Biologically Coherent MicroRNA Signature for Machine-Learning-Based Colorectal Cancer Detection
DOI:
https://doi.org/10.14500/aro.13036Keywords:
Biomarker discovery, Colorectal cancer, Feature selection, microRNA, Random forestAbstract
Colorectal cancer (CRC) biomarker discovery is frequently limited by signature instability, methodological heterogeneity, and insufficient external validation. This study aimed to develop a reproducible bioinformatics and machine learning framework for identifying a compact mature-microRNA (miRNA) signature capable of discriminating CRC tissues from matched normal controls. Small RNA-seq data from a paired discovery cohort (PRJNA387172; 104 tumor–normal pairs) and three independent external high-throughput sequencing cohorts (GSE125961, GSE183437, and GSE236991) were processed through uniform pre-processing, mature-miRNA quantification, counts per-million filtering, and TMM/logCPM normalization. Within the discovery cohort, pair-preserving 80:20 partitioning was combined with repeated stratified five-fold cross-validation with 10 repeats, train-only differential-expression analysis, and consensus feature selection using Elastic Net, Boruta, and random forest recursive feature elimination. This framework identified a stable locked three-miRNA signature comprising hsa-miR-135b-5p, hsa-miR-378a-5p, and hsa-miR-549a-5p. A random forest classifier trained on this panel achieved perfect discrimination in the discovery partitions, with an area under the curve (AUC) of 1.000 in both the training and independent test subsets, and showed preliminary external performance, with panel AUCs of 0.917, 1.000, and 0.840 across three small validation cohorts and 0.961 in pooled external analysis. Expression direction was preserved across datasets, with miR-135b-5p and miR-549a-5p upregulated and miR-378a-5p downregulated in tumors. Downstream target integration analysis recognized 401 overlap-supported miRNA-target interactions spanning 393 unique genes, with enrichment in Wnt, Hippo, transforming growth factor beta, focal adhesion, and CRC-related pathways. These findings support a biologically coherent three-miRNA random forest model for CRC biomarker discovery and prioritize candidates for future independent and experimental validation.
Downloads
References
Akbar, S., Mashreghi, S., Kalani, M.R., Valanik, A., Ahmadi, F., Aalikhani, M. and Bazi, Z., 2024. Blood miRNAs miR-549a, miR-552, and miR-592 serve as potential disease-specific panels to diagnose colorectal cancer. Heliyon, 10, p. e28492.
Beam, A.L., and Kohane, I.S., 2018. Big data and machine learning in health care. JAMA, 319, pp.1317-1318.
Chang, L.M., and Xia, J., 2022. MicroRNA regulatory network analysis using miRNet 2.0. In: Transcription Factor Regulatory Networks. Springer, Berlin. Chen, Y., Lun, A.T., and Smyth, G.K., 2016. From reads to genes to pathways: Differential expression analysis of RNA-Seq experiments using Rsubread and the edgeR quasi-likelihood pipeline. F1000Research, 5, p.1438.
Degroat, W., Abdelhalim, H., Peker, E., Sheth, N., Narayanan, R., Zeeshan, S., Liang, B.T., and Ahmed, Z., 2024. Multimodal AI/ML for discovering novel biomarkers and predicting disease using multi-omics profiles of patients with cardiovascular diseases. Scientific Reports, 14, p.26503.
Fasano, M., Pirozzi, M., Miceli, C.C., Cocule, M., Caraglia, M., Boccellino, M., Vitale, P., De Falco, V., Farese, S., Zotta, A., Ciardiello, F., and Addeo, R., 2024. TGF-β modulated pathways in colorectal cancer: New potential therapeutic opportunities. International Journal of Molecular Sciences, 25, p.7400.
Hozaka, Y., Kita, Y., Yasudome, R., Tanaka, T., Wada, M., Idichi, T., Tanabe, K., Asai, S., Moriya, S., and Toda, H., 2021. RNA-sequencing based microRNA expression signature of colorectal cancer: The impact of oncogenic targets regulated by miR-490-3p.
