Redefine feasibility in medicine


Traditional targets

  • Deep pockets with clear geometric constraint
  • Easy to design
  • Low-hanging fruit mostly gone

Undruggable targets

  • Large, flat and highly hydrophobic
  • Extremely difficult even for hit finding
  • Potential to address high unmet medical needs

Leverage AI to generate customized chemical space better suited for challenging targets

Pinpointing superior molecules with unrivaled affinity insights, empowered by AI-enhanced sampling and target-centric parameterization

Orchestrating complex scientific workflows to transform connectivity into intelligent insight

Research

  • FeaSynth

    Highlight: FeaSynth integrates an Expert Encoding Scheme with 145 annotated reaction templates to resolve critical chemical conflicts and significantly outperform… read more

  • scNext

    Highlight: scNext is a generative foundation model that transforms static single-cell data into predictive temporal sequences, enabling the forecasting of… read more

  • ΔPSA

    Highlight: Cost-Effective Prediction of Macrocyclic Peptide Permeability via Dynamic Conformational Analysis We introduce a computationally efficient molecular dynamics framework that… read more

Be the Change. Join Anew.