journal article·2026-07-09Open access

Discovering Potential Taxonomic Biomarkers of Gastrointestinal Cancers from Various Human Microbiota via G-S-M Machine Learning Approach

Beyza Canakcimaksutoglu, Nur Sebnem Ersoz, Burcu Bakir-Gungor, Malik Yousef

Applied Sciences· Volume 16· Issue 14

Abstract

Analysis of microbial abundance profiles offers significant potential for improving cancer prediction and candidate biomarker discovery. This study aimed to identify cancer-associated microbial biomarkers across five gastrointestinal (GI) cancers: head and neck, esophagus, stomach, colon, and colorectal cancers by analyzing tissue and blood samples from the TCMA dataset in parallel. A novel machine learning model, MicrobiomeGSM, was developed to enhance biological interpretability and reduce computational complexity through a taxonomic grouping strategy. Classification performance of MicrobiomeGSM was rigorously evaluated using a Random Forest Classifier with 100-fold Monte Carlo Cross-Validation. MicrobiomeGSM model effectively identified colon adenocarcinoma (COAD) using a set of 30 genus-level species, achieving a 97% AUC and 97% specificity. Comparative analysis was also performed with six traditional feature selection (TFS) algorithms; CMIM, mRMR, FCBF, IG, XGB, and SKB. Comparison of MicrobiomeGSM with TFS methods showed that while TFS methods capture statistical patterns, MicrobiomeGSM effectively leverages biological structures to identify clinically relevant candidate biomarkers. Also, MicrobiomeGSM competes with TFS methods in the analysis of high-dimensional datasets. In conclusion, these findings demonstrate that incorporating microbial abundance profiles with their taxonomic information into machine learning improve the interpretability and effectiveness of microbiome-based candidate biomarker discovery and may support future precision oncology application.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Gut microbiota and health · Machine Learning in Bioinformatics · Bacterial Identification and Susceptibility Testing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Bioengineering, Graduate School, Abdullah Gul University, Kayseri 38080, Türkiye

Department of Computer Engineering, Faculty of Engineering, Abdullah Gul University, Kayseri 38080, Türkiye

Department of Software Engineering, Kinneret Academic College on the Sea of Galilee, Zemach 1513200, Israel

Funding

TÜBİTAK Directorate of Science Fellowships and Grant Programme (BİDEB) 2211- National Graduate Scholarship Program · TÜBİTAK Directorate of Science Fellowships and Grant Programme (BİDEB) 2211-A National PhD. Scholarship Program · Kinneret Academic College · Abdullah Gul University Support Foundation (AGUV) and L’Oréal-UNESCO Young Women Scientist Program

References (84)

