dataccaML & physics for drug discovery
Better binders, discovered in silico
datacca generates and ranks therapeutic binder libraries — peptides, small molecules, and nanobodies — against your target, combining ML models with physics-based molecular dynamics to optimize potency alongside the clinical properties (ADMET, immunogenicity) that decide what advances.
Modalities
3
Peptides · small molecules · nanobodies
Objectives
2
ADMET · immunogenicity
Ranking
ML + MD
Learned + physics-based ranking
From target to a ranked shortlist
ML-driven generation and physics-based simulation — a shortlist of developable binders before anything touches the bench.
In silico binder library design & ranking
We generate and rank libraries of peptides, small molecules, and nanobodies against your target, using ML models to push the Pareto frontier across potency and clinical properties — ADMET and immunogenicity — so the candidates you advance are developable, not just tight binders.
Physics-based binder ranking
We rank candidate binders against your target with physics-based molecular dynamics, grounding the shortlist in simulated structure and energetics before you commit wet-lab time.
Computation that de-risks discovery
We bring learned models and physics-based simulation together so the candidates that reach the bench are the ones most likely to advance.
Start a conversation
Tell us about your target and what "developable" means for your program. We'll get back to you within one business day.
Or email us directly at info@datacca.com.