RT Journal Article
SR Electronic
T1 DNetPRO: A network approach for low-dimensional signatures from high-throughput data
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 773622
DO 10.1101/773622
A1 Curti, Nico
A1 Giampieri, Enrico
A1 Levi, Giuseppe
A1 Castellani, Gastone
A1 Remondini, Daniel
YR 2019
UL http://biorxiv.org/content/early/2019/09/19/773622.abstract
AB The objective of many high-throughput “omics” studies is to obtain a relatively low-dimensional set of observables - signature - for sample classification purposes (diagnosis, prognosis, stratification). We propose DNetPRO, Discriminant Analysis with Network PROcessing, a supervised signature identification method based on a bottom-up combinatorial approach that exploits the discriminant power of all variable pairs. The algorithm is easily scalable allowing efficient computing even for high number of observables (104 − 105). We show applications on real high-throughput genomic datasets in which our method outperforms existing results, or compares to them but with a smaller number of selected variables. Moreover the linearity of DNetPRO allows a clearer interpretation of the obtained signatures in comparison to non linear classification models