Model type
Frozen spectral/molecular encoders with learned alignment projections
MSAlign retrieves candidate molecules from tandem mass spectra by aligning pretrained molecular and spectral representations.
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Frozen spectral/molecular encoders with learned alignment projections
MS/MS spectrum and a set of candidate molecular structures.
Candidate-molecule retrieval scores in a shared representation space.
Official project documentation and implementation: https://arxiv.org/abs/2605.19752
limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Deployment facts recorded for MSAlign [MSAlign v2]. Fields the record does not carry are marked not recorded.
3 evaluations · 9 results. Different protocols are not a single leaderboard.
Sorted by Top-1 accuracy (retrieval) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | Protocol and dataset | Top-1 accuracy (retrieval) | Top-20 accuracy (retrieval) | Top-5 accuracy (retrieval) |
|---|---|---|---|---|
| MSAlign [MSAlign v2]Evaluation | MSAlign v2 retrieval: massspecgym-formula-formula-free, MSAlign v2 massspecgym-formula-formula-free | 47.5 ± 3.4% (best in column) | 87.0 ± 1.1% (best in column) | 71.3 ± 2.6% (best in column) |
| MSAlign [MSAlign v2]Evaluation | MSAlign v2 retrieval: spectraverse-formula-free, MSAlign v2 spectraverse-formula-free | 31.8 ± 2.6% | 78.3 ± 1.7% | 58.2 ± 1.9% |
| MSAlign [MSAlign v2]Evaluation | MSAlign v2 retrieval: massspecgym-mces-formula-free, MSAlign v2 massspecgym-mces-formula-free | 19.0 ± 3.2% | 64.9 ± 0.9% | 41.2 ± 2.5% |
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: massspecgym-formula-formula-free Dataset subset: MSAlign v2 massspecgym-formula-formula-free | 47.5 ± 3.4% Top-1 accuracy (retrieval) percent · higher Uncertainty: SD 3.4 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign massspecgym-formula-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; massspecgym-formula block, R@1 row, MSAlign column |
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: massspecgym-formula-formula-free Dataset subset: MSAlign v2 massspecgym-formula-formula-free | 87.0 ± 1.1% Top-20 accuracy (retrieval) percent · higher Uncertainty: SD 1.1 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign massspecgym-formula-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; massspecgym-formula block, R@20 row, MSAlign column |
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: massspecgym-formula-formula-free Dataset subset: MSAlign v2 massspecgym-formula-formula-free | 71.3 ± 2.6% Top-5 accuracy (retrieval) percent · higher Uncertainty: SD 2.6 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign massspecgym-formula-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; massspecgym-formula block, R@5 row, MSAlign column |
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: massspecgym-mces-formula-free Dataset subset: MSAlign v2 massspecgym-mces-formula-free | 19.0 ± 3.2% Top-1 accuracy (retrieval) percent · higher Uncertainty: SD 3.2 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign massspecgym-mces-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; massspecgym-mces block, R@1 row, MSAlign column |
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: massspecgym-mces-formula-free Dataset subset: MSAlign v2 massspecgym-mces-formula-free | 64.9 ± 0.9% Top-20 accuracy (retrieval) percent · higher Uncertainty: SD 0.9 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign massspecgym-mces-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; massspecgym-mces block, R@20 row, MSAlign column |
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: massspecgym-mces-formula-free Dataset subset: MSAlign v2 massspecgym-mces-formula-free | 41.2 ± 2.5% Top-5 accuracy (retrieval) percent · higher Uncertainty: SD 2.5 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign massspecgym-mces-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; massspecgym-mces block, R@5 row, MSAlign column |
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: spectraverse-formula-free Dataset subset: MSAlign v2 spectraverse-formula-free | 31.8 ± 2.6% Top-1 accuracy (retrieval) percent · higher Uncertainty: SD 2.6 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign spectraverse-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; spectraverse block, R@1 row, MSAlign column |
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: spectraverse-formula-free Dataset subset: MSAlign v2 spectraverse-formula-free | 78.3 ± 1.7% Top-20 accuracy (retrieval) percent · higher Uncertainty: SD 1.7 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign spectraverse-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; spectraverse block, R@20 row, MSAlign column |
| Configuration: MSAlign [MSAlign v2] | Protocol: MSAlign v2 retrieval: spectraverse-formula-free Dataset subset: MSAlign v2 spectraverse-formula-free | 58.2 ± 1.9% Top-5 accuracy (retrieval) percent · higher Uncertainty: SD 1.9 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMSAlign spectraverse-formula-free Not reported Aggregation: Not reported MSAlign arXiv v2 Table 3 · Table 3 p7; spectraverse block, R@5 row, MSAlign column |
Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.
