Development of a multigenomic liquid biopsy (PROSTest) for prostate cancer in whole blood.
PCa
PSA
adenocarcinoma
biomarker
diagnosis
liquid biopsy
mRNA
prostate cancer
qPCR
whole blood
Journal
The Prostate
ISSN: 1097-0045
Titre abrégé: Prostate
Pays: United States
ID NLM: 8101368
Informations de publication
Date de publication:
03 Apr 2024
03 Apr 2024
Historique:
revised:
04
03
2024
received:
05
01
2024
accepted:
25
03
2024
medline:
4
4
2024
pubmed:
4
4
2024
entrez:
4
4
2024
Statut:
aheadofprint
Résumé
We describe the development of a molecular assay from publicly available tumor tissue mRNA databases using machine learning and present preliminary evidence of functionality as a diagnostic and monitoring tool for prostate cancer (PCa) in whole blood. We assessed 1055 PCas (public microarray data sets) to identify putative mRNA biomarkers. Specificity was confirmed against 32 different solid and hematological cancers from The Cancer Genome Atlas (n = 10,990). This defined a 27-gene panel which was validated by qPCR in 50 histologically confirmed PCa surgical specimens and matched blood. An ensemble classifier (Random Forest, Support Vector Machines, XGBoost) was trained in age-matched PCas (n = 294), and in 72 controls and 64 BPH. Classifier performance was validated in two independent sets (n = 263 PCas; n = 99 controls). We assessed the panel as a postoperative disease monitor in a radical prostatectomy cohort (RPC: n = 47). A PCa-specific 27-gene panel was identified. Matched blood and tumor gene expression levels were concordant (r = 0.72, p < 0.0001). The ensemble classifier ("PROSTest") was scaled 0%-100% and the industry-standard operating point of ≥50% used to define a PCa. Using this, the PROSTest exhibited an 85% sensitivity and 95% specificity for PCa versus controls. In two independent sets, the metrics were 92%-95% sensitivity and 100% specificity. In the RPCs (n = 47), PROSTest scores decreased from 72% ± 7% to 33% ± 16% (p < 0.0001, Mann-Whitney test). PROSTest was 26% ± 8% in 37 with normal postoperative PSA levels (<0.1 ng/mL). In 10 with elevated postoperative PSA, PROSTest was 60% ± 4%. A 27-gene whole blood signature for PCa is concordant with tissue mRNA levels. Measuring blood expression provides a minimally invasive genomic tool that may facilitate prostate cancer management.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : Individual Medical Institutions. Wren Laboratories provided free sample measurement.
Informations de copyright
© 2024 Wiley Periodicals LLC.
Références
Sandhu S, Moore CM, Chiong E, Beltran H, Bristow RG, Williams SG. Prostate Cancer. Lancet; 2021.
Gillessen S, Attard G, Beer TM, et al. Management of patients with advanced prostate cancer: report of the advanced prostate cancer consensus conference 2019. Eur Urol. 2020;77(4):508‐547.
Casanova‐Salas I, Athie A, Boutros PC, et al. Quantitative and qualitative analysis of blood‐based liquid biopsies to inform clinical decision‐making in prostate cancer. Eur Urol. 2021;79(6):762‐771.
Oesterling JE. Prostate specific antigen: a critical assessment of the most useful tumor marker for adenocarcinoma of the prostate. J Urol. 1991;145(5):907‐923.
Leal J, Welton NJ, Martin RM, et al. Estimating the sensitivity of a prostate cancer screening programme for different PSA cut‐off levels: a UK case study. Cancer Epidemiol. 2018;52:99‐105.
Koie T, Mitsuzuka K, Narita S, et al. A solitary positive prostate cancer biopsy does not predict a unilateral lesion in radical prostatectomy specimens. Scand J Urol. 2015;49(2):103‐107.
Galper SL, Chen MH, Catalona WJ, Roehl KA, Richie JP, D'Amico AV. Evidence to support a continued stage migration and decrease in prostate cancer specific mortality. J Urol. 2006;175(3 Pt 1):907‐912.
