Loading…
Every biological foundation model, evaluated and ranked by the bio.rodeo team
Showing 169–192 of 2336 models
Optical chemical structure recognition model that turns molecule images into SMILES, reaching 93.8% exact match on USPTO with full stereochemistry.
Multimodal microbiome foundation model pretrained on 1.8 million samples. Frozen representations transfer to biome classification and forecasting.
Antigen-specific antibody design model that conditions an ESM3 backbone on epitope geometry, then aligns CDR generation with calibrated DPO.
Molecule generation conditioned on single-cell transcriptomes, designing cell-type-specific compounds that revert diseased cell states.
Cell type annotation model mapping human single-cell and spatial transcriptomes onto one hierarchical typology of 381 types across 23 tissues.
Antibody CDR design model post-trained by on-policy distillation, cutting RAbD CDR-H3 backbone RMSD from 2.37 Å to 1.95 Å.
Self-supervised colorectal histopathology model turning H&E tiles into interpretable phenotype clusters and a disease-free survival risk score.
Protein language model for post-translational modifications, predicting PTM sites, types, and crosstalk across 40 modification classes.
RNA and single-stranded DNA 3D structure prediction from sequence alone, with no MSA or language-model inputs and roughly 100x cheaper inference.
Protein conformational ensemble generator and coarse-grained force field in one normalizing flow. Samples faster than diffusion-based baselines.
Spatial proteomics prediction from routine H&E slides, generating 21-channel virtual multiplex immunofluorescence maps of the tumor microenvironment.
Protein-ligand binding affinity prediction from sequence and SMILES, without MSAs. Coarse-grained cofolding runs over 10x faster than Boltz-2.
Distilled whole-slide pathology foundation model pairing a 22M-parameter ViT-S tile encoder with a LongNet slide encoder for cohort-scale analysis.
EEG foundation model turning a short dry-electrode session into quantitative brain-function metrics for psychiatric and neurological assessment.
Molecular representation learning from surface point clouds, 3D graphs, and fragment tokens. Cuts ESOL RMSE to 0.740 under scaffold splitting.
B-cell receptor DNA language model pretrained on antibody heavy-chain nucleotide sequences, with embeddings that outperform protein language models.
Protein language model pretrained on structural domain segments, encoding fold and contact signals for remote-homology detection from sequence alone.
Protein function captioning model fusing sequence, Foldseek structure tokens, and text through a BLIP-2 Q-Former for open-ended free-text annotation.
Mixed-modality metagenomic language model using bidirectional Mamba blocks to embed proteins within 20K tokens of coding and non-coding DNA.
m6A RNA modification site prediction across the transcriptome, using a CNN-Transformer hybrid to surface unannotated N6-methyladenosine sites.
Somatic mutation risk model predicting base-pair mutability from DNA sequence per COSMIC signature, separating passenger hotspots from cancer drivers.
Genomics foundation model that represents individual DNA fragments in a learned semantic space for cell-free DNA cancer detection and cell typing.