发表机构
AI Scientist, Albany, NY, USA, 12205（AI Scientist，奥尔巴尼，纽约州，美国，12205）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Mirror-Score，一种校准的仅推理评分框架，用于D-肽设计，揭示ProteinMPNN NLL排序的局限，并通过Boltz-2置信度实现有效的亲和力排序。
AI 中文摘要
D-肽兼具蛋白酶抗性与高靶标特异性，但其计算设计仍不成熟。Mirror-Peptidizer引入了利用靶标反射、骨架生成和ProteinMPNN序列设计的计算机镜像筛选流程，但其原始ProteinMPNN负对数似然（NLL）排序未针对实测亲和力进行验证，且9个测试的MDM2设计中仅4个可检测到结合。我们提出Mirror-Score，一种针对异手性D-肽/L-蛋白复合物的校准的、仅推理评分框架，以及一个包含四个靶标家族31个晶体复合物的公共基准，其中18个具有文献验证的亲和力。原始ProteinMPNN NLL并非有效的亲和力排序器：其与亲和力的合并Spearman相关系数为0.19，且相关性在MDM2/CHIP（+0.62）与gp41（-0.70）之间发生反转。因此，我们评估了Boltz-2镜像空间共折叠置信度。对于完整的病毒进入家族（代表3种肽的7个结构），界面预测局部距离差异测试（pLDDT）实现了结构级留一法Spearman rho = 0.90（p = 0.006），并正确按亲和力对所有三种肽排序，而NLL则失败（结构级rho = 0.18）。由于仅代表三个独立的化学型，该结果表明方向一致性而非统计验证的预测器。在当前样本量下，跨家族校准不可迁移，支持家族匹配校准作为实际部署模式。我们还为来自铜绿假单胞菌的抗菌素耐药靶标LasR和LecB指定了一个前瞻性设计协议，包括镜像结构、配体衍生热点图、扩散模型就绪输入和Mirror-Score排序。代码、基准数据、结构和分析脚本可在该https URL公开获取。
英文摘要
D-peptides combine protease resistance with high target specificity, but computational design of D-peptide binders remains immature. Mirror-Peptidizer introduced an in silico mirror-image screening pipeline using target reflection, backbone generation, and ProteinMPNN sequence design, but its raw ProteinMPNN negative log-likelihood (NLL) ranking was not validated against measured affinities, and only 4 of 9 tested MDM2 designs bound detectably. We introduce Mirror-Score, a calibrated, inference-only scoring framework for heterochiral D-peptide/L-protein complexes, and a public benchmark of 31 crystal complexes across four target families, including 18 with literature-verified affinities. Raw ProteinMPNN NLL is not a valid affinity ranker: its pooled Spearman correlation with affinity is 0.19, and correlations reverse between MDM2/CHIP (+0.62) and gp41 (-0.70). We therefore evaluate Boltz-2 mirror-space cofolding confidence. For the complete viral-entry family (7 structures representing 3 peptides), interface predicted local distance difference test (pLDDT) achieves structure-level leave-one-out Spearman rho = 0.90 (p = 0.006) and correctly orders all three peptides by affinity, whereas NLL fails (structure-level rho = 0.18). Because only three independent chemotypes are represented, this result indicates directional consistency rather than a statistically validated predictor. Cross-family calibration does not transfer at current sample sizes, supporting family-matched calibration as the practical deployment mode. We also specify a prospective design protocol for the antimicrobial-resistance targets LasR and LecB from Pseudomonas aeruginosa, including mirrored structures, ligand-derived hotspot maps, diffusion-model-ready inputs, and Mirror-Score ranking. Code, benchmark data, structures, and analysis scripts are openly available at https://github.com/Jiadalee/Mirror-Score.
