Loading…
Every biological foundation model, evaluated and ranked by the bio.rodeo team
Showing 1–24 of 392 filtered models
3D small-molecule generation conditioned on an interaction profile of shape, electrostatics and directional pharmacophores rather than a pocket.
De novo small-molecule generation conditioned on disease-reversal gene expression, with a contrastive transcriptome encoder steering a MolT5 decoder.
Pocket-conditioned 3D ligand generation for structure-based drug design, with variance-exploding diffusion that keeps generated geometry low-strain.
Retention time prediction for reversed-phase HPLC, trained on 179 chromatographic methods plus MD and DFT properties computed for 21,431 molecules.
Protein-sequence-conditioned mixture-of-experts language model that designs small molecules and emits an explicit synthesis route for each one.
Diffusion generator for 2D molecular graphs that blends spatial and spectral denoising branches under signal-to-noise-guided fusion weights.
Drug repurposing model that propagates transcriptional signatures through a pretrained graph autoencoder of the human protein interaction network.
Structure-based drug design model building 3D ligands atom by atom inside a protein pocket, with explicit hydrogens and fragment completion.
Drug-target interaction model that retains intermediate encoder states and probes them per atom and residue, so weak functional-group signals persist.
Compound-protein interaction model fusing bilinear attention over atoms and residues with cross-attention over ESM-2 and ChemBERTa sequence features.
Pretrained atomic representation of non-canonical amino acids, scoring binding affinity, selectivity and cell permeability of therapeutic peptides.
Pocket-conditioned 3D ligand generator that steers flow matching with LLM-written chemical priors, for de novo design and scaffold hopping.
Fragment-protein interaction model trained on cellular chemoproteomics, pairing ESM-2 residue embeddings with bilinear attention over ligand atoms.
Multi-task cellular foundation model predicting drug sensitivity, perturbation expression and drug-protein binding from one pretrained checkpoint.
NMR foundation model that turns 1D 1H spectra into reusable embeddings, with a shared encoder serving denoising, peak detection, and retrieval.
Sequence-only dual-encoder contrastive model that ranks whole molecule libraries against a protein target without 3D structures or per-pair scoring.
Molecular foundation model for drug discovery that masks entire data modalities and predicts their latent embeddings from the remaining ones.
Drug- and dose-conditioned latent transition predictor pretrained on the Tahoe-100M perturbation atlas and transferred frozen to tumor RNA-seq.
Protein-ligand co-folding model on the OpenFold3 architecture, trained on PDB structures through June 2025 with inference-time chemical steering.
Long-context co-folding model for protein, nucleic-acid and ligand assemblies, folding systems up to 16,384 residues on a single GPU.