Integrated Machine Learning and Single-Sample Gene Set Enrichment Analysis Identifies a TGF-Beta Signaling Pathway Derived Score in Headneck Squamous Cell Carcinoma

<div>The TGF-<i>β</i> signal score promoted individual immunotherapy for HNSC. (a) ROC curve of TGF-<i>β</i> signal score in Ascierto cohort 2016, Riaz cohort 2018, Homet cohort 2019, Cho cohort 2020, Kim cohort 2019, and VanAllen cohort 2015, respectively. (b) Patients in the low-TGF-<i>β</i> signal score group (orange) displayed better overall survival than those in the high- TGF-<i>β</i> signal score group (gray) when using CTLA-4 and PD-L1 monoclonal antibody, while patients in the low-TGF-<i>β</i> signal score group (orange) displayed worse overall survival than those in the high- TGF-<i>β</i> signal score group (gray) when using PD-1 monoclonal antibody.</div>

Journal of Oncology

fig5

Figure 5

Figure 5: Integrated Machine Learning and Single-Sample Gene Set Enrichment Analysis Identifies a TGF-Beta Signaling Pathway Derived Score in Headneck Squamous Cell Carcinoma 

Figure 5 | Integrated Machine Learning and Single-Sample Gene Set Enrichment Analysis Identifies a TGF-Beta Signaling Pathway Derived Score in Headneck Squamous Cell Carcinoma 