Task

miRNA-mRNA interaction prediction

miRNA–mRNA interaction classification evaluates paired sequence representations on a benchmark split and an independent collection.

Sources

Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions

1 evaluation · 1 metric row

At a glance

Inputs, training, access and other details

Explanatory 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.

Data, procedure and scoring
Property	Description and evidence
Datasets	MirTarRAW positive/negative miRNA–mRNA pairs, plus DeepMirTarLeft. Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions
Splits	MirTarRAW is partitioned 72:8:20 for training, validation and testing; DeepMirTarLeft is an additional independent dataset. Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions
Metrics	F1, precision, recall, accuracy and AUC for miRNA–mRNA interaction classification. Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions
Baselines	DeepMirTar, RNA-FM, RNABERT, RNA-MSM and RNAErnie in the interaction comparison; other RNA-task baselines are separate. Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions
Leakage controls	MirTarRAW is divided 72%/8%/20% for training/validation/test, with DeepMirTarLeft as an additional test set. The RNAret methods do not specify a miRNA-identity, transcript-identity or homology-grouped holdout for this task. The paper’s explicit RNAStrAlign/ArchiveII overlap exclusion belongs to secondary-structure prediction and must not be transferred here. · Not reported in inspected sources Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: miRNA-mRNA interaction prediction; Methods: Statistics and reproducibility
Uncertainty	Table 1 reports point classification metrics. RNAret’s Statistics and reproducibility section and Supplementary Information do not specify repeated-run intervals or an uncertainty estimator for miRNA–mRNA prediction. Intervals reported in the original miTAR study would not quantify RNAret’s results. · Not reported in inspected sources Sources (2) Retentive Network promotes efficient RNA language modeling of long sequences; rnaret-2026__42003_2026_9757_MOESM2_ESM.pdf · Table 1; Methods: Statistics and reproducibility; Supplementary Information
Entity type	Paper-specific computational evaluation protocol. Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions
Organisms	Human miRNA–target pairs. The original miTAR study identifies its DeepMirTar and miRAW inputs as human datasets; MirTarRAW combines portions of these two datasets and DeepMirTarLeft is the withheld remainder of DeepMirTar. Sources (2) Retentive Network promotes efficient RNA language modeling of long sequences; PMC7912887.xml · RNAret: miRNA-mRNA interaction prediction; miTAR: Abstract and Methods/Datasets
Assays	miRNA–mRNA interaction labels. Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions
Allowed inputs	Paired miRNA and mRNA sequences. Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions
Adaptation	Supervised pair classification on the training portion with validation and independent testing. Sources Retentive Network promotes efficient RNA language modeling of long sequences · Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions

How it works

How it worksComputational evaluation flow

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Sources

Evaluation methodology

MirTarRAW positive/negative miRNA–mRNA pairs, plus DeepMirTarLeft. MirTarRAW is partitioned 72:8:20 for training, validation and testing; DeepMirTarLeft is an additional independent dataset. F1, precision, recall, accuracy and AUC for miRNA–mRNA interaction classification. DeepMirTar, RNA-FM, RNABERT, RNA-MSM and RNAErnie in the interaction comparison; other RNA-task baselines are separate. MirTarRAW is divided 72%/8%/20% for training/validation/test, with DeepMirTarLeft as an additional test set. The RNAret methods do not specify a miRNA-identity, transcript-identity or homology-grouped holdout for this task. The paper’s explicit RNAStrAlign/ArchiveII overlap exclusion belongs to secondary-structure prediction and must not be transferred here.

Sources

Recorded evaluations

Each evaluation records what was tested and under which conditions.

RNAret: miRNA-mRNA interaction prediction

Tested entities and results

Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
RNAret: miRNA-mRNA interaction prediction Configuration: RNAretTask: miRNA-mRNA interaction predictionDataset: MirTarRAW 5-mer RNAret classifier; 72/8/20 train/validation/test split Author-reported evaluation · Evaluation metadata: needs review
0.9622 F1 Unit: fraction · Direction: unknown	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedRetentive Network promotes efficient RNA language modeling of long sequences · Table 1, MirTarRAW / 5-mer RNAret row, F1 column Source checking is not independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.

Paper or primary resource	Version	Reference
Retentive Network promotes efficient RNA language modeling of long sequences	journal full text in PMC	Read source

What is still missing

complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.

