How to use ipSAE Online

Use ipSAE online to calculate interface confidence metrics from a complex structure and PAE matrix.

ipSAE calculates inter-chain confidence metrics from an existing complex prediction rather than generating a new structure. It is useful when a researcher already has a predicted complex from Chai-1, Boltz-2, Protenix, AlphaFold-style workflows, or another source and wants a consistent interface-confidence readout.

On Neurosnap, users upload a multi-chain Structure, a square PAE Matrix, and optionally a separate pLDDT array. If no pLDDT file is provided, the service reads residue-level pLDDT from the structure B-factor field. The PAE Matrix Input Format selector controls how ipSAE aligns source-model payloads such as auto, boltz2, chai1, or protenix.

How ipSAE Works

The service calls Neurosnap's calculate_ipSAE routine directly. It uses the submitted structure to define chain and residue order, combines that order with pLDDT and PAE values, and reports direction-aware chain-pair metrics including ipSAE, inter-chain ipTM, pDockQ, pDockQ2, and LIS.

The most important practical requirement is alignment: the PAE matrix and pLDDT vector must refer to the same residue or token order as the structure and selected source format. When scoring structures exported from supported folding tools, choose the matching PAE Matrix Input Format; use auto for standard residue-aligned PAE arrays. Advanced cutoffs control which PAE and distance relationships count as interface evidence.

Outputs follow the same convention as Chai-1 and Boltz-2 results: scores.csv contains scalar summary metrics such as Mean pLDDT, Min ipSAE, and Max ipTM, while rank_1.json contains per-chain-pair and detailed nested ipSAE data. This makes ipSAE useful as a standalone rescoring step or as a way to compare interface confidence across models produced by different folding backends.

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 ipSAE on Neurosnap

Using ipSAE on Neurosnap could drastically accelerate interface-confidence rescoring for existing predicted complexes.

No refolding required: ipSAE scores an uploaded complex directly, which is faster than rerunning a structure-prediction model.
Model-output aware: The format selector handles common PAE alignment conventions from Boltz-2, Chai-1, and Protenix workflows.
pLDDT fallback: Users can omit a pLDDT file when the structure already stores confidence values in B-factors.
Consistent outputs: Results match the Chai-1/Boltz-2 score-file convention, so interface metrics can be compared across tools.

How to Use ipSAE on Neurosnap

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

Bennett, N. R., Coventry, B., Goreshnik, I., Huang, B., Allen, A., Vafeados, D., Peng, Y. P., Dauparas, J., Baek, M., Stewart, L., DiMaio, F., De Munck, S., Savvides, S. N., & Baker, D. Improving de novo protein binder design with deep learning. Nature Communications. 2023.

Amani, Keaun, and Danial Gharaie Amirabadi. 2024. Neurosnap SDK Package. Software. https://github.com/NeurosnapInc/neurosnap.

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:

ColabDock

LightDock

AF2Bind

Align Structures

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