A robust machine learning model based on ribosomal-subunit-derived piRNAs for diagnostic potential of nonsmall cell lung cancer across multicentre, large-scale of sequencing data

Zitong Gao; Masaki Nasu; Gehan Devendra; Ayman A. Abdul-Ghani; Anthony J. Herrera; Jeffrey A. Borgia; Christopher W. Seder; Donna Lee Kuehu; Zhuokun Feng; Yu Chen; Ting Gong; Zao Zhang; Owen Chan; Hua Yang; Jianhua Yu; Yuanyuan Fu; Lang Wu; Youping Deng

doi:10.1002/ctm2.70418

Clinical and Translational Medicine ›› 2025, Vol. 15 ›› Issue (8) : e70418 DOI: 10.1002/ctm2.70418

RESEARCH ARTICLE

A robust machine learning model based on ribosomal-subunit-derived piRNAs for diagnostic potential of nonsmall cell lung cancer across multicentre, large-scale of sequencing data

Author information +

¹. Department of Quantitative Health Sciences, John A. Burns School of Medicine, University of Hawaii at Manoa, Honolulu, Hawaiʻi, USA

². Molecular Biosciences and Bioengineering Program, College of Tropical Agriculture and Human Resources, University of Hawaii at Manoa, Honolulu, Hawaiʻi, USA

³. Genomics and Bioinformatics Shared Resource, University of Hawaii Cancer Center, Honolulu, Hawaiʻi, USA

⁴. Department of Medicine, John A. Burns School of Medicine, University of Hawaii at Manoa, Honolulu, Hawaiʻi, USA

⁵. Critical Care Medicine, Pulmonary, The Queen's Medical Center, Honolulu, Hawaiʻi, USA

⁶. Cardiothoracic Surgery, The Queen's Medical Center, Honolulu, Honolulu, Hawaiʻi, USA

⁷. Interventional Radiology, The Queen's Medical Center, Honolulu, Hawaiʻi, USA

⁸. Departments of Anatomy & Cell Biology and Pathology, RUSH University Cancer Center, Chicago, Illinois, USA

⁹. Cardiothoracic Residency Program, RUSH University, Chicago, Illinois, USA

¹⁰. Hospitalist Medicine, The Queen's Medical Center, Honolulu, Hawaiʻi, USA

¹¹. Pathology Core Shared Resource, University of Hawaii Cancer Center, Honolulu, Hawaiʻi, USA

¹². Institute for Precision Cancer Therapeutics and Immuno-Oncology, Chao Family Comprehensive Cancer Center, University of California, Irvine, California, USA

¹³. Pacific Center for Genome Research, University of Hawaii Cancer Center, Honolulu, Hawaiʻi, USA

lwu@cc.hawaii.edu

dengy@hawaii.edu

Show less

History +

PDF

Abstract

Nonsmall cell lung cancer (NSCLC) is a lethal cancer and lacks robust biomarkers for noninvasive clinical diagnosis. Detecting NSCLC at the early stage can decrease the mortality rate and minimise harm caused by various treatments. We curated 2050 samples from public tissue and plasma datasets including both invasive and noninvasive types, then supplemented with in-house pooled plasma and exosome samples. Eleven independent transcriptome datasets were utilised to develop a new machine learning model by integrating PIWI-interacting RNA (piRNA) to predict NSCLC. Five piRNA signatures derived from ribosomal subunits identified to be tumour-specific exhibited robust diagnostic ability and were combined into a piRNA-Based Tumour Probability Index (pi-TPI) risk evaluation model. pi-TPI effectively distinguished NSCLC patients from healthy individuals and showed efficacy in identifying early-stage cancers with Area under the ROC Curve (AUC) values over .80. Plasma cohorts exhibited the diagnosis efficacy of pi-TPI with an AUC value of .85. Experimental exosomal data enhances the accuracy of diagnosing noncancerous, benign, and cancer cases. The pi-TPI marker in the noncancer/cancer subgroup exhibited superior predictive performance with an AUC value of .96. These findings underscore the significant clinical potential of the five piRNA signatures as a powerful diagnostic tool for NSCLC, particularly of noninvasive cancer diagnostics.

