TY - JOUR
T1 - Swarm Intelligence-Enhanced Detection of Non-Small-Cell Lung Cancer Using Tumor-Educated Platelets
AU - Best, Myron G.
AU - Sol, Nik
AU - In ‘t Veld, Sjors G.J.G.
AU - Vancura, Adrienne
AU - Muller, Mirte
AU - Niemeijer, Anna Larissa N.
AU - Fejes, Aniko V.
AU - Tjon Kon Fat, Lee Ann
AU - Huis in 't Veld, Anna E
AU - Leurs, Cyra
AU - Le Large, Tessa Y.
AU - Meijer, Laura L.
AU - Kooi, Irsan E.
AU - Rustenburg, François
AU - Schellen, Pepijn
AU - Verschueren, Heleen
AU - Post, Edward
AU - Wedekind, Laurine E.
AU - Bracht, Jillian
AU - Esenkbrink, Michelle
AU - Wils, Leon
AU - Favaro, Francesca
AU - Schoonhoven, Jilian D.
AU - Tannous, Jihane
AU - Meijers-Heijboer, Hanne
AU - Kazemier, Geert
AU - Giovannetti, Elisa
AU - Reijneveld, Jaap C.
AU - Idema, Sander
AU - Killestein, Joep
AU - Heger, Michal
AU - de Jager, Saskia C.
AU - Urbanus, Rolf T.
AU - Hoefer, Imo E.
AU - Pasterkamp, Gerard
AU - Mannhalter, Christine
AU - Gomez-Arroyo, Jose
AU - Bogaard, Harm-Jan
AU - Noske, David P.
AU - Vandertop, W. Peter
AU - van den Broek, Daan
AU - Ylstra, Bauke
AU - Nilsson, R. Jonas A
AU - Wesseling, Pieter
AU - Karachaliou, Niki
AU - Rosell, Rafael
AU - Lee-Lewandrowski, Elizabeth
AU - Lewandrowski, Kent B.
AU - Tannous, Bakhos A.
AU - de Langen, Adrianus J.
AU - Smit, Egbert F.
AU - van den Heuvel, Michel M
AU - Wurdinger, Thomas
N1 - Funding Information:
Financial support was provided by European Research Council E8626 (R.J.A.N., E.F.S., and T.W.) and 336540 (T.W.), the Dutch Organisation of Scientific Research 93612003 and 91711366 (T.W.), the Dutch Cancer Society?(T.W. and H.M.H.), BMS IION (M.M.v.d.H. and T.W.), Stichting STOPhersentumoren.nl (M.G.B., P.W., and T.W.), the KNAW Van Walree stichting (M.G.B.), the NIH/NCI CA176359 and CA069246 (B.A.T.), CFF Norrland (R.J.A.N.), and Swedish Research Council (R.J.A.N.). We are thankful to Esther Drees, Thomas Kuilman, Oscar Krijgsman, Daniel S. Peeper, Dirk van Essen, Paul Eijk, Reno Bladergroen, Jan P.C. Lutgerink, the collaborators and team of the Cancer Pharmacology Lab, AIRC Start-Up Unit, Pisa, the NKI-AVL Core Facility Molecular Pathology and Biobanking (CFMPB) for supplying NKI-AVL Biobank material and lab support, Sebastiaan van de Sand (SIT B.V.) for computational resources, and Henk M. Verheul for continuous support. T.W. and R.J.A.N. received funding from Illumina and are shareholders of GRAIL, Inc.
Publisher Copyright:
© 2017 The Authors
PY - 2017/8/14
Y1 - 2017/8/14
N2 - 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.
AB - 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.
KW - blood platelets
KW - cancer diagnostics
KW - liquid biopsies
KW - NSCLC
KW - particle-swarm optimization
KW - RNA
KW - self-learning algorithms
KW - splicing
KW - swarm intelligence
KW - tumor-educated platelets
UR - http://www.scopus.com/inward/record.url?scp=85027221443&partnerID=8YFLogxK
U2 - 10.1016/j.ccell.2017.07.004
DO - 10.1016/j.ccell.2017.07.004
M3 - Article
C2 - 28810146
AN - SCOPUS:85027221443
SN - 1535-6108
VL - 32
SP - 238-252.e9
JO - Cancer Cell
JF - Cancer Cell
IS - 2
ER -