Configuration

MAE (Silverstein et al. 2026)

MAE: DROP v1.4.0; MAE module with allelic balance threshold 70 instead of 80; standard parameters.

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

1 evaluation · 9 results. Different protocols are not a single leaderboard.

Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) · Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)

Sorted by Accuracy (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) (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	Accuracy (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))	F1 (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))	False negatives (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))	False positives (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))	MCC (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))	Precision (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))	Recall (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))	True negatives (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))	True positives (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9))
MAE (Silverstein et al. 2026)Evaluation	0.385	0.556	3	5	-0.433	0.5	0.625	0	5

All 9 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	0.385 Accuracy (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell F10, row 'MAE', column 'Accuracy'
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	0.556 F1 (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell I10, row 'MAE', column 'F1'
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	3 False negatives (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell C10, row 'MAE', column 'False Negatives'
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	5 False positives (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell E10, row 'MAE', column 'False Positives'
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	-0.433 MCC (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell J10, row 'MAE', column 'MCC'
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	0.5 Precision (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell G10, row 'MAE', column 'Precision'
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	0.625 Recall (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell H10, row 'MAE', column 'Recall'
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	0 True negatives (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell D10, row 'MAE', column 'True Negatives'
Configuration: MAE (Silverstein et al. 2026)	Protocol: Recovery of known allelic-imbalance genes and outlier calls in true-negative samples, patient muscle RNA-seq (Silverstein et al. Table S9, ANEVA-H and MAE) Dataset: NIH neuromuscular diagnosed RNA-seq truth set (Silverstein et al. 2026)	5 True positives (positives per known event or gene, negatives per true-negative sample; aggregated across the tissue sets each tool was run on (Table S9)) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance) rna-splicing-20261011-silverstein2026-protocol-allelic-imbalance Aggregation: Not reported Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026); Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Table S9 (sheet 'Table S9') cell B10, row 'MAE', column 'True Positives'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Use this configuration

How it works, versions and access

Strengths, limitations and unresolved questions

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

2 source records and release history

Benchmarking RNA-seq Tools for Real-World Diagnostic Applications (Silverstein et al., medRxiv 2026) · Original source · medRxiv preprint version 1, posted 2026-01-28; JATS source XML
Silverstein et al. 2026 Supplemental Tables S1-S10 (medRxiv media-3.xlsx) · Original source · medRxiv preprint version 1 supplement DC3 (file 344940_file09.xlsx in the JATS XML)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: rna-splicing-20261011-silverstein2026-config-mae

areas: rna-transcriptomes
contexts: clinical_research
method types: conventional_pipeline
reported name: MAE
foundation model eligible: false
version: DROP v1.4.0
parameters: MAE module with allelic balance threshold 70 instead of 80; standard parameters
access reuse: Open-source tool; run by the authors on the NIH Biowulf cluster
source locator: Methods 'Allelic Imbalance Tools'; Table S9 row label
provenance note: MAE as run in the Silverstein et al. 2026 benchmark.

Related records

configuration of: DROP MAE module
system: MAE on the NIH neuromuscular diagnosed RNA-seq truth set (allelic-imbalance)

Suggest a correction