Related Experiment Video
Updated: Sep 2, 2025
A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis
Published on: March 8, 2022
Gene Identification and Potential Drug Therapy for Drug-Resistant Melanoma with Bioinformatics and Deep Learning
1Department of Burn Surgery, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China.
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.
Insights
Computational methods identified potential drug targets for melanoma. This study highlights ERBB2-targeted drugs, including kinase inhibitors and antibody-drug conjugates, for treating drug-resistant melanoma.
Area of Science:
- Oncology
- Genomics
- Pharmacology
Background:
- Melanoma, a skin cancer from melanocytes, is treated with surgery, chemotherapy, and immunotherapy.
- Targeted therapy offers promise for advanced melanoma but faces resistance challenges.
- Identifying novel targets and drugs is crucial for overcoming melanoma drug resistance.
Purpose of the Study:
- To identify potential target genes for drug-resistant melanoma using computational approaches.
- To discover candidate drugs effective against drug-resistant melanoma.
- To leverage bioinformatics and deep learning for drug discovery in melanoma.
Main Methods:
- Text mining (pubmed2ensembl) identified 433 genes linked to drug-resistant melanoma.
- Gene screening involved GO and KEGG pathway enrichment, and PPI network construction (STRING, Cytoscape).
- Survival analysis (GEPIA) and drug screening (Pharmaprojects, DeepPurpose) identified candidate drugs and predicted drug-target interactions.
Main Results:
- 348 genes were associated with enriched pathways, and 27 hub genes were identified.
- Six genes showed statistical significance in survival analysis and literature review.
- 11 ERBB2-targeted drugs, including 10 kinase inhibitors and 1 antibody-drug conjugate, were predicted with high affinity.
Conclusions:
- Text mining and bioinformatics are effective for gene identification in drug discovery.
- DeepPurpose is a valuable deep learning tool for predicting drug-target interactions and selecting candidate drugs.
- ERBB2-targeted therapies show potential for overcoming melanoma drug resistance.
