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

Machine Learning For Multi-Biomarker Screening In Cancer Diagnosis: Integrating Genomic, Proteomic And Metabolic Signatures

Shakhnoza Khamidova
Independent Researcher,USA
tajet 2024
VOL. 6 / NO. 12 DECEMBER
FULL TEXT PP. 247-263
DOWNLOAD PDF

View all articles in this issue ↗

VOLUME 6
ISSUE 12
YEAR 2024
PAGES 247-263
RESEARCH OVERVIEW

Abstract

Cancer screening increasingly requires the integration of molecular signals that capture different aspects of tumor biology. Genomic, proteomic, and metabolic biomarkers provide complementary information, but their high dimensionality, heterogeneous distributions, and biological interdependence make their combined interpretation challenging using conventional statistical approaches. This review examines the application of machine learning (ML) to multi-biomarker cancer screening, with particular emphasis on the integration of genomic, proteomic, and metabolic signatures. Genomic alterations provide relatively stable information concerning tumor identity and molecular lineage, whereas proteomic and metabolic profiles reflect downstream changes in cellular signaling, protein activity, and metabolism. The integration of these molecular layers therefore has the potential to improve discrimination between malignant and non-malignant states while providing information relevant to tumor classification and localization. The review discusses major ML strategies used to harmonize multi-omics data, reduce dimensionality, select informative biomarker features, and integrate heterogeneous molecular measurements through early, intermediate, and late fusion approaches. Evidence from multi-cancer and cancer-specific studies indicates that integrated biomarker models can achieve strong diagnostic discrimination and may outperform individual molecular layers in selected settings. Applications in colorectal, ovarian, breast, hepatocellular, pancreatic, and other cancers demonstrate the potential of combining circulating biomarkers and tissue-derived molecular profiles for early detection and disease characterization. However, promising model performance does not necessarily translate into clinical screening utility. Low tumor-derived signal in early disease, limited cohort sizes, heterogeneous sample processing, class imbalance, external validation gaps, and difficulties in model interpretation remain important limitations. Future progress will require prospective multicenter validation, longitudinal sampling, standardized multi-omics workflows, clinically interpretable biomarker panels, and evaluation in populations containing relevant benign conditions and early-stage disease. Overall, ML-enabled multi-biomarker integration represents a promising framework for cancer screening, but its clinical value will ultimately depend on demonstrating reliable, generalizable, and clinically actionable performance in real-world screening populations.

