Task

MFASS splice-variant prioritisation

MFASS prioritisation asks whether variant scores enrich for experimentally disrupted exon recognition.

Sources

MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files

9 evaluations · 31 results

Overview

Datasets

The linked rewire MFASS v2 protocol defines its reconciled eligible variants and fixed test cohort; this guide is not another dataset release.

Metrics

Precision at 100, average precision and AUROC in the pinned v2 evaluation. Coverage and paired uncertainty belong beside each comparison.

Allowed inputs

Variant scores aligned to the MFASS reporter-assay labels; assay-oriented sequence pairs for the corrected local baseline.

Sources

MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files

Evaluation procedure diagram

How it worksConceptual evaluation workflow

Conceptual task guide. Dataset preparation, parameters and scoring must come from a separately identified protocol.

Sources

MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files

limited source coverage · Automated source review, 2026-09-23. All specifications and missing details

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

Evaluation scope and datasetMetric and reported setup

MFASS matched canonical annotation: Precision at 100

Precision at 100 (dimensionless) · Higher values are better.

MFASS: matched GENCODE 44 canonical annotation · MFASS v2 test: matched canonical annotation coverage

Evidence origin: Rewire evaluation.

MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.*.metrics.precision_at_capacity

8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.
Exploratory comparison: prior results were known. Paired contrast intervals are unadjusted and do not establish a universal model ranking.
Pangolin uses the recorded per-gene masking patch; these are exact configurations, not unqualified upstream model scores.
Precision at 100 is sensitive to tied-score ordering, especially P1. Numerical source checking is automated, not human review or independent reproduction.
Assembly-orientation issue reported at https://github.com/KosuriLab/MFASS/issues/1. Original v1 outputs remain unchanged; corrections require a new version.

Comparison details and limitations

8,297 of 8,324 held-out variants scored in every configuration (314 positives, 460 exon groups). The same 27 rows are excluded: 23 assembly-orientation mismatches and four outside the selected canonical transcript spans. Missing scores are not zero or negative predictions.

Automated source review: 2026-09-25. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Find a tested model or method

Showing 4 of 4 matching rows.

Zoom to observed range

Tested configuration

0.6280.6370.6450.6530.662

Reported score

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Choosing an evaluation

The corrected rewire v2 protocol validates assay-oriented reference and mutant pairs and uses a fixed grouped split. Its baseline window is placed around the validated variant position. This task guide links that concrete protocol without replacing its identity. Preserve specialist sequence context, missing predictions and the chosen review capacity when comparing methods.

Sources

MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files

Task scope

This is a task guide, not a single versioned benchmark protocol. The connected resources provide examples or concrete procedures. A candidate method or proposed control is not evidence that an evaluation has been completed.

Sources

MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Protocols

These source-backed links do not make different protocols or scores interchangeable.

Run this benchmark

Choose a concrete protocol before running an evaluation. Its inputs, split and scoring rules determine which results can be compared.

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Functional reporter labels provide an assay endpoint separate from clinical assertions.
Sources
MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files

Limitations and conditions

Reporter effects are not clinical diagnoses. Different sequence context and missing-prediction coverage prevent an identical-input interpretation.
Sources
MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
The archived v1 baseline is superseded for an orientation/window error. Its preserved comparisons and split-cost claims are not current evidence for the corrected v2 protocol.
Sources
MFASS computational protocol README at bee9133b83f3aedaf2bbb9013f1875515845607e · README.md correction notice lines 3–10

Profile review details

Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied.