Show source-provided references
1. Global Burden of 5 Major Types of Gastrointestinal Cancer10.1053/j.gastro.2020.02.068 ↗
2. Kayali, S., Marabotto, E., and Giannini, E. (2023). Gastrointestinal Tract Cancers, an Increasing Burden of the Modern Era: Epidemiology and Prevention. Cancers, 15.10.3390/cancers15184634 ↗
3. Dysbiosis Signature of Fecal Microbiota in Colorectal Cancer Patients10.1007/s00248-013-0245-9 ↗
4. Zhang, J., He, Y., Xia, L., Yi, J., Wang, Z., Zhao, Y., Song, X., Li, J., Liu, H., and Liang, X. (2022). Expansion of Colorectal Cancer Biomarkers Based on Gut Bacteria and Viruses. Cancers, 14.10.3390/cancers14194662 ↗
5. Zhou, Z., Ge, S., Li, Y., Ma, W., Liu, Y., Hu, S., Zhang, R., Ma, Y., Du, K., and Syed, A. (2020). Human Gut Microbiome-Based Knowledgebase as a Biomarker Screening Tool to Improve the Predicted Probability for Colorectal Cancer. Front. Microbiol., 11.10.3389/fmicb.2020.596027 ↗
6. Altered Intestinal Microbiota Associated with Colorectal Cancer10.1007/s11684-019-0695-7 ↗
7. Integrated Analysis of the Faecal Metagenome and Serum Metabolome Reveals the Role of Gut Microbiome-Associated Metabolites in the Detection of Colorectal Cancer and Adenoma10.1136/gutjnl-2020-323476 ↗
8. Zhu, W., Wang, J.-Z., Liu, Z., and Wei, J.-F. (2022). The Bacteria inside Human Cancer Cells: Mainly as Cancer Promoters. Front. Oncol., 12.10.3389/fonc.2022.897330 ↗
9. Bakir-Gungor, B., Temiz, M., Jabeer, A., Wu, D., and Yousef, M. (2023). microBiomeGSM: The Identification of Taxonomic Biomarkers from Metagenomic Data Using Grouping, Scoring and Modeling (G-S-M) Approach. Front. Microbiol., 14.10.3389/fmicb.2023.1264941 ↗
10. Jabeer, A., KoÇak, A., Akkaş, H., Yenisert, F., Nalbantoğlu, Ö.U., Yousef, M., and Bakir GÜngÖr, B. (2022, January 7–9). Identifying Taxonomic Biomarkers of Colorectal Cancer in Human Intestinal Microbiota Using Multiple Feature Selection Methods. Proceedings of the 2022 Innovations in Intelligent Systems and Applications Conference (ASYU), Antalya, Turkey.10.1109/ASYU56188.2022.9925551 ↗
11. Zhang, C., Hu, A., Li, J., Zhang, F., Zhong, P., Li, Y., and Li, Y. (2022). Combined Non-Invasive Prediction and New Biomarkers of Oral and Fecal Microbiota in Patients with Gastric and Colorectal Cancer. Front. Cell. Infect. Microbiol., 12.10.3389/fcimb.2022.830684 ↗
12. Machine Learning-Based Approaches for Cancer Prediction Using Microbiome Data10.1038/s41598-023-38670-0 ↗
13. Identification of Microbial Markers across Populations in Early Detection of Colorectal Cancer10.1038/s41467-021-23265-y ↗
14. Li, M.-X., Sun, X.-M., Cheng, W.-G., Ruan, H.-J., Liu, K., Chen, P., Xu, H.-J., Gao, S.-G., Feng, X.-S., and Qi, Y.-J. (2021). Using a Machine Learning Approach to Identify Key Prognostic Molecules for Esophageal Squamous Cell Carcinoma. BMC Cancer, 21.10.1186/s12885-021-08647-1 ↗
15. Marcos-Zambrano, L.J., Karaduzovic-Hadziabdic, K., Turukalo, T.L., Przymus, P., Trajkovik, V., Aasmets, O., Berland, M., Gruca, A., Hasic, J., and Hron, K. (2021). Applications of Machine Learning in Human Microbiome Studies: A Review on Feature Selection, Biomarker Identification, Disease Prediction and Treatment. Front. Microbiol., 12.10.3389/fmicb.2021.634511 ↗
16. A Review of Machine Learning Methods for Cancer Characterization from Microbiome Data10.1038/s41698-024-00617-7 ↗
17. (2024, September 03). The Cancer Genome Atlas Program (TCGA)—NCI, Available online: https://www.cancer.gov/ccg/research/genome-sequencing/tcga.
18. The Cancer Microbiome Atlas: A Pan-Cancer Comparative Analysis to Distinguish Tissue-Resident Microbiota from Contaminants10.1016/j.chom.2020.12.001 ↗