Catalona WJ. Prostate cancer screening. Med Clin North Am. 2018;102(2):199‐214.
Thompson IM, Pauler DK, Goodman PJ, et al. Prevalence of prostate cancer among men with a prostate‐specific antigen level < or =4.0 ng per milliliter. N Engl J Med. 2004;350(22):2239‐2246.
Pinsky PF, Parnes H. Screening for prostate cancer. N Engl J Med. 2023;388(15):1405‐1414.
Heitzer E. Circulating tumor DNA for modern cancer management. Clin Chem. 2020;66:143‐145.
Best MG, Sol N, Kooi I, et al. RNA‐seq of tumor‐educated platelets enables blood‐based pan‐cancer, multiclass, and molecular pathway cancer diagnostics. Cancer Cell. 2015;28(5):666‐676.
Albitar M, Zhang H, Goy A, et al. Determining clinical course of diffuse large B‐cell lymphoma using targeted transcriptome and machine learning algorithms. Blood Cancer J. 2022;12(2):25.
Olmos D, Brewer D, Clark J, et al. Prognostic value of blood mRNA expression signatures in castration‐resistant prostate cancer: a prospective, two‐stage study. Lancet Oncol. 2012;13(11):1114‐1124. doi:10.1016/S1470-2045(12)70372-8
Ross RW, Galsky MD, Scher HI, et al. A whole‐blood RNA transcript‐based prognostic model in men with castration‐resistant prostate cancer: a prospective study. Lancet Oncol. 2012;13(11):1105‐1113. doi:10.1016/S1470-2045(12)70263-2
Danila DC, Anand A, Schultz N, et al. Analytic and clinical validation of a prostate cancer‐enhanced messenger RNA detection assay in whole blood as a prognostic biomarker for survival. Eur Urol. 2014;65(6):1191‐1197.
Schlack K, Seitzer K, Wüstmann N, et al. Comparison of circulating tumor cells and AR‐V7 as clinical biomarker in metastatic castration‐resistant prostate cancer patients. Sci Rep. 2022;12(1):11846.
Alshaker H, Mills R, Hunter E, et al. Chromatin conformation changes in peripheral blood can detect prostate cancer and stratify disease risk groups. J Transl Med. 2021;19(1):46.
Modlin IM, Kidd M, Falconi M, et al. A multigenomic liquid biopsy biomarker for neuroendocrine tumor disease outperforms CgA and has surgical and clinical utility. Ann Oncol. 2021;32:1425‐1433.
Öberg K, Califano A, Strosberg JR, et al. A meta‐analysis of the accuracy of a neuroendocrine tumor mRNA genomic biomarker (NETest) in blood. Ann Oncol. 2020;31(2):202‐212. doi:10.1016/j.annonc.2019.11.003
Modlin IM, Kidd M, Oberg K, et al. Early identification of residual disease after neuroendocrine tumor resection using a liquid biopsy multigenomic mRNA signature (NETest). Ann Surg Oncol. 2021;28:7506‐7517.doi:10.1245/s10434-021-10021-1
Kidd M, Kitz A, Drozdov I, Modlin I. Neuroendocrine tumor omic gene cluster analysis amplifies the prognostic accuracy of the NETest. Neuroendocrinology. 2020;111:490‐504. doi:10.1159/000508573
Bodei L, Kidd MS, Singh A, et al. PRRT neuroendocrine tumor response monitored using circulating transcript analysis: the NETest. Eur J Nucl Med Mol Imaging. 2019;14(10):019‐04601.
Modlin IM, Kidd M, Frilling A, et al. Molecular genomic assessment using a blood‐based mRNA signature (NETest) is cost effective and predicts neuroendocrine tumor recurrence with 94% accuracy. Ann Surg. 2021;274(3):481‐490.
Abeshouse A, Ahn J, Akbani R, et al. The molecular taxonomy of primary prostate cancer. Cell. 2015;163(4):1011‐1025.
