AlphaFold3 Alignment Library
A growing OSDF-hosted library of reusable AlphaFold3 multiple sequence alignments for structure prediction workflows.
As of …
— alignments cached
Representing — unique protein sequences
Annotated across — source organisms
Including — community-contributed records
With — queries today
Running AlphaFold2 at scale can be challenging because jobs often spend a long time preparing inputs before structure prediction begins, including searching large reference databases to build alignments. The AlphaFold3 Alignment Library helps reduce this repeated work by allowing compatible OSPool workflows to reuse precomputed alignments when they are already available.
What is the AlphaFold3 Alignment Library?
The AlphaFold3 Alignment Library is a shared index and OSDF namespace for precomputed multiple sequence alignments (MSAs) that can be reused by cache-aware AlphaFold3 workflows running on the OSPool. The initial focus is protein-chain unpaired MSAs in A3M format, which are the alignment artifacts most useful for skipping repeated CPU-heavy sequence search work before GPU inference.
Each record links a normalized protein sequence hash to an alignment file, its OSDF/Pelican location, checksum, source, size, sequence count, and provenance metadata about how the alignment was generated.
Rollout note: This library is currently being grown and tested as cache-aware AlphaFold3 workflows are introduced on the OSPool. If you are interested in using or contributing to the library, please contact [email protected].
Search the library
Check whether the library already holds alignments for your protein chains. Paste one or more sequences below in FASTA format (a >name header followed by the sequence) or simply one sequence per line — or drag and drop FASTA file(s) onto the form — then search. Sequences are hashed in your browser and only the hashes are sent to the registry, so the sequences themselves never leave your computer.
Why cache alignments?
AlphaFold3 workflows often spend substantial CPU time in the data pipeline searching large sequence databases to build MSAs. The alignment library reduces duplicated work by allowing those precomputed alignments to be reused when the sequence, source, and provenance are appropriate for the user’s workflow.
- Faster cache-aware runs — jobs that find an acceptable cached MSA can skip part or all of the repeated sequence-search stage.
- Lower CPU and storage pressure — repeated database searches are replaced with OSDF/Pelican reads of smaller artifacts.
- Reproducibility and provenance — cached records include source and checksum metadata.
- Community reuse — every validated contribution can make later structure-prediction workflows faster for researchers.
Current scope
| Primary artifact | Protein-chain unpaired MSA files in A3M format. |
|---|---|
| Cache key | Normalized protein sequence hash, with one or more alignment records allowed per sequence when sources or provenance differ. |
| Distribution | Alignment files are stored in an OSDF namespace and retrieved through Pelican-aware clients or normal OSDF access patterns. |
| Registry metadata | Sequence identifier, source, OSDF URI, checksum, size, number of aligned sequences, timestamps, and generation/provenance fields. |
| Sources | OSPool-generated AlphaFold3 data-pipeline outputs, curated imported alignment sets, and validated institutional or community contributions. |
| Organism information | Derived from source metadata when available. Organism counts describe annotated source organisms, not a guarantee that each sequence is organism-unique. |
How can I contribute alignments?
Contributing to the library is as easy as running AlphaFold3 using the OSG-provided workflow on your own sequences. Caching of alignments happens automatically when you run the workflow on the OSPool, and your generated alignments will be added to the library’s registry and made available for reuse.
Already have a set of pre-computed alignments you’d like to share? Connect with a Facilitator at [email protected]
Powered by Pelican Platform
Operated by PATh