.png){kind=icon}
.png){kind=icon}
Return
An integrated machine learning and computational framework with experimental validation for the identification of novel CXCR4 inhibitors
.png){kind=icon}
PRE
AI
M
P
F
Y
M
A
Z
A
DOI：10.1016/j.ejmech.2026.118918.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Integrated ML–CADD–experimental workflow enabled rapid CXCR4 inhibitor discovery. • ML models on 608 compounds found 44 consensus CXCR4 inhibitors from 2,146. • Docking and 100 ns MD simulations confirmed stable CXCR4–ligand interactions. • MM/GBSA showed strong binding, with IS00622 having the highest affinity. • In vitro and ELISA assays identified IS00127 as selective with low cytotoxicity
Keywords:
Machine learning
CADD
CXCR4 inhibitors
Molecular docking
MM/GBSA
Journal
IF:
5.9
Papers:
1.7W
Citations:
6.0W
Organization
Cited Papers