Multi-Modal Foundation · IBM Research
Task-specific predictions for binding affinity, blood–brain barrier permeability, and protein solubility.
30s–5min
Runs on On-demand GPU
Runs on our servers with on-demand compute. A first run needs time to load the model; active capacity can be reused and scales down when idle.Run this model
About this model
Runs three IBM Research MAMMAL fine-tunes: BindingDB pKd for a protein–molecule pair, MoleculeNet BBBP for blood–brain barrier permeability, and protein_solubility for a protein sequence. The selected task determines the checkpoint and required inputs. Binding affinity is returned as pKd; BBBP and solubility return binary classes.
Standardized I/O contract
Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.
Inputs
Task
Protein sequence
Ligand SMILES
Outputs
Binding affinity in pKd, or a binary BBBP or protein-solubility classification.
