empyriumz / m-ionic

Protein-metal ion interaction modeling

M-Ionic

Prediction of metal ion binding sites from sequence using residue embeddings

A pipeline to identify proteins which bind to metals as well as which residues in the protein are involved in metal-binding. The output of this method provides ion-specific probabilities for each residue.

Overview:

1. Input: fasta file containing one protein sequence
2. Prepare residue-level embeddings
3. Predict the binding probability using the saved model parameters
4. Output: the predicted binding probability for each ion for each residue in the protein sequence

How to use:

M-Ionic can be used on your protein of interest using a Google Colab Notebook (https://bit.ly/40FrRbK)