★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★Open research. Global perspectives.
editor@theamericanjournals.com Publisher Home ↗
Engineering and Technology OPEN ACCESS

AI-Driven Liquid Biopsy Analysis for Early Cancer Detection: Integrating Circulating Tumor DNA, RNA, and Protein Biomarkers

Shakhnoza Khamidova
Independent Researcher, USA
tajet 2025
VOL. 7 / NO. 12 DECEMBER
FULL TEXT PP. 230-249
DOWNLOAD PDF

View all articles in this issue ↗

VOLUME 7
ISSUE 12
YEAR 2025
PAGES 230-249
RESEARCH OVERVIEW

Abstract

Liquid biopsy has recently proved to be a minimally invasive method used to identify cancer-associated molecular information contained in biological fluid such as circulating tumor DNA (ctDNA), cell-free DNA (cfDNA), circulating RNA, microRNAs (miRNAs), and tumor-associated proteins. The early detection of cancer is difficult, however, because the signals from the tumor are often at low levels in a complex biological background. The computational tools offered by artificial intelligence (AI), such as machine learning and deep learning, enable the extraction of informative molecular features, the generation of biomarker signatures, and the integration of heterogeneous liquid-biopsy datasets. In this review, AI approaches for the early detection of cancer based on ctDNA/cfDNA, circulating RNA, miRNAs, and protein biomarkers will be examined. It explores the biological properties of these analytes, the pre-analytical and analytical process, AI-powered feature selection and classification techniques, and the creation of individual and multimodal biomarker signatures. Special emphasis is placed on multimodal and multi-omics approaches to the integration of genomic, epigenetic, transcriptional, and protein information. The success of AI-driven liquid biopsy in real-world applications, such as those in specific cancers and multi-cancer early detection, underscores its promise in the detection of intricate molecular patterns that might not be detectable by a single biomarker. However, biological heterogeneity, low tumor fraction, pre-analytical variation, assay noise, high-dimensional data, overfitting, population bias, and lack of external validation are still significant obstacles to clinical translation. Scaling up with increasingly larger and more diverse cohorts, standardized workflows, explainable AI, multimodal integration, and prospective longitudinal validation will be needed to support future progress. In summary, AI-based liquid biopsy is a promising approach that holds the potential to transform the diverse landscape of circulating biomarkers into molecular signatures for early cancer detection; however, it must be carefully validated and proven to be clinically reproducible.

RESEARCH TOPICS

Keywords

Artificial intelligence liquid biopsy Early cancer detection circulating tumor DNA

