The treatment of breast cancer has benefitted tremendously from the generation of estrogen receptor-a (ERa)-targeted therapies, but disease relapse continues to pose a challenge due to intrinsic or acquired drug resistance. In an effort to delineate potential predictive biomarkers of therapy responsiveness, multiple groups have identified several uncharacterized cofactors and interacting partners of ERa, including Split Ends (SPEN), a transcriptional corepressor. Here, we demonstrate a role for SPEN in ERa-expressing breast cancers. SPEN nonsense mutations were detectable in the ERa-expressing breast cancer cell line T47D and corresponded to undetectable protein levels. Further analysis of 101 primary breast tumors revealed that 23% displayed loss of heterozygosity at the SPEN locus and that 3% to 4% harbored somatically acquired mutations. A combination of in vitro and in vivo functional assays with microarray-based pathway analyses showed that SPEN functions as a tumor suppressor to regulate cell proliferation, tumor growth, and survival. We also found that SPEN binds ERa in a ligand-independent manner and negatively regulates the transcription of ERa targets. Moreover, we demonstrate that SPEN overexpression sensitizes hormone receptor-positive breast cancer cells to the apoptotic effects of tamoxifen, but has no effect on responsiveness to fulvestrant. Consistent with these findings, two independent datasets revealed that high SPEN protein and RNA expression in ERa-positive breast tumors predicted favorable outcome in patients treated with tamoxifen alone. Together, our data suggest that SPEN is a novel tumor-suppressor gene that may be clinically useful as a predictive biomarker of tamoxifen response in ERa-positive breast cancers. Cancer Res; 75(20); 4351-63. Ó2015 AACR.