BIOLAT：基于QUBO的二进制隐式蛋白质适应度景观优化
Q-BIOLAT: Binary Latent Protein Fitness Landscapes for QUBO-Based Optimization
AI总结：
本文提出Q-BIOLAT框架，利用二进制隐式空间优化蛋白质适应度景观，通过QUBO模型结合预训练嵌入和结构化表示，提升组合优化效果。
摘要：
蛋白质适应度优化本质上是离散组合问题，但大多数基于学习的方法依赖连续表示并主要通过预测准确性评估。我们引入Q-BIOLAT框架，用于建模和优化蛋白质适应度景观的紧凑二进制隐式空间。从预训练的蛋白质语言模型嵌入开始，我们构建二进制隐式表示，并学习一个二次无约束二进制优化（QUBO）替代模型，捕捉一元和二元相互作用。除了其公式化，Q-BIOLAT提供了一个以表示为中心的蛋白质适应度建模视角。我们证明了具有相似预测性能的表示可以诱导根本不同的优化景观。特别是，学习的自编码器基于表示在二值化后崩溃，产生退化的隐式空间，无法支持组合搜索，而简单的结构化表示如PCA则产生高熵、可解码且优化友好的隐式空间。在多个数据集和数据制度上，我们证明经典组合优化方法，包括模拟退火、遗传算法和贪心爬坡法，在结构化二进制隐式空间中非常有效。通过将目标表达为QUBO形式，我们的方法连接了现代机器学习与离散和量子启发式优化。我们的实现和数据集在：https://github.com/HySonLab/Q-BIOLAT-Extended上公开。
英文摘要：
Protein fitness optimization is a discrete search problem, and the representation used for prediction also determines the neighborhood graph traversed by an optimizer. We introduce Q-BioLat, a framework that maps pretrained protein-language-model embeddings to compact binary codes and fits a quadratic unconstrained binary optimization (QUBO) surrogate with unary and pairwise latent interactions. Our central contribution is an optimization-aware view of representation: binary encodings that are similar in pointwise predictive accuracy can induce different Hamming neighborhoods, local optima, and search trajectories. We formalize when a recoding is only a Hamming-isometric reparameterization and give a constructive example showing that exact pointwise agreement does not imply optimization equivalence. We study experimentally measured GFP and AAV fitness landscapes from ProteinGym. The internal QUBO surrogate is evaluated against labels withheld from QUBO fitting. A conservative retrieval analysis maps optimized codes to measured variants and reports their experimental fitness, while neural decoding of potentially unmeasured sequences is evaluated separately with an experiment-trained sequence surrogate and is interpreted only as model-based candidate prioritization. Across the reported comparisons, PCA followed by per-coordinate median thresholding yields a more balanced and decodable binary space than the post-hoc-zero-threshold AE/VAE baselines, despite the latter's low continuous reconstruction error. In the measured-library retrieval analysis, simulated annealing, genetic algorithms, and greedy hill climbing frequently return high-percentile variants; decoded candidates are reported separately using surrogate-predicted scores.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
