TY - JOUR
T1 - Pathway-based subnetworks enable cross-disease biomarker discovery
AU - Haider, Syed
AU - Yao, Cindy Q.
AU - Sabine, Vicky S.
AU - Grzadkowski, Michal
AU - Stimper, Vincent
AU - Starmans, Maud H.W.
AU - Wang, Jianxin
AU - Nguyen, Francis
AU - Moon, Nathalie C.
AU - Lin, Xihui
AU - Drake, Camilla
AU - Crozier, Cheryl A.
AU - Brookes, Cassandra L.
AU - van de Velde, Cornelis J.H.
AU - Hasenburg, Annette
AU - Rea, Daniel
AU - Kieback, Dirk G.
AU - Markopoulos, Christos J.
AU - Dirix, Luc Y.
AU - Seynaeve, Caroline
AU - Kasprzyk, Arek
AU - Lambin, Philippe
AU - Lio', Pietro
AU - Bartlett, John M.S.
AU - Boutros, Paul C.
PY - 2018/11/12
Y1 - 2018/11/12
N2 - Biomarkers lie at the heart of precision medicine. Surprisingly, while rapid genomic profiling is becoming ubiquitous, the development of biomarkers usually involves the application of bespoke techniques that cannot be directly applied to other datasets. There is an urgent need for a systematic methodology to create biologically-interpretable molecular models that robustly predict key phenotypes. Here we present SIMMS (Subnetwork Integration for Multi-Modal Signatures): an algorithm that fragments pathways into functional modules and uses these to predict phenotypes. We apply SIMMS to multiple data types across five diseases, and in each it reproducibly identifies known and novel subtypes, and makes superior predictions to the best bespoke approaches. To demonstrate its ability on a new dataset, we profile 33 genes/nodes of the PI3K pathway in 1734 FFPE breast tumors and create a four-subnetwork prediction model. This model out-performs a clinically-validated molecular test in an independent cohort of 1742 patients. SIMMS is generic and enables systematic data integration for robust biomarker discovery.
AB - Biomarkers lie at the heart of precision medicine. Surprisingly, while rapid genomic profiling is becoming ubiquitous, the development of biomarkers usually involves the application of bespoke techniques that cannot be directly applied to other datasets. There is an urgent need for a systematic methodology to create biologically-interpretable molecular models that robustly predict key phenotypes. Here we present SIMMS (Subnetwork Integration for Multi-Modal Signatures): an algorithm that fragments pathways into functional modules and uses these to predict phenotypes. We apply SIMMS to multiple data types across five diseases, and in each it reproducibly identifies known and novel subtypes, and makes superior predictions to the best bespoke approaches. To demonstrate its ability on a new dataset, we profile 33 genes/nodes of the PI3K pathway in 1734 FFPE breast tumors and create a four-subnetwork prediction model. This model out-performs a clinically-validated molecular test in an independent cohort of 1742 patients. SIMMS is generic and enables systematic data integration for robust biomarker discovery.
UR - http://www.scopus.com/inward/record.url?scp=85056317417&partnerID=8YFLogxK
U2 - 10.1038/s41467-018-07021-3
DO - 10.1038/s41467-018-07021-3
M3 - Article
C2 - 30420699
AN - SCOPUS:85056317417
SN - 2041-1723
VL - 9
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 4746
ER -