Keywords

machine learning / noninvasive diagnosis / nonsmall cell lung cancer / PIWI-interacting RNA / small noncoding RNA

Cite this article

Download citation ▾

Zitong Gao, Masaki Nasu, Gehan Devendra, Ayman A. Abdul-Ghani, Anthony J. Herrera, Jeffrey A. Borgia, Christopher W. Seder, Donna Lee Kuehu, Zhuokun Feng, Yu Chen, Ting Gong, Zao Zhang, Owen Chan, Hua Yang, Jianhua Yu, Yuanyuan Fu, Lang Wu, Youping Deng. A robust machine learning model based on ribosomal-subunit-derived piRNAs for diagnostic potential of nonsmall cell lung cancer across multicentre, large-scale of sequencing data. Clinical and Translational Medicine, 2025, 15(8): e70418 DOI:10.1002/ctm2.70418

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA Cancer J Clin. 2024; 74: 12-49.

[2]	Shiels MS, Graubard BI, McNeel TS, Kahle L, Freedman ND. Trends in smoking-attributable and smoking-unrelated lung cancer death rates in the U.S., 1991–2018. J Natl Cancer Inst. 2023; 116(5): 711-716.

[3]	Purandare NC, Rangarajan V. Imaging of lung cancer: implications on staging and management. Indian J Radiol Imaging. 2015; 25: 109-120.

[4]	Casagrande GMS, Silva MO, Reis RM, Leal LF. Liquid biopsy for lung cancer: up-to-date and perspectives for screening programs. Int J Mol Sci. 2023; 24: 2505.

[5]	Connal S, Cameron JM, Sala A, et al. Liquid biopsies: the future of cancer early detection. J Transl Med. 2023; 21: 118.

[6]	Tomasik B, Skrzypski M, Bienkowski M, Dziadziuszko R, Jassem J. Current and future applications of liquid biopsy in non-small-cell lung cancer-a narrative review. Transl Lung Cancer Res. 2023; 12: 594-614.

[7]	Preethi KA, Selvakumar SC, Ross K, Jayaraman S, Tusubira D, Sekar D. Liquid biopsy: exosomal microRNAs as novel diagnostic and prognostic biomarkers in cancer. Mol Cancer. 2022; 21: 54.

[8]	Chen M, Zhao H. Next-generation sequencing in liquid biopsy: cancer screening and early detection. Hum Genomics. 2019; 13: 34.

[9]	Gao Z, Jijiwa M, Nasu M, et al. Comprehensive landscape of tRNA-derived fragments in lung cancer. Mol Ther Oncolytics. 2022; 26: 207-225.

[10]	Zhao T, Khadka VS, Deng Y. Identification of lncRNA biomarkers for lung cancer through integrative cross-platform data analyses. Aging (Albany NY). 2020; 12: 14506-14527.

[11]	Chen Y, Zitello E, Guo R, Deng Y. The function of LncRNAs and their role in the prediction, diagnosis, and prognosis of lung cancer. Clin Transl Med. 2021; 11: e367.

[12]	Bartolomucci A, Nobrega M, Ferrier T, et al. Circulating tumor DNA to monitor treatment response in solid tumors and advance precision oncology. NPJ Precis Oncol. 2025; 9: 84.

[13]	Cisneros-Villanueva M, Hidalgo-Perez L, Rios-Romero M, et al. Cell-free DNA analysis in current cancer clinical trials: a review. Br J Cancer. 2022; 126: 391-400.

[14]	Toden S, Goel A. Non-coding RNAs as liquid biopsy biomarkers in cancer. Br J Cancer. 2022; 126: 351-360.

[15]	Zhang Z, Tang Y, Song X, Xie L, Zhao S, Song X. Tumor-derived exosomal miRNAs as diagnostic biomarkers in non-small cell lung cancer. Front Oncol. 2020; 10: 560025.

[16]	Tang Y, Zhang Z, Song X, et al. Tumor-Derived exosomal miR-620 as a diagnostic biomarker in non-small-cell lung cancer. J Oncol. 2020; 2020: 6691211.

[17]	Aravin AA, Naumova NM, Tulin AV, Vagin VV, Rozovsky YM, Gvozdev VA. Double-stranded RNA-mediated silencing of genomic tandem repeats and transposable elements in the D. melanogaster germline. Curr Biol. 2001; 11: 1017-1027.

