Generation method

Run RFdiffusion online

Generate a bounded unconditional backbone with RFdiffusion

Generate one deterministic 20–50-residue protein backbone with the RFdiffusion Base model.

Choose an approach

Scientific approaches

Select the analysis that best matches your scientific question. Each approach opens with its relevant inputs and controls.

Unconditional backbone generation

Available

Generate one backbone with fixed seed 0, 15–50 diffusion steps, and no target conditioning.

Start this method

Prepare

Bounded generation parameters

No source Dataset is required. Supply a target residue count and diffusion-step count inside the supported range.

  • Length from 20 through 50 residues
  • Diffusion steps from 15 through 50
  • Exactly one design with deterministic seed 0
Length 20 residues
Diffusion steps 15

How the analysis starts

Choose a Project, open a compatible Dataset, then select the rows you want to analyze. Ubi will open this method with the compatible controls and column mappings ready to review.

Configure the scientific method

These controls appear in the Dataset analysis panel, where values can be checked against the actual input before the run starts.

Backbone length

20–50 residues

Choose the exact length encoded in the unconditional contig.

Diffusion schedule

15–50 steps

More steps cost more CPU time; each analysis produces one design.

Generation model

RFdiffusion Base · deterministic seed 0

Keep the model and seed fixed when comparing diffusion schedules.

Review results as scientific outputs

Results open with the figures, structures, sequences, and metrics needed to answer the scientific question. Downloadable files remain available for downstream analysis.

How to interpret the result

  • The output is an unconditional backbone proposal, not a sequence, binder, motif scaffold, or experimentally validated structure.
  • Review geometry and add independently qualified sequence-design and validation steps before experimental use.
  • Compare repeats only when checkpoint, source trees, length, step count, seed, and runtime image are identical.
1

Predicted backbone structure

Open the PDB and inspect residue count, backbone atoms, and coordinates.

2

Generation settings

Review backbone length, diffusion steps, seed, and model alongside the structure.

Use a complementary method on the same Project data.

Method scope and limitations
  • This tool supports unconditional Base-model generation only; target-conditioned and symmetry modes are not available.
  • Backbone generation may take tens of seconds to minutes.
Terms of Service Privacy Policy © Ubi Biologics
UBI Biologics