Identification of drug compounds for capsular contracture based on text mining and deep learning.

BACKGROUND: Capsular contracture is a common and unpredictable complication after breast implant placement. Currently, the pathogenesis of capsular contracture is unclear and the effectiveness of non-surgical treatment is still doubtful. Our study aimed to investigate new drug therapies for capsular contracture by using computational methods.

METHODS: Genes related to capsular contracture were identified by text mining and GeneCodis. Then the candidate key genes were selected through protein-protein interaction analysis in STRING and Cytoscape. Drugs targeting the candidate genes with relation to capsular contracture were screened out in Pharmaprojects. Based on the drug-target interaction analysis by DeepPurpose, candidate drugs with highest predicted binding affinity were obtained eventually.

RESULTS: Our study identified 55 genes related to capsular contracture. Gene set enrichment analysis and protein-protein interaction analysis generated 8 candidate genes. 100 drugs targeting the candidate genes were selected. 7 candidate drugs with highest predicted binding affinity were determined by DeepPurpose, including tumor necrosis factor alpha (TNF-α) antagonist, estrogen receptor (ESR) agonist, insulin like growth factor 1 (IGF-1) receptor tyrosine kinase inhibitor and matrix metallopeptidase 1 (MMP1) inhibitor.

CONCLUSION: Text mining and DeepPurpose can be used as a promising tool for drug discovery in exploring non-surgical treatment to capsular contracture.