[18]	Platt RN, Vandewege MW, Ray DA. Mammalian transposable elements and their impacts on genome evolution. Chromosome Res. 2018; 26: 25-43.

[19]	Klein SJ, O'Neill RJ. Transposable elements: genome innovation, chromosome diversity, and centromere conflict. Chromosome Res. 2018; 26: 5-23.

[20]	Gebrie A. Transposable elements as essential elements in the control of gene expression. Mob DNA. 2023; 14: 9.

[21]	Sun YH, Lee B, Li XZ. The birth of piRNAs: how mammalian piRNAs are produced, originated, and evolved. Mamm Genome. 2022; 33: 293-311.

[22]	Aravin AA, Sachidanandam R, Girard A, Fejes-Toth K, Hannon GJ. Developmentally regulated piRNA clusters implicate MILI in transposon control. Science. 2007; 316: 744-747.

[23]	Huang X, Fejes Toth K, Aravin AA. piRNA biogenesis in drosophila melanogaster. Trends Genet. 2017; 33: 882-894.

[24]	Toth KF, Pezic D, Stuwe E, Webster A. The piRNA pathway guards the germline genome against transposable elements. Adv Exp Med Biol. 2016; 886: 51-77.

[25]	Guo B, Li D, Du L, Zhu X. piRNAs: biogenesis and their potential roles in cancer. Cancer Metastasis Rev. 2020; 39: 567-575.

[26]	Jian Z, Han Y, Li H. Potential roles of PIWI-interacting RNAs in lung cancer. Front Oncol. 2022; 12: 944403.

[27]	Mei Y, Wang Y, Kumari P, et al. A piRNA-like small RNA interacts with and modulates p-ERM proteins in human somatic cells. Nat Commun. 2015; 6: 7316.

[28]	Peng L, Song L, Liu C, et al. piR-55490 inhibits the growth of lung carcinoma by suppressing mTOR signaling. Tumour Biol. 2016; 37: 2749-2756.

[29]	Yao J, Wang YW, Fang BB, Zhang SJ, Cheng BL. piR-651 and its function in 95-D lung cancer cells. Biomed Rep. 2016; 4: 546-550.

[30]	Ding L, Wang R, Xu W, et al. PIWI-interacting RNA 57125 restrains clear cell renal cell carcinoma metastasis by downregulating CCL3 expression. Cell Death Discov. 2021; 7: 333.

[31]	Reeves ME, Firek M, Jliedi A, Amaar YG. Identification and characterization of RASSF1C piRNA target genes in lung cancer cells. Oncotarget. 2017; 8: 34268-34282.

[32]	Storer J, Hubley R, Rosen J, Wheeler TJ, Smit AF. The Dfam community resource of transposable element families, sequence models, and genome annotations. Mob DNA. 2021; 12: 2.

[33]	Kobayashi T. Strategies to maintain the stability of the ribosomal RNA gene repeats–collaboration of recombination, cohesion, and condensation. Genes Genet Syst. 2006; 81: 155-161.

[34]	Ganley AR, Kobayashi T. Ribosomal DNA and cellular senescence: new evidence supporting the connection between rDNA and aging. FEMS Yeast Res. 2014; 14: 49-59.

[35]	Sun FJ, Caetano-Anolles G. The evolutionary history of the structure of 5S ribosomal RNA. J Mol Evol. 2009; 69: 430-443.

[36]	Elhamamsy AR, Metge BJ, Alsheikh HA, Shevde LA, Samant RS. Ribosome biogenesis: a central player in cancer metastasis and therapeutic resistance. Cancer Res. 2022; 82: 2344-2353.

[37]	Williamson D, Lu YJ, Fang C, Pritchard-Jones K, Shipley J. Nascent pre-rRNA overexpression correlates with an adverse prognosis in alveolar rhabdomyosarcoma. Genes Chromosomes Cancer. 2006; 45: 839-845.

[38]	Kang H, Choi MC, Kim S, et al. USP19 and RPL23 as candidate prognostic markers for advanced-stage high-grade serous ovarian carcinoma. Cancers (Basel). 2021; 13: 3976.

