Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Best MG

PROVIDER: S-EPMC6381325 | biostudies-literature | 2017 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Best Myron G MG Sol Nik N In 't Veld Sjors G J G SGJG Vancura Adrienne A Muller Mirte M Niemeijer Anna-Larissa N AN Fejes Aniko V AV Tjon Kon Fat Lee-Ann LA Huis In 't Veld Anna E AE Leurs Cyra C Le Large Tessa Y TY Meijer Laura L LL Kooi Irsan E IE Rustenburg François F Schellen Pepijn P Verschueren Heleen H Post Edward E Wedekind Laurine E LE Bracht Jillian J Esenkbrink Michelle M Wils Leon L Favaro Francesca F Schoonhoven Jilian D JD Tannous Jihane J Meijers-Heijboer Hanne H Kazemier Geert G Giovannetti Elisa E Reijneveld Jaap C JC Idema Sander S Killestein Joep J Heger Michal M de Jager Saskia C SC Urbanus Rolf T RT Hoefer Imo E IE Pasterkamp Gerard G Mannhalter Christine C Gomez-Arroyo Jose J Bogaard Harm-Jan HJ Noske David P DP Vandertop W Peter WP van den Broek Daan D Ylstra Bauke B Nilsson R Jonas A RJA Wesseling Pieter P Karachaliou Niki N Rosell Rafael R Lee-Lewandrowski Elizabeth E Lewandrowski Kent B KB Tannous Bakhos A BA de Langen Adrianus J AJ Smit Egbert F EF van den Heuvel Michel M MM Wurdinger Thomas T

Cancer cell 20170801 2

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, 0.9 ...[more]

PMID: 28810146

Similar Datasets

Project description:BackgroundTo date, the role of programmed death ligand-1 (PD-L1) messenger RNA (mRNA) derived from tumor-educated platelets (TEPs) has not been well investigated in patients with advanced non-small cell lung cancer (NSCLC). A few reports have examined whether mRNA in TEPs can predict the clinical responses of patients with advanced NSCLC following immunotherapy. This study aimed to identify novel biomarkers to improve the clinical benefits and outcomes of NSCLC patients.MethodsAdvanced NSCLC patients receiving a combination of immunotherapy and chemotherapy, or immunotherapy alone as a first- or second-line treatment at the Fudan University Shanghai Cancer Center were enrolled in this study. All the patients had wild-type epidermal growth factor receptor/anaplastic lymphoma kinase. The patients were enrolled in clinical trials for immune checkpoint inhibitors (ICIs), including nivolumab, pembrolizumab, atezolizumab, durvalumab, tremelimumab, and camrelizumab. Tumoral PD-L1 expression was tested by immunohistochemistry (PD-L1 22C3 pharmDx kit, Agilent, Santa Clara, CA, USA) in archived tissue samples, when available, to calculate the tumor proportion scores (TPSs). RNA and exosomal RNA of blood were isolated before immunotherapy using the Yunying RNA extraction kit (Yunying Medicine, Shanghai, China). The concentration and quality of the RNA was determined using a Qubit fluorometer (Life Technologies, Carlsbad, CA, USA). Finally, we analyzed the predictive value of TEP-derived PD-L1 mRNA expression and association with the level of the tumoral PD-L1 expression.ResultsIn total, 72 patients were enrolled in this study. Most of the patients were male (n=54, 75.0%), had adenocarcinoma (n=49, 68.1%). We found there was no significant correlation between the TEP-derived mRNA of PD-L1 and tumoral PD-L1 expression based on the results of the Pearson Correlation test (r=-0.19, P=0.233). Based on the median of PD-L1 mRNA, 72 patients were divided into a high PD-L1 group and a low PD-L1 group. We found that 19 patients (44.4%) responded to immunotherapy [partial response or progression-free survival (PFS) >6 months] in the high PD-L1 group, but only five patients (13.9%) responded to immunotherapy in the low PD-L1 group (P<0.01). The median PFS of the low PD-L1 group was lower than that of the high PD-L1 group (2.8 vs. 8.3 months, P<0.001). For the patients who were treated with immunotherapy alone (n=64), a similar PFS advantage was observed in the high PD-L1 group (2.8 vs. 8.0 months, P=0.002).ConclusionsThis article presented the first data on TEP-derived PD-L1 mRNA in advanced NSCLC patients following immunotherapy and showed the potential advantage of using it as the surrogate biomarker for predicting the PFS and overall survival of patients following immunotherapy.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets