RITA: a Study on Scaling Up Generative Protein Sequence Models
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:OONDHMZRrecord.jsonopen to challenge →
read the original abstract
In this work we introduce RITA: a suite of autoregressive generative models for protein sequences, with up to 1.2 billion parameters, trained on over 280 million protein sequences belonging to the UniRef-100 database. Such generative models hold the promise of greatly accelerating protein design. We conduct the first systematic study of how capabilities evolve with model size for autoregressive transformers in the protein domain: we evaluate RITA models in next amino acid prediction, zero-shot fitness, and enzyme function prediction, showing benefits from increased scale. We release the RITA models openly, to the benefit of the research community.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
ProteinOPD uses token-level on-policy distillation from multiple preference-specific teacher models into a shared student to balance competing objectives in protein design, delivering gains on targets without losing d...
-
Two-Stage Fine-Tuning for Protein Sequence Generation with Targeted Amino-Acid Composition
A domain-adaptive fine-tuning stage followed by reward-weighted RL fine-tuning produces protein sequences whose amino-acid composition matches a specified target while preserving sequence statistics and diversity.
-
Modeling Protein Evolution with Generative Models: from Extant Sequence Data to Evolutionary Dynamics
Review of generative sequence models and Direct Coupling Analysis for simulating protein evolutionary dynamics from extant data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.