International Journal of Molecular Sciences, 22, p.9876. Khan, A.U., Ali, M., and Wahab, M.A., 2025. Diagnostic potential of cross specimen microRNA panels as biomarkers for colorectal cancer: A systematic review and meta-analysis. Molecular Diagnosis and Therapy, 29, pp.707-719.
Law, C.W., Chen, Y., Shi, W., and Smyth, G.K., 2014. Voom: Precision weights unlock linear model analysis tools for RNA-seq read counts. Genome Biology, 15, p.R29.
Li, K., Zhang, J., Zhang, M., Wu, Y., Lu, X., and Zhu, Y., 2021. miR-378a-5p inhibits the proliferation of colorectal cancer cells by downregulating CDK1. World Journal of Surgical Oncology, 19, p.54.
Li, Q., Geng, S., Luo, H., Wang, W., Mo, Y.Q., Luo, Q., Wang, L., Song, G.B., Sheng, J.P., and Xu, B. 2024. Signaling pathways involved in colorectal cancer: Pathogenesis and targeted therapy. Signal Transduction and Targeted Therapy, 9, p.266.
Ma, L., Guo, H., Zhao, Y., Liu, Z., Wang, C., Bu, J., Sun, T., and Wei, J. 2024. Liquid biopsy in cancer current: Status, challenges and future prospects. Signal Transduction and Targeted Therapy, 9, p.336.
Mohammadpour, S., Torshizi Esfahani, A., Sarpash, S., Vakili, F., Zafarjafarzadeh, N., Mashaollahi, A., Pardakhtchi, A., and Nazemalhosseini Mojarad, E., 2024. Hippo signaling pathway in colorectal cancer: Modulation by various signals and therapeutic potential. Analytical Cellular Pathology, 2024, p.5767535.
Moiz, S., Saha, B., Mondal, V., Bishnu, D., Das, B., Bose, B., Das, S., Banerjee, N., Dutta, A., Chatterjee, K., Goswami, S., Mukhopadhyay, S., and Basu, S., 2025. Differential expression of miRNAs between young-onset and late-onset Indian colorectal carcinoma patients. Non-Coding RNA, 11, p.10.
Naranbat, D., Herdes, E., Tapinos, N., and Tripathi, A., 2025. Review of microRNA detection workflows from liquid biopsy for disease diagnostics. Expert Reviews in Molecular Medicine, pp.1-41.
Pająk, W., Kleinrok, J., Pec, J., Michno, K., Wojtas, J., Badach, M., Teresińska, B., and Baj, J., 2025. Micro RNA in colorectal cancer-potential diagnostic and prognostic markers-an updated review. International Journal of Molecular Sciences, 26, p.8615.
Pudjihartono, N., Fadason, T., Kempa-Liehr, A.W., and O’Sullivan, J.M., 2022. A review of feature selection methods for machine learning-based disease risk prediction. Frontiers in Bioinformatics, 2, p.927312.
Roberts, M., Driggs, D., Thorpe, M., Gilbey, J., Yeung, M., Ursprung, S., Aviles Rivero, A.I., Etmann, C., Mccague, C., Beer, L., Weir-McCall, J.R., Teng, Z., Gkrania-Klotsas, E., Rudd, J.H., Sala, E., Schönlieb, C.B., and Aix-Covnet., 2021. Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans. Nature Machine Intelligence, 3, pp.199-217.
Robinson, M.D., and Oshlack, A., 2010. A scaling normalization method for differential expression analysis of RNA-seq data. Genome Biology, 11, p.R25.
Saha, S., Ghosh, S., Ghosh, S., Nandi, S., and Nayak, A., 2024. Unraveling the complexities of colorectal cancer and its promising therapies - an updated review. International Immunopharmacology, 143, p.113325.
Schwab, S., and Nonaka, T., 2025. Circulating miRNAs as liquid biopsy biomarkers for diagnosis in patients with colorectal cancer: A systematic review and meta-analysis. Frontiers in Genetics, 16, p.1574586.
