Tamarind Scoring Tool

Every score described below can be accessed as part of the Protein Scoring tool, which lets a given (potentially large) set of protein sequences for any number of properties.

Antibody Developability Properties

General Developability

Therapeutic Antibody Profiler (TAP): TAP compares structural metrics of an antibody to known therapeutic antibodies. While the tool itself does not have code available, we’ve reproduced its methodology in our tool to calculate Patches of Surface Hydrophobicity (PSH), Patches of positive charge (PPC), Patches of negative charge (PNC), Structural Fv charge symmetry, and CDR length. We’ll flag any antibodies outside the typical range for therapeutic antibodies.

Immunogenicity

We offer DeepImmuno for Class I Immunogenicity and TLimmuno for Class II Immunogenicity. These tools take every possible n-mer peptide in your protein and assess its response with every HLA allele. You’ll be able to see the maximum and average score for each peptide, as well as the allele where it achieved its maximum.

Characterization

Solubility

We recommend using NetSolP for fast, sequence-based solubility prediction. That said, solubility should usually be optimized after primary metrics like binding affinity or selectivity. If you already have experimental solubility data, our ESM finetuning tool can be trained on it to learn what features drive solubility in your specific context, enabling more tailored predictions.

Stability

ThermoMPNN has been found to find stabilizing point mutations. DeepStabP predicts melting point.

Aggregation

AggreScan3D is a useful tool for identifying aggregation-prone regions within a sequence, helping guide design decisions such as introducing solubilizing mutations or avoiding exposed hydrophobic patches.

Enzyme Activity

We offer DLKcat and CatPred to predict activity of a protein given a protein sequence and smiles substrate. You can also try one of our protein/small molecule docking tools to use binding affinity as a proxy for activity.