Research map / Probabilistic and scientific modeling / Molecules and proteins
La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching
Tomas Geffner, Kieran Didi, Zhonglin Cao, Danny Reidenbach, Zuobai Zhang, Christian Dallago, Emine Kucukbenli, Karsten Kreis, Arash Vahdat
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add triangular multiplicative update layers (ablation) | La-Proteina · Unconditional all-atom generation, lengths 100-500 | all-atom co-designability (%): 68.4 -> 75.0 co-designability; 206 -> 129 structure clusters | Mixed |
| model alpha-carbons explicitly instead of encoding them in the latent space (partially latent vs fully latent) (ablation) | La-Proteina · unconditional generation | co-designability | Improved |
| use separate interpolation times t_x and t_z instead of a single coupled time (ablation) | La-Proteina · unconditional generation | co-designability | Improved |
| generate alpha-carbon backbone at a faster rate than latent variables (ablation) | La-Proteina sampling · unconditional generation | co-designability | Improved |
| reduced noise scaling during sampling (ablation) | La-Proteina · unconditional all-atom generation, lengths 100-500 | co-designability vs diversity: 68.4 -> 60.6 -> 53.8 all-atom co-designability across the three non-tri variants | Mixed |
| unindexed instead of indexed motif scaffolding for motifs with 3+ segments (ablation) | La-Proteina · Atomistic motif scaffolding (26 tasks) | tasks solved | Improved |
| use La-Proteina instead of Protpardelle for atomistic motif scaffolding | Protpardelle · Atomistic motif scaffolding (26 tasks) | tasks solved: 4 -> 21 to 25 of 26 tasks | Improved |
| add beta-sheet filter to training data (ablation) | La-Proteina · Foldseek AFDB training set | beta-sheet content: 3-4% -> approximately 10% | Improved |
| scale La-Proteina to long proteins with 46M-sample AFDB subset | La-Proteina · Long protein generation up to 800 residues | co-designability and diversity | Improved |
Closest papers by meaning
- Proteina: Scaling Flow-based Protein Structure Generative Models (ICLR 2025 · similarity 0.91)
- Full-Atom Peptide Design based on Multi-modal Flow Matching (ICML 2024 · similarity 0.89)
- Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN (ICML 2025 · similarity 0.89)
- AlphaFold Meets Flow Matching for Generating Protein Ensembles (ICML 2024 · similarity 0.89)
- Full-Atom Peptide Design with Geometric Latent Diffusion (NeurIPS 2024 · similarity 0.89)
- Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
