DFMDock

(0.1.0)

Dock protein-protein complexes with diffusion-based sampling and confidence ranking.

Input

Receptor (larger protein)

Ligand (smaller protein)

Number of poses

SDE steps

Use clash force

Random seed

50 credits

Output

Configure inputs to begin

Set options on the left, then click “Submit job” — or start from an example.

Default docking

Multi-pose sampling

Clash-reduced docking

What is DFMDock?

Protein-protein interfaces are hard to dock when no restraints, cross-links, or known interface residues are available. DFMDock addresses that case with a rigid docking model that generates candidate complexes and ranks them with the same learned energy landscape.

The method was developed in the Gray Lab as Denoising Force Matching Dock. It starts from two unbound protein structures, receptor and ligand, and searches rigid-body translations and rotations with a reverse diffusion process. No multiple sequence alignment is required, which makes it useful for fast structure-only screening. The tradeoff is the same one shared by other rigid docking methods: if binding depends on major backbone rearrangement, loop opening, or induced fit, the top pose can still look reasonable while missing the true interface.

How to use DFMDock online

Run DFMDock online by uploading two protein structures, or by entering two RCSB PDB IDs, then choosing how many poses to sample and how many reverse diffusion steps to use. ProteinIQ returns ranked complex PDB files, the cleaned receptor and ligand inputs, learned energy values, clash counts, and pose-level diagnostic metrics in a spreadsheet and 3D viewer.

Inputs

Input	Accepted format	Description
`Receptor (larger protein)`	`.pdb`, `.ent`, or PDB ID	First docking partner. The tool requires protein `ATOM` records and limits each partner to `1000` residues and `50 MB`.
`Ligand (smaller protein)`	`.pdb`, `.ent`, or PDB ID	Second docking partner moved during docking. The same protein-only, `1000`-residue, and `50 MB` limits apply.

Settings

Setting	Default	Description
`Number of poses`	`1`	Number of sampled complexes returned. Range `1` to `20`. Higher values broaden the search over alternative interfaces.
`SDE steps`	`40`	Number of reverse diffusion denoising steps. Range `10` to `200`. More steps give the sampler more refinement iterations but increase runtime.
`Use clash force`	`false`	Adds repulsive guidance during sampling to discourage severe steric overlap between receptor and ligand.
`Random seed`	`42`	Controls reproducibility. The same structures, settings, and seed reproduce the same run.

Results

ProteinIQ returns two reference files, receptor_input.pdb and ligand_input.pdb, plus one PDB file for each sampled complex. The spreadsheet is sorted by energy, lowest first.

Column	Description
`Rank`	Pose rank after sorting by DFMDock energy.
`File`	Downloadable PDB file for the predicted complex.
`Energy`	DFMDock learned energy. Lower values rank ahead of higher values within the same run.
`DockQ`	Diagnostic score returned by the current tool. Useful for comparing poses within one job, not as a benchmark-quality estimate across unrelated jobs.
`iRMSD`	Interface RMSD-style diagnostic reported by the tool. Lower values indicate less movement under that diagnostic.
`LRMSD`	Ligand RMSD-style diagnostic reported by the tool. Lower values indicate less ligand displacement under that calculation.
`cRMSD`	Complex RMSD-style diagnostic reported by the tool.
`Fnat`	Contact-overlap style diagnostic reported by the tool. Higher values indicate more preserved contacts under that calculation.
`Clashes`	Number of steric clashes detected in the final pose. Lower is better.

How does DFMDock work?

DFMDock treats docking as denoising in rigid-body pose space. The ligand is randomized in orientation and translation, then a reverse stochastic differential equation updates that pose over a series of steps. At each step, the model predicts how the ligand should move relative to the receptor.

The network is SE(3)-equivariant, so rotation and translation of the input coordinates do not change the learned physical relationship. Residues are encoded with amino acid identity, backbone geometry, and ESM-2 embeddings. From those features, DFMDock learns two coupled signals:

Denoising force: Translational and rotational updates that move the ligand toward plausible interfaces during sampling.
Energy: A scalar landscape used to score and rank the sampled poses after generation.

That single-model setup is what makes DFMDock distinctive. Classical docking often separates search from rescoring. DFMDock uses one learned representation for both.

The current ProteinIQ tool keeps the workflow thin:

It cleans each uploaded structure down to standard protein ATOM records.
It samples the requested number of rigid docking poses with the chosen SDE steps.
It can add optional clash-force guidance during sampling.
It ranks the sampled complexes by learned energy.
It returns the complex PDB files, the cleaned inputs, and the pose metrics emitted by the inference script.

The tool does not model backbone flexibility, cofactors, glycans, membrane context, or non-protein partners. Inputs with multiple models are reduced to the first model, and only standard protein atoms are kept.