Related profile: MSAlign. This page retains the exact record and its evaluation context.
Exact Table 3 source implementation. Formula-free retrieval; neutral mass is still used.
Frozen DreaMS and ChemBERTa encoders connected by lightweight MLP projections trained with a candidate-based contrastive objective. The documented inputs are MS/MS spectrum and a set of candidate molecular structures. The output consists of candidate-molecule retrieval scores in a shared representation space.
MSAlign arXiv:2605.19752v1, submitted 19 May 2026. The applicable input limits require configuration-specific checking.
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-msalignExplanatory profile: limited source coverage · 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 | Frozen spectral/molecular encoders with learned alignment projectionsSources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Architecture | Frozen DreaMS and ChemBERTa encoders connected by lightweight MLP projections trained with a candidate-based contrastive objective.Sources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Inputs | MS/MS spectrum and a set of candidate molecular structures.Sources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Outputs | Candidate-molecule retrieval scores in a shared representation space.Sources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Parameters | Approximately 4M trainable projection parameters; frozen DreaMS and ChemBERTa backbones are reported as 96M and 92M respectively.Sources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Known versions | MSAlign arXiv:2605.19752v1, submitted 19 May 2026.Sources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Training data | Projection layers are fitted separately on the NPLIB1, MassSpecGym or Spectraverse training splits. The paper distinguishes spectrum/molecule pair counts from unique molecules and controls candidate retrieval using mass matching.Sources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Training cutoff | NPLIB1, MassSpecGym and Spectraverse are separately split training resources. The inspected paper does not define one latest measurement date covering all three. · Not reported in inspected sourcesSources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Context limits | The pipeline inherits spectrum and molecule preprocessing from its frozen DreaMS and ChemBERTa encoders. The inspected MSAlign architecture section does not state a single joint input limit. · Not reported in inspected sourcesSources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Weights licence | The inspected preprint does not state distribution terms for the learned projection checkpoints. Frozen encoder licences remain separate from projection-weight rights. · Not reported in inspected sourcesSources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting; page.html: inspected official source |
| Access | Official project documentation and implementation: https://arxiv.org/abs/2605.19752Sources (2)https://arxiv.org/abs/2605.19752: page.html; msalign: Primary paper PDF · MSAlign paper Section 3 Architecture and Training, Section 4 on splitting, and Section 5.1 Experimental Setting |
| Code licence | The inspected preprint describes the algorithm but does not supply a separate code licence; no code-distribution permission is inferred from the paper licence. · Not reported in inspected sourcesSourceshttps://arxiv.org/abs/2605.19752: page.html · page.html: inspected official source |
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
2 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
Facets: method types1 values
| MSAlign arXiv v2 Table 3 MSAlign arXiv 2605.19752v2 abstract and Section 3 "Foundation model alignment" (p.4): aligns "two frozen foundation models (DreaMS for mass spectra and MolDeBERTa for molecules)" through trained MLP adapters Version: 2605.19752v2, 25 September 2026 | conflicting claim ["source-hash-verification","automated-source-review"] · 2026-10-12 Audit detailsCorrect the method type from none to foundation_model (use-case baseline review 2026-10-12, table 1). Checked as the review required. Score fusion (Section 3, "Late score fusion") combines four alignment scorers and three mass scores with weights fitted on validation data; two of the scorers use both foundation encoders. Evidence from docs/reviews/use-cases/baselines-2026-10-12.md. Independent review 2026-10-12: approved. MSAlign aligns frozen DreaMS and MolDeBERTa encoders through trained MLP adapters (abstract; Section 3); the baselines paragraph and Table 1 describe JESTR and Emb-Cos as trained contrastive models and DeepSets as a fingerprint predictor. See docs/reviews/2026-10-12-method-type-corrections.md. Conflicting source claim: Field: Claim: metadata-correction-tags-20261012-5e4376d070c83b6d8dcc Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Extraction artifact SHA-256: |
| Relationship: configuration of discovery-model-msalign Individual claims | MSAlign arXiv v2 Table 3 Table 3 source column MSAlign; Section 5.1 Baselines Version: 2605.19752v2, 25 September 2026 | source checked ["automated-source-review"] · 2026-09-30T21:40:59.576893+00:00 Audit detailsField: Claim: uc20260930-config-family-05faf370a8a1221e Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Release 2026-11-21-c8bea25e5abb · Record review: source checked
Technical metadata for this record is tracked under stable ID uc20260930-msalign-v2-config-msalign.
Source locator: Table 3 column MSAlign; Sections 3 and 5.1
MSAlign [MSAlign v2]. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/uc20260930-msalign-v2-config-msalign/
Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.
The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence