Configuration

Geneformer V2-316M attention edges, layer 13 (Kendiukhov 2026)

Attention from layer 13, averaged over heads within the layer and then over cells, between the perturbed gene and each other gene. L13 was pre-specified from DLPFC brain data before K562 data were examined.

1 evaluation · 1 result 3 open disagreements between studies involve its model

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 · 1 result. 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: Geneformer V2-316M attention edges, layer 13 (Kendiukhov 2026)	Protocol: Perturbation-first AUROC, K562 CRISPRi (Kendiukhov 2026) Dataset subset: Replogle genome-scale CRISPRi, K562, 280 evaluable perturbations (Kendiukhov 2026)	0.704 AUROC (per-perturbation AUROC for DE targets (LFC > 0.5), summarised over perturbations; K562 CRISPRi) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Geneformer V2-316M attention edges, layer 13 on Replogle genome-scale CRISPRi, K562, 280 evaluable perturbations gfm-guides-20261014-kendiukhov2026-protocol-pf-k562-crispri Aggregation: Not reported Systematic evaluation of single-cell foundation model interpretability: attention-derived edge scores add no incremental value over gene-level features for perturbation-target prediction (Kendiukhov 2026, BMC Genomics 27:634) · Page 7, 'Perturbation-first validation reveals gene-level dominance', paragraph 2, sentence 1: 'AUROC = 0.704 at L13 (n = 280 evaluable perturbations)'

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. 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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
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 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

Systematic evaluation of single-cell foundation model interpretability: attention-derived edge scores add no incremental value over gene-level features for perturbation-target prediction (Kendiukhov 2026, BMC Genomics 27:634) · Original source · Version of record, BMC Genomics 27:634, published 2026-07-22 (received 2026-03-10, accepted 2026-05-14)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guides-20261014-kendiukhov2026-config-geneformer-v2-316m-attention-l13

areas: single-cell; biological-networks
contexts: research
method types: foundation_model
reported name: Geneformer V2-316M attention L13
foundation model eligible: true
representation: Attention from layer 13, averaged over heads within the layer and then over cells, between the perturbed gene and each other gene. L13 was pre-specified from DLPFC brain data before K562 data were examined.
source locator: Page 13 'Models and data', 'Attention extraction and edge score computation', 'Model coverage by analysis family'
training setting: Zero-shot; pretrained weights, attention read out without fine-tuning
checkpoint: Geneformer V2-316M, HuggingFace ctheodoris/Geneformer subfolder Geneformer-V2-316M (18 layers, 18 heads), loaded with attn_implementation='eager'; revision not stated
version: Geneformer V2-316M
access reuse: Analysis code github.com/Biodyn-AI/biomechinterp-framework and Zenodo 10.5281/zenodo.18701417; not pinned to a commit in the article

Related records

configuration of: Geneformer
subject: Geneformer V2-316M layer 13 pre-specified as primary layer (Kendiukhov 2026)
system: Geneformer V2-316M attention edges, layer 13 on Replogle genome-scale CRISPRi, K562, 280 evaluable perturbations

Suggest a correction