La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching
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.
Find the Model Card++ for La-Proteina here.
Setup
For environment setup mamba or micromamba is recommended, but alternatively conda can also be used as a drop-in replacement (substitute mamba with conda ).
mamba env create -f environment.yaml mamba activate laproteina_env pip install torch==2.7.0 --index-url https://download.pytorch.org/whl/cu118 pip install graphein==1.7.7 --no-deps pip install torch_geometric torch_scatter torch_sparse torch_cluster -f https://data.pyg.org/whl/torch-2.7.0+cu118.html
Please download all model checkpoints into the ./checkpoints_laproteina directory, as indicated in the Checkpoints section, which is necessary to sample our models.
If you are only interested in sampling our models, please go to Sampling our models.
To train models and use our minimal dataloaders, create a file .env in the root directory of the repo with the single line
DATA_PATH=/directory/where/you/want/dataset
... continue reading