Non-negative matrix factorization model-based construction for molecular clustering and prognostic assessment of head and neck squamous carcinoma

Xin-Yu Li; Hong-Bang An; Lu-Yu Zhang; Hui Liu; Yu-Chen Shen; Xi-Tao Yang

doi:10.1016/j.heliyon.2022.e10100

Non-negative matrix factorization model-based construction for molecular clustering and prognostic assessment of head and neck squamous carcinoma

Heliyon. 2022 Aug 7;8(8):e10100. doi: 10.1016/j.heliyon.2022.e10100. eCollection 2022 Aug.

Authors

Xin-Yu Li^{1

2}, Hong-Bang An³, Lu-Yu Zhang⁴, Hui Liu⁵, Yu-Chen Shen¹, Xi-Tao Yang¹

Affiliations

¹ Department of Interventional Therapy, Multidisciplinary Team of Vascular Anomalies, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University, Shanghai, China.
² Department of Neurosurgery, Shanghai Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, Shanghai, China.
³ Affiliated Hospital of Weifang Medical University, School of Clinical Medicine, Weifang Medical University, Weifang, China.
⁴ The Department of Kidney Transplantation, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
⁵ Department of Nephrology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, China.

Abstract

Purpose: We aimed at exploring the efficacy of non-negative matrix factorization (NMF) model-based clustering for prognostic assessment of head and neck squamous carcinoma (HNSCC).

Methods: The transcriptome microarray data of HNSCC samples were downloaded from The Cancer Genome Atlas (TCGA) and the Shanghai Ninth People's Hospital. R software packages were used to establish NMF clustering, from which relevant prognostic models were developed.

Results: Based on NMF, samples were allocated into 2 subgroups. Predictive models were constructed using differentially expressed genes between the two subgroups. The high-risk group was associated with poor prognostic outcomes. Moreover, multi-factor Cox regression analysis revealed that the predictive model was an independent prognostic predictor.

Conclusion: The NMF-based prognostic model has the potential for prognostic assessment of HNSCC.

Keywords: Cancer; Head and neck squamous carcinoma; NMF; Non-negative matrix.