Gene Identification and Potential Drug Therapy for Drug-Resistant Melanoma with Bioinformatics and Deep Learning Technology

Abstract

Background: Melanomas are skin malignant tumors that arise from melanocytes which are primarily treated with surgery, chemotherapy, targeted therapy, immunotherapy, radiation therapy, etc. Targeted therapy is a promising approach to treating advanced melanomas, but resistance always occurs. This study is aimed at identifying the potential target genes and candidate drugs for drug-resistant melanoma effectively with computational methods.

Methods: Identification of genes associated with drug-resistant melanomas was conducted using the text mining tool pubmed2ensembl. Further gene screening was carried out by GO and KEGG pathway enrichment analyses. The PPI network was constructed using STRING database and Cytoscape. GEPIA was used to perform the survival analysis and conduct the Kaplan-Meier curve. Drugs targeted at these genes were selected in Pharmaprojects. The binding affinity scores of drug-target interactions were predicted by DeepPurpose.

Results: A total of 433 genes were found associated with drug-resistant melanomas by text mining. The most statistically differential functional enriched pathways of GO and KEGG analyses contained 348 genes, and 27 hub genes were further screened out by MCODE in Cytoscape. Six genes were identified with statistical differences after survival analysis and literature review. 16 candidate drugs targeted at hub genes were found by Pharmaprojects under our restrictions. Finally, 11 ERBB2-targeted drugs with top affinity scores were predicted by DeepPurpose, including 10 ERBB2 kinase inhibitors and 1 antibody-drug conjugate.

Conclusion: Text mining and bioinformatics are valuable methods for gene identification in drug discovery. DeepPurpose is an efficient and operative deep learning tool for predicting the DTI and selecting the candidate drugs.

Figure 1

Flow chart of our study. Figure 1 shows the research process of our study. From left to right, the text labels represent the analysis contents and corresponding tools.

Figure 2

The most statistically significant processes/pathways in drug-resistant melanoma. (a) The biological process, cellular component, and molecular function of GO analysis in drug-resistant melanoma separately. (b) The biological process, cellular component, and molecular function of GO analysis in drug-resistant melanoma together. (c) The KEGG pathway analysis in drug-resistant melanoma. The size of the circles represents the count of genes, and the color represents the values of “- log10 (p value)”.

Figure 3

The protein-protein interaction of candidate genes. The protein-protein interaction analysis of candidate genes from STRING. Each circle represents one protein, and the line represents the interaction between them.

Figure 4

The survival analysis of hub genes in skin cutaneous melanomas from GEPIA. (a) The survival analysis of BAX in melanoma. Blue represents low BAX TPM, and red represents high BAX TPM. (b) The survival analysis of CASP8 in melanoma. Blue represents low CASP8 TPM, and red represents high CASP8 TPM. (c) The survival analysis of CFLAR in melanoma. Blue represents low CFLAR TPM, and red represents high CFLAR TPM. (d) The survival analysis of ERBB2 in melanoma. Blue represents low ERBB2 TPM, and red represents high ERBB2 TPM. (e) The survival analysis of FAS in melanoma. Blue represents low FAS TPM, and red represents high FAS TPM. (f) The survival analysis of NFKBIA in melanoma. Blue represents low NFKBIA TPM, and red represents high NFKBIA TPM.

Figure 5

The candidate drugs for further DTI affinity score analysis. Each color represents a set of candidate drugs targeting the screened gene above. The area represents the proportion.

Figure 6

ERBB2 expression in melanomas and skin melanocytes. (a) The tissue specimen of melanoma with a moderate expression of ERBB2. (b) The tissue specimen of skin without an expression of ERBB2 in melanocytes.

Figure 7

The protein-protein interaction of the six hub genes. (a) The protein-protein interaction analysis of the six hub genes from STRING. Each circle represents one protein, and the line represents the interaction between them. (b) The six hub proteins (red) and the closely related proteins interacting with them (green).