All Competitors

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

Showing 1–12 of 12 filtered models

  • Hybrid Gated Fusion

    2——
    University College LondonApril 17, 2026gated_fusiongo_term_predictionmultimodal+5

    A multimodal deep-learning framework that fuses sequence, structure, text, and interaction embeddings to predict Gene Ontology function annotations, reaching state of the art on CAFA3.

    Protein
    84Openness

  • BioReason-Pro

    1154—
    Arc Institute +3 othersMarch 20, 2026go_term_annotationlarge_language_modelmultimodal+5

    A multimodal reasoning LLM that fuses protein-language-model embeddings with biological context to generate interpretable reasoning traces for protein function and GO-term annotation.

    ProteinLanguage model
    58Openness

  • BioBridge

    —2—
    Tongji University +1 otherFebruary 4, 2026continual_learninglanguage_modelmultimodal+5

    A framework that bridges a protein language model and a general LLM via continual pretraining, giving large language models protein-domain reasoning without losing general capabilities.

    Language modelProtein
    13Openness

  • FoldVision

    ———
    Heinrich Heine University DüsseldorfJanuary 23, 2026cnndrug_discoveryenzymes+5

    A 3D CNN that voxelizes every heavy atom for rotation-robust protein structural representations, matching or beating protein language model encoders on function benchmarks.

    Protein
    20Openness

  • Evolla

    69227
    Westlake UniversityJanuary 6, 2025foundation_modellanguage_modelmultimodal+2

    An 80B-parameter multimodal protein-language model that decodes protein function through natural language dialogue, integrating sequence, structure, and evolutionary context.

    Protein
    67Openness

  • SeqProFT

    24—
    University of BirminghamNovember 18, 2024fine_tunedproperty_predictionprotein_function_prediction+3

    LoRA fine-tuning framework for ESM-2 with multi-head attention pooling and contact map enhancement for sequence-only protein property prediction across diverse tasks.

    Protein
    13Openness

  • Prot2Token

    3810—
    University of MissouriJune 3, 2024foundation_modelmulti_taskprotein_function_prediction+1

    A unified multi-task framework that converts diverse protein prediction tasks into autoregressive next-token prediction using pre-trained protein language model encoders.

    Protein
    13Openness

  • MULAN

    25107
    Skolkovo Institute of Science and TechnologyMay 30, 2024fine_tunedmultimodalproperty_prediction+4

    Multimodal protein language model extending ESM-2 and SaProt with a Structure Adapter that encodes backbone and side-chain torsion angles for improved function prediction.

    Protein
    83Openness

  • gLM

    8991—
    Harvard University +1 otherApril 3, 2024foundation_modelgenomicsmetagenomics+2

    Genomic language model trained on metagenomic scaffolds that learns protein co-regulation and function by modeling gene context and operon structure.

    DNA & Gene
    30Openness

  • DeepGO

    5899—
    Bio-Ontology Research GroupJanuary 1, 2024gene_ontologyprotein_function_prediction

    Deep learning method for protein function prediction using Gene Ontology annotations, combining protein language models with neuro-symbolic reasoning over GO axioms.

    Protein
    63Openness

  • SaProt

    6053153.2K
    Westlake UniversityOctober 1, 2023foundation_modelprotein_function_predictionstructure_prediction+1

    Protein language model combining amino acid and Foldseek 3Di structural tokens, outperforming ESM-2 across 10 downstream tasks including mutation effect prediction.

    Protein
    91Openness

  • ESM-GearNet

    11454—
    MilaMarch 11, 2023foundation_modelgraph_neural_networkprotein_function_prediction+1

    A joint sequence-structure representation learning framework combining ESM-2 protein language model embeddings with GearNet geometric graph neural networks.

    Protein
    30Openness