arXiv Open Access 2024

Preference optimization of protein language models as a multi-objective binder design paradigm

Pouria Mistani Venkatesh Mysore

Lihat Sumber

Abstrak

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 $17\%-60\%$.

Topik & Kata Kunci

physics.bio-ph cs.AI cs.CE q-bio.BM

Penulis (2)

Pouria Mistani

Venkatesh Mysore

Format Sitasi

APA MLA BibTeX

Mistani, P., Mysore, V. (2024). Preference optimization of protein language models as a multi-objective binder design paradigm. https://arxiv.org/abs/2403.04187

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