REVIEW 1 cited by
Preference optimization of protein language models as a multi-objective binder design paradigm
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
We present a multi-objective binder design paradigm based on instruction fine-tuning and direct preference optimization (DPO) of autoregressive protein language models (pLMs). Multiple design objectives are encoded in the language model through direct optimization on expert curated preference sequence datasets comprising preferred and dispreferred distributions. We show the proposed alignment strategy enables ProtGPT2 to effectively design binders conditioned on specified receptors and a drug developability criterion. Generated binder samples demonstrate median isoelectric point (pI) improvements by $17\%-60\%$.
Forward citations
Cited by 1 Pith paper
-
Protein Inverse Folding From Structure Feedback
DPO fine-tuning with ESMFold TM-Score preferences raises sequence recovery and predicted TM-Score of inverse folding models, and multi-round refinement produces large gains on hard targets.
Discussion (0). Continue with ORCID to comment.