Predictive models for stage and risk classification in head and neck squamous cell carcinoma (HNSCC)
Machine learning techniques are increasingly used in the analysis of high throughput genome sequencing data to better understand the disease process and design of therapeutic modalities. In the current study, we have applied state of the art machine learning (ML) algorithms (Random Forest (RF), Supp...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2020-09-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/9656.pdf |
| _version_ | 1797418511427960832 |
|---|---|
| author | Sugandh Kumar Srinivas Patnaik Anshuman Dixit |
| author_facet | Sugandh Kumar Srinivas Patnaik Anshuman Dixit |
| author_sort | Sugandh Kumar |
| collection | DOAJ |
| description | Machine learning techniques are increasingly used in the analysis of high throughput genome sequencing data to better understand the disease process and design of therapeutic modalities. In the current study, we have applied state of the art machine learning (ML) algorithms (Random Forest (RF), Support Vector Machine Radial Kernel (svmR), Adaptive Boost (AdaBoost), averaged Neural Network (avNNet), and Gradient Boosting Machine (GBM)) to stratify the HNSCC patients in early and late clinical stages (TNM) and to predict the risk using miRNAs expression profiles. A six miRNA signature was identified that can stratify patients in the early and late stages. The mean accuracy, sensitivity, specificity, and area under the curve (AUC) was found to be 0.84, 0.87, 0.78, and 0.82, respectively indicating the robust performance of the generated model. The prognostic signature of eight miRNAs was identified using LASSO (least absolute shrinkage and selection operator) penalized regression. These miRNAs were found to be significantly associated with overall survival of the patients. The pathway and functional enrichment analysis of the identified biomarkers revealed their involvement in important cancer pathways such as GP6 signalling, Wnt signalling, p53 signalling, granulocyte adhesion, and dipedesis. To the best of our knowledge, this is the first such study and we hope that these signature miRNAs will be useful for the risk stratification of patients and the design of therapeutic modalities. |
| first_indexed | 2024-03-09T06:33:47Z |
| format | Article |
| id | doaj.art-274ae69017d34c3cb013492ecd88a27d |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:33:47Z |
| publishDate | 2020-09-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-274ae69017d34c3cb013492ecd88a27d2023-12-03T11:01:15ZengPeerJ Inc.PeerJ2167-83592020-09-018e965610.7717/peerj.9656Predictive models for stage and risk classification in head and neck squamous cell carcinoma (HNSCC)Sugandh Kumar0Srinivas Patnaik1Anshuman Dixit2Computational Biology and Bioinformatics Laboratory, Institute of Life Science, Bhubaneswar, Odisha, IndiaSchool of Biotechnology, Kalinga Institute of Industrial Technology (KIIT) University, Bhubaneswar, Odisha, IndiaComputational Biology and Bioinformatics Laboratory, Institute of Life Science, Bhubaneswar, Odisha, IndiaMachine learning techniques are increasingly used in the analysis of high throughput genome sequencing data to better understand the disease process and design of therapeutic modalities. In the current study, we have applied state of the art machine learning (ML) algorithms (Random Forest (RF), Support Vector Machine Radial Kernel (svmR), Adaptive Boost (AdaBoost), averaged Neural Network (avNNet), and Gradient Boosting Machine (GBM)) to stratify the HNSCC patients in early and late clinical stages (TNM) and to predict the risk using miRNAs expression profiles. A six miRNA signature was identified that can stratify patients in the early and late stages. The mean accuracy, sensitivity, specificity, and area under the curve (AUC) was found to be 0.84, 0.87, 0.78, and 0.82, respectively indicating the robust performance of the generated model. The prognostic signature of eight miRNAs was identified using LASSO (least absolute shrinkage and selection operator) penalized regression. These miRNAs were found to be significantly associated with overall survival of the patients. The pathway and functional enrichment analysis of the identified biomarkers revealed their involvement in important cancer pathways such as GP6 signalling, Wnt signalling, p53 signalling, granulocyte adhesion, and dipedesis. To the best of our knowledge, this is the first such study and we hope that these signature miRNAs will be useful for the risk stratification of patients and the design of therapeutic modalities.https://peerj.com/articles/9656.pdfHead and neck cancerTNM stageMachine learningBiomarkermicroRNAmRNA |
| spellingShingle | Sugandh Kumar Srinivas Patnaik Anshuman Dixit Predictive models for stage and risk classification in head and neck squamous cell carcinoma (HNSCC) PeerJ Head and neck cancer TNM stage Machine learning Biomarker microRNA mRNA |
| title | Predictive models for stage and risk classification in head and neck squamous cell carcinoma (HNSCC) |
| title_full | Predictive models for stage and risk classification in head and neck squamous cell carcinoma (HNSCC) |
| title_fullStr | Predictive models for stage and risk classification in head and neck squamous cell carcinoma (HNSCC) |
| title_full_unstemmed | Predictive models for stage and risk classification in head and neck squamous cell carcinoma (HNSCC) |
| title_short | Predictive models for stage and risk classification in head and neck squamous cell carcinoma (HNSCC) |
| title_sort | predictive models for stage and risk classification in head and neck squamous cell carcinoma hnscc |
| topic | Head and neck cancer TNM stage Machine learning Biomarker microRNA mRNA |
| url | https://peerj.com/articles/9656.pdf |
| work_keys_str_mv | AT sugandhkumar predictivemodelsforstageandriskclassificationinheadandnecksquamouscellcarcinomahnscc AT srinivaspatnaik predictivemodelsforstageandriskclassificationinheadandnecksquamouscellcarcinomahnscc AT anshumandixit predictivemodelsforstageandriskclassificationinheadandnecksquamouscellcarcinomahnscc |