scFoundation cell-type annotation comparison Zheng68K: Zheng68K cell-type annotation

Overview

Zheng68K cell-type annotation. Scored with Macro F1 on Zheng68K subset used in scFoundation Supplementary Table4. Cell-type annotation evaluated by unweighted mean of cell-type F1 scores. Each class F1=TP/(TP+0.5*(FP+FN)), defined in Supplementary Note3. Exact dataset release, split manifest, fitting and preprocessing remain unextracted.

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

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

scFoundation cell-type annotation comparison Zheng68K: Zheng68K cell-type annotation

macro_f1 (fraction) · Higher values are better.

Every method scFoundation cell-type annotation comparison reports on Zheng68K cell-type annotation, scored with Macro F1 on Zheng68K subset used in scFoundation Supplementary Table4.

scFoundation cell-type annotation comparison Zheng68K: Zheng68K cell-type annotation · Zheng68K subset used in scFoundation Supplementary Table4 (scFoundation cell-type annotation comparison split)

Evidence origin: Author-reported evaluation, Evaluation origin not reported. Numerical source review does not establish independent reproduction.

scFoundation primary supplement, Table4 · Supplementary Table4, PDF p16; Supplementary Note3, Macro F1 score.

Complete seven-method by two-dataset comparison. Macro F1 is the unweighted mean of class-level F1 scores (Supplementary Note3).

All comparison limitations (5)

Complete seven-method by two-dataset comparison. Macro F1 is the unweighted mean of class-level F1 scores (Supplementary Note3).
No uncertainty, seeds or scored denominators printed in this table.
Exact training/fine-tuning procedure and split manifests are unextracted; do not assume zero-shot evaluation or matched training data.
Comparator executor provenance remains unreported from the inspected supplement; the table is the source, not an independent reproduction.
The scFoundation Zheng68K score also appears as the scale-100M result in Table2; do not count these as independent evidence.

Automated source review: 2026-09-23.

Find a tested model or method

No unavailable values; missing scores remain labelled and are never plotted as zero.

Showing 7 of 7 matching rows.

Zoom to observed range

Tested configuration

00.250.50.751

Reported score

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.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Evaluation design

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

Benchmarks

scFoundation cell-type annotation comparison

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

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 1
unreported: 6

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV · Model evaluation matrix · Source table · Release and checksums

Coverage is derived from release 2026-09-23-2b89723c6dd9. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

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

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-23-2b89723c6dd9
Property and statement	Original source and location	Review and provenance
Relationship: part of model-coverage-scfoundation-cell-annotation Individual claims	scFoundation primary supplement, Table4 Original source ↗ Supplementary Table4, PDF p16; Supplementary Note3, Macro F1 score. Version: 10.1038/s41592-024-02305-7 publisher supplement Retrieved: 2026-09-23T11:36:02.116209+00:00	source checked automated source review · 2026-09-23 Audit details Primary-source transcription with no human sign-off and no independent reproduction. Field: `links:part_of:model-coverage-scfoundation-cell-annotation` Claim: scfoundation-2024-supp-table4-association-zheng68k Source artifact SHA-256: `9ef9ed1b87014fb72b22cfc99a5382b01e6a6395a0c5de36921d155848162ae1` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

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

Sources and history

View linked audit checks and correction history

Release 2026-09-23-2b89723c6dd9 · Record review: source checked

1 source records and release history

scFoundation primary supplement, Table4 · Original source · 10.1038/s41592-024-02305-7 publisher supplement

Download this release

Technical metadata and extraction receipts

Stable ID: scfoundation-2024-supp-table4-task-zheng68k

areas: cells-spatial-multiomics
tasks: Zheng68K cell-type annotation
metric: Macro F1
metric direction: higher
dataset: Zheng68K subset used in scFoundation Supplementary Table4
protocol: Cell-type annotation evaluated by unweighted mean of cell-type F1 scores. Each class F1=TP/(TP+0.5*(FP+FN)), defined in Supplementary Note3. Exact dataset release, split manifest, fitting and preprocessing remain unextracted.
source locator: Supplementary Table4, PDF p16; Supplementary Note3, Macro F1 score.
comparison panels: id: scfoundation-2024-supp-table4-panel-zheng68k; title: scFoundation cell-type annotation comparison Zheng68K: Zheng68K cell-type annotation; protocol id: scfoundation-2024-supp-table4-task-zheng68k; dataset id: scfoundation-2024-supp-table4-dataset-zheng68k-subset-used-in-scfoundation-supplementary-table4; metric: macro_f1; unit: fraction; direction: higher; result ids: scfoundation-2024-supp-table4-result-scfoundation-zheng68k-macro-f1; scfoundation-2024-supp-table4-result-scbert-zheng68k-macro-f1; scfoundation-2024-supp-table4-result-celltypist-zheng68k-macro-f1; scfoundation-2024-supp-table4-result-scanvi-zheng68k-macro-f1; scfoundation-2024-supp-table4-result-actinn-zheng68k-macro-f1; scfoundation-2024-supp-table4-result-scanpy-zheng68k-macro-f1; scfoundation-2024-supp-table4-result-singlecellnet-zheng68k-macro-f1; source ids: coverage-source-scfoundation-supp; source locator: Supplementary Table4, PDF p16; Supplementary Note3, Macro F1 score.; context: Every method scFoundation cell-type annotation comparison reports on Zheng68K cell-type annotation, scored with Macro F1 on Zheng68K subset used in scFoundation Supplementary Table4.; caveats: Complete seven-method by two-dataset comparison. Macro F1 is the unweighted mean of class-level F1 scores (Supplementary Note3).; No uncertainty, seeds or scored denominators printed in this table.; Exact training/fine-tuning procedure and split manifests are unextracted; do not assume zero-shot evaluation or matched training data.; Comparator executor provenance remains unreported from the inspected supplement; the table is the source, not an independent reproduction.; The scFoundation Zheng68K score also appears as the scale-100M result in Table2; do not count these as independent evidence.; review: method: automated_source_review; date: 2026-09-23
entity level: protocol

Related records