How to use SuperMetal Online

Use SuperMetal online to predict zinc-ion binding locations from protein structures.

SuperMetal predicts zinc-ion binding locations directly from protein structures using a generative diffusion workflow. It is designed for structural biology, metalloprotein analysis, enzyme engineering, and drug-discovery settings where a structure may be available without annotated metal coordinates or a known number of binding sites.

On Neurosnap, researchers upload one PDB or mmCIF protein structure and can tune diffusion sampling, confidence filtering, and spatial clustering in Advanced Options. The service returns final zinc coordinates as a CSV table together with zinc-only and combined protein-plus-zinc PDB files for visualization and downstream analysis.

How SuperMetal Works

SuperMetal first represents the protein as a geometric graph and uses an SE(3)-equivariant score-based diffusion model to move randomly initialized zinc probes toward plausible coordination environments. A separately trained confidence model can remove weak candidates, after which DBSCAN clustering converts nearby retained samples into final predicted sites. The released checkpoints integrated here are trained for zinc, even though the broader framework can be adapted to other metal ions.

Candidate Count controls the breadth of the initial search, while Inference Steps controls diffusion refinement. Confidence Threshold trades exploratory coverage for selectivity, and Clustering Radius determines how aggressively nearby candidates are merged. The site table reports each final coordinate and the confidence of its nearest sampled candidate, while the candidate table exposes the complete pre-clustering population for deeper review.

Predicted zinc sites should be treated as structural hypotheses. Researchers should inspect local coordinating residues and geometry, compare against homologs or experimental evidence, and use suitable energetic or quantum-chemical follow-up before assigning catalytic or mechanistic roles.

What is Neurosnap?

Neurosnap is the leading platform for bioinformatics and computational science focused on expanding access to powerful modeling and simulation tools. Because many state-of-the-art machine learning systems remain complex to install, configure, and scale, Neurosnap offers a clean, browser-based workspace that removes the burden of infrastructure management, dependency conflicts, and command-line tooling.

Built for biologists, chemists, and cross-disciplinary scientists, the platform enables advanced computational workflows without requiring expertise in software engineering or cloud architecture. Researchers can launch analyses through an intuitive interface, connect programmatically through a comprehensive API, and rely on automated resource management to scale workloads efficiently. By taking care of the underlying compute and operational complexity, Neurosnap allows teams to devote their energy to scientific progress and faster iteration. Security and data protection remain foundational principles, with clear safeguards outlined in our Terms of Use and Privacy Policy to ensure your work stays protected.

Advancing Discovery with SuperMetal on Neurosnap

Using SuperMetal on Neurosnap could drastically accelerate zinc-binding site prediction and metalloprotein structure interpretation from uploaded protein coordinates.

No site-count requirement: SuperMetal samples candidate zinc positions without requiring users to specify how many sites should exist.
Geometry-aware generation: The equivariant diffusion model reasons over three-dimensional protein environments rather than relying only on sequence motifs.
Confidence-guided refinement: Users can retain broader exploratory predictions or apply stricter filtering before clustering.
Analysis-ready results: Coordinate tables and combined PDB structures make predicted sites easy to inspect in molecular viewers or carry into downstream workflows.

How to Use SuperMetal on Neurosnap

To harness the capabilities of SuperMetal, researchers can follow this streamlined workflow within Neurosnap:

Access Neurosnap: Start by logging in to the Neurosnap website.
Select Tool: From the list of available tools, choose SuperMetal.
Provide Inputs: Provide all the inputs specified within the submission panel and optionally configure the tool as desired.
Run Tool: Submit the SuperMetal job and Neurosnap will execute it in the cloud, automatically notifying you as soon as your results are ready.
Review Output: Explore your results through rich visualizations, including figures, plots, and interactive views designed to help you analyze findings with clarity and confidence.

Citations

Please cite the original work when using SuperMetal in publications or research outputs.

Lin X, Su Z, Liu Y, Liu J, Kuang X, Cummings PT, Spencer-Smith J, Meiler J. SuperMetal: a generative AI framework for rapid and precise metal ion location prediction in proteins. Journal of Cheminformatics. 2025;17:107. https://doi.org/10.1186/s13321-025-01038-9

Neurosnap Inc. (2022). Neurosnap: An online platform for computational biology and chemistry. Available at: https://neurosnap.ai/

Similar Services

Explore related tools that support similar research workflows:

SuperWater

AFcluster

Align Structures

Aliphatic Index

Proudly supporting 50,000+ scientists worldwide, including 7,000+ leading biotech and global biopharma organizations.