orthrus-mlm
Linear probe, trained per mRNABench task, on frozen embeddings averaged over nucleotides from orthrus-mlm, an Orthrus checkpoint; Orthrus is a Mamba mRNA foundation model pretrained by contrastive learning on mRNA splice isoforms and orthologs.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluations and results
8 evaluations · 8 results. Different protocols are not a single leaderboard.
Sorted by AUPRC (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.
All 8 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Pipeline: orthrus-mlm | Protocol: mRNABench variant probes eCLIP: eCLIP binding site prediction Dataset subset: mRNABench eCLIP (mRNABench split) | 0.465 ± 0.003 AUPRC fraction · higher Uncertainty: 95% CI ± 0.003 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceorthrus-mlm on mRNABench variant probes eCLIP: eCLIP binding site prediction Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 5 (XML T2), data row 35, XML tr 37, column 4 (eCLIP | AUPRC), model orthrus-mlm |
| Pipeline: orthrus-mlm | Protocol: mRNABench variant probes GO: Gene Ontology term prediction Dataset subset: mRNABench GO (mRNABench split) | 0.435 ± 0.005 AUPRC fraction · higher Uncertainty: 95% CI ± 0.005 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceorthrus-mlm on mRNABench variant probes GO: Gene Ontology term prediction Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 6 (XML T3), data row 35, XML tr 37, column 5 (GO | AUPRC), model orthrus-mlm |
| Pipeline: orthrus-mlm | Protocol: mRNABench variant probes HL: mRNA half life Dataset subset: mRNABench HL (mRNABench split) | 0.696 ± 0.005 Pearson unitless · higher Uncertainty: 95% CI ± 0.005 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceorthrus-mlm on mRNABench variant probes HL: mRNA half life Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 6 (XML T3), data row 35, XML tr 37, column 2 (HL | Pearson R), model orthrus-mlm |
| Pipeline: orthrus-mlm | Protocol: mRNABench variant probes MRL-HL-Pair: Paired mean ribosome load and half life Dataset subset: mRNABench MRL-HL-Pair (mRNABench split) | 0.633 ± 0.047 Pearson unitless · higher Uncertainty: 95% CI ± 0.047 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceorthrus-mlm on mRNABench variant probes MRL-HL-Pair: Paired mean ribosome load and half life Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 6 (XML T3), data row 35, XML tr 37, column 3 (MRL-HL-Pair | Pearson R), model orthrus-mlm |
| Pipeline: orthrus-mlm | Protocol: mRNABench variant probes MRL-MPRA: Mean ribosome load on an MPRA library Dataset subset: mRNABench MRL MPRA (mRNABench split) | 0.639 ± 0.001 Pearson unitless · higher Uncertainty: 95% CI ± 0.001 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceorthrus-mlm on mRNABench variant probes MRL-MPRA: Mean ribosome load on an MPRA library Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 6 (XML T3), data row 35, XML tr 37, column 4 (MRL-MPRA | Pearson R), model orthrus-mlm |
| Pipeline: orthrus-mlm | Protocol: mRNABench variant probes MRL: Mean ribosome load Dataset subset: mRNABench MRL (mRNABench split) | 0.460 ± 0.012 Pearson unitless · higher Uncertainty: 95% CI ± 0.012 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceorthrus-mlm on mRNABench variant probes MRL: Mean ribosome load Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 5 (XML T2), data row 35, XML tr 37, column 5 (MRL | Pearson R), model orthrus-mlm |
| Pipeline: orthrus-mlm | Protocol: mRNABench variant probes Prot-Loc: Protein localisation Dataset subset: mRNABench Prot Loc (mRNABench split) | 0.396 ± 0.005 AUPRC fraction · higher Uncertainty: 95% CI ± 0.005 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceorthrus-mlm on mRNABench variant probes Prot-Loc: Protein localisation Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 6 (XML T3), data row 35, XML tr 37, column 6 (Prot-Loc | AUPRC), model orthrus-mlm |
| Pipeline: orthrus-mlm | Protocol: mRNABench variant probes VEP: Variant effect prediction Dataset subset: mRNABench VEP (mRNABench split) | 0.323 ± 0.032 AUPRC fraction · higher Uncertainty: 95% CI ± 0.032 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceorthrus-mlm on mRNABench variant probes VEP: Variant effect prediction Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 5 (XML T2), data row 35, XML tr 37, column 6 (VEP | AUPRC), model orthrus-mlm |
Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.
Use this pipeline
How it works, versions and access
Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this pipeline. Consult the linked sources and evaluation records below.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Description Linear probe, trained per mRNABench task, on frozen embeddings averaged over nucleotides from orthrus-mlm, an Orthrus checkpoint; Orthrus is a Mamba mRNA foundation model pretrained by contrastive learning on mRNA splice isoforms and orthologs. Individual claims | mRNABench: A curated benchmark for mature mRNA property and function prediction expansion-p3-mrnabench-2025: Appendix A, Overview of Evaluated Models (family and variant rows; naive baselines paragraph); Section 4.3, Linear Probing ('training a linear classifier on frozen embeddings'; 'averaging over per-nucleotide embeddings') Version: preprint archived 2025-07-08 | source checked ["automated-source-review","ai-assisted-source-review"] · 2026-10-11 Audit detailsApproved. Checked the 10 method and model descriptions against their sources (EVmutation, GEMME and RSALOR abstracts, the FramePool k-mer random forests, the RhoMax BLASSO text) and spot-checked the 49 mRNABench rows against Appendix A; all accurate. Licences on the 3 new sources match their Europe PMC records. At the reviewer's suggestion, the en dash printed in some checkpoint names is written as a hyphen in the descriptions. Field: Claim: metadata-correction-fca11f864c58ff9589cf Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
- mRNABench: A curated benchmark for mature mRNA property and function prediction · Original source · preprint archived 2025-07-08
Technical metadata and extraction receipts
Stable ID: mrnabench-variants-2025-method-orthrus-mlm
- areas
- rna-transcriptomes
- source locator
- Tables 5/6, row orthrus-mlm; Appendix A (APP1), C (APP3), D (APP4)
- missing metadata
- checkpoint revision: reason: unreported; parameters: reason: unextracted
Related records
- subject: orthrus-mlm: description
- system: orthrus-mlm on mRNABench variant probes eCLIP: eCLIP binding site prediction
- system: orthrus-mlm on mRNABench variant probes GO: Gene Ontology term prediction
- system: orthrus-mlm on mRNABench variant probes HL: mRNA half life
- system: orthrus-mlm on mRNABench variant probes MRL: Mean ribosome load
- system: orthrus-mlm on mRNABench variant probes MRL-HL-Pair: Paired mean ribosome load and half life
- system: orthrus-mlm on mRNABench variant probes MRL-MPRA: Mean ribosome load on an MPRA library
- system: orthrus-mlm on mRNABench variant probes Prot-Loc: Protein localisation
- system: orthrus-mlm on mRNABench variant probes VEP: Variant effect prediction