LORIS: A LOgistic Regression-based Immunotherapy-response Score

This is a repository of scripts for reproducing the paper titled "LORIS robustly predicts patient outcomes with immune checkpoint blockade therapy using common clinical, pathologic, and genomic features" by Chang et al. (Nature Cancer 2024). Briefly, in this work, Chang et al. developed a new clinical score called the LOgistic Regression-based Immunotherapy-response Score (LORIS) using a transparent and concise 6-feature logistic regression model. LORIS outperforms previous signatures in ICB response prediction and can identify responsive patients, even those with low tumor mutational burden or tumor PD-L1 expression. Importantly, LORIS consistently predicts both objective responses and short-term and long-term survival across multiple cancer types. Moreover, LORIS showcases a near-monotonic relationship with ICB response probability and patient survival, enabling more precise patient stratification across the board. As the method is accurate, interpretable, and only utilizes a few readily measurable features, it may help improve clinical decision-making practices in precision medicine to maximize patient benefit.本代码仓库包含复现Chang等人2024年发表于《自然·癌症》（Nature Cancer）的论文《LORIS基于常见临床、病理及基因组特征稳健预测免疫检查点阻断治疗患者预后》的相关脚本。 简言之，该研究中Chang等人基于透明简洁的6特征逻辑回归模型，开发了一款全新的临床评分工具——基于逻辑回归的免疫治疗应答评分（LORIS，全称Logistic Regression-based Immunotherapy-response Score）。在免疫检查点阻断治疗（immune checkpoint blockade, ICB）应答预测任务中，LORIS的性能优于既往相关特征标签，可精准识别应答患者，包括肿瘤突变负荷较低或肿瘤PD-L1表达水平偏低的人群。尤为关键的是，LORIS在多种癌型中均可稳定预测客观缓解情况与患者的短期、长期生存结局。此外，LORIS与ICB应答概率及患者生存状态呈现近乎单调的相关性，可实现全维度的精准患者分层。由于该方法兼具精准性与可解释性，且仅需少量易于获取的检测特征，有望助力优化精准医疗领域的临床决策流程，进而最大化患者获益。