Abstract Preclinical models such as cell lines and mice are the backbone of drug development and experimental-mechanistic oncology. However, we currently lack a detailed understanding of the direct clinical relevance of data collected in most preclinical models, hampering the development of new treatments. Despite this, few formal approaches have been proposed to determine how the various preclinical models represent/resemble primary patient tumors. Here, we present the first comprehensive single-cell RNA-seq analysis of neuroblastoma across an extensive cohort of patient tumors and a variety of preclinical model systems (n = 126 total samples assembled – the largest cohort of its kind). By developing an unsupervised machine learning method, which we term “automatic consensus nonnegative matrix factorization” (acNMF), we have integrated and contrasted the transcriptional landscapes of patient tumors with those of cell lines, patient-derived xenografts (PDX), and genetic mouse models (GEMM). We discovered that the dominant adrenergic gene expression programs commonly found in neuroblastoma patient tumors were generally preserved across all preclinical models. However, the presumptive chemo-resistant mesenchymal-like programs, while identifiable in cell lines, were primarily restricted to subpopulations of cancer-associated fibroblasts and Schwann-like cells in vivo. Surprisingly however, a mesenchymal-like program could be acutely chemotherapy-induced in GEMM and was evident in pre-treated patient and PDX samples, suggesting a previously uncharacterized mechanism of therapy escape resulting from an acute shift in cell state. In addition, our approach could further delineate the classical neuroblastoma adrenergic and mesenchymal gene expression programs, discovering for example, novel subpopulations of cancer associated fibroblasts and reproducible subtypes of adrenergic programs. These behaviors were conserved across tumors and preclinical models, which we validated by RNA in situ hybridization, an ultra-sensitive, high resolution, spatial transcriptomics technology. Overall, we offer a nuanced, high-resolution view of neuroblastoma pre-clinical systems for advancing therapeutic development, as well as a generalizable set of computational tools, which can be applied in other diseases. We have created an open-source web resource, featuring this integrated map to aid the scientific community in further exploration of these integrated data (available at http://pscb.stjude.org). Citation Format: Richard H. Chapple, Xueying Liu, Sivaraman Natarajan, Margaret I.M. Alexander, Yuna Kim, Anand G. Patel, Christy W. LaFlamme, Min Pan, William C. Wright, Hyeong-Min Lee, Yinwen Zhang, Meifen Lu, Selene C. Koo, Courtney Long, John Harper, Chandra Savage, Melissa D. Johnson, Thomas Confer, Walter J. Akers, Michael A. Dyer, Heather Sheppard, John Easton, Paul Geeleher. An integrated single-cell RNA-seq map of human neuroblastoma tumors and preclinical models uncovers divergent mesenchymal-like gene expression programs [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Advances in Pediatric Cancer Research; 2024 Sep 5-8; Toronto, Ontario, Canada. Philadelphia (PA): AACR; Cancer Res 2024;84(17 Suppl):Abstract nr B006.