19. Robust Rank Aggregation for Gene List Integration and Meta-Analysis10.1093/bioinformatics/btr709 ↗
20. Yousef, M., Allmer, J., İnal, Y., and Gungor, B.B. (2024). G-S-M: A Comprehensive Framework for Integrative Feature Selection in Omics Data Analysis and Beyond. BioRxiv, BioRxiv:2024.03.30.585514.10.1101/2024.03.30.585514 ↗
21. maTE: Discovering Expressed Interactions between microRNAs and Their Targets10.1093/bioinformatics/btz204 ↗
22. Yousef, M., Ozdemir, F., Jaber, A., Allmer, J., and Bakir-Gungor, B. (2023). PriPath: Identifying Dysregulated Pathways from Differential Gene Expression via Grouping, Scoring, and Modeling with an Embedded Feature Selection Approach. BMC Bioinform., 24.10.1186/s12859-023-05187-2 ↗
23. GediNET for Discovering Gene Associations across Diseases Using Knowledge Based Machine Learning Approach10.1038/s41598-022-24421-0 ↗
24. miRcorrNet: Machine Learning-Based Integration of miRNA and mRNA Expression Profiles, Combined with Feature Grouping and Ranking10.7717/peerj.11458 ↗
25. Unlu Yazici, M., Marron, J.S., Bakir-Gungor, B., Zou, F., and Yousef, M. (2023). Invention of 3Mint for Feature Grouping and Scoring in Multi-Omics. Front. Genet., 14.10.3389/fgene.2023.1093326 ↗
26. Ersoz, N.S., Bakir-Gungor, B., and Yousef, M. (2023). GeNetOntology: Identifying Affected Gene Ontology Terms via Grouping, Scoring, and Modeling of Gene Expression Data Utilizing Biological Knowledge-Based Machine Learning. Front. Genet., 14.10.3389/fgene.2023.1139082 ↗
27. Voskergian, D., Bakir-Gungor, B., and Yousef, M. (2023). TextNetTopics Pro, a Topic Model-Based Text Classification for Short Text by Integration of Semantic and Document-Topic Distribution Information. Front. Genet., 14.10.3389/fgene.2023.1243874 ↗
28. miRGediNET: A Comprehensive Examination of Common Genes in miRNA-Target Interactions and Disease Associations: Insights from a Grouping-Scoring-Modeling Approach10.1016/j.heliyon.2023.e22666 ↗
29. Jabeer, A., Temiz, M., Bakir-Gungor, B., and Yousef, M. (2023). miRdisNET: Discovering microRNA Biomarkers That Are Associated with Diseases Utilizing Biological Knowledge-Based Machine Learning. Front. Genet., 13.10.3389/fgene.2022.1076554 ↗
30. Yousef, M., Goy, G., and Bakir-Gungor, B. (2022). miRModuleNet: Detecting miRNA-mRNA Regulatory Modules. Front. Genet., 13.10.3389/fgene.2022.767455 ↗
31. CogNet: Classification of Gene Expression Data Based on Ranked Active-Subnetwork-Oriented KEGG Pathway Enrichment Analysis10.7717/peerj-cs.336 ↗
32. Söylemez, Ü.G., Yousef, M., and Bakir-Gungor, B. (2023). AMP-GSM: Prediction of Antimicrobial Peptides via a Grouping–Scoring–Modeling Approach. Appl. Sci., 13.10.3390/app13085106 ↗
33. Minimum Redundancy Feature Selection from Microarray Gene Expression Data10.1142/S0219720005001004 ↗
34. Conditional Likelihood Maximisation: A Unifying Framework for Information Theoretic Feature Selection
35. François Fleuret Fast Binary Feature Selection with Conditional Mutu-al Information
36. Senliol, B., Gulgezen, G., Yu, L., and Cataltepe, Z. (2008, January 27–29). Fast Correlation Based Filter (FCBF) with a Different Search Strategy. Proceedings of the 2008 23rd International Symposium on Computer and Information Sciences, Istanbul, Turkey.10.1109/ISCIS.2008.4717949 ↗
37. Scikit-Learn: Machine Learning in Python
38. Inflammatory Bowel Disease Biomarkers of Human Gut Microbiota Selected via Different Feature Selection Methods10.7717/peerj.13205 ↗
