La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching

TL;DR

La-Proteina is a novel generative model that efficiently produces fully atomistic protein structures and sequences simultaneously, overcoming previous limitations in side-chain modeling and enabling scalable, high-quality protein design.

Contribution

It introduces a partially latent representation and flow matching approach for joint atomistic and sequence protein generation, achieving state-of-the-art results and scalability.

Findings

State-of-the-art performance on multiple benchmarks

Effective atomistic motif scaffolding capabilities

Scalable to proteins of up to 800 residues

Abstract

Recently, many generative models for de novo protein structure design have emerged. Yet, only few tackle the difficult task of directly generating fully atomistic structures jointly with the underlying amino acid sequence. This is challenging, for instance, because the model must reason over side chains that change in length during generation. We introduce La-Proteina for atomistic protein design based on a novel partially latent protein representation: coarse backbone structure is modeled explicitly, while sequence and atomistic details are captured via per-residue latent variables of fixed dimensionality, thereby effectively side-stepping challenges of explicit side-chain representations. Flow matching in this partially latent space then models the joint distribution over sequences and full-atom structures. La-Proteina achieves state-of-the-art performance on multiple generation benchmarks, including all-atom co-designability, diversity, and structural validity, as confirmed through detailed structural analyses and evaluations. Notably, La-Proteina also surpasses previous models in atomistic motif scaffolding performance, unlocking critical atomistic structure-conditioned protein design tasks. Moreover, La-Proteina is able to generate co-designable proteins of up to 800 residues, a regime where most baselines collapse and fail to produce valid samples, demonstrating La-Proteina's scalability and robustness.