Classification of Cancer Epitope Mutations Using Random Forest, SVM and Sequence-Derived Features
-
Miftahurrahma Rosyda
*
Universitas Ahmad Dahlan, Yogyakarta,
Indonesia
- Dinan Yulianto Universitas Ahmad Dahlan, Yogyakarta, Indonesia (*) Corresponding Author
Abstract
Cancer remains a major global health challenge, with increasing incidence and mortality rates worldwide. One promising approach in cancer immunotherapy is the identification of epitopes, particularly mutated epitopes that play a critical role in immune recognition. This study aims to classify cancer epitope mutations using machine learning approaches based on sequence-derived physicochemical features. A dataset consisting of 234 samples was used, comprising into tumor and mutated tumor epitopes. Feature extraction was performed using physicochemical properties such as molecular weight, isoelectric point, aliphatic index, aromaticity, and hydrophobicity. Two machine learning models, namely Support Vector Machine and Random Forest were selected due to their proven effectiveness in biological sequence classification tasks and their robustness in handling small-to-medium-sized datasets. The results show that Random Forest achieved the best performance with an accuracy of 83% and a macro average F1-score of 0.70, while consistently outperforming the Support Vector Machine model across all data partition scenarios. However, further analysis revealed that the model exhibits limitations in detecting mutated epitopes, as indicated by a relatively high false-negative rate. This issue is likely due to the use of global sequence-derived features, which may not effectively capture local variations caused by mutations. This study contributes to the field of computational immunology by providing a comparative evaluation of Random Forest and Support Vector Machine for mutation epitope classification using sequence-derived physicochemical features. In addition, the integration of machine learning analysis with structural bioinformatics interpretation offers further biological insight into mutation-associated epitopes and their potential relevance in cancer immunotherapy.
Downloads
References
Badan Pusat Statistik, Statistik Indonesia, vol. 53. 2025. [Online]. Available: https://www.bps.go.id/id/publication/2025/02/28/8cfe1a589ad3693396d3db9f/statistik-indonesia-2025.html
F. Bray et al., “Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries,” CA. Cancer J. Clin., vol. 74, no. 3, pp. 229–263, 2024, doi: https://doi.org/10.3322/caac.21834.
M. J. Kamali, M. Salehi, and M. K. Fath, “Advancing personalized immunotherapy for melanoma: Integrating immunoinformatics in multi-epitope vaccine development, neoantigen identification via NGS, and immune simulation evaluation,” Comput. Biol. Med., vol. 188, p. 109885, Apr. 2025, doi: 10.1016/j.compbiomed.2025.109885.
W. Chronister, A. Sette, and B. Peters, “Epitope-Specific T Cell Receptor Data and Tools in the Immune Epitope Database,” in T-Cell Repertoire Characterization, H. Huang and M. M. Davis, Eds., New York, NY: Springer US, 2022, pp. 267–280. doi: 10.1007/978-1-0716-2712-9_13.
G. Dolton et al., “Targeting of multiple tumor-associated antigens by individual T cell receptors during successful cancer immunotherapy,” Cell, vol. 186, no. 16, pp. 3333-3349.e27, Aug. 2023, doi: 10.1016/j.cell.2023.06.020.
H. Lin et al., “Identification of Tumor Antigens and Immune Subtypes of Glioblastoma for mRNA Vaccine Development,” Front. Immunol., vol. 13, 2022, doi: 10.3389/fimmu.2022.773264.
S. Grewal, N. Hegde, and S. K. Yanow, “Integrating machine learning to advance epitope mapping,” Front. Immunol., vol. 15, 2024, doi: 10.3389/fimmu.2024.1463931.
F. Villanueva-Flores, J. I. Sanchez-Villamil, and I. Garcia-Atutxa, “AI-driven epitope prediction: a systematic review, comparative analysis, and practical guide for vaccine development,” Npj Vaccines, vol. 10, no. 1, p. 207, Aug. 2025, doi: 10.1038/s41541-025-01258-y.
B. Dou et al., “Machine Learning Methods for Small Data Challenges in Molecular Science,” Chem. Rev., vol. 123, no. 13, pp. 8736–8780, Jul. 2023, doi: 10.1021/acs.chemrev.3c00189.
P. Gautam and P. Mitra, “ConfPred: ML-Based Conformational B-cell Epitope Prediction Using Novel Features,” in Proceedings of the 12th International Conference on Bioinformatics Research and Applications, in ICBRA ’25. New York, NY, USA: Association for Computing Machinery, Dec. 2025, pp. 103–110. doi: 10.1145/3774976.3774994.
W. Alghamdi, M. Attique, E. Alzahrani, M. Z. Ullah, and Y. D. Khan, “LBCEPred: a machine learning model to predict linear B-cell epitopes,” Brief. Bioinform., vol. 23, no. 3, p. bbac035, May 2022, doi: 10.1093/bib/bbac035.
T.-O. Tran and N. Q. K. Le, “Sa-TTCA: An SVM-based approach for tumor T-cell antigen classification using features extracted from biological sequencing and natural language processing,” Comput. Biol. Med., vol. 174, p. 108408, May 2024, doi: 10.1016/j.compbiomed.2024.108408.
