Products
Find the right model or tool for your drug discovery work.
AI/ML models and tools available now on TuneLab
AbLab v1, v2
Predicts antibody developability across 22 endpoints, including stability, aggregation, and solubility, from sequence alone.
Antibody-Antigen Binding Affinity (ΔΔG)
TuneLab’s Antibody–Antigen Binding Affinity model predicts how a specific mutation changes binding affinity between an antibody and its antigen.
ChemLab v1, v2 Federated
Predicts ADMET and physicochemical properties to help prioritize compounds for synthesis.
Immunogenicity Model (MHC-II Peptide Presentation)
Predicts MHC class II presentation likelihood and 9-mer binding cores for antibody peptides across 12 HLA-DRB1 alleles.
in vivo PK (developed by insitro)
Predicts preclinical in vivo PK, including clearance and Vss, across multi species, developed by insitro for Lilly.
NanoLab (VHH Developability)
Predicts five biophysical developability endpoints for VHH nanobody sequences to rank leads before wet lab testing.
Small Molecule Computational Workflows
Configurable workflows that generate, filter, score, predict properties and rank small molecules to automate drug discovery campaigns.
TuneLab’s Antibody–Antigen Binding Affinity model predicts how a specific mutation changes binding affinity between an antibody and its antigen. Given the structure of the complex, the parent sequence, and the variant sequence being scored, it returns the predicted difference in binding between parent and variant, together with an uncertainty estimate. It is built on an inverse-folding protein backbone and trained on computationally generated labels. It is designed for protein engineers running affinity maturation and optimization campaigns who need to rank a set of variants before committing to expression and characterization.
Rank-ordering of point and multi-point variants against a fixed parent within an engineering campaign, using either a crystal structure or a predicted complex.
A per-variant uncertainty estimate alongside the point prediction. This carries signal of its own and, in parent-relative campaigns, often helps separate binders from non-binders better than the point prediction does.
Structure-based scoring that needs no mutant structure and no per-target retraining, so it applies across new targets without modification.