Inspect alignment artifacts for one human protein, or prepare native model inputs from one protein, multiple protein chains, sequences, or an existing model file. GreenFold prepares the reusable MSA evidence; structure prediction still runs in your model's own environment.
Inspect paired and unpaired A3Ms, retained STO sources, sequence variants, and alignment statistics.
Build a single-chain or multi-chain input from UniProt IDs, sequences and entities, or an existing model file.
Start here
Choose the model whose native input you want to build, then describe one protein or a multi-chain complex.
Prepared output
FASTA plus a staged precomputed-MSA tree for monomer or multimer execution.
Entities · MSA resolution · Native input · Run commands
Prepare AF2 input →Prepared output
AF3 JSON with paired and unpaired A3Ms staged for every protein chain.
Entities · MSA resolution · Native input · Run commands
Prepare AF3 input →Prepared output
Boltz YAML plus model-ready per-chain CSV MSAs and explicit fallback warnings.
Entities · MSA resolution · Native input · Run commands
Prepare Boltz input →Prepared output
Query JSON, runner YAML, and staged OpenFold3-oriented A3M files.
Entities · MSA resolution · Native input · Run commands
Prepare OpenFold3 input →Prepared output
Protenix JSON with normalized pairing and non-pairing alignments.
Entities · MSA resolution · Native input · Run commands
Prepare Protenix input →Don't need a model-specific bundle? Direct download MSA (A3M) →
API access
Both options are generated from the same OpenAPI contract. Choose the interface that fits your task.
How to use GreenFold
GreenFold prepares reusable alignment evidence for the model you selected. The original prediction software and its model weights remain unchanged.
What the service adds
GreenFold preserves how the alignments were produced, understands sequence edits, and translates the same evidence into the different pairing and input contracts used by modern structure-prediction models.
The indexed corpus comes from the AF3 protein-search route across UniRef90, MGnify, small BFD, and the UniProt paired-search channel. MMseqs2 is not substituted for JackHMMER in this primary precomputation.
The searches span four documented AF3-compatible channels: UniRef90, MGnify, small BFD, and the UniProt paired-search source. The current artifact index retains these channel identities but does not encode a database-release field for each artifact.
For an indexed target, the user retrieves and adapts existing evidence instead of waiting for four database searches to run again. Online work begins with artifact resolution, transformation, and model-specific packaging.
GreenFold recognizes substitutions, deletions, truncations, and short insertions, updates the requested protein sequence, and rewrites the corresponding query-relative MSA columns. Related constructs can therefore reuse the indexed search rather than launch a new one.
A paired.a3m download is not universally prediction-ready because each model
coordinates homologs differently. GreenFold prepares pairing according to the selected
model's input contract before native inference, rather than handing every predictor the
same file and assuming it will interpret the rows correctly. For example, Boltz requires
per-chain CSV alignments whose shared non-negative keys coordinate homologous rows across
chains; GreenFold constructs this representation from the indexed paired and unpaired A3Ms.
User-facing guides for API usage and model workflows.