利用蛋白语言模型定制CRISPR-Cas PAM特异性，这一成果由美国Profiluent Bio公司Ali Madani小组经过不懈努力而取得。2026年2月2日出版的《自然—生物技术》杂志发表了这一最新研究成果。

该研究组引入了一个进化信息深度学习模型，Protein2PAM，以有效地指导Cas蛋白变体的设计，以识别特定的PAM。Protein2PAM在超过45000个CRISPR-Cas PAM数据集上进行了训练，可以快速准确地直接预测I型，II型和V型CRISPR-Cas系统中Cas蛋白的PAM特异性。利用硅诱变技术，该模型在没有主题化结构信息的情况下识别Cas9中PAM识别的关键残基。该课题组人员以Protein2PAM为主题，计算进化Nme1Cas9，产生具有更宽PAM识别的变体，与体外野生型相比，PAM切割率增加了50倍。他们的机器学习方法允许Cas酶靶向以前由于PAM限制而无法进入的序列，潜在地增加了个性化基因组编辑的目标灵活性。

研究人员表示，CRISPR-Cas酶通常识别原间隔邻近基序（PAM）来编辑基因组位点，这极大地限制了基因组中可靶向序列的范围。虽然存在改变PAM特异性的工程策略，但它们通常需要大量的劳动和反复的实验。

附：英文原文

Title: Customizing CRISPR–Cas PAM specificity with protein language models

Author: Nayfach, Stephen, Bhatnagar, Aadyot, Novichkov, Andrey, Kim, Nahye, Hoffnagle, Alexander M., Hussain, Riffat, Estevam, Gabriella O., Hill, Emily, Ruffolo, Jeffrey A., Silverstein, Rachel A., Gallagher, Joseph, Kleinstiver, Benjamin P., Meeske, Alexander J., Cameron, Peter, Madani, Ali

Issue&Volume: 2026-02-02

Abstract: CRISPR–Cas enzymes must recognize a protospacer-adjacent motif (PAM) to edit a genomic site, greatly limiting the range of targetable sequences in a genome. Although engineering strategies to alter PAM specificity exist, they typically require labor-intensive, iterative experimentation. We introduce an evolution-informed deep learning model, Protein2PAM, to efficiently guide the design of Cas protein variants tailored to recognize specific PAMs. Trained on a dataset of over 45,000 CRISPR–Cas PAMs, Protein2PAM rapidly and accurately predicts PAM specificity directly from Cas proteins across type I, II and V CRISPR–Cas systems. Using in silico mutagenesis, the model identifies residues critical for PAM recognition in Cas9 without using structural information. We use Protein2PAM to computationally evolve Nme1Cas9, generating variants with broadened PAM recognition and up to a 50-fold increase in PAM cleavage rates compared to the wild type in vitro. Our machine learning approach allows Cas enzymes to target sequences that were previously inaccessible because of PAM constraints, potentially increasing target flexibility in personalized genome editing.

DOI: 10.1038/s41587-025-02995-0

Source: https://www.nature.com/articles/s41587-025-02995-0