Shao, Y., Zhang, S., Pan, Y., Peng, Z., and Dong, Y., 2025. miR-135b: A key role in cancer biology and therapeutic targets. Non-Coding RNA Research, 12, pp.67-80.
Shirzad, S., Eterafi, M., Karimi, Z., and Barazesh, M., 2025. MicroRNAs involved in colorectal cancer, a rapid mini-systematic review. BMC Cancer, 25, p.934.
Siegel, R.L., Giaquinto, A.N., and Jemal, A., 2024. Cancer statistics, 2024. CA: A Cancer Journal for Clinicians, 74, pp.12-49.
Tejeda-Muñoz, N., and Mei, K.C., 2024. Wnt signaling in cell adhesion, development, and colon cancer. IUBMB Life, 76, pp.383-396.
Todorović, N., and Amedei, A., 2024. Metadherin-driven promotion of cancer stem cell phenotypes and its effect on immunity in hepatocellular carcinoma. World Journal of Gastroenterology, 30, pp.2624-2628.
Wang, J., Zhang, Z., and Wang, Y., 2025. Utilizing feature selection techniques for AI-driven tumor subtype classification: Enhancing precision in cancer diagnostics. Biomolecules, 15, p.81.
Wang, Z., Ma, B., Ji, X., Deng, Y., Zhang, T., Zhang, X., Gao, H., Sun, H., Wu, H., and Chen, X., 2015. MicroRNA-378-5p
suppresses cell proliferation and induces apoptosis in colorectal cancer cells by targeting BRAF. Cancer Cell International, 15, p.40.
Włodarczyk, M., Maryńczak, K., Burzyński, J., Włodarczyk, J., Basak, J., Fichna, J., Majsterek, I., Ciesielski, P., Spinelli, A., and Dziki, Ł., 2025. The role of miRNAs in the pathogenesis, diagnosis, and treatment of colorectal cancer and colitis-associated cancer. Clinical and Experimental Medicine, 25, p.86.
Wu, S.M., Tsai, W.S., Chiang, S.F., Lai, Y.H., Ma, C.P., Wang, J.H., Lin, J., Lu, P.S., Yang, C.Y., and Tan, B.C.M., 2020. Comprehensive transcriptome profiling of Taiwanese colorectal cancer implicates an ethnic basis for pathogenesis. Scientific Reports, 10, p.4526.
Zhou, F., Tang, D., Xu, Y., He, H., Wu, Y., Lin, L., Dong, J., Tan, W., and Dai, Y., 2020. Identification of microRNAs and their endonucleolytic cleavaged target mRNAs in colorectal cancer. BMC Cancer, 20, p.242.
Zhu, L., Zhao, T., Su, H., Li, J., Shen, X., Zhang, L., Chen, J., and Song, Y., 2025. NUCKS1 promotes invasion and metastasis of colorectal cancer by stabilizing HDAC2 and activating AKT. Oncogenesis, 14, p.19.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rebaz M. Mustafa, Kamaran Abdoulrahman, Mohammad Hamid
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who choose to publish their work with Aro agree to the following terms:
-
Authors retain the copyright to their work and grant the journal the right of first publication. The work is simultaneously licensed under a Creative Commons Attribution License [CC BY-NC-SA 4.0]. This license allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors have the freedom to enter into separate agreements for the non-exclusive distribution of the journal's published version of the work. This includes options such as posting it to an institutional repository or publishing it in a book, as long as proper acknowledgement is given to its initial publication in this journal.
-
Authors are encouraged to share and post their work online, including in institutional repositories or on their personal websites, both prior to and during the submission process. This practice can lead to productive exchanges and increase the visibility and citation of the published work.
By agreeing to these terms, authors acknowledge the importance of open access and the benefits it brings to the scholarly community.
Accepted 2026-07-12
Published 2026-11-08
ARO Journal is a scientific, peer-reviewed, periodical, and diamond OAJ that has no APC or ASC.