regen(multioracle): tile LegNet across the locus for the IGV browser; dedup CAGE - #99
Merged
Merged
Conversation
…sis_figures render_finemap_table + the `finemap` subcommand produce Fig 5 (fig_rs9504151_finemap.png) for the chorus-article post: a clean Top-N causal-variant table from a prioritize_causal_variants run, highlighting the lead (rs9504151, #1) and the high-LD neighbour rs62384944. The article's figures/README.md and reproduce/ steps already reference `regenerate_analysis_figures.py finemap`; this commits the code behind it so Fig 5 is reproducible from the repo (ism/tf_scan were already committed in #96). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
… dedup CAGE The multi-oracle genome-browser figure showed LegNet only as a 200 bp blip at the variant while every other oracle spanned the locus (ChromBPNet swaps in a predict_sliding track; LegNet had no equivalent). Add `_legnet_sliding_prediction` — tiles LegNet's 200 bp window non-overlapping across ±512 kb via predict_bigseq and expands each window's MPRA-activity scalar to a 1 bp-resolution OraclePrediction matching ChromBPNet's contract — and swap it into the legnet report's IGV-display predictions in `run_legnet`. The variant-effect TABLE value is unchanged (still the native 200 bp window). Also drop the redundant CAGE `/-` strand from ALPHAGENOME_TRACKS and add a consolidator-side `_dedup_duplicate_display_tracks` guard, so the AlphaGenome CAGE band is not duplicated in the unified browser. Addresses co-author (Lorenzo) review of the chorus-article SORT1 worked example. Note: the regenerated multioracle HTML is large (LegNet 1 bp track over 1 Mb); the committed article figure is a PNG, and example HTML is regenerable, so it is not committed here. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
lucapinello
added a commit
that referenced
this pull request
Jun 22, 2026
…101) #99 deduped the duplicated AlphaGenome CAGE track by keeping the + strand, but that strand scores +1.22 while the article (Fig 3) cites +1.52 — which is the MINUS strand (same 501 bp / sum / log2FC scorer; pure strand difference). Keep the - strand so a fresh `regenerate_multioracle` reproduces the published +1.52, and because the SORT1/CELSR2/PSRC1 locus is transcribed on the minus strand. Still a single CAGE display track (the dedup from #99 is preserved). Co-authored-by: lp698 <lp698@dimm2fv07n65x.partners.org> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
lucapinello
added a commit
that referenced
this pull request
Jul 31, 2026
…#117) The ChromBPNet per-track CDFs changed (#113 + the HF background rebuild), so every committed ChromBPNet artefact drifted. Regenerating them also surfaced three artefacts stale against EARLIER merged changes that were never re-executed. All four effects are separated so nothing is misattributed to expm1. 1. expm1 (the intended change). ChromBPNet raw counts come down by exactly the window softmax mass w; percentile RANKINGS unchanged: SORT1 DNASE:HepG2 ref 287.857 -> 287.237 (-0.620) alt 747.653 -> 747.014 (-0.639) log2FC +1.37394 -> +1.37581 effect %ile 0.9995, activity %ile 0.9059 (unchanged) klf1 locus profile max 127.333 -> 127.307, mean 0.462 -> 0.461 2. SORT1_chrombpnet was stale since 2026-05-09, predating the 2026-06-17 windowing fix (#94). That is the large jump (ref 48.53 -> 287.24, log2FC +0.318 -> +1.376), NOT expm1 — the post-#94 multioracle artefact already carried +1.37394, which the regenerated value matches to within the expm1 residual. 3. klf1's EPInformer-seq cells were stale against the 2026-06-04 "widewin-roadmap retrain (sparse H3K27ac)" weights swap on lucapinello/chorus-epinformerseq-v2 (HF commit 2654c05b7c) — committed alongside it but never re-executed. Hence K562 H3K27ac mean 1.771 -> 0.132. Verified NOT device-dependent: cpu vs cuda agree to 0.006 on a 3.78 range (0.16%). epinformerseq.py:416 calls hf_hub_download with no `revision`, which is what let this drift silently. 4. The AlphaGenome report was stale against the CAGE minus-strand dedup (#99/#101); it still carried both strands. all_scores 61 -> 32 is entirely CAGE:HepG2 58 -> 29 — the duplicate #101 exists to remove. No track lost: same 4 unique descriptions before and after. Notebooks re-executed on H100, zero error outputs: klf1 14/14 cells, advanced_multi_oracle 57/57, comprehensive_showcase 38/38. Registering the documented `chorus` kernelspec (examples/notebooks/README.md:45) was required first. Re-execution also dropped a foreign-home path leak (/Users/jieconglin) from klf1's outputs. DELIBERATELY NOT REGENERATED — blocked, needs a decision: rs12740374_SORT1_legnet_report.html and rs12740374_SORT1_multioracle_report.html are left at their origin/main bytes. #99 (2026-06-18) added "tile LegNet across the locus for the IGV browser", but the legnet artefact was last committed 2026-06-17 (#95, single-window), so the tiling has never been applied. Applying it embeds a locus-wide 1-bp array and the report becomes 137 MB / the consolidated one 145 MB — both above GitHub's 100 MiB file limit, i.e. unpushable. Dropping legnet's .pkl instead yields a shippable 9.55 MB but silently loses legnet's 3 IGV tracks (21 -> 18). The committed 9.93 MB / 21-track artefact came from a pre-#99 single-window .pkl and is not reproducible with current code. So #99 has been unshippable since it merged. Options: bin/downsample the embedded IGV arrays, revert the tiling, or move these HTMLs to Git LFS. Consequence: the consolidated example_output.{md,json} here carry the corrected ChromBPNet numbers while the consolidated HTML does not, until that is resolved. Fast suite: 477 passed, 4 skipped, 0 errors. Co-authored-by: Claude Opus 5 <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.
Makes the LegNet track in the multi-oracle genome browser span the locus (tiled 200 bp windows -> predicted-MPRA profile, 1 bp-resolution OraclePrediction like ChromBPNet's predict_sliding) instead of a 200 bp blip; the variant-effect table value is unchanged. Also removes a duplicate AlphaGenome CAGE display track at the source. Addresses Lorenzo's review of the chorus-article SORT1 example.