Add eight-model foundation-model GRN benchmark (revision) - #1
Open
Kendiukhov wants to merge 1 commit into
Open
Conversation
Broadens the cross-model comparison to eight single-cell foundation models
spanning six architectures (scGPT, Geneformer V1-10M/V2-104M/V2-316M,
AIDO.Cell-100M, scFoundation, tGPT, ESM2-3B/UCE control) under a uniform
embedding-cosine edge derivation, with paired significance tests.
Key results: ENETS2 mean per-TF AUROC spans 0.499-0.549 (chance 0.50); the
three best models are statistically indistinguishable and Geneformer vs scGPT
is not significant (paired Wilcoxon p = 0.67). A scGPT attention-vs-embedding
concordance check shows the weak-recovery finding is robust to edge-derivation
choice. Addresses the editor/Reviewer-2 request for broader benchmarking.
Adds revision/scripts/{crossmodel_foundation_benchmark,attention_embedding_concordance}.py,
their outputs under revision/outputs/, and a README section.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Broadens the cross-model comparison to eight single-cell foundation models spanning six architectures, addressing the editor (Prof. Lin Hou) and Reviewer 2 request to benchmark a broader set of foundation models and to test whether the Geneformer-vs-scGPT gap in Table 2 is significant.
Key results
Files
revision/scripts/crossmodel_foundation_benchmark.py,revision/scripts/attention_embedding_concordance.pyrevision/outputs/(CSVs, summaries, figure)Note: manuscript and response-letter materials are intentionally excluded from the public repo per
.gitignore; this PR contains only the reproducible analysis code and outputs.🤖 Generated with Claude Code