All Competitors

Every biological foundation model, evaluated and ranked by the bio.rodeo team

Showing 114 of 14 filtered models

  • ATOMICA

    3
    Harvard UniversityMarch 16, 2026binding_site_predictionfoundation_modelgraph_neural_network+6

    Geometric deep learning model that learns atomic-scale representations of molecular interfaces across proteins, small molecules, and nucleic acids.

    ProteinSmall moleculeRNA
    88Openness
  • MolChord

    2
    Beijing Zhongguancun Academy +1 otherOctober 31, 2025de_novo_designdiffusiondrug_discovery+4

    Structure-based drug design model that generates ligands for a protein pocket, pairing a diffusion structure encoder with preference optimization.

    Small moleculeProtein
    23Openness
  • PairMixer

    334
    Genesis Therapeutics +1 otherOctober 21, 2025molecular_dockingprotein_designrepresentation_learning+3

    Structure prediction backbone that swaps AlphaFold3-style triangle attention for triangle multiplication, cutting compute without losing accuracy.

    ProteinSmall molecule
    77Openness
  • PUMBA

    1
    Florida International UniversityOctober 19, 2025protein_protein_interactionrepresentation_learningstate_space_model+2

    Protein-protein docking scorer that ranks interface poses from image-encoded patches, swapping PIsToN's Vision Transformer for Vision Mamba.

    Protein
    20Openness
  • Matcha

    325
    AIRI Institute +1 otherOctober 16, 2025binding_pose_predictiondrug_discoveryflow_matching+3

    Molecular docking model that predicts protein-ligand binding poses with multi-stage Riemannian flow matching, yielding physically valid geometry.

    Small moleculeProtein
    23Openness
  • FoldMatch

    11
    RCSB Protein Data Bank +1 otherMarch 6, 2025embeddingsrepresentation_learningstructural_biology+2

    Protein structure embedding model that compresses each 3D fold into a single fixed-length vector for proteome-wide similarity search and clustering.

    Protein
    23Openness
  • Chan Zuckerberg InitiativeFebruary 1, 2025cnncryo_etparticle_picking+3

    Cryo-ET particle picking model that averages tiny, medium, and large 3D U-Nets pretrained on simulated tomograms and fine-tuned on experimental data.

    Imaging
    86Openness
  • Chan Zuckerberg InitiativeFebruary 1, 2025cnncryo_etparticle_picking+3

    Cryo-ET particle picking ensemble of three 3D segmentation models predicting particle-center heatmaps with ResNet50d and EfficientNetV2-M backbones.

    Imaging
    95Openness
  • TopCUP

    3
    Chan Zuckerberg InitiativeFebruary 1, 2025cnncryo_etparticle_picking+3

    Cryo-ET particle picking model, an ensemble of 3D U-Nets with EfficientNet encoders that finds protein complexes in tomograms by heatmap segmentation.

    Imaging
    96Openness
  • BPD

    2
    Chan Zuckerberg InitiativeFebruary 1, 2025cnncryo_etparticle_picking+3

    Cryo-ET particle picking model that localizes six protein complexes in tomograms using an ensemble of lightweight 3D U-Nets.

    Imaging
    67Openness
  • Octopi

    13
    Chan Zuckerberg InitiativeJanuary 1, 2025cnncryo_etparticle_picking+3

    Cryo-ET particle picking model that localizes and classifies multiple protein complexes in a tomogram with a single 3D U-Net forward pass.

    Imaging
    81Openness
  • SABER

    18
    Chan Zuckerberg InitiativeJanuary 1, 2025cryo_etfoundation_modelsegmentation+3

    Cryo-ET segmentation framework adapting SAM2 to vesicles and membrane-bound compartments in tomograms and 2D micrographs, zero-shot or fine-tuned.

    Imaging
    78Openness
  • CryoLens

    19
    Chan Zuckerberg InitiativeJanuary 1, 2025cnncryo_etgenerative+6

    Variational autoencoder that learns interpretable representations of protein subtomograms from cryo-ET, trained on 5.8 million synthetic particles.

    Imaging
    74Openness
  • Cryo-IEF

    73
    Westlake UniversityNovember 6, 2024contrastive_learningcryo_emfoundation_model+3

    Cryo-EM foundation model pre-trained on 65 million particle images, enabling zero-shot classification, pose clustering, and quality assessment.

    Imaging
    42Openness