Downloads

Download data is not yet available.
SOURCES & SCHOLARSHIP

References

  1. J. D. Schiffman, P. G. Fisher, and P. Gibbs, “Early detection of cancer: Past, present, and future,” ASCO Educational Book, vol. 35, no. 1, pp. 57–65, 2015.
  2. A. A. Ahmed and M. Abedalthagafi, “Cancer diagnostics: The journey from histomorphology to molecular profiling,” Oncotarget, vol. 7, no. 36, p. 58696, 2016.
  3. R. C. Fitzgerald et al., “The future of early cancer detection,” Nature Medicine, vol. 28, no. 4, pp. 666–677, 2022.
  4. W. She, Y. Garitaonaindia, and Y. Lin, “The latest advances in liquid biopsy for lung cancer—a narrative review,” Translational Lung Cancer Research, vol. 13, no. 11, p. 3241, 2024.
  5. X. Wu et al., “Circulating tumor DNA as an emerging liquid biopsy biomarker for early diagnosis and therapeutic monitoring in hepatocellular carcinoma,” International Journal of Biological Sciences, vol. 16, no. 9, p. 1551, 2020.
  6. S. N. Lone et al., “Liquid biopsy: A step closer to transform diagnosis, prognosis and future of cancer treatments,” Molecular Cancer, vol. 21, no. 1, p. 79, 2022.
  7. S. Grabuschnig et al., “Putative origins of cell-free DNA in humans: A review of active and passive nucleic acid release mechanisms,” International Journal of Molecular Sciences, vol. 21, no. 21, p. 8062, 2020.
  8. F. Leung et al., “Circulating tumor DNA as a cancer biomarker: Fact or fiction?,” Clinical Chemistry, vol. 62, no. 8, pp. 1054–1060, 2016.
  9. Y. M. D. Lo et al., “Epigenetics, fragmentomics, and topology of cell-free DNA in liquid biopsies,” Science, vol. 372, no. 6538, Art. no. eaaw3616, 2021.
  10. S.-P. Liu et al., “The messenger RNA and long non-coding RNA expression profiles in ectopic and eutopic endometrium provide novel insights into endometriosis,” Reproductive and Developmental Medicine, vol. 3, no. 1, pp. 11–17, 2019.
  11. P. S. Mitchell et al., “Circulating microRNAs as stable blood-based markers for cancer detection,” Proceedings of the National Academy of Sciences, vol. 105, no. 30, pp. 10513–10518, 2008.
  12. K. Felekkis and C. Papaneophytou, “The circulating biomarkers league: Combining miRNAs with cell-free DNAs and proteins,” International Journal of Molecular Sciences, vol. 25, no. 6, p. 3403, 2024.
  13. V. Ungerer, A. J. Bronkhorst, and S. Holdenrieder, “Preanalytical variables that affect the outcome of cell-free DNA measurements,” Critical Reviews in Clinical Laboratory Sciences, vol. 57, no. 7, pp. 484–507, 2020.
  14. W. Hemstrom et al., “Next-generation data filtering in the genomics era,” Nature Reviews Genetics, vol. 25, no. 11, pp. 750–767, 2024.
  15. J. A. B. Brandão, “Dimensionality reduction in survival models based on gene expression data: An application to brain cancer,” 2024.
  16. Q. Li, Y. He, and J. Pan, “CrossFuse-XGBoost: Accurate prediction of the maximum recommended daily dose through multi-feature fusion, cross-validation screening and extreme gradient boosting,” Briefings in Bioinformatics, vol. 25, no. 1, Art. no. bbad511, 2024.
  17. K. Wang et al., “Liquid biopsy techniques and pancreatic cancer: Diagnosis, monitoring, and evaluation,” Molecular Cancer, vol. 22, no. 1, p. 167, 2023.
  18. L. K. K. Rajendran, “Genomic profiling: Utilizing multi-omics data to identify potential therapeutic targets and resistance markers,” Power System Protection and Control, vol. 52, no. 4, pp. 159–166, 2024.
  19. M. Greenacre et al., “Principal component analysis,” Nature Reviews Methods Primers, vol. 2, no. 1, p. 100, 2022.
  20. J. Doroszkiewicz, M. Groblewska, and B. Mroczko, “Molecular biomarkers and their implications for the early diagnosis of selected neurodegenerative diseases,” International Journal of Molecular Sciences, vol. 23, no. 9, p. 4610, 2022.
  21. J. E. Medina et al., “Cell-free DNA approaches for cancer early detection and interception,” Journal for Immunotherapy of Cancer, vol. 11, no. 9, Art. no. e006013, 2023.
  22. M. Karimzadeh et al., “Deep generative AI models analyzing circulating orphan non-coding RNAs enable accurate detection of early-stage non-small cell lung cancer,” medRxiv, 2024.
  23. P. Tighe et al., “Utility, reliability and reproducibility of immunoassay multiplex kits,” Methods, vol. 61, no. 1, pp. 23–29, 2013.
  24. Y. Nam et al., “Harnessing artificial intelligence in multimodal omics data integration: Paving the path for the next frontier in precision medicine,” Annual Review of Biomedical Data Science, vol. 7, no. 1, pp. 225–250, 2024.
  25. S. Hieke et al., “Integrating multiple molecular sources into a clinical risk prediction signature by extracting complementary information,” BMC Bioinformatics, vol. 17, no. 1, p. 327, 2016.
  26. R. Li et al., “Machine learning meets omics: Applications and perspectives,” Briefings in Bioinformatics, vol. 23, no. 1, Art. no. bbab460, 2022.
  27. M. Kim and J. Costello, “DNA methylation: An epigenetic mark of cellular memory,” Experimental & Molecular Medicine, vol. 49, no. 4, Art. no. e322, 2017.
  28. L. Pikor et al., “The detection and implication of genome instability in cancer,” Cancer and Metastasis Reviews, vol. 32, no. 3, pp. 341–352, 2013.
CONTINUE EXPLORING

Most read articles by the same author(s)

Explore other published research by the authors of this article.