Soto, Luisa M. Solis

Abstract Background: Immune checkpoint inhibitors (ICIs) have improved survival in non-small-cell lung cancer (NSCLC), yet only a subset of patients benefits, and biomarkers like PD-L1 remain limited. Here, we introduce a deep learning-based pathomics framework that utilizes routine H&E-stained slides to predict therapeutic response and survival outcomes in ICI-treated metastatic NSCLC. Methods: The study included 797 ICI-treated NSCLC patients from MD Anderson, with external validation in 280 patients from Mayo Clinic, Gustave Roussy, and the Phase III ICI-naïve LUSC Lung-MAP S1400I trial receiving nivolumab with or without ipilimumab. Path-IO (Pathology-Driven Immunotherapy Optimization) comprised of four major steps: (1) pathologist-verified tissue classifier segmented WSIs into eight compartments—Background, Bronchi, Immune, Lung, Necrosis, Stroma, Tumor, and Vessel—and was validated on TCGA and CPTAC dataset; (2) a survival prediction module generating patient-level risk scores in the MD Anderson cohort and validated across external datasets; (3) integration of Path-IO risk scores with radiomics and clinical features to improve prognostic accuracy; and (4) biological interpretability analyses correlating Path-IO risk immune contexture from multiplex immunofluorescence and transcriptomic signatures from NanoString profiling. Results: Path-IO effectively stratified patients into high and low-risk groups with significant survival differences. In the MD Anderson cohort, it achieved HR = 2.11 (p < 0.001) and HR = 2.51 (p < 0.001) for OS in the discovery and validation sets, and HR = 2.34 (p < 0.001) and HR = 1.87 (p < 0.001) for PFS, respectively. In the multicenter Phase III Lung-MAP S1400I trial, Path-IO achieved HR = 1.78 (p = 0.016) for OS and HR = 2.76 (p = 0.006) for PFS. In external validation, it predicted outcomes in the Gustave Roussy (OS = 1.97, p = 0.003; PFS = 1.51, p = 0.046) and Mayo Clinic (OS = 2.46, p = 0.007; PFS = 2.45, p = 0.027) cohorts. Path-IO outperformed PD-L1 and remained an independent predictor in multivariate analysis (p < 0.001). It enabled data-driven frontline selection between anti-PD-1 monotherapy and chemo-immunotherapy, offering guidance toward more personalized treatment decisions. Integration with radiomics and clinical features further improved predictive accuracy (OS 0.63→0.75; PFS C-index 0.58→0.70), while high Path-IO risk scores correlated with immune-cold phenotypes identified by multiplex immunofluorescence and NanoString transcriptomics. Conclusions: Path-IO demonstrates that deep learning models rooted in histopathologic architecture can generate interpretable and biologically informed survival predictions in NSCLC treated with ICIs. By integrating pathology, radiology, and clinical data, Path-IO provides complementary predictive value beyond established biomarkers such as PD-L1. Citation Format: Rukhmini Bandyopadhyay, Linghzi Hong, Mihaela Aldea, Shenduo Li, Lodovica Zullo, Frank R. Rojas, Maliazurina B. Saad, Maricel C. Marin, Muhammad Waqas, Jiexin Zhang, Eman Showkatian, Claudio A. Arrechedera, Xiaoyu Han, Yuliya Kitsel, Sherif Ismail, Muhammad Aminu, Bo Zhu, Carol C. Wu, Brett W. Carter, Joe Y Chang, Zhongxing Liao, Maria R. Ghigna, Davide Soldato, Hai T. Tran, Xiuning Le, Tina Cascone, Bingnan Zhang, Haniel A. Araujo, Mehmet Altan, Simon Heeke, David Jaffray, Don L. Gibbons, Ara Vaporciyan, J Jack Lee, Neda Kalhor, Cara Haymaker, Ignacio Wistuba, John V. Heymach, Yanyan Lou, Natalie Vokes, Luisa M. Solis Soto, Jianjun Zhang, Jia Wu. Path-IO: A deep learning pathomics framework for personalized immunotherapy selection and outcome prediction in metastatic non-small cell lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 4003.

Abstract Background: Cancer-associated fibroblasts (CAFs) are a highly diverse cell population that plays a crucial role in shaping the tumor microenvironment (TME). Their spatial interactions within the TME remain to be systematically characterized, and the factors driving their phenotypic heterogeneity are not yet fully understood. Recent advancements in single-cell spatial transcriptomics technologies and cell segmentation approaches enable the precise measurement of thousands of transcripts at subcellular resolution. Combined with innovative bioinformatics, these advancements have unlocked unprecedented opportunities for in-depth characterization of CAFs and their interactions within the TME. Methods: We conducted a comprehensive spatial transcriptomic analysis of CAFs across 8 cancer types, using the CosMx and MERSCOPE platforms to profile nearly 6 million cells as part of our discovery cohorts. We developed a novel computational method to spatially cluster CAF subpopulations and defined four distinct spatial CAF subtypes. We further examined their phenotypic differences, spatial niche organization, and interactions with neighboring cells. Additionally, we investigated the influence of CAF subtypes on immune cell phenotypes and infiltration levels. To validate our findings, we employed multiple spatial platforms, including Visium, Xenium, COMET, CODEX, and IMC, to ensure reproducibility across diverse technologies. Moreover, we performed correlative studies in large-cohorts with rich clinical data to evaluate the clinical significance of these CAF subtypes. Results: Our approach provided an unprecedented high-resolution examination of the spatial phenotypes of CAFs in large, complex tissues, uncovering novel insights. We comprehensively characterized CAFs across various solid tumor types and identified four conserved spatial CAF subtypes. These subtypes are characterized by distinct cell organizational patterns, neighboring cell compositions, interaction networks, and transcriptomic features. Moreover, they demonstrate significant correlations with the abundance, distribution, and phenotypes of tumor-infiltrating immune cells, as well as associations with tumor histopathological features and clinical outcomes. Conclusions: Our study provides a pan-cancer, high-resolution characterization of CAF spatial organization and interactions in solid tumors and identified conserved spatial CAF subtypes linked to distinct organizational patterns. Our findings reveal that the transcriptomic states and phenotypes of CAFs are significantly shaped by their interactions with neighboring cancer and immune cells. Beyond offering novel insights into the spatial heterogeneity of CAFs, this work paves the way for developing strategies to effectively target and modulate CAFs for therapeutic benefit. Citation Format: Yunhe Liu, Ansam Sinjab, Jimin Min, Guangchun Han, Francesca Paradiso, Yuanyuan Zhang, Yang Liu, Ruiping Wang, Guangsheng Pei, Kyung Serk Cho, Enyu Dai, Akshay Basi, Jared K. Burks, Kimal I. Rajapakshe, Yanshuo Chu, Jiahui Jiang, Daiwei Zhang, Xinmiao Yan, Paola A. Guerrero, Alejandra Serrano, Mingyao Li, Tae Hyun Hwang, Andrew Futreal, Jaffer A. Ajani, Luisa M Solis Soto, Amir A. Jazaeri, Humam Kadara, Anirban Maitra, Linghua Wang. Spatial subtypes and cellular interactions of cancer-associated fibroblasts revealed by single-cell spatial omics [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 166.