Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer (Q6711025)

This repository contains the radiomic, pathomic, and transcriptomic features used in:"Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer" The cohort includes 317 metastatic non-small cell lung cancer (NSCLC) patients treated with first-line immunotherapy (pembrolizumab), with or without concomitant chemotherapy, at Institut Curie (Paris, France). At baseline, the following data were collected: Clinical information from routine care 18F-FDG PET/CT scans, from which radiomic features were extracted Digitized pathological slides, from which pathomic features were extracted Bulk RNA-seq profiles from solid biopsies, from which transcriptomic features were extracted These features were used as inputs to multimodal machine learning pipelines designed to predict immunotherapy outcomes. Clinical data availability: Due to patient privacy requirements, curated clinical data could not be shared in this repository. They are available upon request to Nicolas Girard and Emmanuel Barillot. Immunotherapy outcomes (i.e., OS, PFS, and best observed RECIST response) are available in this repository. * Please refer to README.md for more details about each modality as well as contact information * Associated journal article: Captier, N., Lerousseau, M., Orlhac, F. et al. Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer. Nat Commun 16, 614 (2025).