Abstract
Acute myeloid leukemia (AML) is a clinically aggressive hematologic malignancy driven by complex genetic and epigenetic aberrations. Circular RNAs (circRNAs), characterized by covalently closed structures and exceptional stability, have emerged as promising diagnostic biomarkers. However, existing circRNA-based predictive models largely depend on differential expression, overlooking the potential impact of higher-order chromatin organization on circRNA formation and function. Here, we propose a machine learning framework that integrates three-dimensional (3D) genome architecture to refine circRNA selection for AML prediction. By mapping 9,565 circRNAs onto a 3D chromatin model reconstructed from Hi-C data, we analyzed their spatial clustering and biological pathway enrichment. Eighteen pathways exhibited significant 3D aggregation of circRNAs, enabling radial stratification based on nuclear localization. Five circRNA panels were designed using complementary strategies combining expression, pathway, and spatial features. Cross-validation and external validation across six machine learning algorithms showed that the panel derived from the fifth radial layer (Panel-3DG-Radius5) achieved the most robust and consistent performance (ROC-AUC > 0.99). Integrating 3D genomic context reduced feature collinearity while enhancing biological interpretability. Overall, our study establishes a 3D genome-informed paradigm for circRNA biomarker discovery, demonstrating that spatial genome organization can substantially improve the precision and robustness of AML predictive modeling.
Similar content being viewed by others
Data Availability
The original dataset can be downloaded from GEO database under the accession numbers GSE158596 and GSE149237. The data are provided in Supplementary Data, any additional data is available from the corresponding author upon reasonable request.
Code availability
The source code is available here: https://github.com/feelingyi1840/circRNA_AML.
References
Y. Mirazimi, A. H. Aghayan, A. Atashi, D. Mohammadi, M. Rafiee, Prognostic value of circular RNAs expression and their correlation with clinicopathological features in acute myeloid leukemia: a systematic review and meta-analysis. Ann. Hematol. 104, 2095–2124 (2025).
Gao, L. et al. Circular RNA as diagnostic and prognostic biomarkers in hematological malignancies:systematic review. Technol. Cancer Res. Treat. 23, 15330338241285149 (2024).
Ye, F. et al. Screening and validating circular RNAs that estimate disease risk and treatment response of pediatric acute myeloid leukemia: a microarray-based analyses and RT-qPCR validation. J. Cancer Res. Clin. Oncol. 149, 11233–11245 (2023).
Rahmati, A. et al. Circular RNAs: pivotal role in the leukemogenesis and novel indicators for the diagnosis and prognosis of acute myeloid leukemia. Front. Oncol. 13, 1149187 (2023).
Liu, Y. et al. Role of microRNAs, circRNAs and long noncoding RNAs in acute myeloid leukemia. J. Hematol. Oncol. 12, 51 (2019).
Li, M., Meng, F. & Lu, Q. Expression profile screening and bioinformatics analysis of circRNA, LncRNA, and mRNA in acute myeloid leukemia drug-resistant cells. Turk. J. Haematol. 37, 104–110 (2020).
Pourrajab, F., Zare-Khormizi, M. R., Hashemi, A. S. & Hekmatimoghaddam, S. Genetic characterization and risk stratification of acute myeloid leukemia. Cancer Manag. Res. 12, 2231–2253 (2020).
Hu, L., Zheng, B., Yang, Y., Chen, C. & Hu, M. Construction of circRNA-miRNA-mRNA network reveal functional circRNAs and key genes in acute myeloid leukemia. Int J. Gen. Med. 16, 1491–1504 (2023).
Kristensen, L. S., Hansen, T. B., Veno, M. T. & Kjems, J. Circular RNAs in cancer: opportunities and challenges in the field. Oncogene 37, 555–565 (2018).
Zhou, M., Gao, X., Zheng, X. & Luo, J. Functions and clinical significance of circular RNAs in acute myeloid leukemia. Front Pharm. 13, 1010579 (2022).
Ping, L., Jian-Jun, C., Chu-Shu, L., Guang-Hua, L. & Ming, Z. Silencing of circ_0009910 inhibits acute myeloid leukemia cell growth through increasing miR-20a-5p. Blood Cells Mol. Dis. 75, 41–47 (2019).
Huang, W. et al. Regulatory mechanism of miR-20a-5p expression in cancer. Cell Death Discov. 8, 262 (2022).
Chen, K., Ning, X., Yan, X. & Song, L. Circ_0104700 contributes to acute myeloid leukemia progression by enhancing MCM2 expression through targeting miR-665. Hematology 28, 2227489 (2023).
Singh, V., Uddin, M. H., Zonder, J. A., Azmi, A. S. & Balasubramanian, S. K. Circular RNAs in acute myeloid leukemia. Mol. Cancer 20, 149 (2021).
Das, A., Das, D. & Panda, A. C. Validation of circular RNAs by PCR. Methods Mol. Biol. 2392, 103–114 (2022).
Li, X. & Wu, Y. Detecting circular RNA from high-throughput sequence data with de Bruijn graph. Bmc Genomics 21, 749 (2020).
Li, A. et al. Increasing upstream chromatin long-range interactions may favor induction of circular RNAs in LysoPC-activated human aortic endothelial cells. Front. Physiol. 10, 433 (2019).
Chi, R. et al. Prediction of Alzheimer’s disease based on 3D genome selected circRNA. J. Prev. Alzheimers Dis. 11, 1055–1062 (2024).
Fang, C., Rao, S., Crispino, J. D. & Ntziachristos, P. Determinants and role of chromatin organization in acute leukemia. Leukemia 34, 2561–2575 (2020).