[39]	Luo S, Zhao J, Fowdur M, Wang K, Jiang T, He M. Highly expressed ribosomal protein L34 indicates poor prognosis in osteosarcoma and its knockdown suppresses osteosarcoma proliferation probably through translational control. Sci Rep. 2016; 6: 37690.

[40]	Chen J, Wei Y, Feng Q, et al. Ribosomal protein S15A promotes malignant transformation and predicts poor outcome in colorectal cancer through misregulation of p53 signaling pathway. Int J Oncol. 2016; 48: 1628-1638.

[41]	Bornelov S, Reynolds N, Xenophontos M, et al. The nucleosome remodeling and deacetylation complex modulates chromatin structure at sites of active transcription to fine-tune gene expression. Mol Cell. 2018; 71: 56-72 e54.

[42]	Alhmoud JF, Woolley JF, Al Moustafa AE, Malki MI. DNA damage/repair management in cancers. Cancers (Basel). 2020; 12: 1050.

[43]	Wyld L, Bellantuono I, Tchkonia T, et al. Senescence and cancer: a review of clinical implications of senescence and senotherapies. Cancers (Basel). 2020; 12: 2134.

[44]	Matthews HK, Bertoli C, de Bruin RAM. Cell cycle control in cancer. Nat Rev Mol Cell Biol. 2022; 23: 74-88.

[45]	Nooreldeen R, Bach H. Current and future development in lung cancer diagnosis. Int J Mol Sci. 2021; 22: 8661.

[46]	Grunnet M, Sorensen JB. Carcinoembryonic antigen (CEA) as tumor marker in lung cancer. Lung Cancer. 2012; 76: 138-143.

[47]	Okamura K, Takayama K, Izumi M, Harada T, Furuyama K, Nakanishi Y. Diagnostic value of CEA and CYFRA 21-1 tumor markers in primary lung cancer. Lung Cancer. 2013; 80: 45-49.

[48]	Bauml JM, Li BT, Velcheti V, et al. Clinical validation of Guardant360 CDx as a blood-based companion diagnostic for sotorasib. Lung Cancer. 2022; 166: 270-278.

[49]	Kurth HM, Mochizuki K. 2'-O-methylation stabilizes Piwi-associated small RNAs and ensures DNA elimination in Tetrahymena. RNA. 2009; 15: 675-685.

[50]	Gainetdinov I, Colpan C, Cecchini K, et al. Terminal modification, sequence, length, and PIWI-protein identity determine piRNA stability. Mol Cell. 2021; 81: 4826-4842 e4828.

[51]	Horwich MD, Li C, Matranga C, et al. The drosophila RNA methyltransferase, DmHen1, modifies germline piRNAs and single-stranded siRNAs in RISC. Curr Biol. 2007; 17: 1265-1272.

[52]	Mai D, Zheng Y, Guo H, et al. Serum piRNA-54265 is a new biomarker for early detection and clinical surveillance of human colorectal cancer. Theranostics. 2020; 10: 8468-8478.

[53]	Qu A, Wang W, Yang Y, et al. A serum piRNA signature as promising non-invasive diagnostic and prognostic biomarkers for colorectal cancer. Cancer Manag Res. 2019; 11: 3703-3720.

[54]	Mai D, Ye Y, Zhuang L, Zheng J, Lin D. Detection of piRNA-54265 in human serum: evidence and significance. Cancer Commun (Lond). 2023; 43: 276-279.

[55]	Wang C, Zhang C, Fu Q, et al. Increased serum piwi-interacting RNAs as a novel potential diagnostic tool for brucellosis. Front Cell Infect Microbiol. 2022; 12: 992775.

[56]	Li Y, Dong Y, Zhao S, et al. Serum-derived piR-hsa-164586 of extracellular vesicles as a novel biomarker for early diagnosis of non-small cell lung cancer. Front Oncol. 2022; 12: 850363.

[57]	He L, Wu X, Wu R, et al. Seminal plasma piRNA array analysis and identification of possible biomarker piRNAs for the diagnosis of asthenozoospermia. Exp Ther Med. 2022; 23: 347.

