bio.rodeo
ModelsOrganizationsProvidersLeaderboardAboutSign in
bio.rodeo

The authoritative source for evaluating biological foundation models. No hype, just honest analysis.

Categories
  • DNA & Gene
  • RNA
  • Protein
  • Small molecule
  • Single-cell
  • Spatial omics
  • Pathology
  • Imaging
  • Metabolomics
  • Biosignals
  • Language model
bio.rodeoModelsOrganizationsProvidersLeaderboardAboutFAQSubmit a modelContact
© 2026 Pulsatance. All rights reserved. ~
Built by Pulsatance
models / protein / cpsde
ProteinSmall molecule
ByteDance SeedUniversity of Chinese Academy of SciencesChinese Academy of SciencesTsinghua UniversityShanghai Jiao Tong UniversityReleased May 2025

CpSDE

Cyclic peptide design conditioned on target protein structure, generating all four cyclization types via all-atom, all-bond harmonic SDE modeling.

12Openness

Where to run it

No providers recorded yet. Browse all providers

CpSDEProteinByteDance Seed

Cyclic peptides are attractive therapeutics: closing a peptide into a macrocycle makes it far more resistant to enzymatic hydrolysis than its linear counterpart and often improves both conformational stability and target affinity. Computational design of cyclic peptides has nevertheless lagged behind linear peptide design for three structural reasons — there are very few solved 3D structures of protein targets bound to cyclic peptide ligands, cyclization imposes hard geometric constraints that residue-frame representations cannot express, and the linking chemistry frequently involves non-canonical amino acids.

CpSDE, from ByteDance Seed with collaborators at the University of Chinese Academy of Sciences, CASIA, Tsinghua University, and Shanghai Jiao Tong University, addresses all three by abandoning the residue frame entirely and modeling peptides as atoms and bonds. It pairs two networks: AtomSDE, a generative structure predictor built on a harmonic stochastic differential equation, and ResRouter, a residue-type predictor that reads denoised structures. A routed sampling algorithm alternates between them, updating structure and sequence together until a complete cyclic peptide emerges in the binding pocket of a given target.

Because atoms and bonds are the shared vocabulary of small molecules, linear peptides, and macrocycles, this representation lets CpSDE learn from abundant protein–ligand complex data rather than the scarce cyclic peptide structures. Presented at ICML 2025, it is the first generative method able to design all four cyclization topologies directly against a 3D protein target.

#Key Features

  • All four cyclization topologies: Head-to-tail, head-to-side, side-to-tail, and side-to-side macrocycles are generated by the same model, specified through a chemical graph of the cyclization region supplied at sampling time.
  • Explicit atom and bond modeling: Rather than residue frames, CpSDE represents every heavy atom and every covalent bond, which is what makes ring-closure geometry and non-canonical linking chemistry expressible at all.
  • Harmonic SDE prior: AtomSDE's forward process uses a harmonic stochastic differential equation whose prior respects chain connectivity, giving a physically sensible starting distribution for denoising a bonded molecule.
  • Routed sequence–structure co-design: ResRouter is invoked only in the second half of the reverse process, once denoised coordinates carry enough signal to determine residue identity, which both improves sequence quality and cuts inference cost.
  • Data reuse across ligand classes: Training on small-molecule and linear-peptide complexes sidesteps the scarcity of cyclic peptide structures without any cyclic-specific pretraining corpus.

#Technical Details

Both components are SE(3)-equivariant message-passing networks operating over two graphs — a k-nearest-neighbour graph capturing protein–ligand interactions and the ligand's chemical bond graph. AtomSDE trains on a curated small-molecule set of 14,348 PDBBind complexes plus peptide complexes with fewer than 200 heavy atoms; ResRouter trains on the full curated peptide set of 20,033 complexes drawn from the RCSB PDB, Propedia, and PepBDB, with ligands under 30 residues. Splits are clustered at 30% receptor sequence identity. Training used AdamW at a constant learning rate of 1e-4, converging in 48 hours (AtomSDE) and 18 hours (ResRouter) on 8 NVIDIA H100 GPUs; routed sampling runs 1,000 steps, invoking ResRouter only below t = 0.5.

On 100 large-volume protein pockets, Rosetta-scored designs from the mixed-topology setting reach an average total energy of -580.67 and interface binding energy of -55.71, against -576.39 / -46.98 for ProteinGenerator, -576.16 / -47.88 for PepFlow, and -359.44 / -45.06 for PepGLAD. Structural diversity is 0.79 across all four topologies, versus 0.55 for RFdiffusion paired with ProteinMPNN, which scores the best raw energy but collapses toward a repeated α-helical motif.

#Applications

CpSDE targets the macrocyclic peptide segment of drug discovery, where the goal is a protease-resistant binder against a protein surface that small molecules cannot address. Given a receptor structure and a desired cyclization chemistry, it produces candidate macrocycles across a range of lengths for downstream Rosetta relaxation, molecular dynamics triage, and synthesis. The paper illustrates this with two case studies: head-to-tail inhibitors of the oncogenic methyltransferase SMYD2 and side-to-side inhibitors of SET8, each followed by MD simulation of the designed conformational ensembles.

#Impact

CpSDE establishes atom-and-bond modeling as a practical route around the data bottleneck that has held back cyclic peptide design, and it makes topology a controllable input rather than a fixed architectural assumption. The authors report that generated macrocycles can still exhibit invalid conformations — distorted bond lengths or receptor clashes — that require expensive Rosetta relaxation to repair, and note that self-consistency evaluation of the kind standard in protein design is not yet possible because no accurate cyclic peptide structure predictor or docking model exists. Validation is entirely computational; no wet-lab synthesis is reported. Neither code nor trained weights have been released.

At a glance

Released
May 2025
Category
Protein
Organizations
ByteDance Seed / University of Chinese Academy of Sciences / Chinese Academy of Sciences / Tsinghua University / Shanghai Jiao Tong University

Links

Research Paper

Tags

de_novo_designdiffusiongenerativegraph_neural_networkpeptide_design

Something wrong?

Much of this page is generated or calculated automatically. Flag anything that looks off and we will re-run it.