A Random Forest Genomic Classifier for Tumor Agnostic Prediction of Response to Anti-PD1 Immunotherapy.
A Random Forest Genomic Classifier for Tumor Agnostic Prediction of Response to Anti-PD1 Immunotherapy.
复制标题
DOI：
10.1177/11769351221136081
复制
发表时间：
2022
影响因子：
2
通讯作者：
Yarchoan, Mark
中科院分区：
文献类型：
--
作者：
Bigelow, Emma;Saria, Suchi;Piening, Brian;Curti, Brendan;Dowdell, Alexa;Weerasinghe, Roshanthi;Bifulco, Carlo;Urba, Walter;Finkelstein, Noam;Fertig, Elana J.;Baras, Alex;Zaidi, Neeha;Jaffee, Elizabeth;Yarchoan, Mark
关键词：
肿瘤突变负荷 (TMB) 是肿瘤新表位负荷的替代物，被用作泛肿瘤生物标志物，用于识别可能受益于抗程序细胞死亡 1 (PD1) 免疫治疗的患者，但它是一个不完善的生物标志物。多个额外的基因组特征与抗 PD1 反应相关，但这些特征的综合预测价值以及每个特征的附加信息仍然未知。我们评估了使用源自全外显子组测序 (WES) 的抗 PD1 反应的拟议决定因素的机器学习 (ML) 方法是否可以比单独使用 TMB 更好地预测抗 PD1 反应者。随机森林分类器根据公开的抗 PD1 数据进行训练 (n = 104)，随后在独立的抗 PD1 队列中进行测试 (n = 69)。训练和测试数据集都包括一系列癌症类型，例如非小细胞肺癌（NSCLC）、头颈鳞状细胞癌（HNSCC）、黑色素瘤以及少量其他肿瘤类型的患者。使用的特征包括 TMB 和移码突变数量等摘要，以及更多基因级特征，例如与免疫检查点反应和耐药性相关的突变计数。两种 ML 算法都显示出接受者-操作者曲线下面积 (AUC) 超过单独的 TMB（AUC 0.63“人工引导”、0.64“集群”和单独的 0.58 TMB）。相对于肿瘤新表位负荷的总体贡献，癌基因内的突变不成比例地调节抗 PD1 反应。与单独使用 TMB 相比，使用 ML 算法评估多个提出的抗 PD1 反应基因组决定因素可适度提高性能，这凸显了整合其他生物标志物以进一步提高模型性能的必要性。
Tumor mutational burden (TMB), a surrogate for tumor neoepitope burden, is used as a pan-tumor biomarker to identify patients who may benefit from anti-program cell death 1 (PD1) immunotherapy, but it is an imperfect biomarker. Multiple additional genomic characteristics are associated with anti-PD1 responses, but the combined predictive value of these features and the added informativeness of each respective feature remains unknown. We evaluated whether machine learning (ML) approaches using proposed determinants of anti-PD1 response derived from whole exome sequencing (WES) could improve prediction of anti-PD1 responders over TMB alone. Random forest classifiers were trained on publicly available anti-PD1 data (n = 104), and subsequently tested on an independent anti-PD1 cohort (n = 69). Both the training and test datasets included a range of cancer types such as non-small cell lung cancer (NSCLC), head and neck squamous cell carcinoma (HNSCC), melanoma, and smaller numbers of patients from other tumor types. Features used include summaries such as TMB and number of frameshift mutations, as well as more gene-level features such as counts of mutations associated with immune checkpoint response and resistance. Both ML algorithms demonstrated area under the receiver-operator curves (AUC) that exceeded TMB alone (AUC 0.63 “human-guided,” 0.64 “cluster,” and 0.58 TMB alone). Mutations within oncogenes disproportionately modulate anti-PD1 responses relative to their overall contribution to tumor neoepitope burden. The use of a ML algorithm evaluating multiple proposed genomic determinants of anti-PD1 responses modestly improves performance over TMB alone, highlighting the need to integrate other biomarkers to further improve model performance.
登录
查看更多内容
影响因子：
30.8
作者：
Lindeboom, Rik G. H.;Vermeulen, Michiel;Supek, Fran
通讯作者：
Supek, Fran
影响因子：
8.4
作者：
Eisenhauer, E. A.;Therasse, P.;Verweij, J.
通讯作者：
Verweij, J.
影响因子：
28.2
作者：
Chen PL;Roh W;Reuben A;Cooper ZA;Spencer CN;Prieto PA;Miller JP;Bassett RL;Gopalakrishnan V;Wani K;De Macedo MP;Austin-Breneman JL;Jiang H;Chang Q;Reddy SM;Chen WS;Tetzlaff MT;Broaddus RJ;Davies MA;Gershenwald JE;Haydu L;Lazar AJ;Patel SP;Hwu P;Hwu WJ;Diab A;Glitza IC;Woodman SE;Vence LM;Wistuba II;Amaria RN;Kwong LN;Prieto V;Davis RE;Ma W;Overwijk WW;Sharpe AH;Hu J;Futreal PA;Blando J;Sharma P;Allison JP;Chin L;Wargo JA
通讯作者：
Wargo JA
影响因子：
64.8
作者：
Matsushita, Hirokazu;Vesely, Matthew D.;Koboldt, Daniel C.;Rickert, Charles G.;Uppaluri, Ravindra;Magrini, Vincent J.;Arthur, Cora D.;White, J. Michael;Chen, Yee-Shiuan;Shea, Lauren K.;Hundal, Jasreet;Wendl, Michael C.;Demeter, Ryan;Wylie, Todd;Allison, James P.;Smyth, Mark J.;Old, Lloyd J.;Mardis, Elaine R.;Schreiber, Robert D.
通讯作者：
Schreiber, Robert D.
影响因子：
30.8
作者：
Miao D;Margolis CA;Vokes NI;Liu D;Taylor-Weiner A;Wankowicz SM;Adeegbe D;Keliher D;Schilling B;Tracy A;Manos M;Chau NG;Hanna GJ;Polak P;Rodig SJ;Signoretti S;Sholl LM;Engelman JA;Getz G;Jänne PA;Haddad RI;Choueiri TK;Barbie DA;Haq R;Awad MM;Schadendorf D;Hodi FS;Bellmunt J;Wong KK;Hammerman P;Van Allen EM
通讯作者：
Van Allen EM