Loading…
Every biological foundation model, evaluated and ranked by the bio.rodeo team
Showing 985–1008 of 2565 models
Protein stability predictor scoring ΔΔG for point mutations by fusing ESM-2 embeddings with ProteinMPNN backbone geometry. Wet-lab validated.
De novo transmembrane protein design by joint all-heavy-atom sequence and structure diffusion, validated by a 1.7 A crystal structure.
Medical image grounding model that localizes text phrases in CT, MRI, X-ray, ultrasound, endoscopy, dermoscopy, and fundus images.
All-atom structure prediction for arbitrary biomolecular complexes of proteins, nucleic acids, and ligands, with code and weights under a BSD license.
Structure-based virtual screening that rescores docking poses with a deep learning model, reaching 2.6x the enrichment factor of AutoDock Vina.
Structure-based drug design pipeline generating 3D molecules in binding pockets, raising zero-shot CrossDocked2020 docking success from 53% to 64%.
Blind protein-ligand docking model adding Ollivier-Ricci curvature descriptors and degree-aware message passing, predicting poses in 0.09 seconds.
Cas9 PAM preference prediction from protein sequence with an ESM-2 backbone, extending PAM annotation to 50,308 metagenome-mined orthologs.
Single-cell ATAC-seq foundation model pretrained on 2.8 million cells across 1.15 million chromatin regions via masked peak reconstruction.
Single-cell transcriptomics model fine-tuned on 1.12M CAR-T profiles to annotate T cell subtypes and predict therapy response and neurotoxicity.
Mammography report generation model, a LoRA adaptation of MedGemma-4B-it that writes narrative radiology reports carrying BI-RADS assessments.
De novo protein design model that co-generates sidechains, backbone, and sequence in one flow-matching process instead of backbone only.
Histology vision transformer with 80M parameters that predicts spatial gene expression from H&E tissue images and transfers to tumor detection.
Retinal OCT vision-language model that writes layer-by-layer clinical summaries and assigns six-class disease labels from a single B-scan.
Red blood cell morphology foundation model pretrained on 1.25 million single-cell crops, released as small, base, and large ViT feature extractors.
Multi-sequence MRI foundation model pretrained on 336,476 volumetric scans, ranking first on 41 of 44 downstream clinical benchmarks.
Tri-modal contrastive model aligning protein structure, sequence, and text in a shared space for zero-shot cross-modal retrieval and classification.
Model quality assessment network predicting per-residue lDDT, CAD-score, and RMSD for protein loops in predicted and designed structures.
RNA language model transfer-trained from ESM-2 via a pseudo-protein alphabet mapping, outperforming 12 RNA language models in zero-shot evaluation.
Single-cell perturbation prediction by conditional flow matching, using one cell-type-conditioned model in place of a separate model per cell type.
Brain MRI model for noninvasive IDH genotyping of glioma, adapting a pretrained SWIN-UNETR backbone to reach 90.6% AUC on an external cohort.
Gram-negative bacterial effector prediction refining frozen ESM-1b embeddings with a mixture of convolutional experts and a transformer.
Blind flexible protein-ligand docking model trained by two-player self-play, predicting bound ligand and pocket poses in 0.32 seconds per complex.