Swarm Intelligence-Enhanced Detection of Non-Small-Cell Lung Cancer Using Tumor-Educated Platelets

Publication date: 14 August 2017
Source:Cancer Cell, Volume 32, Issue 2
Author(s): Myron G. Best, Nik Sol, Sjors G.J.G. In 't Veld, Adrienne Vancura, Mirte Muller, Anna-Larissa N. Niemeijer, Aniko V. Fejes, Lee-Ann Tjon Kon Fat, Anna E. Huis In 't Veld, Cyra Leurs, Tessa Y. Le Large, Laura L. Meijer, Irsan E. Kooi, François Rustenburg, Pepijn Schellen, Heleen Verschueren, Edward Post, Laurine E. Wedekind, Jillian Bracht, Michelle Esenkbrink, Leon Wils, Francesca Favaro, Jilian D. Schoonhoven, Jihane Tannous, Hanne Meijers-Heijboer, Geert Kazemier, Elisa Giovannetti, Jaap C. Reijneveld, Sander Idema, Joep Killestein, Michal Heger, Saskia C. de Jager, Rolf T. Urbanus, Imo E. Hoefer, Gerard Pasterkamp, Christine Mannhalter, Jose Gomez-Arroyo, Harm-Jan Bogaard, David P. Noske, W. Peter Vandertop, Daan van den Broek, Bauke Ylstra, R. Jonas A. Nilsson, Pieter Wesseling, Niki Karachaliou, Rafael Rosell, Elizabeth Lee-Lewandrowski, Kent B. Lewandrowski, Bakhos A. Tannous, Adrianus J. de Langen, Egbert F. Smit, Michel M. van den Heuvel, Thomas Wurdinger
Blood-based liquid biopsies, including tumor-educated blood platelets (TEPs), have emerged as promising biomarker sources for non-invasive detection of cancer. Here we demonstrate that particle-swarm optimization (PSO)-enhanced algorithms enable efficient selection of RNA biomarker panels from platelet RNA-sequencing libraries (n = 779). This resulted in accurate TEP-based detection of early- and late-stage non-small-cell lung cancer (n = 518 late-stage validation cohort, accuracy, 88%; AUC, 0.94; 95% CI, 0.92–0.96; p < 0.001; n = 106 early-stage validation cohort, accuracy, 81%; AUC, 0.89; 95% CI, 0.83–0.95; p < 0.001), independent of age of the individuals, smoking habits, whole-blood storage time, and various inflammatory conditions. PSO enabled selection of gene panels to diagnose cancer from TEPs, suggesting that swarm intelligence may also benefit the optimization of diagnostics readout of other liquid biopsy biosources.

Graphical abstract

Teaser

Best et al. use particle-swarm optimization algorithms and RNA-seq of tumor-educated platelets from patients to generate RNA sets capable of identifying patients with non-small-cell lung cancer, including those having early stage, from individuals without cancer, including those having inflammatory conditions.


http://ift.tt/2uU2Evs