Abstract
BackgroundAlternative splicing (AS) plays important roles in transcriptome and proteome diversity. Its dysregulation has a close affiliation with oncogenic processes. This study aimed to evaluate AS-based biomarkers by machine learning algorithms for lung squamous cell carcinoma (LUSC) patients.MethodThe Cancer Genome Atlas (TCGA) database and TCGA SpliceSeq database were utilized. After data composition balancing, Boruta feature selection and Spearman correlation analysis were used for differentially expressed AS events. Random forests and a nested fivefold cross-validation were applied for lymph node metastasis (LNM) classifier building. Random survival forest combined with Cox regression model was performed for a prognostic model, based on which a nomogram was developed. Functional enrichment analysis and Spearman correlation analysis were also conducted to explore underlying mechanisms. The expression of some switch-involved AS events along with parent genes was verified by qRT-PCR with 20 pairs of normal and LUSC tissues.ResultsWe found 16 pairs of splicing events from same parent genes which were strongly related to the splicing switch (intrapair correlation coefficient = − 1). Next, we built a reliable LNM classifier based on 13 AS events as well as a nice prognostic model, in which switched AS events behaved prominently. The qRT-PCR presented consistent results with previous bioinformatics analysis, and some AS events like ITIH5-10715-AT and QKI-78404-AT showed remarkable detection efficiency for LUSC.ConclusionAS events, especially switched ones from the same parent genes, could provide new insights into the molecular diagnosis and therapeutic drug design of LUSC.
Highlights
Lung cancer is a worldwide medical problem and carries a heavy disease burden
We found 16 pairs of splicing events from same parent genes which were strongly related to the splicing switch
Alternative splicing (AS) data deriving from 49 normal samples and 501 lung squamous cell carcinoma (LUSC) samples, a total of 550, were left for the analysis of LUSC-specific AS events; 495 patients with available lymph node metastasis (LNM) data (319 negatives and 176 positives) were included for identification of LNM-related classifier; 501 patients with at least 30 days of follow-up were brought into the analysis of survival-related AS events (Additional file 2: Table S2)
Summary
Lung cancer is a worldwide medical problem and carries a heavy disease burden. At present, lung cancer is still a commonly diagnosed cancer in the world (11.4%) onlyHe et al Cancer Cell International (2022) 22:5 because of medical progress such as early screening, surgical techniques, and chemoradiation, the prognosis of lung cancer has been improved a lot [5]. Lung cancer is still a commonly diagnosed cancer in the world (11.4%) only. It is of great significance to develop novel biomarkers and help the diagnosis and treatment for LUSC patients. RNA alternative splicing (AS) is an essential process of post-transcriptional gene expression regulation, by which exons of pre-mRNAs could be retained or excluded in the mature messenger RNA (mRNA) isoforms [7]. The machine learning technology, which aims to construct predictive models from complex datasets based on underlying algorithms [20], offers a novel medium for the investigation of AS situations in LUSC. This study aimed to evaluate AS-based biomarkers by machine learning algorithms for lung squamous cell carcinoma (LUSC) patients
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
