Cianferoni Damiano, Vizarraga David, Fernández-Escamilla Ana María, Fita Ignacio, Hamdani Rahma, Reche Raul, Delgado Javier, Serrano Luis
Centre for Genomic Regulation (CRG), The Barcelona Institute for Science and Technology, Barcelona, Spain.
Universitat de Barcelona (UB), Barcelona, Spain.
Protein Sci. 2025 Aug;34(8):e70210. doi: 10.1002/pro.70210.
Since AlphaFold2's rise, many deep learning methods for protein design have emerged. Here, we validate widely used and recognized tools, compare them with first-principle methods, and explore their combinations, focusing on their effectiveness in protein redesign and potential for therapeutic repurposing. We address two challenges: evaluating tools and combinations ability to detect the effects of multiple concurrent mutations in protein variants, and leveraging large-scale datasets to compare modeling-free methods, namely force fields, which handle point mutations well with limited backbone rearrangement, and inverse folding tools, which excel at native sequence recovery but may struggle with non-natural proteins. Debuting TriCombine, a tool that identifies residue triangles in input structures, matches them to a structural database, and scores mutants based on substitution frequencies, we shortlisted candidates, modeled them with FoldX, and generated 16 SH3 mutants carrying up to 9 concurrent substitutions. The dataset was expanded to include 36 mutants and 11 crystal structures (7 newly solved), along with a parallel set of multiple non-concurrent mutants from three additional proteins. For broader validation, we analyzed 160,000 four-site GB1 mutants and 163,555 (single and double) variants across 179 natural and de novo domains. We show that combining AI-based modeling tools with force field scoring functions yields the most reliable results. Inverse folding tools perform very well but lose accuracy on less-represented proteins. First-principle force fields like FoldX remain the most accurate for point mutations. All methods perform worse when applied to unsolved de novo models, underscoring the need for hybrid strategies in robust protein design.
自AlphaFold2兴起以来，出现了许多用于蛋白质设计的深度学习方法。在此，我们对广泛使用和认可的工具进行验证，将它们与第一性原理方法进行比较，并探索它们的组合方式，重点关注它们在蛋白质重新设计中的有效性以及治疗性重新利用的潜力。我们解决了两个挑战：评估工具及其组合检测蛋白质变体中多个并发突变影响的能力，以及利用大规模数据集比较无模型方法，即力场（能很好地处理点突变且主链重排有限）和逆折叠工具（在天然序列恢复方面表现出色，但可能难以处理非天然蛋白质）。我们推出了TriCombine工具，该工具可识别输入结构中的残基三角形，将它们与结构数据库进行匹配，并根据替换频率对突变体进行评分。我们筛选出候选者，用FoldX对它们进行建模，并生成了16个携带多达9个并发替换的SH3突变体。数据集得到扩展，包括36个突变体和11个晶体结构（7个新解析的），以及来自另外三种蛋白质的一组平行的多个非并发突变体。为了进行更广泛的验证，我们分析了160,000个四位点GB1突变体以及179个天然和从头设计结构域中的163,555个（单突变和双突变）变体。我们表明，将基于人工智能的建模工具与力场评分函数相结合可产生最可靠的结果。逆折叠工具表现非常出色，但在代表性较差的蛋白质上会失去准确性。像FoldX这样的第一性原理力场在点突变方面仍然是最准确的。当应用于未解析的从头设计模型时，所有方法的性能都会变差，这突出了在稳健的蛋白质设计中采用混合策略的必要性。
