ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
  • NVIDIA
    DSMBind
    Model
    NVIDIA
    DSMBind

    DSMBind is an energy-based model that has been trained on protein-ligand complexes to predict binding affinities. The model produces comparative values that are useful for ranking protein-ligand binding affinities.

    This model is backed by NVIDIA's Plus Plus (++) Promise
    to learn more about the quality of the datasets used to train this model.
    FieldResponse
    Intended Application(s) & Domain(s):Protein-Ligand Binding Affinity Prediction
    Model Type:Structural Biology for Drug Discovery
    Intended Users:This model is intended for developers or researchers who want to study protein-ligand binding.
    Outputs:A scalar value indicating the binding affinity
    Describe how the model works:This model takes a 3D protein-ligand complex structure as input and produces a scalar value with the learned model weights.
    Technical Limitations:This model produces only comparative values instead of absolute binding energy and may perform less well on non-crystal structures.
    Verified to have met prescribed NVIDIA standards:Yes
    Performance Metrics:Pearson correlation between the prediction values and ground truth binding affinities
    Potential Known Risks:Output value could lead to incorrect inference on binding affinity of a complex
    Licensing:https://www.apache.org/licenses/LICENSE-2.0