Conditional Protein Structure Generation with Protpardelle-1c
Tianyu LuiD, Richard W. ShuaiiD, Petr KoubaiD, Zhaoyang LiiD, Yilin CheniD, Akio ShiraliiD, Jinho KimiD, Po‐Ssu HuangiD
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-1cs MotifBench score from 4.97 to 28.16, outperforming RFdiffusions 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.
02 /Specification & Classification
Click any tag to browse matching papersReproducibility ledger
Nobody has reported trying to reproduce this paper yet. Did you replicate an experiment or run the code? Your report saves the next lab a week.
Sign in to file a reproducibility report.
Related papers
- An all-atom protein generative model
A. E. Chu, L. Cheng, … P.-S. Huang·bioRxiv·May 24, 2023
- Illuminating protein space with a programmable generative model
John Ingraham, Max Baranov, … Gevorg Grigoryan·NaturePeer-reviewed·Nov 15, 2023
- P(all-atom) Is Unlocking New Path For Protein Design
Wei Qu, Jiawei Guan, … Haobo Wang·bioRxiv·Aug 16, 2024
- ProteinSGM: Score-based generative modeling for de novo protein design
Jin Seop Lee, Ji‐Sun Kim, Philip M. Kim·Nature Computational SciencePeer-reviewed·May 4, 2023
- PANDA: Protein All-atom Nested-tree Denoising Architecture for End-to-End Generation
Jie Bai, Huifeng Jiang·bioRxiv·Sep 13, 2026
- Ambient Proteins: Training Diffusion Models on Low Quality Structures
Giannis Daras, Jeffrey Ouyang-Zhang, … Daniel J. Diaz·bioRxiv·Jul 3, 2025