Amiti is our molecular embedding model for discovery teams. It supports small molecules, peptides, and antibodies in one workflow, and it includes drug-likeness signals early in screening.
Amiti is the internal model behind AgentCures. It maps proteins, ligands, and assay context into a shared representation so we can compare candidates consistently across projects.
Instead of maintaining separate models for each task, we use one core model and adapt the same embedding space to ranking, filtering, and prioritization. That keeps decisions easier to interpret and reduces handoff friction.
Traditional virtual screening gives you a list of binders. That is useful, but it is not enough. Many binders fail later because of exposure, safety, or metabolism. Amiti is designed to rank for both binding and developability from the start.
Amiti can run very large batches quickly, so teams can explore broad chemical space without enterprise-level budgets.
Amiti factors ADMET signals into screening so you can avoid spending time on compounds that look strong early but fail basic drug-likeness checks.
By scoring potency and developability together, Amiti helps teams prioritize candidates that are more realistic to move forward.
We focus on EF@1%, or enrichment factor in the top 1% of ranked candidates. A score of 1x means a model is acting like random selection. Higher is better, because discovery teams spend most of their time on the very top of the list. On the public comparisons shown here, Amiti-3 beats GNINA on both screening benchmarks and extends beyond docking into ADMET-aware ranking.
Many drug discovery models are built for only one modality. Amiti uses one shared representation so teams can work across small molecules, peptides, and antibodies without switching tools.
This means Amiti can screen small molecules against a protein target one moment, then evaluate peptide binders or score antibody candidates the next, all within the same framework.
In practice, this reduces context switching for scientists and makes it easier to compare candidates fairly across modalities.
Amiti is not limited to one benchmark task. It provides a consistent representation across targets and modalities.
The encoder architecture supports very large screens while keeping runtime and cost manageable for applied teams.
Small molecules, peptides, and antibodies are handled in one model. No more stitching together separate tools for different modalities.
Drug-likeness is considered during screening so teams can focus on candidates that are more likely to progress.
Amiti powers target ranking, virtual screening, and lead prioritization in the AgentCures workflow.
The focus is not on demos. The model is tuned for day-to-day discovery work where ranking quality and throughput both matter.
Amiti is the model behind the AgentCures platform. If you want to evaluate it for your discovery workflow, get in touch.