DeepEMhancer

Sharpen and denoise cryo-EM maps.

Docs

Input

Cryo-EM Map

Processing model

Batch size

30 credits

Output

Configure input settings on the left, then click "Submit job"

What is DeepEMhancer?

DeepEMhancer performs automatic post-processing of cryo-EM density maps using deep learning. Rather than applying a global B-factor correction like traditional sharpening, it learns a non-linear mapping from raw experimental maps to locally sharpened, masked, and denoised outputs — all in a single step and without requiring an atomic model.

The approach was developed by Sanchez-Garcia et al. at the Spanish National Center for Biotechnology (CNB-CSIC). A 3D U-Net was trained on pairs of experimental cryo-EM maps and their corresponding LocScale-sharpened versions, allowing the network to learn the relationship between noisy input maps and their post-processed targets. On a test set of 20 maps, DeepEMhancer improved local resolution by a median of ~0.4 Å (measured by DeepRes), outperforming both automatic RELION B-factor correction and manually tuned EMDB depositions.

How does DeepEMhancer work?

The network uses a 3D U-Net architecture with three downsampling and three upsampling blocks connected by skip connections. Input maps are divided into overlapping 64×64×64 voxel cubes, each processed independently on the GPU, then reassembled into the full output volume.

Training targets were not simulated from atomic coordinates directly. Instead, LocScale — which requires an atomic model — was used to generate sharpened reference maps from 107 experimental entries. The network learned to reproduce LocScale-quality output from experimental maps alone, effectively distilling model-based sharpening into a model-free tool.

When half-maps are provided, DeepEMhancer uses both to estimate noise statistics more accurately, producing better local masking. With only a single full map, the tool estimates noise from the map itself, which works well for most cases but can struggle with hollow or fibrous proteins where automatic noise estimation is unreliable.

How to use DeepEMhancer online

ProteinIQ runs DeepEMhancer on GPU infrastructure with no software installation or Python environment setup required.

Inputs

Input	Description
`Cryo-EM Map`	MRC or MAP file of the unprocessed reconstruction. Must not already be sharpened or masked. Up to 500 MB.
`Half Map 2`	Optional second half-map (MRC/MAP). When provided alongside the first half-map, enables more accurate local noise estimation.

Half-map input is recommended when available. The first half-map goes in the main input slot; the second in the optional slot.

Settings

Setting	Description
`Processing model`	Controls masking behavior: `tightTarget` (default), `wideTarget`, or `highRes`. See below.
`Batch size`	Number of map chunks processed in parallel on the GPU (1–12, default 6). Reduce if processing fails on very large maps.

Processing models

Model	Best for	Behavior
`tightTarget`	Most maps	Tight masking around the macromolecule. Default choice.
`wideTarget`	Maps where tightTarget clips peripheral density	More permissive mask that preserves surrounding features like detergent belts or flexible domains.
`highRes`	Maps better than ~4 Å overall resolution	Trained on a high-resolution subset (<4 Å). Produces more detail but noisier output than the other models.

If tightTarget removes density that should be kept, try wideTarget. Use highRes only when overall resolution justifies it — on lower-resolution maps it tends to amplify noise without meaningful enhancement.

Output

The result is a post-processed MRC map file combining sharpening, masking, and denoising. Download and open it in visualization software like ChimeraX, Coot, or the PDB Viewer for inspection.

Limitations

No ligands or post-translational modifications in training data: The network was trained exclusively on protein density. Ligands, glycans, and modified residues may be inaccurately represented in the output.
Pre-processed maps will fail: Input must be an unsharpened, unmasked reconstruction. Maps that have already been B-factor corrected or masked will produce artifacts.
Noise estimation on unusual morphologies: Hollow or fibrous structures can confuse automatic noise estimation when only a full map (no half-maps) is provided.
Resolution is not created from nothing: DeepEMhancer enhances existing signal but cannot recover information absent from the data. Visual improvement does not always correspond to genuine resolution gain.

Related tools

SuperWater

Predict protein hydration sites from a structure using a diffusion model with ESM features and a confidence-filtering head.

AllMetal3D

Predict metal and water binding sites in protein structures using 3D convolutional neural networks (AllMetal3D + Water3D).

MolProbity

Validate protein structure quality with all-atom contact analysis, Ramachandran plots, rotamer assessment, and geometry checks.

PDBsum

Generate a downloadable PDBsum structural summary report archive for a single protein structure.

DR-BERT

DR-BERT is a compact protein language model that predicts intrinsically disordered regions (IDRs) in proteins. It outputs per-residue disorder probability scores (0–1) from amino acid sequences, enabling fast and accurate annotation of disordered regions without structural data.

AF-Cluster

Cluster Multiple Sequence Alignments to predict alternative protein conformations with AlphaFold2. Uses DBSCAN clustering to identify sequence subgroups.

Aggrescan3D

Faithful static-mode Aggrescan3D tool for per-residue aggregation propensity analysis from a single protein structure.

DockQ

Assess docking model quality by comparing predicted complexes against native references. DockQ v2.1.3 supports protein, nucleic-acid, and supported small-molecule interfaces with faithful native metrics.

DSSP

Assign protein secondary structure using the DSSP algorithm. The gold standard for hydrogen bond-based structure assignment from coordinates.

IPSAE

Scoring function for interprotein interactions in AlphaFold2, AlphaFold3 and Boltz predictions. Calculates ipSAE, ipTM, pDockQ, pDockQ2, and LIS scores to assess protein-protein interface quality.

What is DeepEMhancer?

How does DeepEMhancer work?

How to use DeepEMhancer online

ProteinIQ runs DeepEMhancer on GPU infrastructure with no software installation or Python environment setup required.

Inputs

Input	Description
`Cryo-EM Map`	MRC or MAP file of the unprocessed reconstruction. Must not already be sharpened or masked. Up to 500 MB.
`Half Map 2`	Optional second half-map (MRC/MAP). When provided alongside the first half-map, enables more accurate local noise estimation.

Half-map input is recommended when available. The first half-map goes in the main input slot; the second in the optional slot.

Settings

Setting	Description
`Processing model`	Controls masking behavior: `tightTarget` (default), `wideTarget`, or `highRes`. See below.
`Batch size`	Number of map chunks processed in parallel on the GPU (1–12, default 6). Reduce if processing fails on very large maps.

Processing models

Model	Best for	Behavior
`tightTarget`	Most maps	Tight masking around the macromolecule. Default choice.
`wideTarget`	Maps where tightTarget clips peripheral density	More permissive mask that preserves surrounding features like detergent belts or flexible domains.
`highRes`	Maps better than ~4 Å overall resolution	Trained on a high-resolution subset (<4 Å). Produces more detail but noisier output than the other models.

Output

The result is a post-processed MRC map file combining sharpening, masking, and denoising. Download and open it in visualization software like ChimeraX, Coot, or the PDB Viewer for inspection.

Limitations

No ligands or post-translational modifications in training data: The network was trained exclusively on protein density. Ligands, glycans, and modified residues may be inaccurately represented in the output.
Pre-processed maps will fail: Input must be an unsharpened, unmasked reconstruction. Maps that have already been B-factor corrected or masked will produce artifacts.
Noise estimation on unusual morphologies: Hollow or fibrous structures can confuse automatic noise estimation when only a full map (no half-maps) is provided.
Resolution is not created from nothing: DeepEMhancer enhances existing signal but cannot recover information absent from the data. Visual improvement does not always correspond to genuine resolution gain.