Welcome to Cordax, a structure-based machine learning approach that explores sequence determinants of amyloid propensity beyond their traditional limits.

Cordax employs the FoldX force field to translate structural compatibility and interaction energies into sequence aggregation propensity (see ‘About’ for details).

Enter a protein sequence to retrieve an amyloidogenic profile, along with structural models of the topologies predicted for identified fibril-forming hot spots.

This approach is computationally intensive and will take some time to complete. For this reason, the length of the input sequence (n<50) and the number of jobs per user is limited to 10. The tool employs a 'lazy' interface strategy that stores pre-calculated sequences in a growing database. This bypasses unnecessary computation for recurring sequence segments or future runs.

Users are welcome to download the standalone package which can be applied locally for larger screens. To acquire the standalone, users may contact us by email at cordax@switchlab.org.

By proceeding, you are agreeing with the terms and conditions of use.

When using Cordax, please cite:

• Louros, N., et al. Structure-based machine-guided mapping of amyloid sequence space reveals uncharted sequence clusters with higher solubilities. Nat Commun 11, 3314 (2020).