Protein-protein interactions are central mediators in many biological
processes. Accurately predicting the effects of mutations on interactions is
crucial for guiding the modulation of these interactions, thereby playing a
significant role in therapeutic development and drug discovery. Mutations
generally affect interactions hierarchically across three levels: mutated
residues exhibit different sidechain conformations, which lead to changes in
the backbone conformation, eventually affecting the binding affinity between
proteins. However, existing methods typically focus only on sidechain-level
interaction modeling, resulting in suboptimal predictions. In this work, we
propose a self-supervised multi-level pre-training framework, ProMIM, to fully
capture all three levels of interactions with well-designed pretraining
objectives. Experiments show ProMIM outperforms all the baselines on the
standard benchmark, especially on mutations where significant changes in
backbone conformations may occur. In addition, leading results from zero-shot
evaluations for SARS-CoV-2 mutational effect prediction and antibody
optimization underscore the potential of ProMIM as a powerful next-generation
tool for developing novel therapeutic approaches and new drugs.

通过自我监督的多层预训练框架 ProMIM，全面捕获三个层级的蛋白质相互作用，该框架在标准基准测试中表现优异，特别是在可能导致蛋白质背骨构象显著变化的突变上，还能进行零样本评估，显示了其作为新一代强大的药物开发工具在 SARS-CoV-2 突变效应预测和抗体优化方面的潜力。

蛋白质突变影响预测的多级交互建模

Multi-level Interaction Modeling for Protein Mutational Effect  Prediction

The field of pharmaceutical development and therapeutic application both face
substantial challenges. Therapeutic domain calls for more treatment
alternatives while numerous promising pre-clinical drugs fail in clinical
trails. One of the reasons is the inadequacy of Cross-drug Response Evaluation
(CRE) during the late stage of drug development. Although in-silico CRE models
offer a solution to this problem, existing methodologies are either limited to
early development stages or lack the capacity for a comprehensive CRE analysis.
Herein, we introduce a novel computational model named DeepCRE and present the
potential of DeepCRE in advancing therapeutic discovery and development.
DeepCRE outperforms the existing best models by achieving an average
performance improvement of 17.7\% in patient-level CRE, and a 5-fold increase
in indication-level CRE. Furthermore, DeepCRE has identified six drug
candidates that show significantly greater effectiveness than a comparator set
of two approved drug in 5/8 colorectal cancer (CRC) organoids. This highlights
DeepCRE's ability to identify a collection of drug candidates with superior
therapeutic effects, underscoring its potential to revolutionize the field of
therapeutic development.

药物开发与治疗应用领域面临巨大挑战，交叉药物反应评估在药物开发的后期阶段的不足成为一个原因。现有的计算模型存在局限性，无法进行全面的交叉药物反应评估分析。本文介绍了一种名为 DeepCRE 的新型计算模型，并展示了 DeepCRE 在推动治疗发现与开发方面的潜力。通过在病患层面的交叉药物反应评估中，DeepCRE 的平均性能提升达到 17.7%，指示性的交叉药物反应评估提升了 5 倍。此外，DeepCRE 在 5/8 的结肠直肠癌有机体中，已确定了与两种已批准药物相比，6 种显示出显著更有效的药物候选物。这凸显了 DeepCRE 鉴定具有更优疗效的药物候选物的能力，突显其在治疗发展领域的潜力革新。