Predicting Tumor Mutational Burden and Survival in Head and Neck Squamous Cancer Patients Using Machine Learning and Bioinformatics Approaches
Authors: 
Nguyen-Kieu Viet-Nhi, Le Nguyen Quoc Khanh, Vu Cong Truc, Thi Thuy Nguyen, Tran Nguyen Anh Duy, Nguyen Tu Thai Bao, How Tseng, Shih-Han HungAuthors Info & Claims
Article No.: 87, Page 1
Abstract
Head and neck squamous cancer (HNSC) is a prevalent malignancy with a complex genetic profile. Tumor Mutational Burden (TMB) is an emerging biomarker associated with prognostic and therapeutic implications. In this study, we aimed to develop machine-learning models for predicting TMB and patient survival using RNA sequencing data and clinical features.
Methods: We collected RNA sequencing data and clinical information of HNSC patients from Gene Expression Omnibus (GEO) (GSE142083) and The Cancer Genome Atlas (TCGA) databases. Machine learning models, including Random Forest, Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Logistic Regression, were built to predict TMB levels based on patient gene expression profiles. The top 100 important features (genes) were selected from these models to create a survival prediction model.
Results: Among the tested models, Random Forest showed the highest accuracy (0.8011), followed by SVM (0.796), kNN (0.777), and logistic regression (0.704). Using the top 100 important genes, we developed a model to predict HNSC patient survival (under 3 years, 3--5 years, and over 5 years). Random forest achieved an accuracy of 0.70, while SVM and kNN reached 0.65. We identified five genes (KRT14, KRT6B, COL1A1, FN1, KRT6C) most closely related to TMB and patient survival. Through KEGG pathway analysis and neural network approaches, we discovered that these genes play a significant role in three pathways: PI3K-Akt signaling pathway, Human papillomavirus infection, and Bacterial invasion of epithelial cells.
In Conclusion, our study highlights the potential of machine learning in integrating bioinformatics for predicting TMB and patient survival in HNSC. The identified genes (KRT14, KRT6B, COL1A1, FN1, KRT6C) and related pathways may serve as potential biomarkers and therapeutic targets in HNSC treatment and prognosis.
Index Terms
- Predicting Tumor Mutational Burden and Survival in Head and Neck Squamous Cancer Patients Using Machine Learning and Bioinformatics Approaches
Recommendations
A multi-omics machine learning framework in predicting the survival of colorectal cancer patients
Abstract BackgroundColorectal cancer (CRC), the 3rd most universal cancer globally, accounts for approximately 10% of newly diagnosed cancer incidences each year. Identifying biomarkers associated with CRC survival and predicting ...
Highlights- To compare the survival time prediction ability of different molecular omics for colorectal cancer patients.
Scientific Review: A new insight on predicting tumour malignancies using synergistic computational intelligence and bioinformatics approaches
Recently, the National Human Genome Research Institute and National Cancer Institute, both part of NIH, US Department of Health and Human Services, have launched The Cancer Genome Atlas (TCGA). Based on the mission of TCGA, we have proposed a further ...
Machine Learning Approach for Predicting Metastatic Sites of Prostate Cancer
BCB '19: Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health InformaticsAnalyzing Genomic profiles of prostate cancer patients with the similar metastatic site may unveil the progression mechanism of cancer and assist in the diagnose and the treatment of cancer. In this model, we propose a machine learning approach based on ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2023
626 pages
Copyright © 2023 Owner/Author(s).
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 04 October 2023
Check for updates
Author Tags
Qualifiers
- Abstract
Conference
BCB '23
Sponsor:
BCB '23: 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
September 3 - 6, 2023
TX, Houston, USA
Acceptance Rates
Overall Acceptance Rate 254 of 885 submissions, 29%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 35Total Downloads
- Downloads (Last 12 months)11
- Downloads (Last 6 weeks)1
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in