N. Flechas Manrique et al., “epiGPTope: A Machine Learning-Based Epitope Generator and Classifier,” ACS Synth. Biol., vol. 15, no. 2, pp. 631–642, Feb. 2026, doi: 10.1021/acssynbio.5c00693.
R.-S. Hu, K. Gu, M. Ehsan, S. H. A. Raza, and C.-R. Wang, “Transformer-based deep learning enables improved B-cell epitope prediction in parasitic pathogens: A proof-of-concept study on Fasciola hepatica,” PLoS Negl. Trop. Dis., vol. 19, no. 4, p. e0012985, Apr. 2025, doi: 10.1371/journal.pntd.0012985.
A. Albutti, “An Integrated Approach to Develop a Potent Vaccine Candidate Construct Against Prostate Cancer by Utilizing Machine Learning and Bioinformatics,” Cancer Rep., vol. 7, no. 12, p. e70079, 2024, doi: 10.1002/cnr2.70079.
N. Biswas, S. Chakrabarti, V. Padul, L. D. Jones, and S. Ashili, “Designing neoantigen cancer vaccines, trials, and outcomes,” Front. Immunol., vol. 14, 2023, doi: 10.3389/fimmu.2023.1105420.
S. Feola, J. Chiaro, and V. Cerullo, “Integrating immunopeptidome analysis for the design and development of cancer vaccines,” Semin. Immunol., vol. 67, p. 101750, May 2023, doi: 10.1016/j.smim.2023.101750.
M. Łuksza et al., “A neoantigen fitness model predicts tumour response to checkpoint blockade immunotherapy,” Nature, vol. 551, no. 7681, pp. 517–520, Nov. 2017, doi: 10.1038/nature24473.
P. Karnati et al., “Performance of Novel Antimicrobial Protein Bg_9562 and In Silico Predictions on Its Properties with Reference to Its Antimicrobial Efficiency against Rhizoctonia solani,” Antibiotics, vol. 11, no. 3, p. 363, Mar. 2022, doi: 10.3390/antibiotics11030363.
S. Kumar, V. K. Duggineni, V. Singhania, S. P. Misra, and P. A. Deshpande, “Unravelling and Quantifying the Biophysical– Biochemical Descriptors Governing Protein Thermostability by Machine Learning,” Adv Theory Simul., vol. 6, no. 3, 2023, doi: 10.1002/adts.202200703.
H. Salman, A. Kalakech, and A. Steiti, “Random Forest Algorithm Overview,” Babylon. J. Mach. Learn., vol. 2024, pp. 69–79, Jun. 2024, doi: 10.58496/BJML/2024/007.
A. Y. Mahmoud, “Novel efficient feature selection: Classification of medical and immunotherapy treatments utilising Random Forest and Decision Trees,” Intell.-Based Med., vol. 10, p. 100151, Jan. 2024, doi: 10.1016/j.ibmed.2024.100151.
C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, Sep. 1995, doi: 10.1007/BF00994018.
L. Revathi and R. Murugesh, “A review of support vector machine in cancer prediction on genomic data,” Int. J. Bioinforma. Res. Appl., vol. 20, no. 2, pp. 161–180, Jan. 2024, doi: 10.1504/IJBRA.2024.138709.
G. O. Anyanwu, C. I. Nwakanma, J.-M. Lee, and D.-S. Kim, “RBF-SVM kernel-based model for detecting DDoS attacks in SDN integrated vehicular network,” Ad Hoc Netw., vol. 140, p. 103026, Mar. 2023, doi: 10.1016/j.adhoc.2022.103026.
T. Nadira and Z. Rustam, “Classification of cancer data using support vector machines with features selection method based on global artificial bee colony,” presented at the AIP Conference Proceedings, Oct. 2018, p. 020205. doi: 10.1063/1.5064202.
S. K. Burley et al., “RCSB Protein Data Bank (RCSB.org): delivery of experimentally-determined PDB structures alongside one million computed structure models of proteins from artificial intelligence/machine learning,” Nucleic Acids Res., vol. 51, no. D1, pp. D488–D508, Jan. 2023, doi: 10.1093/nar/gkac1077.
D. Feng et al., “Phosphorylation of ACTN4 Leads to Podocyte Vulnerability and Proteinuric Glomerulosclerosis,” J. Am. Soc. Nephrol., vol. 31, no. 7, p. 1479, Jul. 2020, doi: 10.1681/ASN.2019101032.
P. Rana, A. Sowmya, E. Meijering, and Y. Song, “Imbalanced classification for protein subcellular localization with multilabel oversampling,” Bioinformatics, vol. 39, no. 1, p. btac841, Jan. 2023, doi: 10.1093/bioinformatics/btac841.
E. Jafarigol, T. Trafalis, and N. Mohammadi, “A Review of Machine Learning Techniques in Imbalanced Data and Future Trends,” Sep. 07, 2025, arXiv: arXiv:2310.07917. doi: 10.48550/arXiv.2310.07917.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Classification of Cancer Epitope Mutations Using Random Forest, SVM and Sequence-Derived Features
Pages: 363-373
Copyright (c) 2026 Miftahurrahma Rosyda, Dinan Yulianto
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
