Cells capture intracellular proteins and organelles by the process of macroautophagy (autophagy hereafter), which delivers them to lysosomes where they are degraded. The breakdown products of autophagy cargo such as amino acids, sugars, nucleosides and lipids, are released from lysosomes into the cytoplasm where they are reused. Autophagy thereby recycles intracellular components to sustain cell and organism metabolism and survival in starvation, a function conserved from yeast to mammals. Autophagy is also a mechanism for eliminating cellular waste such as damaged proteins and organelles, particularly mitochondria, the accumulation of which is toxic. This protein and organelle quality control function of autophagy is also highly conserved and required for homeostasis. Autophagy levels are normally low, but are dramatically induced by starvation and stress to facilitate cellular adaptation. Cancer cells also rely on autophagy, but more so than normal cells. This may be due to high metabolic demand imposed by cancer cell growth and residence in a stressful microenvironment. In contrast to normal cells, cancer cells often have autophagy induced under fed conditions. For example, Ras-driven cancers commonly have high levels of basal autophagy and are extremely dependent on autophagy for sustaining mitochondrial respiration, for survival in stress and for tumorigenesis. Thus, in comparison to normal cells, some cancers may be addicted to autophagy and preferentially sensitive to autophagy inhibition, prompting interest in inhibiting autophagy to improve cancer therapy. Precisely how autophagy supports cancer growth and survival, the extent to which normal tissues and tumors are differentially affected, and the most effective means is to implement this concept in the clinic, remain open questions. To address these questions we examined the role of autophagy using genetically engineered mouse models (GEMMs) for K-rasG12D-driven non-small-cell lung cancer (NSCLC) and B-rafV600E- driven lung cancer. We found that deficiency in the essential autophagy gene atg7 causes tumor cells to accumulate large numbers of defective mitochondria and undergo atrophy. Atg7 deficiency also diverts progression of lung adenomas and carcinomas to oncocytomas. Oncocytomas are rare, predominantly benign neoplasms that arise in epithelial tissues that are characterized by the accumulation of large numbers of respiration-defective, mutant mitochondria. This discovery revealed for the first time that autophagy is a cancer fate determinant, that autophagy defects may be the molecular basis for the genesis of oncocytomas, and that oncocytomas can derive from adenomas and carcinomas when autophagy is impaired. We will test the central hypothesis that autophagy defects are the molecular basis for the genesis of oncocytomas. We will determine if atg7 deficiency produces mitochondrial genome mutations that convert carcinomas to oncocytomas, if mutations in essential autophagy genes cause human oncocytomas, and if producing oncocytomas by knocking out autophagy creates sensitivity to metabolic stress, enhancing cancer therapy.