Stable record: catalog-task-mfass-splice

Specifications

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-23. 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
Entity type	Task guide; concrete protocol identities remain separate. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Datasets	The linked rewire MFASS v2 protocol defines its reconciled eligible variants and fixed test cohort; this guide is not another dataset release. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Organisms	Human variants evaluated through the MFASS reporter assay; this is not a population-level clinical validation. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Assays	MFASS reporter-based exon-recognition measurements, using the labels and eligibility rules preserved by the v2 protocol. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Splits	Use the grouped split-v2 manifests in the pinned runner revision. Preserve the train/test assignment and exclusions. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Allowed inputs	Variant scores aligned to the MFASS reporter-assay labels; assay-oriented sequence pairs for the corrected local baseline. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Adaptation	The corrected baseline and frozen-encoder logistic pipeline fit the training arm; the specialist scorers retain their published configurations. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Metrics	Precision at 100, average precision and AUROC in the pinned v2 evaluation. Coverage and paired uncertainty belong beside each comparison. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Baselines	The v2 k-mer/position baseline is a trained comparator. SpliceAI, Pangolin and the frozen DNABERT-2 logistic pipeline retain their own input and fitting definitions. Sources MFASS v2 pinned rewire artifacts · Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files
Coverage and comparison scope	The linked rewire v2 protocol has 8,324 held-out variants, but scored coverage depends on the method. Compare candidate and baseline on their common scored variants and retain excluded counts and connected-group counts. This guide defines no additional cohort or split. Sources (4) MFASS computational protocol README at bee9133b83f3aedaf2bbb9013f1875515845607e; Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-spliceai.json; Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-pangolin-maskFalse.json; Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-dnabert2.json · README.md lines 141–171; comparison JSON: denominators and independent_groups
Uncertainty	For the linked v2 comparisons, intervals describe paired candidate-minus-baseline differences from 2,000 whole-group bootstrap draws. They do not represent absolute method confidence intervals; capacity-100 precision keeps the review-list fraction fixed during resampling. Sources (4) Protocol metadata evidence: mfass-metrics.py; Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-spliceai.json; Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-pangolin-maskFalse.json; Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-dnabert2.json · metrics.py lines 65–140; comparison JSON: capacity, seed and paired.*

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.

Paper or primary resource	Version	Reference
mfass original	PMC primary-source artifact, version pinned by SHA256	Read source
A Multiplexed Assay for Exon Recognition Reveals that an Unappreciated Fraction of Rare Genetic Variants Cause Large-Effect Splicing Disruptions	Original published article	Read source DOI: 10.1016/j.molcel.2018.10.037

Historical gaps recorded on 2026-09-17

The catalogue now holds 31 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.

Primary browser text accessible but rawXML endpoint 500, PMC HTMLreCAPTCHA and mirror returned 0 bytes. Existing MFASS corrected runs must retain identities and assay-oriented window correction; no new score duplicates or revert to withdrawn v 1 conclusion.

Search and extraction details

broad task primary raw retrieval blocked existing corrected run retained

Searches

MFASS v2 pinned rewire artifacts primary paper benchmark results

Evidence locations

Original MFASS paper discovered through PMC/DOI; assay design and variant library; existing Rewire v2 artifacts

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.

26 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual task guide. Dataset preparation, parameters and scoring must come from a separately identified protocol. Individual claims	MFASS v2 pinned rewire artifacts Original source ↗ Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-16T10:50:02Z	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d` Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash
Diagram steps Validate assay-oriented sequence pairs Apply the fixed grouped split Score each declared method Report prioritisation, ranking and coverage Individual claims	MFASS v2 pinned rewire artifacts Original source ↗ Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-16T10:50:02Z	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d` Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash
Diagram title Conceptual evaluation workflow Individual claims	MFASS v2 pinned rewire artifacts Original source ↗ Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-16T10:50:02Z	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d` Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash
Entity type Task guide; concrete protocol identities remain separate. Individual claims	MFASS v2 pinned rewire artifacts Original source ↗ Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-16T10:50:02Z	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d` Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash
Datasets The linked rewire MFASS v2 protocol defines its reconciled eligible variants and fixed test cohort; this guide is not another dataset release. Individual claims	MFASS v2 pinned rewire artifacts Original source ↗ Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-16T10:50:02Z	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d` Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash
Uncertainty For the linked v2 comparisons, intervals describe paired candidate-minus-baseline differences from 2,000 whole-group bootstrap draws. They do not represent absolute method confidence intervals; capacity-100 precision keeps the review-list fraction fixed during resampling. Individual claims	Protocol metadata evidence: mfass-metrics.py Original source ↗ metrics.py lines 65–140; comparison JSON: capacity, seed and paired.* Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-23T18:43:09.582943+00:00	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `4030374ed11d38e523fc9991ddd792f8800e7739ac71588085bfff91f912d7f7` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty For the linked v2 comparisons, intervals describe paired candidate-minus-baseline differences from 2,000 whole-group bootstrap draws. They do not represent absolute method confidence intervals; capacity-100 precision keeps the review-list fraction fixed during resampling. Individual claims	Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-dnabert2.json Original source ↗ metrics.py lines 65–140; comparison JSON: capacity, seed and paired.* Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-23T18:39:03.239354+00:00	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `52216e003f4e5332ecb43511864c9f0b3df7b1ed0f731c631412dc7311f505c3` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty For the linked v2 comparisons, intervals describe paired candidate-minus-baseline differences from 2,000 whole-group bootstrap draws. They do not represent absolute method confidence intervals; capacity-100 precision keeps the review-list fraction fixed during resampling. Individual claims	Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-pangolin-maskFalse.json Original source ↗ metrics.py lines 65–140; comparison JSON: capacity, seed and paired.* Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-23T18:39:03.230617+00:00	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `fd938e1414fa1c6611c6b62597c7b7a3c2df0078301e47e23ba82183095c1097` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty For the linked v2 comparisons, intervals describe paired candidate-minus-baseline differences from 2,000 whole-group bootstrap draws. They do not represent absolute method confidence intervals; capacity-100 precision keeps the review-list fraction fixed during resampling. Individual claims	Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-spliceai.json Original source ↗ metrics.py lines 65–140; comparison JSON: capacity, seed and paired.* Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-23T18:39:03.206346+00:00	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `7790098265ad4cac961e26d44ecd197fc314f5214891fc93d452d2eca65f62e0` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Organisms Human variants evaluated through the MFASS reporter assay; this is not a population-level clinical validation. Individual claims	MFASS v2 pinned rewire artifacts Original source ↗ Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files Version: bee9133b83f3aedaf2bbb9013f1875515845607e Retrieved: 2026-09-16T10:50:02Z	source checked automated source review · 2026-09-23 Audit details Follow-up review of Coverage and comparison scope, Uncertainty. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `a3af693afc070b39b334e359beed7f9affd76f7456a4f9264e2d1e9dab26111d` Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash

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

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: discovered

12 source records and release history

DNABERT-2 official resource · Original source · Not reported
Nucleotide Transformer v2 official resource · Original source · Not reported
SpliceAI official resource · Original source · Not reported
Pangolin official resource · Original source · Not reported
mfass original · Original source · PMC primary-source artifact, version pinned by SHA256
A Multiplexed Assay for Exon Recognition Reveals that an Unappreciated Fraction of Rare Genetic Variants Cause Large-Effect Splicing Disruptions · Original source · Original published article
MFASS v2 pinned rewire artifacts · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
MFASS computational protocol README at bee9133b83f3aedaf2bbb9013f1875515845607e · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-spliceai.json · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-pangolin-maskFalse.json · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
Protocol metadata evidence: mfass-results-compare-baseline-v2-vs-dnabert2.json · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
Protocol metadata evidence: mfass-metrics.py · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e

Download this release

Technical metadata and extraction receipts

Stable ID: catalog-task-mfass-splice

areas: dna-genomes
entity level: task
version: Not reported
task: MFASS splice-variant prioritisation
scope note: Functional exon-recognition assay; mfass-v2 reports a corrected baseline and one complete local DNABERT-2 protocol.
benchmark research: review date: 2026-09-17; status: broad_task_primary_raw_retrieval_blocked_existing_corrected_run_retained; primary sources: evidence-expansion-p2-mfass-original-noartifact-2; evidence-expansion-p2-mfass-primary-bibliographic-noartifact-2; inspected locators: Original MFASS paper discovered through PMC/DOI; assay design and variant library; existing Rewire v2 artifacts; searched queries: MFASS v2 pinned rewire artifacts primary paper benchmark results; gaps: Primary browser text accessible but rawXML endpoint 500, PMC HTMLreCAPTCHA and mirror returned 0 bytes. Existing MFASS corrected runs must retain identities and assay-oriented window correction; no new score duplicates or revert to withdrawn v 1 conclusion.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
historical missing metadata: protocol version: not_yet_extracted
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 record identifies the biological prediction question or a suite-specific task, rather than a uniquely fixed evaluated procedure. Preserve its task identity and leave split, model adaptation and scoring details on linked protocols/evaluations.; source ids: rewire-mfass-v2-source; source locator: Pinned MFASS v2 README: Correction, Dataset, Cohort reconciliation and Split; committed results files; ambiguities: None recorded

Related records

evaluates task: MFASS: matched GENCODE 44 canonical annotation
evaluates task: MFASS v1 (superseded)
evaluates task: MFASS v2

Suggest a correction