Kloetgen, A. et al. Three-dimensional chromatin landscapes in T cell acute lymphoblastic leukemia. Nat. Genet 52, 388–400 (2020).
Akdemir, K. C. et al. Disruption of chromatin folding domains by somatic genomic rearrangements in human cancer. Nat. Genet. 52, 294–305 (2020).
Chen, J. B. et al. Modeling circRNA expression pattern with integrated sequence and epigenetic features demonstrates the potential involvement of H3K79me2 in circRNA expression. Bioinformatics 37, 3386 (2021).
Conn, V. M. et al. Circular RNAs drive oncogenic chromosomal translocations within the MLL recombinome in leukemia. Cancer Cell 41, 1309–1326 e1310 (2023).
Sun, Y. M. et al. Chen, circMYBL2, a circRNA from MYBL2, regulates FLT3 translation by recruiting PTBP1 to promote FLT3-ITD AML progression. Blood 134, 1533–1546 (2019).
Yuan, Y. et al. DeepGene: an advanced cancer type classifier based on deep learning and somatic point mutations. BMC Bioinforma. 17, 476 (2016).
Trac, Q. T. et al. Prediction model for drug response of acute myeloid leukemia patients. npj Precis. Oncol. 7, 32 (2023).
Cai, Z., Poulos, R. C., Liu, J. & Zhong, Q. Machine learning for multi-omics data integration in cancer. iScience 25, 103798 (2022).
Yuan, Y. et al. Cancer type prediction based on copy number aberration and chromatin 3D structure with convolutional neural networks. BMC Genomics 19, 565 (2018).
Y. Song, et al. Classification of acute myeloid leukemia based on multi-omics and prognosis prediction value. Mol. Oncol. 19, 1836–1854 (2025).
Kosvyra, A., Karadimitris, A., Papaioannou, M. & Chouvarda, I. Machine learning and integrative multi-omics network analysis for survival prediction in acute myeloid leukemia. Comput. Biol. Med. 178, 108735 (2024).
H. Li, Y. Qian, Z. Sun, H. Zhu, Prediction of circRNA-disease associations via graph isomorphism transformer and dual-stream neural predictor. Biomolecules 15, 234 (2025).
Warnat-Herresthal, S. et al. Scalable prediction of acute myeloid leukemia using high-dimensional machine learning and blood transcriptomics. iScience 23, 100780 (2020).
Lieberman-Aiden, E. et al. Comprehensive mapping of long-range interactions reveals folding principles of the human genome. Science 326, 289–293 (2009).
K. Y. Li, et al. 3D genome-selected microRNAs to improve Alzheimer’s disease prediction. Front. Neurol. 14, 1059492 (2023).
Shi, Y. et al. Chromatin accessibility contributes to simultaneous mutations of cancer genes. Sci. Rep. 6, 35270 (2016).
Guo, Z. H. et al. 3D genome assisted protein-protein interaction prediction. Future Gener. Comp. Sy 137, 87–96 (2022).
Lux, S. et al. Deregulated expression of circular RNAs in acute myeloid leukemia. Blood Adv. 5, 1490–1503 (2021).
Davis, A. G. et al. Alternative polyadenylation dysregulation contributes to the differentiation block of acute myeloid leukemia. Blood 139, 424–438 (2022).
Gao, Y., Wang, J. & Zhao, F. CIRI: an efficient and unbiased algorithm for de novo circular RNA identification. Genome Biol. 16, 4 (2015).
Gao, Y., Zhang, J. & Zhao, F. Circular RNA identification based on multiple seed matching. Brief. Bioinform 19, 803–810 (2018).
Shin, H. et al. TopDom: an efficient and deterministic method for identifying topological domains in genomes. Nucleic Acids Res. 44, e70 (2016).
Shi, Y. et al. DeepAntigen: a novel method for neoantigen prioritization via 3D genome and deep sparse learning. Bioinformatics 36, 4894–4901 (2020).
Acknowledgements
The authors would like to express their sincere gratitude to all the involved participants for their support. This project is supported by the National Key Research and Development Program (2022YFE0125300, 2024YFC2707002), Innovation Program of Shanghai Municipal Education Commission (2023ZKZD16), Shanghai Municipal Science and Technology Major Project (2017SHZDZX01, 20JC1418600), the Shanghai Leading Academic Discipline Project (B205), Key Technology Breakthrough Program of Ningbo Sci-Tech Innovation YONGJIANG 2035 (2024Z221), and Shanghai Jiao Tong University STAR Grant (YG2025QNA46, YG2023ZD26, YG2022ZD024, YG2022QN111, YG2023LC14, YG2024QNA59).
Author information
Authors and Affiliations
Contributions
Y.S., G.H., H.L., Y.L., H.C., M.T., K.F., and H.K. conceptualized and designed the study; Y.S. and G.H. supervised the study; Z.Y., W.Y., R.W., and S.Y. acquired the data; Z.Y., C.P., X.R., and W.D. organized the data; Y.S. and Z.Y. designed the ML analysis pipeline; Z.Y. conducted the ML in silicon experiments; Z.Y., W.Y., R.W., H.C., H.S., and S.Y. discovered the biological insights. Y.S. and Z.Y. wrote and reviewed the manuscript; Y.S., G.H., H.L., Y.L., Y.Z., and H.S. revised the manuscript. All authors approved the final version of the manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Yuan, Z., Yan, W., Wang, R. et al. Machine learning prediction for AML based on 3D genome selected circRNA. npj Syst Biol Appl (2026). https://doi.org/10.1038/s41540-025-00638-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41540-025-00638-3
