Cancer evolution determines molecular and morphological intra-tumor heterogeneity and challenges the design of effective treatments. In lung adenocarcinoma, disease progression and prognosis are associated with the appearance of morphologically diverse tumor regions, termed histologic patterns. However, the link between molecular and histological features remains elusive. Here, we generated multi-omics and spatially resolved molecular profiles of histologic patterns from primary lung adenocarcinoma, which we integrated with molecular data from >2,000 patients. The transition from indolent to aggressive patterns was not driven by genetic alterations but by epigenetic and transcriptional reprogramming reshaping cancer cell identity. A signature quantifying this transition was an independent predictor of patient prognosis in multiple human cohorts. Within individual tumors, highly multiplexed protein spatial profiling revealed coexistence of immune desert, inflamed, and excluded regions, which matched histologic pattern composition. Our results provide a detailed molecular map of lung adenocarcinoma intra-tumor spatial heterogeneity, tracing non-genetic routes of cancer evolution. Statement of significance Lung adenocarcinomas are classified based on histologic pattern prevalence. However, individual tumors exhibit multiple patterns with unknown molecular features. We characterized non-genetic mechanisms underlying intra-tumor patterns and molecular markers predicting patient prognosis. Intra-tumor patterns determined diverse immune microenvironments warranting their study in the context of current immunotherapies.