Between 2002-2007 we assembled a large cohort (N= 96,000) named Adventist Health Study-2 (AHS-2). The cohort contains 25,000 Black subjects, and also has a broad representation from all social classes, from all 50 states of the U.S. and all provinces and territories of Canada. About 45% are vegetarian, but another 25% on average consume 139 gm of meat per day. Thus a very important feature is a wide range of dietary habits. The main goals of this work are to first evaluate associations between plant-based compared to omnivorous diets on risks of colorectal, breast and prostate cancers, as previous work suggests that these exist. Next to focus on nutrients, phytochemicals, vitamins and food groups that differ between these dietary patterns, including red meat, tomatoes, dairy foods, cruciferous vegetables, isoflavones, long-chain fatty acids, and others. This population has a relatively high intake of most fruits and vegetables, a consumption of soy that approaches Asian levels, and has both high intake and high adipose levels of n-3 fatty acids. Many key dietary exposures in this population appear to have a variance that is 1.5- 3 times that of other well-known study populations. This translates to the statistical power of a population 1.5--3 times the nominal size of AHS-2, indicating that this is very cost-effective research. Each study member has completed a 50 page questionnaire that covers diet in detail, also medical history, physical activity, female history, and demographics. A large and comprehensive calibration study of 1011 representative subjects has been formed to validate the estimation of dietary intake, and also to facilitate measurement error correction in regression analyses. Data collected from calibration study subjects includes 6 carefully timed 24-hour dietary recalls, a second food frequency questionnaire, two one week physical activity recalls, and an unusually rich group of biological samples from which to estimate biomarkers: serum, plasma, buffy coat, RBCs, an overnight urine, and a subcutaneous fat aspirate. For measurement error correction, traditional regression calibration will be used, as well as an innovative recently published biomarker-guided calibration method. As required for this, we have estimated a large number of biomarkers of intake from the calibration study data. Many correlations with dietary recalls are relatively high-valued. The validity of questionnaire dietary indices (compared to recalls) is also in keeping with the best experience of others. Incident cancers are found by matching with state cancer registries, and also from biennial questionnaires as a secondary source. Initial estimates suggest we will miss only 2.5% of these cancers. The main categories of activity planned during the next 5 years are to a) continue and complete the detection of incident cancers; b) continue the production of an annual newsletter, also popular articles to promote cohort retention, and maintain up-to-date contact information; c) finally and most importantly, complete analyses and produce manuscripts that address the listed specific aims.