Search and extraction details

primary comparison tables located

Searches

Retentive Network promotes efficient RNA language modeling of long sequences 10.1038/s42003-026-09757-x

Evidence locations

Table 1; XML table Tab1

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

A pair-level partition does not establish unseen-miRNA or unseen-transcript performance. RNAret’s secondary-structure overlap exclusions and another method’s uncertainty estimates do not apply to this interaction result.
Sources (3)
Retentive Network promotes efficient RNA language modeling of long sequences; rnaret-2026__42003_2026_9757_MOESM2_ESM.pdf; PMC7912887.xml · Results: miRNA-mRNA interaction prediction; Methods: Statistics and reproducibility; Table 1; Methods: Statistics and reproducibility; Supplementary Information; RNAret: miRNA-mRNA interaction prediction; miTAR: Abstract and Methods/Datasets

Profile review details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Stable record: reported-task-46e927bea10702

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.

21 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["Input: Paired miRNA and mRNA sequences.","Evaluation: MirTarRAW is partitioned 72:8:20 for training, validation and testing; DeepMirTarLeft is an additional independent dataset.","Readout: F1, precision, recall, accuracy and AUC for miRNA–mRNA interaction classification."] Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets MirTarRAW positive/negative miRNA–mRNA pairs, plus DeepMirTarLeft. Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits MirTarRAW is partitioned 72:8:20 for training, validation and testing; DeepMirTarLeft is an additional independent dataset. Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Supervised pair classification on the training portion with validation and independent testing. Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics F1, precision, recall, accuracy and AUC for miRNA–mRNA interaction classification. Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines DeepMirTar, RNA-FM, RNABERT, RNA-MSM and RNAErnie in the interaction comparison; other RNA-task baselines are separate. Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls MirTarRAW is divided 72%/8%/20% for training/validation/test, with DeepMirTarLeft as an additional test set. The RNAret methods do not specify a miRNA-identity, transcript-identity or homology-grouped holdout for this task. The paper’s explicit RNAStrAlign/ArchiveII overlap exclusion belongs to secondary-structure prediction and must not be transferred here. Individual claims	Retentive Network promotes efficient RNA language modeling of long sequences Original source ↗ Results: miRNA-mRNA interaction prediction; Methods: Statistics and reproducibility Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558224+00:00	unreported automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `e970e7322e07fb3c9d12efd315691cc5de5575a3f2616f4b788614c8c706dd0b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty Table 1 reports point classification metrics. RNAret’s Statistics and reproducibility section and Supplementary Information do not specify repeated-run intervals or an uncertainty estimator for miRNA–mRNA prediction. Intervals reported in the original miTAR study would not quantify RNAret’s results. Individual claims	rnaret-2026__42003_2026_9757_MOESM2_ESM.pdf Original source ↗ Table 1; Methods: Statistics and reproducibility; Supplementary Information Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved 2026-09-16; sha256:8464ff052a60b946bd08fa18860f22b2f390fe93dd0549eb845c8e9a68cf5fcc Retrieved: 2026-09-16T21:06:05.136898+00:00	unreported automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `8464ff052a60b946bd08fa18860f22b2f390fe93dd0549eb845c8e9a68cf5fcc` Hash scope: Hash scope not separately documented; inspect source record Archive member: 42003_2026_9757_MOESM2_ESM.pdf Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

4 source records and release history

Retentive Network promotes efficient RNA language modeling of long sequences · Original source · journal full text in PMC
Retentive Network promotes efficient RNA language modeling of long sequences · Original source · journal full text in PMC
rnaret-2026__42003_2026_9757_MOESM2_ESM.pdf · Original source · Retrieved 2026-09-16; sha256:8464ff052a60b946bd08fa18860f22b2f390fe93dd0549eb845c8e9a68cf5fcc
PMC7912887.xml · Original source · Retrieved 2026-09-16; sha256:3504a0fa3b62698b7eff78418e682bf2484236ed05645597a8be4fa2e97b3efc

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-46e927bea10702

areas: rna-transcriptomes
tasks: miRNA-mRNA interaction prediction
entity level: task
version: Not reported
task: miRNA-mRNA interaction prediction
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
benchmark research: review date: 2026-09-17; status: primary_comparison_tables_located; primary sources: evidence-expansion-rnaret-2026-e970e732; inspected locators: Table 1; XML table Tab1; searched queries: Retentive Network promotes efficient RNA language modeling of long sequences 10.1038/s42003-026-09757-x; gaps: complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.; exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.; claim scope: Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
historical missing metadata: protocol version: not_reported_in_legacy_extract
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: benchmark
entity classification: review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: rnaret-2026; source locator: Results: RNA–RNA interaction task; Methods: RNA–RNA interaction prediction; cached text lines 17, 79; task metric definitions and corresponding results table; matching task comparison table/ablation captions; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.

Related records

dataset: MirTarRAW
benchmark: RNAret: miRNA-mRNA interaction prediction

Suggest a correction