Applications of Machine Learning to Predict Cisplatin Resistance in Lung Cancer

Abstract

Purpose Lung cancer, mainly lung adenocarcinoma, lung squamous cell carcinoma and small cell lung cancer, has the highest incidence and cancer-related mortality worldwide. Platinum-based chemotherapy plays an important role in the treatment of various lung cancer subtypes, but not all patients benefit from this treatment regimen; thus, it is worth identifying lung cancer patients who are resistant or sensitive to platinum-based therapy. Methods The drug response and sequencing data of 170 lung cancer cell lines were downloaded from the Genomics of Drug Sensitivity in Cancer (GDSC) database, and support vector machines (SVMs) and beam search were used to select an optimal gene panel that can predict the sensitivity of cell lines to cisplatin. Then, we used available cell line data to explore the potential mechanisms. Results In this work, the drug response and sequencing data of 170 lung cancer cell lines were downloaded from the GDSC database, and SVMs and beam search were used to screen a panel of genes related to lung cancer cell line resistance to cisplatin. A final panel of nine genes (PLXNC1, KIAA0649, SPTBN4, SLC14A2, F13A1, COL5A1, SCN2A, PLEC, and ALMS1) was identified, and achieved an area under the curve (AUC) of 0.873 ± 0.004. The natural logarithm of the half maximal inhibitory concentration (lnIC50) values of the mutant-type (panel-MT) group was significantly higher than that of the wild-type (panel-WT) group, regardless of the lung cancer subtype. The differentially expressed pathways between the two groups may explain this difference. Conclusion In this study, we found that a panel of nine genes can accurately predict sensitivity to cisplatin, which may provide individualized treatment recommendations to improve the prognosis of patients with lung cancer.

A deep tabular data learning model predicting cisplatin sensitivity identifies BCL2L1 dependency in cancer

“…In previous research, only six to 15 genes were used to predict cisplatin sensitivity [21] , [22] , [23] , [24] . However, due to the heterogeneous nature of cancer, patients with the same cancer subtype may express signature genes at varying levels.…”

“…Using a 15-gene signature (BARD1, BCL2, BCL2L1, CDKN2C, FAAP24, FEN1, MAP3K1, MAPK13, MAPK3, NFKB1, NFKB2, SLC22A5, SLC31A2, TLR4, and TWIST1), a support vector machine (SVM), and data from The Cancer Genome Atlas (TCGA) patients with bladder, ovarian and colorectal cancer, Mucaki et al achieved 55–71 % accuracy in predicting cisplatin response [21] . Moreover, using lung cancer cell line data and SVM, Gao et al identified a nine-gene signature (PLXNC1, KIAA0649, SPTBN4, SLC14A2, F13A1, COL5A1, SCN2A, PLEC, and ALMS1) that can predict cisplatin sensitivity [22] . Furthermore, while Shannon et al identified four genes (CYTH3, GALNT3, S100A14, and ERI1) [23] , Sui et al , applying a regularized logistic regression model to multi-omics data, identified six genes (FOXA2, BATF3, SIX1, HOXA1, IRF5, and ZBTB38) associated with in vitro cisplatin sensitivity [24] .…”

The Potential Role of MUC16 (CA125) Biomarker in Lung Cancer: A Magic Biomarker but with Adversity

“…Globally, lung cancer is considered the most common cancer with the highest incidence and mortalities, in particular pulmonary adenocarcinoma, SCLC, and lung squamous cell carcinoma. Cisplatin has the greatest importance in treating different subtypes of lung cancer, but this treatment is not beneficial for all individuals; thus, it is very important to determine the resistance or susceptibility of lung cancer patients to platinum-based therapy [ 90 ]. A panel of nine genes can precisely predict the sensitivity of patients to cisplatin, which can provide personalized treatment to lung cancer patients to improve their prognosis [ 90 ].…”

“…Cisplatin has the greatest importance in treating different subtypes of lung cancer, but this treatment is not beneficial for all individuals; thus, it is very important to determine the resistance or susceptibility of lung cancer patients to platinum-based therapy [ 90 ]. A panel of nine genes can precisely predict the sensitivity of patients to cisplatin, which can provide personalized treatment to lung cancer patients to improve their prognosis [ 90 ]. High levels of MUC16 in local residents could be one of the molecular characteristics of FLC.…”

Expression of lncRNA LINC00943 in lung squamous cell carcinoma and its relationship with tumor progression

“…Lung squamous cell carcinoma (LUSC) is the second most common type of lung cancer after lung adenocarcinoma, with the highest morbidity and mortality in China, and the number of patients continues to increase [ 1 , 2 ]. The patient eventually mutated into LUSC due to chronic stimulation and damage to the columnar epithelial cells of the bronchial mucosa, loss of cilia, and squamous metaplasia of basal cells [ 3 ].…”