Loading…
Every biological foundation model, evaluated and ranked by the bio.rodeo team
Showing 745–768 of 1004 filtered models
Structure-based molecule optimization that steers a Bayesian flow network with property gradients over 3D coordinates and atom types at once.
Predicts protein properties from sequence alone by LoRA fine-tuning ESM-2 and ESM-C backbones, with contact maps biasing attention pooling.
Prompt-guided protein sequence design conditioned on 3D backbones, fold blueprints, and functional tags. 63.21% native sequence recovery on CATH.
Protein function prediction from 3D structure and sequence, assigning Gene Ontology terms with an ensemble built around rare long-tail terms.
Macrocyclic peptide binder design against protein targets, cyclizing a diffusion backbone generator's positional encoding so it closes rings.
Peptide-spectrum match rescoring for DDA proteomics, learned end to end from raw MS2 spectra and peptide sequence across 271 million PSMs.
Immune protein structure prediction for TCRs, antibodies, and nanobodies. Adapts ESMFold with LoRA, reaching 1.31 Å RMSD on the CDR3-beta loop.
Missense pathogenicity prediction that folds wild-type and mutant sequences with ESMFold and encodes each structure as a graph autoencoder embedding.
Sparse autoencoders on ESM-2 embeddings that expose thousands of interpretable features per layer, tied to binding sites, motifs, and domains.
De novo atomic model building from cryo-EM density maps, adapting AlphaFold2 with local attention and a 3D rotary position embedding.
DIA proteomics scoring model that identifies and quantifies peptide precursors, pretrained across 952 mass spectrometry runs instead of one.
Text-guided protein design that generates functional sequences from natural language prompts through a contrastive protein-text embedding space.
Antibody-antigen binding affinity prediction and sequence optimization, pre-trained on 7.5 million quantitative yeast-display affinity measurements.
Protein language models that split translated algal genomes into real genes and contaminants, classifying the dark proteome without homology search.
De novo enzyme design conditioned on the reaction to be catalysed: substrate and product SMILES in, catalytic pocket, enzyme, and docked complex out.
Generative masked protein language model with an interpretable concept layer, letting designers set 718 biophysical and annotation concepts directly.
Antibody language model that generates paired heavy and light variable domains, with a developability-conditioned variant for manufacturable designs.
Controllable protein sequence generator adapted from Llama-3-8B with LoRA, prompted in plain English to emit enzymes from ten property classes.
Pocket-conditioned 3D ligand generator trained on its own predicted conformations, closing the train-inference gap that degrades diffusion sampling.
Compact protein sequence generator adapted from Phi-3-mini with LoRA, emitting enzymes for ten named property classes from a plain-English prompt.
Two-stage backbone generator that designs protein domains separately, then weaves them into one long chain with an SE(3) diffusion assembly module.
Intrinsic disorder prediction from protein sequence at proteome scale, distilling consensus disorder scores and AlphaFold2 pLDDT into one network.
Aligns structure, binding-pocket, text and molecular-dynamics encoders to a protein sequence anchor, giving frozen embeddings that transfer widely.