Aligning protein-generative models to experimental fitness with ProteinDPO
Ranking
Overall
84
Content
100
Popularity
45
Observed public metrics from 1 member.
Merged summary
TL;DR - ProteinDPO uses direct preference optimization to align a structure-conditioned protein language model with experimental biophysical fitness. It delivers stability predictions competitive with task-specific models while outperforming unsupervised and fine-tuned baselines.
- Applies DPO to protein generation using experimental fitness information.
- Aligns an unsupervised, structure-conditioned language model with biophysical properties.
- Demonstrates that preference optimization can improve protein stability prediction.
- Consistently surpasses the model’s unsupervised and conventionally fine-tuned versions.
Sources (1)
Aligning protein-generative models to experimental fitness with ProteinDPO
Public signals
OpenAlex citations 0
TL;DR - ProteinDPO uses direct preference optimization to align a structure-conditioned protein language model with experimental biophysical fitness. It delivers stability predictions competitive with task-specific models while outperforming unsupervised and fine-tuned baselines.
- Applies DPO to protein generation using experimental fitness information.
- Aligns an unsupervised, structure-conditioned language model with biophysical properties.
- Demonstrates that preference optimization can improve protein stability prediction.
- Consistently surpasses the model’s unsupervised and conventionally fine-tuned versions.