Conditional Protein Structure Generation with Protpardelle-1c

Tianyu Lu, Richard W. Shuai, Petr Kouba, Zhaoyang Li, Yilin Chen, Akio Shirali, Jinho Kim, Po‐Ssu HuangbioRxiv 2025 · DOI

Abstract

We present Protpardelle-1c, a collection of protein structure generative models with robust motif scaffolding and support for multi-chain complex generation under hotspot-conditioning. Enabling sidechain-conditioning to a backbone-only model increased Protpardelle-1c’s MotifBench score from 4.97 to 28.16, outperforming RFdiffusion’s 21.27. The crop-conditional all-atom model achieved 208 unique solutions on the La-Proteina all-atom motif scaffolding benchmark, on par with La-Proteina while having ~10 times fewer parameters. At 22M parameters, Protpardelle-1c enables rapid sampling, taking 40 minutes to sample all 3000 MotifBench backbones on an NVIDIA A100-80GB, compared to 31 hours for RFdiffusion.

Introduction

In protein engineering, function is inextricably linked to form. A common design challenge is "motif scaffolding": building a stable protein structure around a specific functional site—such as a binding pocket or catalytic center—to maintain its precise geometry. Current state-of-the-art tools often struggle with high computational costs, the neglect of sidechain atoms (which are critical for chemical function), and the difficulty of designing multi-chain complexes. Protpardelle-1c addresses these challenges by providing a lightweight, efficient diffusion model that incorporates sidechain-aware conditioning and optimized training data to surpass existing benchmarks in both accuracy and speed.

Methods

Protpardelle-1c is built on the Elucidated Diffusion Model (EDM) framework. Notably, the model is non-equivariant by design, learning to "pick a frame" during denoising by training on randomly rotated and translated protein structures. This architectural choice, combined with a Diffusion Transformer (DiT) style noise residual, allowed the authors to reduce the parameter count to 22M.

Key innovations include:

  • Classifier-Free Guidance: The model attends directly to motif coordinates as conditional input, avoiding the brittleness of traditional reconstruction guidance.
  • Sidechain Conditioning: By conditioning on both backbone and sidechain atoms, the model ensures the generated scaffold is chemically compatible with the functional motif.
  • Augmented Training Data: The model was trained on AI-CATH (ESMFold-predicted structures redesigned by ProteinMPNN) and MD-CATH (molecular dynamics simulations) to better understand the space of designable and flexible proteins.

Results

Protpardelle-1c demonstrates significant improvements over the industry-standard RFdiffusion. On the MotifBench benchmark, Protpardelle-1c achieved a score of 28.16, compared to 21.27 for RFdiffusion. The model's efficiency is a standout feature: it sampled 3,000 backbones in just 40 minutes on a single NVIDIA A100, whereas RFdiffusion required 31 hours for the same task—a 46x speedup.

Comparison of MotifBench solutions for RFdiffusion and Protpardelle-1c.

Furthermore, the model's ability to generate high-quality all-atom structures is evidenced by its performance on the La-Proteina benchmark, where it produced 208 unique solutions. The model successfully generated binders for complex targets like SpCas9, demonstrating its utility for real-world therapeutic design.

Example of a successful scaffold generated for the 26_3B5V motif problem.

Discussion and Limitations

While Protpardelle-1c sets a new bar for efficiency and sidechain-aware design, limitations remain. Users must currently pre-specify motif indices within the sequence, and the model exhibits a slight bias toward alpha-helical structures, likely due to the nature of the training data. Future work will focus on automated motif placement and diversifying the topological variety of generated scaffolds.

Summary updated

Abstract

Abstract We present Protpardelle-1c, a collection of protein structure generative models with robust motif scaffolding and support for multi-chain complex generation under hotspot-conditioning. Enabling sidechain-conditioning to a backbone-only model increased Protpardelle-1c’s MotifBench score from 4.97 to 28.16, outperforming RFdiffusion’s 21.27. The crop-conditional all-atom model achieved 208 unique solutions on the La-Proteina all-atom motif scaffolding benchmark, on par with La-Proteina while having ~10 times fewer parameters. At 22M parameters, Protpardelle-1c enables rapid sampling, taking 40 minutes to sample all 3000 MotifBench backbones on an NVIDIA A100-80GB, compared to 31 hours for RFdiffusion.
BibTeX
@misc{lu2025conditional,
  author = {Tianyu Lu and Richard W. Shuai and Petr Kouba and Zhaoyang Li and Yilin Chen and Akio Shirali and Jinho Kim and Po‐Ssu Huang},
  title = {{Conditional Protein Structure Generation with Protpardelle-1c}},
  year = {2025},
  doi = {10.1101/2025.08.18.670959},
  howpublished = {bioRxiv},
}
Figure