The paper examines two large-scale, North-American and European clinical trials designed to validate two commercially available genomic tumor signatures that predict a patient's risk of breast cancer recurrence and response to chemotherapy. The paper builds on empirical evidence from the two trials to explore the emergence of diverse regulatoryscientific hybrids, i.e. configurations of genomic practice and bioclinical work that depend on linkages between technical, commercial, patient, clinical, and legal interests and institutions. The development of the genomic signatures for each trial -Oncotype DX and MammaPrint -has followed quite different routes. Oncotype began as a commercial platform: the company that produced it did not discover a signature but rather constructed it by asking users at every step what clinical question they wanted the signature to answer and what data would be credible in that regard. The test has been designed to minimally disrupt existing clinical workflows. MammaPrint, on the other hand, began as a breast cancer signature: the researchers who discovered it, at the Netherlands Cancer Institute (NKI), established a company to commercialize it as a test after the fact. MammaPrint requires a change in pathologists' routines. Thus, while these two trials signify a new departure for clinical cancer trials on a number of levels -they both incorporate new models of interaction between biotech companies and public research, and they both aim to establish the clinical relevance of genomic markersthey also embody different socio-technical scripts: one attempts to accommodate established routines, while the other openly challenges prevailing evidential hierarchies and existing biomedical configurations.