Johnston WL, Catton CN, Swallow CJ. Unbiased data mining identifies cell cycle transcripts that predict non‐indolent Gleason score 7 prostate cancer. BMC Urol. 2019;19(1):4. doi:10.1186/s12894-12018-10433-12895
Kidd M, Nadler B, Mane S, et al. GeneChip, Genorm, and gastrointestinal tumors: novel reference genes for real‐time PCR. Physiol Genomics. 2007;30(3):363‐370.
Breiman L. Random forests. Mach Learn. 2001;45(1):5‐32.
Díaz‐Uriarte R, Alvarez de Andrés S. Gene selection and classification of microarray data using random forest. BMC Bioinformatics. 2006;7:3.
Weidner L, Laner‐Plamberger S, Horner D, et al. Sample buffer containing guanidine‐hydrochloride combines biological safety and RNA preservation for SARS‐CoV‐2 molecular diagnostics. Diagnostics. 2022;12(5):1186.
Kidd M, Drozdov IA, Matar S, et al. Utility of a ready‐to‐use PCR system for neuroendocrine tumor diagnosis. PLoS One. 2019;14(6):e0218592. doi:10.1371/journal.pone.0218592
Edd JF, Mishra A, Smith KC, et al. Isolation of circulating tumor cells. iScience. 2022;25(8):104696.
Stuart EA. Matching methods for causal inference: a review and a look forward. Stat Sci. 2010;25(1):1‐21.
Mullen SA, Das D, Ziamiavaghi N, High R, Datta K, Teply BA. Association of plasma NRP2 and VEGF‐C levels with prostate cancer disease severity. Prostate. 2024;84(3):277‐284.
Zhang Y, Ling C. A strategy to apply machine learning to small datasets in materials science. NPJ Comput Mater. 2018;4:25.
Pardakhti M, Mandal N, Ma AWK, Yang Q. Practical active learning with model selection for small data. 2021. Accessed December 01, 2021. https://ui.adsabs.harvard.edu/abs/2021arXiv211211572P
Maclin R, Opitz D. Popular ensemble methods: an empirical study. 2011. Accessed June 01, 2011. https://arvix.org/abs/1106.0257
Szubert B, Cole JE, Monaco C, Drozdov I. Structure‐preserving visualisation of high dimensional single‐cell datasets. Sci Rep. 2019;9(1):8914.
Ashburner M, Ball CA, Blake JA, et al. Gene ontology: tool for the unification of biology. Nature Genet. 2000;25(1):25‐29.
Aleksander SA, Balhoff J, Carbon S, et al. The gene ontology knowledgebase in 2023. Genetics. 2023;224(1):iyad0310.
Karlsson M, Zhang C, Méar L, et al. A single‐cell type transcriptomics map of human tissues. Sci Adv. 2021;7(31).
Lonsdale J, Thomas J, Salvatore M, et al. The genotype‐tissue expression (GTEx) project. Nature Genet. 2013;45(6):580‐585.
eGTEx Project. Enhancing GTEx by bridging the gaps between genotype, gene expression, and disease. Nature Genet. 2017;49(12):1664‐1670.
Gogishvili D, Vromen EM, Koppes‐den Hertog S, et al. Discovery of novel CSF biomarkers to predict progression in dementia using machine learning. Sci Rep. 2023;13(1):6531.
Caffarini J, Gjini K, Sevak B, et al. Engineering nonlinear epileptic biomarkers using deep learning and Benford's law. Sci Rep. 2022;12(1):5397.
Derderian S, Vesval Q, Wissing MD, et al. Liquid biopsy‐based targeted gene screening highlights tumor cell subtypes in patients with advanced prostate cancer. Clin Transl Sci. 2022;15(11):2597‐2612.
Jackson HR, Miglietta L, Habgood‐Coote D, et al. Diagnosis of multisystem inflammatory syndrome in children by a whole‐blood transcriptional signature. J Pediatric Infect Dis Soc. 2023;12(6):322‐331.