[58]	Dabi Y, Suisse S, Marie Y, et al. New class of RNA biomarker for endometriosis diagnosis: the potential of salivary piRNA expression. Eur J Obstet Gynecol Reprod Biol. 2023; 291: 88-95.

[59]	Rui T, Wang K, Xiang A, et al. Serum exosome-derived piRNAs could be promising biomarkers for HCC diagnosis. Int J Nanomedicine. 2023; 18: 1989-2001.

[60]	Sidhom K, Obi PO, Saleem A. A review of exosomal isolation methods: is size exclusion chromatography the best option? Int J Mol Sci. 2020; 21: 6466.

[61]	Limanowka P, Ochman B, Swietochowska E. PiRNA obtained through liquid biopsy as a possible cancer biomarker. Diagnostics (Basel). 2023; 13: 1895.

[62]	Makkar S, Rana N, Priyadarshi N, Bajaj G, Kumar S, Singhal NK. Unravelling the therapeutic properties of aptamer-modified exosome nanocomposite. Adv Colloid Interface Sci. 2025; 342: 103517.

[63]	Nasu M, Khadka VS, Jijiwa M, Kobayashi K, Deng Y. Exploring optimal biomarker sources: a comparative analysis of exosomes and whole plasma in fasting and non-fasting conditions for liquid biopsy applications. Int J Mol Sci. 2023; 25: 371.

[64]	Zhou M, Bao S, Gong T, et al. The transcriptional landscape and diagnostic potential of long non-coding RNAs in esophageal squamous cell carcinoma. Nat Commun. 2023; 14: 3799.

[65]	Poh KC, Ren TM, Ling GL, et al. Development of a miRNA-Based model for lung cancer detection. Cancers (Basel). 2025; 17: 942.

[66]	Zhong Y, She Y, Deng J, et al. Deep learning for prediction of N2 metastasis and survival for clinical stage I non-small cell lung cancer. Radiology. 2022; 302: 200-211.

[67]	Carrillo-Perez F, Morales JC, Castillo-Secilla D, Gevaert O, Rojas I, Herrera LJ. Machine-learning-based late fusion on multi-omics and multi-scale data for non-small-cell lung cancer diagnosis. J Pers Med. 2022; 12: 601.

[68]	Coudray N, Ocampo PS, Sakellaropoulos T, et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med. 2018; 24: 1559-1567.

[69]	Li J, Xu HL, Li WX, Ma XY, Liu XH, Zhang ZF. Prognostic factors of survival in patients with lung cancer after low-dose computed tomography screening: a multivariate analysis of a lung cancer screening cohort in China. BMC Cancer. 2025; 25: 646.

[70]	Ardila D, Kiraly AP, Bharadwaj S, et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med. 2019; 25: 954-961.

[71]	Song P, Hou J, Xiao N, et al. MSTS-Net: malignancy evolution prediction of pulmonary nodules from longitudinal CT images via multi-task spatial-temporal self-attention network. Int J Comput Assist Radiol Surg. 2023; 18: 685-693.

[72]	Durgam R, Panduri B, Balaji V, Khadidos AO, Khadidos AO, Selvarajan S. Enhancing lung cancer detection through integrated deep learning and transformer models. Sci Rep. 2025; 15: 15614.

[73]	Yu L, Tao G, Zhu L, et al. Prediction of pathologic stage in non-small cell lung cancer using machine learning algorithm based on CT image feature analysis. BMC Cancer. 2019; 19: 464.

[74]	Smith-Bindman R, Chu PW, Azman Firdaus H, et al. Projected lifetime cancer risks from current computed tomography imaging. JAMA Intern Med. 2025; 185: 710-719.

[75]	Wang J, Shi Y, Zhou H, et al. piRBase: integrating piRNA annotation in all aspects. Nucleic Acids Res. 2022; 50: D265-D272.

[76]	Gu Z, Gu L, Eils R, Schlesner M, Brors B. circlize Implements and enhances circular visualization in R. Bioinformatics. 2014; 30: 2811-2812.

RIGHTS & PERMISSIONS

2025 The Author(s). Clinical and Translational Medicine published by John Wiley & Sons Australia, Ltd on behalf of Shanghai Institute of Clinical Bioinformatics.