PANDA: Protein All-atom Nested-tree Denoising Architecture for End-to-End Generation
- 1College of Biotechnology, Tianjin University of Science and Technology
Abstract
Deep generative models have expanded the scope of computational protein design, yet most approaches still separate backbone generation from sequence assignment or rely on latent and torsional representations that do not operate directly on all atoms in Cartesian space. We present PANDA, an end-to-end generative architecture that performs denoising in a unified all-atom representation, recovering sequence identity directly from atomic occupancy patterns. By coupling global and local coordinate tracks and introducing a sampling strategy that preserves side-chain geometry, PANDA achieves the highest self-consistency design success across protein lengths among evaluated all-atom methods. For functional design it conditions on pairwise distances between motif atoms rather than fixing their coordinates, allowing the functional atoms to be positioned jointly with the scaffold. On the Atomic Motif Enzyme benchmark, PANDA preserves motif geometry and delivers substantially higher scaffolding success than previous approaches, particularly for larger motifs. PANDA thus provides an efficient route to high-quality all-atom generative design with flexible atomic-level control.
Related
- CBAT-Net: a unified CNN–BiLSTM–MultiHead transformer architecture for joint Q3/Q8 protein secondary structure prediction
- Inhibitory Activity of Red Panda Islet Amyloid Polypeptide on Human IAPP Aggregation
- Lipid-Protein Reciprocal Coupling: A Quantitative Analysis of Membrane Curvature, Architecture, and Protein Association
- Dynamic protein phosphorylation shapes mitochondrial catalysis, import, and architecture
- Molecular architecture of TE-seeded chromosome-naive initiation networks of protein-protein interactions delineates the Human Protein Map of the assembly of multiprotein complexes
BibTeX
@misc{bai2026panda,
title = {{PANDA: Protein All-atom Nested-tree Denoising Architecture for End-to-End Generation}},
author = {J. Bai and H. Jiang},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.11.750898},
url = {https://www.biorxiv.org/content/10.64898/2026.09.11.750898v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - PANDA: Protein All-atom Nested-tree Denoising Architecture for End-to-End Generation
AU - J. Bai
AU - H. Jiang
PY - 2026
DA - 2026/09/11
PB - bioRxiv
DO - 10.64898/2026.09.11.750898
UR - https://www.biorxiv.org/content/10.64898/2026.09.11.750898v1
AB - Deep generative models have expanded the scope of computational protein design, yet most approaches still separate backbone generation from sequence assignment or rely on latent and torsional representations that do not operate directly on all atoms in Cartesian space. We present PANDA, an end-to-end generative architecture that performs denoising in a unified all-atom representation, recovering sequence identity directly from atomic occupancy patterns. By coupling global and local coordinate tracks and introducing a sampling strategy that preserves side-chain geometry, PANDA achieves the highest self-consistency design success across protein lengths among evaluated all-atom methods. For functional design it conditions on pairwise distances between motif atoms rather than fixing their coordinates, allowing the functional atoms to be positioned jointly with the scaffold. On the Atomic Motif Enzyme benchmark, PANDA preserves motif geometry and delivers substantially higher scaffolding success than previous approaches, particularly for larger motifs. PANDA thus provides an efficient route to high-quality all-atom generative design with flexible atomic-level control.
ER -