AlphaFold 2 / 3
The model that solved the 50-year protein-folding problem.
Evidence4/7 evidence fields documented
AccessLimited open access
ComputeGPU / managed server
BenchmarkCASP14 / complex evaluations
Genomic Foundation Models
Genomic foundation models can learn sequence representations and generative patterns, but biological function, causality and safety require separate evidence. BioAtlas preserves those boundaries.
Curated model passports
33 relevant BioAtlas records.
Open evidence passport →
RoseTTAFold / All-Atom
The three-track network that followed folding into all-atom space.
Evidence4/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkCASP14 / complex modelling
ESMFold
Structure from a single sequence — no alignment required.
Evidence3/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkNot yet curated
RFdiffusion
Diffusion models that hallucinate brand-new proteins.
Evidence5/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkExperimental binder validation
ProteinMPNN / LigandMPNN
Given a shape, design the sequence that folds into it.
Evidence3/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkNot yet curated
ESM3
A generative model that reasons over sequence, structure & function at once.
Evidence4/7 evidence fields documented
AccessLimited open access
ComputeGPU / hosted service
BenchmarkGenerative protein evaluations
Evo / Evo 2
A genomic foundation model that reads and writes DNA at scale.
Evidence4/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkGenomic sequence evaluations
AlphaGenome
Reading the genome's 'dark matter' at base-pair resolution.
Evidence2/7 evidence fields documented
AccessLimited open access
ComputeGPU recommended
BenchmarkNot yet curated
Enformer
Transformers that predict gene expression from raw sequence.
Evidence2/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkNot yet curated
AlphaMissense
Classifying which missense mutations cause disease.
Evidence2/7 evidence fields documented
AccessLimited open access
ComputeGPU recommended
BenchmarkNot yet curated
Nucleotide Transformer
BERT-style foundation models for the human genome.
Evidence3/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkNot yet curated
Geneformer
A transfer-learning foundation model of gene networks.
Evidence2/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkNot yet curated
HyenaDNA
Long-context genomics without attention's quadratic cost.
Evidence3/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkNot yet curated
BigRNA
An RNA foundation model for oligonucleotide therapeutics.
Evidence1/7 evidence fields documented
AccessProprietary
ComputeVendor managed
BenchmarkNot yet curated
Absci — Integrated Drug Creation
Generative de novo antibody design fused with wet-lab scale.
Evidence1/7 evidence fields documented
AccessProprietary
ComputeManaged platform or GPU
BenchmarkNot yet curated
IgLM / AntiBERTy
The antibody-specific language models many tools build on.
Evidence4/7 evidence fields documented
AccessOpen source
ComputeManaged platform or GPU
BenchmarkAntibody sequence evaluations
BigHat Biosciences — Milliner
Closing the ML–wet-lab loop for antibody engineering.
Evidence1/7 evidence fields documented
AccessProprietary
ComputeManaged platform or GPU
BenchmarkNot yet curated
Basecamp Research (EDEN / BaseFold)
Biodiversity-scale data as the fuel for better bio-models.
Evidence1/7 evidence fields documented
AccessLimited open access
ComputePlatform dependent
BenchmarkNot yet curated
Cradle Bio
Generative protein engineering for any wet lab.
Evidence1/7 evidence fields documented
AccessProprietary
ComputePlatform dependent
BenchmarkNot yet curated
Isomorphic Labs (IsoDDE)
AlphaFold's spin-off, aiming to 'solve all disease'.
Evidence1/7 evidence fields documented
AccessProprietary
ComputeVendor managed
BenchmarkNot yet curated
Generate:Biomedicines
Generative biology turned into a clinical-stage pipeline.
Evidence1/7 evidence fields documented
AccessLimited open access
ComputeVendor managed
BenchmarkNot yet curated
RFantibody
De novo epitope-specific antibody design from the RFdiffusion lineage.
Evidence4/7 evidence fields documented
AccessLimited open access
ComputeGPU recommended
BenchmarkExperimental antibody design
ESM-2
A foundational protein language model for residue- and sequence-level representations.
Evidence4/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkProtein representation and structure evaluations
ProtT5
A widely used protein Transformer for transferable sequence embeddings.
Evidence1/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkNot yet curated
MegaMolBART
A BART-style chemical language model for molecular embeddings and generation.
Evidence1/7 evidence fields documented
AccessLimited open access
ComputeGPU recommended
BenchmarkNot yet curated
DNABERT-2
A BERT-style genomic foundation model with efficient DNA tokenization and multi-species pretraining.
Evidence4/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkGenomic downstream tasks
Caduceus
Reverse-complement-equivariant bidirectional long-range DNA modelling.
Evidence4/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkLong-range genomic benchmarks
GROVER
A genomic foundation model for transferable DNA representations.
Evidence1/7 evidence fields documented
AccessLimited open access
ComputeGPU recommended
BenchmarkNot yet curated
Borzoi
DNA-to-RNA regulatory modelling across cell and tissue contexts.
Evidence4/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkFunctional-genomics and RNA-seq evaluations
RiNALMo
A large RNA language model for transferable nucleotide representations.
Evidence4/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkRNA downstream and structure tasks
RNA-FM
A foundational BERT-style model for non-coding RNA sequence representations.
Evidence2/7 evidence fields documented
AccessOpen source
ComputeGPU recommended
BenchmarkNot yet curated
UNI-RNA
A 400M-scale encoder foundation model for RNA representation.
Evidence1/7 evidence fields documented
AccessLimited open access
ComputeGPU recommended
BenchmarkNot yet curated
LucaOne
A unified biological foundation model spanning DNA, RNA and protein sequence.
Evidence3/7 evidence fields documented
AccessLimited open access
ComputeGPU recommended
BenchmarkDNA/RNA/protein downstream tasks
How to interpret this topic
Choose by context of use.
Inputs matter
Sequence, structure, ligand, assay and single-cell inputs imply different data-quality and preprocessing assumptions.
Outputs are not interchangeable
A predicted pose, confidence score, affinity estimate, generated sequence and perturbation profile support different decisions.
Benchmarks are protocol-bound
Claims should only be compared when task, dataset, split, metric and evaluation protocol genuinely align.
Validation remains external
BioAtlas records evidence boundaries; prospective scientific and experimental validation is still required for consequential use.