RT Journal Article
SR Electronic
T1 eTumorMetastasis, a network-based algorithm predicts clinical outcomes using whole-exome sequencing data of cancer patients
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 268680
DO 10.1101/268680
A1 Jean-Sébastien Milanese
A1 Chabane Tibiche
A1 Naif Zaman
A1 Jinfeng Zou
A1 Pengyong Han
A1 Zhiganag Meng
A1 Andre Nantel
A1 Arnaud Droit
A1 Edwin Wang
YR 2018
UL http://biorxiv.org/content/early/2018/02/22/268680.abstract
AB Continual reduction in sequencing cost is expanding the accessibility of genome sequencing data for routine clinical applications. However, the lack of methods to construct machine learning-based predictive models using these datasets has become a crucial bottleneck for the application of sequencing technology in clinics. Here we developed a new algorithm, eTumorMetastasis, which transforms tumor functional mutations into network-based profiles, and identify network operational gene signatures (NOG signatures) which model the tipping point at which a tumor cell shifts from a state that doesn’t favor recurrences to one that does. We showed that NOG signatures derived from genomic mutations of tumor founding clones (i.e., the ‘most recent common ancestor’ of the cells within a tumor) significantly distinguished recurred and non-recurred breast tumors. These results imply that somatic mutations of tumor founders are association with tumor recurrence and can be used to predict clinical outcomes. Finally, the concepts underlying the eTumorMetastasis pave the way for the application of genome sequencing in predictions for other complex genetic diseases.