The ability to engineer novel proteins with higher fitness for a desired property would be revolutionary for biotechnology and medicine. Modeling the combinatorially large space of sequences is infeasible; prior methods often constrain optimization to a small mutational radius, but this drastically limits the design space. Instead of heuristics, we propose smoothing the fitness landscape to facilitate protein optimization. First, we formulate protein fitness as a graph signal then use Tikunov regularization to smooth the fitness landscape. We find optimizing in this smoothed landscape leads to improved performance across multiple methods in the GFP and AAV benchmarks. Second, we achieve state-of-the-art results utilizing discrete energy-based models and MCMC in the smoothed landscape. Our method, called Gibbs sampling with Graph-based Smoothing (GGS), demonstrates a unique ability to achieve 2.5 fold fitness improvement (with in-silico evaluation) over its training set. GGS demonstrates potential to optimize proteins in the limited data regime. Code: https://github.com/kirjner/GGS

翻译：对具备更高适应度的新型蛋白质进行工程化改造，以使其具备所需特性，这将在生物技术和医学领域引发革命性变革。然而，对组合规模庞大的序列空间进行建模并不可行；现有方法往往将优化限制在较小的突变半径内，但这严重制约了设计空间。为此，我们提出摒弃启发式策略，转而采用平滑适应度景观来促进蛋白质优化。首先，将蛋白质适应度表示为图信号，并利用Tikhonov正则化对适应度景观进行平滑处理。研究发现，在平滑后的景观中进行优化，能够在绿色荧光蛋白（GFP）和腺相关病毒（AAV）基准测试中显著提升多种方法的性能。其次，我们在平滑景观中结合离散能量模型与马尔可夫链蒙特卡洛方法（MCMC），取得了当前最优结果。我们提出的方法——基于图平滑的吉布斯采样（GGS），展现出独特能力：能够在训练集基础上实现2.5倍的适应度提升（基于计算机模拟评估）。GGS在数据有限条件下展现出优化蛋白质的巨大潜力。代码地址：https://github.com/kirjner/GGS