Understanding the results

Energy is the main ranking signal. DFMDock was trained to make that value useful for selecting among poses sampled in the same run, so it should be read as a within-job score rather than an absolute affinity estimate. A large gap between the top pose and the rest is usually more meaningful than the raw value itself.

Clashes is the fastest physical sanity check. A pose with a slightly worse energy but far fewer clashes is often the better candidate for inspection or follow-up refinement.

The remaining columns, DockQ, iRMSD, LRMSD, cRMSD, and Fnat, deserve careful reading. In the current ProteinIQ tool, these are emitted directly by the inference script as pose diagnostics even though a true native reference complex is not supplied at submission time. They are best used for relative comparison among poses from the same job, not as standalone claims that a complex is CAPRI-high-quality or experimentally near-native.

For practical triage, the most useful pattern is usually:

Prefer low Energy
Prefer low Clashes
Use the remaining metrics as secondary diagnostics when several poses have similar energy

When to use DFMDock vs alternatives

DFMDock is a good fit when both unbound structures are already available and the goal is to screen plausible rigid interfaces without building restraints first.

Tool	Best fit	Why choose it
`DFMDock`	Fast structure-only protein-protein docking	Learned sampling and ranking in one model, no MSA required
AF2Dock	AlphaFold2-style protein-protein docking from two structures	Useful when AF2-style confidence and refinement are part of the workflow
GeoDock	Geometry-aware protein complex prediction	Useful for learned rigid-body complex generation with geometric constraints
HADDOCK3	Interface residues, cross-links, mutagenesis, or other restraints are available	Restraint-guided docking is usually the stronger option when experimental evidence exists
LightDock	Broader exploratory sampling is needed	Swarm-based search can be useful when interface hypotheses are still wide open
EquiDock	One fast deep-learning pose is enough	Deterministic and lightweight when pose diversity is less important
ColabDock	AlphaFold-style docking with external restraints is preferred	Better aligned with workflows built around AlphaFold2-derived complex prediction

DFMDock is especially attractive for MSA-poor systems and early exploratory docking runs. It is less attractive when binding requires major conformational change or when strong experimental restraints are already available, because those cases favor flexible or data-driven docking workflows.

HADDOCK3: Restraint-guided macromolecular docking when interface evidence is available.
LightDock: Swarm-based protein docking for broader blind-search exploration.
EquiDock: Fast equivariant rigid docking for protein pairs.
ColabDock: AlphaFold2-based docking with restraint support.
DockQ: Evaluate a predicted complex against a known reference complex.

Based on the Gray Lab DFMDock repository and preprint, plus the current ProteinIQ DFMDock hosted implementation.

Related tools

AF2Dock

AF2Dock adapts AlphaFold2-style co-folding for structure-based protein-protein docking. It docks receptor and ligand protein structures with flow-matching refinement and ranks sampled complexes by iPTM.

EquiDock

EquiDock is an SE(3)-equivariant graph neural network for rigid protein-protein docking. It predicts a binding pose for a protein-protein complex from unbound structures using geometric deep learning, with DIPS and DB5 pretrained checkpoints from the native release.

GeoDock

GeoDock predicts flexible protein-protein docking complexes from two separate protein structures using a multi-track iterative transformer and the DIPS 0.3 checkpoint from the Gray Lab release.

ColabDock

ColabDock is a protein-protein docking framework that uses AlphaFold2 to predict complex structures guided by experimental restraints from cross-linking mass spectrometry, NMR, or other sources.

HADDOCK3

HADDOCK (High Ambiguity Driven protein-protein DOCKing) is an integrative modeling platform for biomolecular complexes. It uses experimental data and bioinformatic predictions to guide the docking process, generating accurate protein-protein complex structures.

LightDock

LightDock is a protein-protein, protein-peptide, and protein-DNA docking framework using Glowworm Swarm Optimization (GSO). It predicts macromolecular binding modes and interfaces for biological complexes.

ParaSurf

ParaSurf is a state-of-the-art surface-based deep learning model for predicting interactions between antibodies and antigens. It identifies paratope binding sites on antibody structures with high accuracy across multiple benchmark datasets.

SurfDock

SurfDock is a surface-informed diffusion generative model for protein-ligand docking, published in Nature Methods 2024. It leverages protein surface geometry to guide a diffusion process for reliable and accurate protein-ligand complex prediction.

DiffDock-L

DiffDock-L is a state-of-the-art molecular docking tool that uses diffusion models to predict how small molecule ligands bind to protein targets. It generates multiple binding poses with confidence scores.

DynamicBind

DynamicBind is an AI-powered protein-ligand binding prediction tool that recovers ligand-induced conformational changes from unbound protein structures. It predicts both ligand binding poses and protein conformational changes.