How to use PottsMPNN Online

Use PottsMPNN online for backbone-conditioned protein design and mutation energy prediction.

Upload one protein structure and choose Sequence Design or Energy Prediction. PottsMPNN learns a structure-conditioned Potts energy model alongside an autoregressive sequence generator. It supports vanilla and soluble checkpoints, including MSA-trained models.

How PottsMPNN Works

In Sequence Design, choose the chains to redesign, the number of sequences, and sampling temperature. Fixed Positions use original PDB residue labels such as A:42 or A:43B. Undesigned chains remain fixed as structural context. Optional optimization requires Number Sequences = 1 and returns both sampled and optimized sequences. Potts optimization may harm binder designs.

In Energy Prediction, provide one mutant per line, such as A:V42G, or combine mutations with commas. Leave Mutations blank for saturation scanning. Binding Partitions such as A|B:C estimate bound-minus-unbound mutation energy. Every chain must occur exactly once.

Results include a CSV table; sequence design also returns FASTA. Colons separate chains in the displayed Chain Order. Model energies use arbitrary units, not kcal/mol. Negative uncentered ΔΔG favors a mutant relative to wildtype. Center Scores removes the mutant-set mean and changes that reference. Compare energies only for the same structure and settings. This service runs the core PottsMPNN workflows; the separate AlphaFold3/PISA iterative optimization pipeline is not included.

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 PottsMPNN on Neurosnap

Using PottsMPNN on Neurosnap could drastically accelerate structure-conditioned protein sequence generation and mutation energy screening.

Design multiple sequences for a fixed backbone.
Screen single and combined mutations using a learned Potts model.
Assess candidate binding mutations using chain partitions.

How to Use PottsMPNN on Neurosnap

To harness the capabilities of PottsMPNN, 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 PottsMPNN.
Provide Inputs: Provide all the inputs specified within the submission panel and optionally configure the tool as desired.
Run Tool: Submit the PottsMPNN 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 PottsMPNN in publications or research outputs.

Birnbaum and Keating. Beyond native sequence recovery: Improved modeling of the sequence-energy landscape of protein structures. PNAS (2026). doi:10.1073/pnas.2535494123.

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:

BindFilter

Efficient Evolution

EvoEF2

EvoEF2 Mutant Stability Analysis

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