Haas NB, LaRiviere MJ, Buckingham TH, et al. Blood‐based gene expression signature associated with metastatic castrate‐resistant prostate cancer patient response to abiraterone plus prednisone or enzalutamide. Prostate Cancer Prostatic Dis. 2021;24(2):448‐456.
Dominy K, Mokretar K, Reid AG, Khorashad JS. Molecular monitoring of chronic myeloid leukemia. Methods Mol Biol. 2020;2065:153‐173.
Roedder S, Sigdel T, Salomonis N, et al. The kSORT assay to detect renal transplant patients at high risk for acute rejection: results of the multicenter AART study. PLoS Med. 2014;11(11):e1001759.
Piccolo SR, Mecham A, Golightly NP, Johnson JL, Miller DB. The ability to classify patients based on gene‐expression data varies by algorithm and performance metric. PLoS Comput Biol. 2022;18(3):e1009926.
Cao X, Xing L, Majd E, He H, Gu J, Zhang X. A systematic evaluation of supervised machine learning algorithms for cell phenotype classification using single‐cell RNA sequencing data. Front Genet. 2022;13:836798.
Mahendran N, Durai Raj Vincent PM, Srinivasan K, Chang CY. Machine learning based computational gene selection models: a survey, performance evaluation, open issues, and future research directions. Front Genet. 2020;11:603808.
Cancer stat facts: common cancer sites. Accessed October 25, 2023. https://seer.cancer.gov/statfacts/html/common.html
Uhlen M, Karlsson MJ, Zhong W, et al. A genome‐wide transcriptomic analysis of protein‐coding genes in human blood cells. Science. 2019;366(6472):eaax9198.
Connal S, Cameron JM, Sala A, et al. Liquid biopsies: the future of cancer early detection. J Transl Med. 2023;21(1):118.
Kohaar I, Petrovics G, Srivastava S. A rich array of prostate cancer molecular biomarkers: opportunities and challenges. Int J Mol Sci. 2019;20(8):1813.
Cann GM, Gulzar ZG, Cooper S, et al. mRNA‐Seq of single prostate cancer circulating tumor cells reveals recapitulation of gene expression and pathways found in prostate cancer. PLoS One. 2012;7(11):e49144.
Iguchi T, Wang CY, Delongchamps NB, et al. Occult prostate cancer effects the results of case‐control studies due to verification bias. Anticancer Res. 2008;28(5b):3007‐3010.
Crook T, Leonard R, Mokbel K, et al. Accurate screening for early‐stage breast cancer by detection and profiling of circulating tumor cells. Cancers. 2022;14(14):3341.
Limaye S, Chowdhury S, Rohatgi N, et al. Accurate prostate cancer detection based on enrichment and characterization of prostate cancer specific circulating tumor cells. Cancer Med. 2023;12(8):9116‐9127.
Eggener SE, Berlin A, Vickers AJ, Paner GP, Wolinsky H, Cooperberg MR. Low‐grade prostate cancer: time to stop calling it cancer. J Clin Oncol. 2022;40(27):3110‐3114.
Iremashvili V, Manoharan M, Rosenberg DL, Soloway MS. Biopsy features associated with prostate cancer progression in active surveillance patients: comparison of three statistical models. BJU Int. 2013;111(4):574‐579.
Moses KA, Sprenkle PC, Bahler C, et al. NCCN guidelines® insights: prostate cancer early detection, version 1.2023. J Natl Compr Canc Netw. 2023;21(3):236‐246.
Sartor O, de Bono J, Chi KN, et al. Lutetium‐177‐PSMA‐617 for metastatic castration‐resistant prostate cancer. N Engl J Med. 2021;385(12):1091‐1103.
Kind F, Fassbender TF, Andrieux G, Boerries M, Meyer PT, Ruf J. Early PSA change after [(177)Lu]PSMA‐617 radioligand therapy as a predicator of biochemical response and overall survival. Cancers. 2021;14(1):149.
Thuret R, Massard C, Gross‐Goupil M, et al. The postchemotherapy PSA surge syndrome. Ann Oncol. 2008;19(7):1308‐1311.