39. D’Elia, D., Truu, J., Lahti, L., Berland, M., Papoutsoglou, G., Ceci, M., Zomer, A., Lopes, M.B., Ibrahimi, E., and Gruca, A. (2023). Advancing Microbiome Research with Machine Learning: Key Findings from the ML4Microbiome COST Action. Front. Microbiol., 14.10.3389/fmicb.2023.1257002 ↗
40. Monte Carlo Cross Validation10.1016/S0169-7439(00)00122-2 ↗
41. Preisach, C., Burkhardt, H., Schmidt-Thieme, L., and Decker, R. (2008). KNIME: The Konstanz Information Miner. Proceedings of the Data Analysis, Machine Learning and Applications, Springer.10.1007/978-3-540-78246-9 ↗
42. Data Quality Assessment of Maintenance Reporting Procedures10.1016/j.eswa.2016.06.043 ↗
43. Deep Learning Approaches to Biomedical Image Segmentation10.1016/j.imu.2020.100297 ↗
44. Yang, F., Sun, S., and Yang, F. (2021). Prognostic and Predicted Significance of FENDRR in Colon and Rectum Adenocarcinoma. Front. Oncol., 11.10.3389/fonc.2021.668595 ↗
45. Microbiota-Driven Mechanisms at Different Stages of Cancer Development10.1016/j.neo.2022.100829 ↗
46. Establishment and Evaluation of Prediction Model for Multiple Disease Classification Based on Gut Microbial Data10.1038/s41598-019-46249-x ↗
47. The Development of an Efficient Artificial Intelligence-Based Classification Approach for Colorectal Cancer Response to Radiochemotherapy: Deep Learning vs. Machine Learning10.1038/s41598-024-84023-w ↗
48. Effects of Data Transformation and Model Selection on Feature Importance in Microbiome Classification Data10.1186/s40168-024-01996-6 ↗
49. Common Microbial Signatures in Blood and Their Amplification in Clinical Disorders10.1080/29933935.2025.2473450 ↗
50. Gut Microbiota Alterations and Health Status in Aging Adults: From Correlation to Causation10.1002/agm2.12167 ↗
51. Tumor-derived Prevotella Intermedia Aggravates Gastric Cancer by Enhancing Perilipin 3 Expression10.1111/cas.16080 ↗
52. Oral Microbiota and Gastric Cancer: Recent Highlights and Knowledge Gaps10.1080/20002297.2024.2391640 ↗
53. Association of Prevotella Intermedia with Oropharyngeal Cancer: A Patient-Control Study10.1016/j.heliyon.2023.e14293 ↗
54. Moreira, C., Figueiredo, C., and Ferreira, R.M. (2023). The Role of the Microbiota in Esophageal Cancer. Cancers, 15.10.3390/cancers15092576 ↗
55. Prevotella Species as Oral Residents and Infectious Agents with Potential Impact on Systemic Conditions10.1080/20002297.2022.2079814 ↗
56. Consistent Signatures in the Human Gut Microbiome of Old- and Young-Onset Colorectal Cancer10.1038/s41467-024-47523-x ↗
57. Yu, J., Feng, L., Luo, Z., Yang, J., Zhang, Q., Liu, C., Liang, D., Xie, Y., Li, H., and Gong, J. (2024). Interleukin-10 Deficiency Suppresses Colorectal Cancer Metastasis by Enriching Gut Parabacteroides Distasonis. J. Adv. Res.10.1016/j.jare.2024.11.024 ↗
58. Identification of Colorectal Cancer Progression-Associated Intestinal Microbiome and Predictive Signature Construction10.1186/s12967-023-04119-1 ↗
59. Increased Abundance of Clostridium and Fusobacterium in Gastric Microbiota of Patients with Gastric Cancer in Taiwan10.1038/s41598-017-18596-0 ↗
60. Detection of Fusobacterium in Oral and Head and Neck Cancer Samples: A Systematic Review and Meta-Analysis10.1016/j.archoralbio.2020.104669 ↗
61. Changes in Bacteroides and the Microbiota in Patients with Obstructed Colorectal Cancer: Retrospective Cohort Study10.1093/bjsopen/zrad105 ↗
62. The Mechanism of Bacteroides Fragilis Toxin Contributes to Colon Cancer Formation10.21315/mjms2020.27.4.2 ↗
63. Clinical Significance of Bacteroides Fragilis as a Potential Prognostic Factor in Colorectal Cancer10.1016/j.anaerobe.2023.102784 ↗
