Model type
Sequence-search and folding pipeline
Pipeline
ColabFold
ColabFold packages sequence-search and protein-folding workflows for notebooks and local batch prediction.
Sources
sokrypton/ColabFold: README.md · README.md: notebook table and FAQHow it worksColabFold workflow
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Sources
sokrypton/ColabFold: README.md · README.md: notebook table and FAQAt a glance
Inputs
Protein sequences, optionally templates and the selected alignment procedure.
Sources
sokrypton/ColabFold: README.md · README.md: notebook table and FAQOutputs
Predicted structures and confidence outputs from the chosen underlying folding model.
Sources
sokrypton/ColabFold: README.md · README.md: notebook table and FAQSource reviewed · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 0 evaluations · 0 metric rows. Different protocols are not a single leaderboard.
No evaluations linked in this release.
How it works
How it works
ColabFold packages sequence-search and protein-folding workflows for notebooks and local batch prediction. A prediction pipeline that can combine MMseqs2 alignments with AlphaFold-family or other folding models; it is not a single neural architecture. The documented inputs are protein sequences, optionally templates and the selected alignment procedure. The output consists of predicted structures and confidence outputs from the chosen underlying folding model.
Sources
sokrypton/ColabFold: README.md · README.md: notebook table and FAQVersions and reproducibility
README identifies ColabFold 1.6.3 and separately lists AlphaFold2, OpenFold3, ESMFold and beta notebooks. Hardware- and predictor-dependent. The README gives approximate 16GB-GPU guidance, not a universal model context.
Sources
sokrypton/ColabFold: README.md · README.md: notebook table and FAQStrengths and limitations
Strengths supported by sources
- Notebook and batch interfaces make several folding workflows available with documented input choices.
Sources
sokrypton/ColabFold: README.md · README.md: notebook table and FAQ
Limitations and conditions
- The repository distinguishes supported, beta and retired notebooks. GPU memory limits and MSA-server usage policies apply; the underlying predictor and database version must be named in a benchmark.
Sources
sokrypton/ColabFold: README.md · README.md: notebook table and FAQ
Profile review details
Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.
Stable record: discovery-model-colabfoldSpecifications
Inputs, training, access and other details
Explanatory profile: source reviewed · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Sequence-search and folding pipelineSourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Architecture | A prediction pipeline that can combine MMseqs2 alignments with AlphaFold-family or other folding models; it is not a single neural architecture.Sourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Inputs | Protein sequences, optionally templates and the selected alignment procedure.Sourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Outputs | Predicted structures and confidence outputs from the chosen underlying folding model.Sourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Parameters | Depends on the underlying folding model; no single ColabFold parameter total.Sourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Known versions | README identifies ColabFold 1.6.3 and separately lists AlphaFold2, OpenFold3, ESMFold and beta notebooks.Sourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Training data | ColabFold assembles existing prediction models and search databases; their provenance must be recorded separately.Sourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Training cutoff | Inapplicable as one pipeline-wide date: the selected folding weights and the MSA/template databases have separate releases and cutoffs. · Not applicableSourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Context limits | Hardware- and predictor-dependent. The README gives approximate 16GB-GPU guidance, not a universal model context.Sourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Weights licence | Each underlying model has its own weight licence; repository code terms do not replace those licences.Sourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Access | Official project documentation and implementation: https://github.com/sokrypton/ColabFoldSourcessokrypton/ColabFold: README.md · README.md: notebook table and FAQ |
| Code licence | MITSourcessokrypton/ColabFold: LICENSE · LICENSE: licence text |
Applicable tests and references
Applicability is distinct from a completed evaluation.
- CASP · Proposed association
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
20 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram steps ["Protein sequences","Selected alignment search","Selected folding model","Structure and confidence"] Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram title ColabFold workflow Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Model type Sequence-search and folding pipeline Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Architecture A prediction pipeline that can combine MMseqs2 alignments with AlphaFold-family or other folding models; it is not a single neural architecture. Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Access Official project documentation and implementation: https://github.com/sokrypton/ColabFold Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Code licence MIT Individual claims | sokrypton/ColabFold: LICENSE LICENSE: licence text Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Inputs Protein sequences, optionally templates and the selected alignment procedure. Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Outputs Predicted structures and confidence outputs from the chosen underlying folding model. Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Parameters Depends on the underlying folding model; no single ColabFold parameter total. Individual claims | sokrypton/ColabFold: README.md README.md: notebook table and FAQ Version: 84c27d9cc500489fd9b97545d2325b9d00f251d5 | source checked automated source review · 2026-09-16 Audit detailsInspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: discovered
3 source records and release history
- sokrypton/ColabFold official source · Original source · 84c27d9cc500489fd9b97545d2325b9d00f251d5
- sokrypton/ColabFold: README.md · Original source · 84c27d9cc500489fd9b97545d2325b9d00f251d5
- sokrypton/ColabFold: LICENSE · Original source · 84c27d9cc500489fd9b97545d2325b9d00f251d5
Technical metadata and extraction receipts
Stable ID: discovery-model-colabfold
- areas
- protein-structure
- access
- official_source_linked
- benchmark applicability
- candidate; not evidence of a reported evaluation
- candidate benchmark ids
- discovery-benchmark-casp
- entity level
- method
- reported name
- ColabFold
- version
- Not reported
- historical missing metadata
- checkpoint: unextracted; code licence: unextracted; parameters: unextracted; training cutoff: unextracted; training data: unextracted; version: unextracted; weights licence: unextracted
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This record identifies a composed analysis workflow with separately identifiable upstream models, representations or tools and a downstream prediction/scoring procedure. Results belong to that complete composition rather than to an upstream model alone.; source ids: evidence-official-efc93d867cbf62e80ebb; source locator: README.md: notebook table and FAQ; ambiguities: None recorded
Related records
- applicable to: CASP