Development of a Machine Learning-Based Autophagy-Related lncRNA Signature to Improve Prognosis Prediction in Osteosarcoma Patients.

Guang-Zhi Zhang,Wen-Hua Yuan,Qi-Qi Xie,En-Hui Ren,Chun-Ying Li,Zuo-Long Wu,Ya-Jun Deng

doi:10.3389/fmolb.2021.615084

Abstract

BackgroundOsteosarcoma is a frequent bone malignancy in children and young adults. Despite the availability of some prognostic biomarkers, most of them fail to accurately predict prognosis in osteosarcoma patients. In this study, we used bioinformatics tools and machine learning algorithms to establish an autophagy-related long non-coding RNA (lncRNA) signature to predict the prognosis of osteosarcoma patients.MethodsWe obtained expression and clinical data from osteosarcoma patients in the Therapeutically Applicable Research to Generate Effective Treatments (TARGET) and Gene Expression Omnibus (GEO) databases. We acquired an autophagy gene list from the Human Autophagy Database (HADb) and identified autophagy-related lncRNAs by co-expression analyses. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses of the autophagy-related lncRNAs were conducted. Univariate and multivariate Cox regression analyses were performed to assess the prognostic value of the autophagy-related lncRNA signature and validate the relationship between the signature and osteosarcoma patient survival in an independent cohort. We also investigated the relationship between the signature and immune cell infiltration.ResultsWe initially identified 69 autophagy-related lncRNAs, 13 of which were significant predictors of overall survival in osteosarcoma patients. Kaplan-Meier analyses revealed that the 13 autophagy-related lncRNAs could stratify patients based on their outcomes. Receiver operating characteristic curve analyses confirmed the superior prognostic value of the lncRNA signature compared to clinically used prognostic biomarkers. Importantly, the autophagy-related lncRNA signature predicted patient prognosis independently of clinicopathological characteristics. Furthermore, we found that the expression levels of the autophagy-related lncRNA signature were significantly associated with the infiltration levels of different immune cell subsets, including T cells, NK cells, and dendritic cells.ConclusionThe autophagy-related lncRNA signature established here is an independent and robust predictor of osteosarcoma patient survival. Our findings also suggest that the expression of these 13 autophagy-related lncRNAs may promote osteosarcoma progression by regulating immune cell infiltration in the tumor microenvironment.

Highlights

Osteosarcoma is a common bone malignancy in children and young adults (Wedekind et al, 2018; Heymann et al, 2019)
Therapeutically Applied Research To Generate Effective Treatments (TARGET) was used as the training set, GSE39055 was used as the verification set, and we classified mRNA and long non-coding RNA (lncRNA) on the gene list of the expression matrix of the training set and extracted the lncRNA expression matrix
Multivariate Cox regression analyses revealed that tumor metastasis (HR = 0.013, P < 0.001), stage (HR = 0.196, P = 0.014), tumor site (HR = 2.999, P = 0.007), and expression level of the autophagy-related lncRNA signature (HR = 1.002, P < 0.001) were significantly associated with osteosarcoma patient prognosis (Figure 8). These results suggest that the autophagy-related lncRNA signature is an independent prognostic factor in osteosarcoma patients

Summary

Introduction

Osteosarcoma is a common bone malignancy in children and young adults (Wedekind et al, 2018; Heymann et al, 2019) It is characterized by high metastasis and recurrence rates, with approximately 10–20% of patients with metastatic osteosarcoma experiencing pain and swelling (Liu et al, 2018). Recent clinical studies have shown that adjuvant chemotherapy can improve the survival rate of such patients, the prognosis remains poor (Tian et al, 2019; Wang J. et al, 2019). Mounting evidence indicates that autophagy is a key determinant of cancer progression by regulating cell growth, metastasis, and response to chemotherapy (Folkerts et al, 2019). In mouse osteosarcoma models, silencing of the autophagy-promoting gene BECN1 has been shown to enhance cancer cell metastasis (Zhang et al, 2018). We used bioinformatics tools and machine learning algorithms to establish an autophagyrelated long non-coding RNA (lncRNA) signature to predict the prognosis of osteosarcoma patients

Methods

Results

Conclusion