We propose an integrated multiple-PI Project to systematically discover and replicate additional common genetic variants associated with breast cancer, assess their biological significance, and develop evidence based assessments of the clinical validity of prediction algorithms using these variants, and their suitability for translation into clinical practice. In sub-Project 1 we will combine the resources of (a) major GWAS for breast cancer amounting to >15,000 cases and (b) three pre-existing Consortia with over 48,000 additional cases to provide the large sample size needs necessary in the replication phase of GWAS. We will fine map the associated loci in collaboration with the major Consortia conducting GWAS for breast cancer in Asian and African-American women. In sub-Project 2 we will conduct a series of investigations to (a) assign a gene function to each replicated risk variant by measuring expression of 24,000 RNA transcripts in breast tumor tissue and normal tissue, from women for whom we also have an lllumina 540 GWAS available; by identifying networks of genes in which alterations of expression can be linked to specific germline risk variants; and by using Chromosomal Conformation Capture assays to examine whether associated intergenic regions fold physically in a way that brings them into contact with distant genie regions. We will also (b) examine whether loss or gain of function of the genes implicated in (a) in breast epithelial cells or stromal cells alter phenotypes in vitro in a 3-D model of breast morphogenesis and oncogenesis. In sub- Project 3, we will develop breast cancer prediction models that can be used to stratify women according to breast cancer risk. We will attempt to discover gene-gene interactions by reanalyzing the GWAS data, and we will systematically examine the genome-wide significant gene variants for effect modification by established breast cancer risk factors, using the largest set of prospective studies available. We will develop and refine risk models that incorporate both the germline risk factors and the established non-genetic risk factors, and also assess these in a cohort of women with higher familial risk of breast cancer (to specifically address the clinical needs of women at high risk due to a strong family history of breast cancer). Finally, we will analyze data from the major trials of primary prevention of breast cancer to address the question of whether the protective effect of tamoxifen is altered by risk status for our prediction models, data with a direct bearing on clinical decision-making with respect to chemoprevention for women at known high risk.