# Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2

arXiv: https://arxiv.org/abs/2405.15489 · HTML: https://mlsanity.com/paper/2405.15489/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 51 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 15 of 15)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design](https://mlsanity.com/paper/2402.04997/) (2024)
- [Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem](https://mlsanity.com/paper/2206.04119/) (2022)
- [Practical and Asymptotically Exact Conditional Sampling in Diffusion Models](https://mlsanity.com/paper/2306.17775/) (2023)
- [SE(3) diffusion model with application to protein backbone generation](https://mlsanity.com/paper/2302.02277/) (2023)
- [Protein structure generation via folding diffusion](https://mlsanity.com/paper/2209.15611/) (2022)
- [Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2205.15019/) (2022)
- [Neural Machine Translation in Linear Time](https://mlsanity.com/paper/1610.10099/) (2016)
- [Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds](https://mlsanity.com/paper/2301.12485/) (2023)
- [Improved motif-scaffolding with SE(3) flow matching](https://mlsanity.com/paper/2401.04082/) (2024)
- [A Latent Diffusion Model for Protein Structure Generation](https://mlsanity.com/paper/2305.04120/) (2023)
- [A framework for conditional diffusion modelling with applications in motif scaffolding for protein design](https://mlsanity.com/paper/2312.09236/) (2023)
- [Ophiuchus: Scalable Modeling of Protein Structures through Hierarchical Coarse-graining SO(3)-Equivariant Autoencoders](https://mlsanity.com/paper/2310.02508/) (2023)

## Built on by (most cited first, 30 of 35)

- [Proteina: Scaling Flow-based Protein Structure Generative Models](https://mlsanity.com/paper/2503.00710/) (2025)
- [The Superposition of Diffusion Models Using the Ito Density Estimator](https://mlsanity.com/paper/2412.17762/) (2024)
- [La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching](https://mlsanity.com/paper/2507.09466/) (2025)
- [Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation](https://mlsanity.com/paper/2512.18741/) (2025)
- [SimpleFold: Folding Proteins is Simpler than You Think](https://mlsanity.com/paper/2509.18480/) (2025)
- [Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute](https://mlsanity.com/paper/2603.27950/) (2026)
- [ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation](https://mlsanity.com/paper/2502.14637/) (2025)
- [Calibrating Generative Models to Distributional Constraints](https://mlsanity.com/paper/2510.10020/) (2025)
- [EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamics](https://mlsanity.com/paper/2410.00327/) (2024)
- [Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion](https://mlsanity.com/paper/2502.09890/) (2025)
- [Constrained Diffusion for Protein Design with Hard Structural Constraints](https://mlsanity.com/paper/2510.14989/) (2025)
- [On diffusion posterior sampling via sequential Monte Carlo for zero-shot scaffolding of protein motifs](https://mlsanity.com/paper/2412.05788/) (2024)
- [ProxelGen: Generating Proteins as 3D Densities](https://mlsanity.com/paper/2506.19820/) (2025)
- [Flow Autoencoders are Effective Protein Tokenizers](https://mlsanity.com/paper/2510.00351/) (2025)
- [Triangle Multiplication Is All You Need For Biomolecular Structure Representations](https://mlsanity.com/paper/2510.18870/) (2025)
- [HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens](https://mlsanity.com/paper/2512.15133/) (2025)
- [Protein Language Model Embeddings Improve Generalization of Implicit Transfer Operators](https://mlsanity.com/paper/2602.11216/) (2026)
- [Reaction-conditioned De Novo Enzyme Design with GENzyme](https://mlsanity.com/paper/2411.16694/) (2024)
- [VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL](https://mlsanity.com/paper/2505.15791/) (2025)
- [ProteinAE: Protein Diffusion Autoencoders for Structure Encoding](https://mlsanity.com/paper/2510.10634/) (2025)
- [MotifBench: A standardized protein design benchmark for motif-scaffolding problems](https://mlsanity.com/paper/2502.12479/) (2025)
- [Flexibility-Conditioned Protein Structure Design with Flow Matching](https://mlsanity.com/paper/2508.18211/) (2025)
- [Adaptive Protein Tokenization](https://mlsanity.com/paper/2602.06418/) (2026)
- [ProtPainter: Draw or Drag Protein via Topology-guided Diffusion](https://mlsanity.com/paper/2504.14274/) (2025)
- [SPID: Distilled Protein Backbone Generation](https://mlsanity.com/paper/2510.03095/) (2025)
- [Variable-Length Generative Protein Design via Generalized Poisson Flow](https://mlsanity.com/paper/2607.09039/) (2026)
- [SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign](https://mlsanity.com/paper/2609.03377/) (2026)
- [Protein generation with embedding learning for motif diversification](https://mlsanity.com/paper/2510.18790/) (2025)
- [Protein Autoregressive Modeling via Multiscale Structure Generation](https://mlsanity.com/paper/2602.04883/) (2026)
- [PI-Mamba: Linear-Time Protein Backbone Generation via Spectrally Initialized Flow Matching](https://mlsanity.com/paper/2603.26705/) (2026)

## Abstract (arXiv)

Protein diffusion models have emerged as a promising approach for protein design. One such pioneering model is Genie, a method that asymmetrically represents protein structures during the forward and backward processes, using simple Gaussian noising for the former and expressive SE(3)-equivariant attention for the latter. In this work we introduce Genie 2, extending Genie to capture a larger and more diverse protein structure space through architectural innovations and massive data augmentation. Genie 2 adds motif scaffolding capabilities via a novel multi-motif framework that designs co-occurring motifs with unspecified inter-motif positions and orientations. This makes possible complex protein designs that engage multiple interaction partners and perform multiple functions. On both unconditional and conditional generation, Genie 2 achieves state-of-the-art performance, outperforming all known methods on key design metrics including designability, diversity, and novelty. Genie 2 also solves more motif scaffolding problems than other methods and does so with more unique and varied solutions. Taken together, these advances set a new standard for structure-based protein design. Genie 2 inference and training code, as well as model weights, are freely available at: https://github.com/aqlaboratory/genie2.