Published June 6, 2026
| Version v1
Publication
Open
Graph Neural Network-Based Drug Candidate Shortlisting for Cancer Treatment
Description
This paper presents OncoScreen AI, a Graph Neural
Network based system for predicting anticancer drug
potency. Trained on real-world ChEMBL and NCI-60
datasets, achieving 85% accuracy and 0.91 AUC-ROC,
outperforming traditional ANN by 7%. Developed as
final year project at Vidyavardhini's College of
Engineering and Technology, Mumbai.
Files
IEEE Template 1234.pdf
Files
(899.5 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:e98f19cb3f243411b1ad94f26c85a806
|
899.5 kB | Preview Download |