A GPT-2 model fine-tuned with disease MeSH + protein sequence inputs and GRPO rewards produces more unique, valid, drug-like, high-PLAPT-affinity ligands than DrugGPT or DrugGen on five diabetic-nephropathy targets.
Machine learn- ing in drug design: Use of artificial intelligence to explore the chemical structure–biological activity relationship.WIREs Comput Mol Sci
1 Pith paper cite this work, alongside 145 external citations. Polarity classification is still indexing.
1
Pith paper citing it
145
external citations · OpenAlex
fields
q-bio.QM 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DrugGen 2: A disease-aware language model for enhancing drug discovery
A GPT-2 model fine-tuned with disease MeSH + protein sequence inputs and GRPO rewards produces more unique, valid, drug-like, high-PLAPT-affinity ligands than DrugGPT or DrugGen on five diabetic-nephropathy targets.