An integrative approach of digital image analysis and transcriptome profiling to explore potential predictive biomarkers for TGFβblockade therapy

作     者：Robert Pomponio Qi Tang Anthony Mei Anne Caron Bema Coulibaly Joachim Theilhaber Maximilian Rogers-Grazado Michele Sanicola-Nadel Souad Naimi Reza Olfati-Saber Cecile Combeau Jack Pollard Tun Tun Lin Rui Wang Robert Pomponio;Qi Tang;Anthony Mei;Anne Caron;Bema Coulibaly;Joachim Theilhaber;Maximilian Rogers-Grazado;Michele Sanicola-Nadel;Souad Naimi;Reza Olfati-Saber;Cecile Combeau;Jack Pollard;Tun Tun Lin;Rui Wang

作者机构：Sanofi Translational Medicine Early Development CambridgeMA 02142USA Sanofi Artificial Intelligence and Deep Analytics Data and Data SciencesCambridgeMA 02142USA Sanofi Translational ScienceVitry sur Seine 94403France Sanofi Precision Oncology CambridgeMA 02142USA Sanofi Oncology Early Development CambridgeMA 02142USA 

出 版 物：《Acta Pharmaceutica Sinica B》 (药学学报（英文版）)

年 卷 期：2022年第12卷第9期

页      面：3594-3601页

核心收录：

学科分类：1007[医学-药学(可授医学、理学学位)] 1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

基　　金：Sanofi 

主　　题：Digital pathology Artificial intelligence TGFβ Predictive biomarker Tumor topography T cell infiltration Transcriptomic profiling Machine learning 

摘      要：Increasing evidence suggests that the presence and spatial localization and distribution pattern of tumor infiltrating lymphocytes(TILs)is associate with response to *** studies have identified TGFβactivity and signaling as a determinant of T cell exclusion in the tumor microenvironment and poor response to PD-1/PD-L1 *** we coupled the artificial intelligence(AI)-powered digital image analysis and gene expression profiling as an integrative approach to quantify distribution of TILs and characterize the associated TGFβpathway *** of T cell spatial distribution in the solid tumor biopsies revealed substantial differences in the distribution *** digital image analysis approach achieves 74%concordance with the pathologist assessment for tumor-immune *** transcriptomic profiling suggests that the TIL score was negatively correlated with TGFβpathway activation,together with elevated TGFβsignaling activity observed in excluded and desert tumor *** present results demonstrate that the automated digital pathology algorithm for quantitative analysis of CD8 immunohistochemistry image can successfully assign the tumor into one of three infiltration phenotypes:immune desert,immune excluded or immune *** association between“coldtumor-immune phenotypes and TGFβsignature further demonstrates their potential as predictive biomarkers to identify appropriate patients that may benefit from TGFβblockade.