64. Chen, X., Winckler, B., Lu, M., Cheng, H., Yuan, Z., Yang, Y., Jin, L., and Ye, W. (2015). Oral Microbiota and Risk for Esophageal Squamous Cell Carcinoma in a High-Risk Area of China. PLoS ONE, 10.10.1371/journal.pone.0143603 ↗
65. A Non-Endoscopic Device to Sample the Oesophageal Microbiota: A Case-Control Study10.1016/S2468-1253(16)30086-3 ↗
66. Gut Microbiota Shifts in Patients with Gastric Cancer in Perioperative Period10.1097/MD.0000000000016626 ↗
67. Yang, C.-Y., Yeh, Y.-M., Yu, H.-Y., Chin, C.-Y., Hsu, C.-W., Liu, H., Huang, P.-J., Hu, S.-N., Liao, C.-T., and Chang, K.-P. (2018). Oral Microbiota Community Dynamics Associated with Oral Squamous Cell Carcinoma Staging. Front. Microbiol., 9.10.3389/fmicb.2018.00862 ↗
68. Increased Virulence of the Oral Microbiome in Oral Squamous Cell Carcinoma Revealed by Metatranscriptome Analyses10.1038/s41368-018-0037-7 ↗
69. Solobacterium moorei Promotes the Progression of Adenomatous Polyps by Causing Inflammation and Disrupting the Intestinal Barrier10.1186/s12967-024-04977-3 ↗
70. Solobacterium moorei Promotes Tumor Progression via the Integrin A2/Β1-PI3K-AKT-mTOR-C-Myc Signaling Pathway in Colorectal Cancer10.7150/ijbs.102742 ↗
71. Small, but Smelly: The Importance of Solobacterium moorei in Halitosis and Other Human Infections10.1016/j.heliyon.2020.e05371 ↗
72. Gastric Microbial Community Profiling Reveals a Dysbiotic Cancer-Associated Microbiota10.1136/gutjnl-2017-314205 ↗
73. Alauzet, C., Aujoulat, F., Lozniewski, A., Ben Brahim, S., Domenjod, C., Enault, C., Lavigne, J.-P., and Marchandin, H. (2021). A New Look at the Genus Solobacterium: A Retrospective Analysis of Twenty-Seven Cases of Infection Involving S. moorei and a Review of Sequence Databases and the Literature. Microorganisms, 9.10.3390/microorganisms9061229 ↗
74. Oral Microbiome Composition Reflects Prospective Risk for Esophageal Cancers10.1158/0008-5472.CAN-17-1296 ↗
75. Six Cases of Solobacterium moorei Isolated Alone or in Mixed Culture in Hungary and Comparison with Previously Published Cases10.1016/j.anaerobe.2020.102241 ↗
76. Fujiwara-Tani, R., Fujii, K., Mori, S., Kishi, S., Sasaki, T., Ohmori, H., Nakashima, C., Kawahara, I., Nishiguchi, Y., and Mori, T. (2020). Role of Clostridium Perfringens Enterotoxin on YAP Activation in Colonic Sessile Serrated Adenoma/Polyps with Dysplasia. Int. J. Mol. Sci., 21.10.3390/ijms21113840 ↗
77. Effect of Clostridium Perfringens Enterotoxin on Gastric Cancer Cells SGC7901 Which Highly Expressed Claudin-4 Protein10.4251/wjgo.v9.i4.153 ↗
78. Streptococcus anginosus: The Potential Role in the Progression of Gastric Cancer10.1007/s00432-025-06201-1 ↗
79. Predominant Presence of Streptococcus anginosus in the Saliva of Alcoholics10.1111/j.1399-302X.2005.00242.x ↗
80. Frequent and Preferential Infection of Treponema denticola, Streptococcus mitis, and Streptococcus anginosus in Esophageal Cancers10.1111/j.1349-7006.2004.tb02488.x ↗
81. Autoimmune Gastritis Studies and Gastric Cancer: True Renaissance or Bibliometric Illusion10.3748/wjg.v30.i32.3783 ↗
82. Purulent Pericarditis as the First Manifestation of Esophageal Carcinoma
83. Role of Salivary Glycopatterns for Oral Microbiota Associated with Gastric Cancer10.1016/j.ijbiomac.2022.04.133 ↗
84. Kageyama, S., Takeshita, T., Takeuchi, K., Asakawa, M., Matsumi, R., Furuta, M., Shibata, Y., Nagai, K., Ikebe, M., and Morita, M. (2019). Characteristics of the Salivary Microbiota in Patients with Various Digestive Tract Cancers. Front. Microbiol., 10.10.3389/fmicb.2019.01780 ↗