Diversity-regularized DPO fine-tuning of ProteinMPNN improves structural similarity scores by at least 8% over base model and sequence diversity by up to 20% over standard DPO for peptide inverse folding on OpenFold structures.
Preference Optimization for Molecular Language Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2024 2verdicts
UNVERDICTED 2representative citing papers
SmileyLlama is an LLM transformed via SFT and DPO to generate valid novel drug-like molecules with user-specified properties and optimized 3D conformations for high binding affinity.
citing papers explorer
-
Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization
Diversity-regularized DPO fine-tuning of ProteinMPNN improves structural similarity scores by at least 8% over base model and sequence diversity by up to 20% over standard DPO for peptide inverse folding on OpenFold structures.
-
SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration
SmileyLlama is an LLM transformed via SFT and DPO to generate valid novel drug-like molecules with user-specified properties and optimized 3D conformations for high binding affinity.