NT 2.5b-m-s (Manzo et al. 2025)

Overview

NT 2.5b-m-s (Manzo et al. 2025) as evaluated in the cited comparison.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

4 evaluations · 4 results. Different protocols are not a single leaderboard.

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: NT 2.5b-m-s (Manzo et al. 2025)	Protocol: Allelic reporter effect correlation in HeLa (Manzo et al. 2025 Table 1) Dataset: HeLa regulatory variant reporter data (Manzo et al. 2025)	0.066 pearson-correlation unitless · higher Uncertainty: SE 0.027. Standard error as printed in brackets; its basis is not defined in the caption Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5b-m-s on HeLa reporter variant effects regulatory-variant-20261009-protocol-manzo2025-hela-pearson Aggregation: Not reported Comparative Analysis of Deep Learning Models for Predicting Causative Regulatory Variants · Table 1 row 'NT 2.5b-m-s', column 'Hela (5241 SNPs)'
Configuration: NT 2.5b-m-s (Manzo et al. 2025)	Protocol: Allelic reporter effect correlation in HepG2 (Manzo et al. 2025 Table 1) Dataset: HepG2 regulatory variant reporter data (Manzo et al. 2025)	0.139 pearson-correlation unitless · higher Uncertainty: SE 0.027. Standard error as printed in brackets; its basis is not defined in the caption Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5b-m-s on HepG2 reporter variant effects regulatory-variant-20261009-protocol-manzo2025-hepg2-pearson Aggregation: Not reported Comparative Analysis of Deep Learning Models for Predicting Causative Regulatory Variants · Table 1 row 'NT 2.5b-m-s', column 'HepG2 (16,255 SNPs)'
Configuration: NT 2.5b-m-s (Manzo et al. 2025)	Protocol: Allelic reporter effect correlation in K562 (Manzo et al. 2025 Table 1) Dataset: K562 regulatory variant reporter data (Manzo et al. 2025)	0.153 pearson-correlation unitless · higher Uncertainty: SE 0.055. Standard error as printed in brackets; its basis is not defined in the caption Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5b-m-s on K562 reporter variant effects regulatory-variant-20261009-protocol-manzo2025-k562-pearson Aggregation: Not reported Comparative Analysis of Deep Learning Models for Predicting Causative Regulatory Variants · Table 1 row 'NT 2.5b-m-s', column 'K562 (19,321 SNPs)'
Configuration: NT 2.5b-m-s (Manzo et al. 2025)	Protocol: Allelic reporter effect correlation in NPC (Manzo et al. 2025 Table 1) Dataset: NPC regulatory variant reporter data (Manzo et al. 2025)	0.027 pearson-correlation unitless · higher Uncertainty: SE 0.001. Standard error as printed in brackets; its basis is not defined in the caption Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5b-m-s on NPC reporter variant effects regulatory-variant-20261009-protocol-manzo2025-npc-pearson Aggregation: Not reported Comparative Analysis of Deep Learning Models for Predicting Causative Regulatory Variants · Table 1 row 'NT 2.5b-m-s', column 'NPC (14,042 SNPs)'

Source checking is not independent reproduction. Release 2026-10-10-6e93f504adfc.

Use this model

How it works, versions and access

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 2026-10-10-6e93f504adfc
Property and statement	Original source and location	Review and provenance

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

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

Sources and history

Release 2026-10-10-6e93f504adfc · Record review: source checked

1 source records and release history

Comparative Analysis of Deep Learning Models for Predicting Causative Regulatory Variants · Original source · Genes 16(10):1223, published 2025-10-15; PMC12562713 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: regulatory-variant-20261009-config-manzo2025-nt-2-5b-m-s

areas: dna-genomes
contexts: research
method types: foundation_model
reported name: NT 2.5b-m-s (Manzo et al. 2025)
foundation model eligible: true
parameters: Fine-tuned per cell line for enhancer versus control classification on 1 kb sequences (Table 2); variant effect is the log2 ratio of alternative to reference scores
source locator: Table 1 row 'NT 2.5b-m-s'; Table 2
missing metadata: version: reason: unreported; note: The table prints only the label 'NT 2.5b-m-s'; no release or checkpoint identifier.

Related records

configuration of: Nucleotide Transformer
system: NT 2.5b-m-s on HeLa reporter variant effects
system: NT 2.5b-m-s on HepG2 reporter variant effects
system: NT 2.5b-m-s on K562 reporter variant effects
system: NT 2.5b-m-s on NPC reporter variant effects