bbioptimus/h-optimus/0/embed
Create pooled tile-level histopathology representations with the 1.1B-parameter H-optimus-0 vision transformer trained on H&E-stained whole-slide image tiles.
Open biological models and first-party primitives, served for production through one API.
Explore the labs powering models on Rafflesia
Create pooled tile-level histopathology representations with the 1.1B-parameter H-optimus-0 vision transformer trained on H&E-stained whole-slide image tiles.
Build a deterministic, content-addressed, unpaired protein MSA with the current or an explicitly pinned generic configuration.
Build the full AlphaFold 2 UniRef90, BFD plus UniRef30, and MGnify MSA through immutable Tomato releases.
Build one AlphaFold-Multimer component MSA with full AF2 unpaired lanes and an immutable UniProt pairing-source lane.
Build AlphaFold 3 UniRef90, Small BFD, MGnify, and UniProt MSA inputs through immutable Tomato releases.
Build complete per-chain Boltz key-sequence CSV inputs and a ready-to-use ZIP bundle from immutable Tomato releases.
Build per-chain Chai aligned-Parquet inputs and a ready-to-use ZIP bundle from immutable Tomato releases.
Build ColabFold-compatible UniRef30 and environmental query-anchored alignments through immutable Tomato releases.
Materialize genomic representations from explicit sequence inputs and model releases.
Create tile-level representations from H&E histopathology images.
Search immutable protein corpora with reproducible releases and alignment evidence.
Complete a partially specified protein across sequence, structure, and function tracks at once.
Build query-anchored alignments and paired assemblies against pinned database releases.
Build a deterministic, content-addressed, unpaired protein MSA with the current or an explicitly pinned generic configuration.
Build the full AlphaFold 2 UniRef90, BFD plus UniRef30, and MGnify MSA through immutable Tomato releases.
Build one AlphaFold-Multimer component MSA with full AF2 unpaired lanes and an immutable UniProt pairing-source lane.
Build AlphaFold 3 UniRef90, Small BFD, MGnify, and UniProt MSA inputs through immutable Tomato releases.
Build complete per-chain Boltz key-sequence CSV inputs and a ready-to-use ZIP bundle from immutable Tomato releases.
Build per-chain Chai aligned-Parquet inputs and a ready-to-use ZIP bundle from immutable Tomato releases.
Build ColabFold-compatible UniRef30 and environmental query-anchored alignments through immutable Tomato releases.
Build one generic MSA per distinct protein component and assemble deterministic cross-component row assignments without a predictor-specific compatibility claim.
Sample sequences from structures, residue constraints, temperatures, and seeds.
Create pooled or residue-level representations from protein sequences.
biohub/esmc/300m/embedCreate pooled or residue-level protein sequence representations with the compact ESM Cambrian model.
biohub/esmc/600m/embedCreate higher-capacity pooled or residue-level protein sequence representations with ESM Cambrian.
biohub/esmc/6b/embedCreate pooled or residue-level protein representations with the 6B-parameter ESM Cambrian checkpoint used as the frozen language-model backbone of ESMFold-2.
biohub/esm3/1.4b-open/embedCreate pooled or residue-level protein representations with the open 1.4B-parameter ESM3 checkpoint.
Create pooled or residue-level protein representations with the 6-layer, 8M-parameter ESM-2 checkpoint.
Create pooled or residue-level protein representations with the 12-layer, 35M-parameter ESM-2 checkpoint.
Sample nucleotide sequence continuations from an explicit prompt, length, and seed.
Score how plausible a whole sequence is under a genome or protein language model.
Fold proteins and biomolecular complexes from explicit sequences and molecular inputs.
biohub/esmfold/2-fast/foldPredict one small protein structure directly from sequence with the frozen ESMC 6B backbone and the inference-optimized, non-MSA ESMFold-2 Fast checkpoint.
boltz-community/boltz/2/foldPredict biomolecular complex structures and optional binding-affinity measurements through Rafflesia's durable prediction jobs in explicit query-only alignment mode.
biohub/esmfold/2/foldPredict protein monomer and complex structures directly from sequence or an optional MSA with ESMFold-2.
chaidiscovery/chai/1/foldPredict all-atom biomolecular complexes containing proteins, nucleic acids, ligands, and modified residues in explicit query-only alignment mode.
bytedance/protenix/v2/foldPredict all-atom protein, nucleic-acid, and ligand complex structures with the 464M-parameter Protenix v2 checkpoint in explicit query-only alignment mode.
google-deepmind/alphafold/2-monomer/foldPredict one protein chain with pinned AlphaFold2 parameters in deterministic single-sequence mode.
rosettacommons/rosettafold/3/foldPredict all-atom biomolecular structures with protein, nucleic-acid, ligand, and covalent-modification inputs in explicit query-only alignment mode.
biohub/esm3/1.4b-open/foldPredict a protein structure by decoding the ESM3 structure track from sequence with the open 1.4B-parameter checkpoint.
Measure substitution likelihoods with explicit scoring methods and reference windows.
biohub/esmc/300m/variant-effectsScore amino acid substitutions as ESM Cambrian masked marginals with the compact 300M checkpoint.
biohub/esmc/600m/variant-effectsScore amino acid substitutions as ESM Cambrian masked marginals with the 600M checkpoint.
biohub/esmc/6b/variant-effectsScore amino acid substitutions as ESM Cambrian masked marginals with the 6B-parameter checkpoint.
biohub/esm3/1.4b-open/variant-effectsScore amino acid substitutions with ESM3 masked marginals from the open 1.4B-parameter checkpoint.
arc-institute/evo2/7b-base/variant-effectsScore nucleotide substitutions and indels as Evo 2 delta log-likelihoods over an explicit reference window, with the window, strand policy, and reference likelihood returned alongside every score.