RESEARCH TOPICS

Keywords

Cancer Diagnosis Proteomic, Metabolic Genomic Multi Biomarker

Downloads

Download data is not yet available.
SOURCES & SCHOLARSHIP

References

  1. Smelik, M., Zhao, Y., Mansour Aly, D., Mahmud, A. F., Sysoev, O., Li, X., & Benson, M. (2024). Multiomics biomarkers were not superior to clinical variables for pan-cancer screening. Communications Medicine, 4(1), 234.
  2. Fu, X., Hu, Y., Li, B., Feng, Y., Wang, H., Lin, X., ... & Krishna, R. (2024, September). Blink: Multimodal large language models can see but not perceive. In European Conference on Computer Vision (pp. 148-166). Cham: Springer Nature Switzerland.
  3. Hu, J., Wang, S. G., Hou, Y., Chen, Z., Liu, L., Li, R., ... & Chen, K. (2024). Multi-omic profiling of clear cell renal cell carcinoma identifies metabolic reprogramming associated with disease progression. Nature genetics, 56(3), 442-457.
  4. Sharma, A., Debik, J., Naume, B., Ohnstad, H. O., Bathen, T. F., & Giskeødegård, G. F. (2024). Comprehensive multi-omics analysis of breast cancer reveals distinct long-term prognostic subtypes. Oncogenesis, 13(1), 22.
  5. Jiang, Y. Z., Ma, D., Jin, X., Xiao, Y., Yu, Y., Shi, J., ... & Shao, Z. M. (2024). Integrated multiomic profiling of breast cancer in the Chinese population reveals patient stratification and therapeutic vulnerabilities. Nature cancer, 5(4), 673-690.
  6. Xiong, D., Han, T., Li, Y., Hong, Y., Li, S., Li, X., ... & Li, C. (2024). TOTEM: a multi-cancer detection and localization approach using circulating tumor DNA methylation markers. BMC cancer, 24(1), 840.
  7. Xu, R., Wang, J., Zhu, Q., Zou, C., Wei, Z., Wang, H., ... & Zhang, S. (2023). Integrated models of blood protein and metabolite enhance the diagnostic accuracy for Non-Small Cell Lung Cancer. Biomarker Research, 11(1), 71.
  8. Xing, X., Hu, E., Ouyang, J., Zhong, X., Wang, F., Liu, K., ... & Liu, X. (2023). Integrated omics landscape of hepatocellular carcinoma suggests proteomic subtypes for precision therapy. Cell reports medicine, 4(12).
  9. Wang, H., Guo, H., Sun, J., & Wang, Y. (2023). Multi-omics analyses based on genes associated with oxidative stress and phospholipid metabolism revealed the intrinsic molecular characteristics of pancreatic cancer. Scientific Reports, 13(1), 13564.
  10. Osipov, A., Nikolic, O., Gertych, A., Parker, S., Hendifar, A., Singh, P., ... & Theodorescu, D. (2024). The Molecular Twin artificial-intelligence platform integrates multi-omic data to predict outcomes for pancreatic adenocarcinoma patients. Nature cancer, 5(2), 299-314.
  11. Picard, M., Scott-Boyer, M. P., Bodein, A., Périn, O., & Droit, A. (2021). Integration strategies of multi-omics data for machine learning analysis.
  12. Chai, H., Zhou, X., Zhang, Z., Rao, J., Zhao, H., & Yang, Y. (2021). Integrating multi-omics data through deep learning for accurate cancer prognosis prediction. Computers in biology and medicine, 134, 104481.
  13. Zhang, X., Xing, Y., Sun, K., & Guo, Y. (2021). OmiEmbed: a unified multi-task deep learning framework for multi-omics data. Cancers, 13(12), 3047.
  14. Ma, B., Meng, F., Yan, G., Yan, H., Chai, B., & Song, F. (2020). Diagnostic classification of cancers using extreme gradient boosting algorithm and multi-omics data. Computers in biology and medicine, 121, 103761.
  15. Cai, Z., Poulos, R. C., Liu, J., & Zhong, Q. (2022). Machine learning for multi-omics data integration in cancer. Iscience, 25(2).
  16. Ma, B., Meng, F., Yan, G., Yan, H., Chai, B., & Song, F. (2020). Diagnostic classification of cancers using extreme gradient boosting algorithm and multi-omics data. Computers in biology and medicine, 121, 103761.
  17. Ouyang, D., Liang, Y., Li, L., Ai, N., Lu, S., Yu, M., ... & Xie, S. (2023). Integration of multi-omics data using adaptive graph learning and attention mechanism for patient classification and biomarker identification. Computers in biology and medicine, 164, 107303.
  18. Cohen, J. D., Li, L., Wang, Y., Thoburn, C., Afsari, B., Danilova, L., ... & Papadopoulos, N. (2018). Detection and localization of surgically resectable cancers with a multi-analyte blood test. Science, 359(6378), 926-930.
  19. Putcha, G., Liu, T. Y., Ariazi, E., Bertin, M., Drake, A., Dzamba, M., ... & Sansanwal, P. (2020). Blood-based detection of early-stage colorectal cancer using multiomics and machine learning. J Clin Oncol, 38(suppl 4), 66.
  20. Battista, A., Battista, R. A., Battista, F., Iovane, G., & Landi, R. E. (2021). BH-index: A predictive system based on serum biomarkers and ensemble learning for early colorectal cancer diagnosis in mass screening. Computer Methods and Programs in Biomedicine, 212, 106494.
  21. Su, Y., Tian, X., Gao, R., Guo, W., Chen, C., Chen, C., ... & Lv, X. (2022). Colon cancer diagnosis and staging classification based on machine learning and bioinformatics analysis. Computers in biology and medicine, 145, 105409.
  22. Ban, D., Housley, S. N., Matyunina, L. V., McDonald, L. D., Bae-Jump, V. L., Benigno, B. B., ... & McDonald, J. F. (2024). A personalized probabilistic approach to ovarian cancer diagnostics. Gynecologic oncology, 182, 168-175.