Spaces:
Running
Running
Commit History
17 days ago
-
Deploy 6b1026c
github-actions[bot]Merge pull request #245 from WINTER4000/feat/self-service-cancel Source: https://github.com/WINTER4000/turingDNA/commit/6b1026caf551278420c4486fbe6bb596b24f61b457de896
22 days ago
-
Deploy 0ab3126
github-actions[bot]Merge pull request #212 from WINTER4000/claude/tender-mendel-v81ess Source: https://github.com/WINTER4000/turingDNA/commit/0ab31265a77936adff630619459a518791a73de6ff6973d
-
Deploy 1dc745d
github-actions[bot]Prime editing: design the pegRNA instead of refusing Source: https://github.com/WINTER4000/turingDNA/commit/1dc745d9b21b0e40c1a8317cfbeb3a4075e0a58b0bdb418 -
Deploy 53117c1
github-actions[bot]Validation corpus, a specificity handoff, and the design record Source: https://github.com/WINTER4000/turingDNA/commit/53117c103469b28cb1ec444c32e955243a998aa8ea9cb88
-
Deploy a2e39fd
github-actions[bot]Merge pull request #26 from WINTER4000/fix/dms-manifest-citation Source: https://github.com/WINTER4000/turingDNA/commit/a2e39fd538db248f9c830bb81b779c4ffe3bdce8729d57f
-
Deploy 121a500
github-actions[bot]Freemium: enforce the monthly run limit that the copy already promised Source: https://github.com/WINTER4000/turingDNA/commit/121a5004965fbdcbb911d6e20d5a2a9f614d5984cb1ea1c
-
Deploy 3a1eb78
github-actions[bot]Every recorded failure, replayed, so none of them can happen twice Source: https://github.com/WINTER4000/turingDNA/commit/3a1eb7883af2692c008f133b5c561df1d9d2ed15fcc9c2f
-
Deploy 01b0d87
github-actions[bot]The agent can read the vector catalogue instead of remembering one Source: https://github.com/WINTER4000/turingDNA/commit/01b0d87657c7fa96b312320edd6058984492315f4d448b3
-
Deploy: promoter library 10 entries across E. coli, plant and mammalian
Tengo Gzirishvili +1: ClaudeSquashed deploy of GitHub main. Sequences machine-extracted from GenBank records' own feature tables, each agreed by 2+ independent accessions (scripts/import_promoters.py). CaMV 35S, EF-1alpha, U6, lac, tac and araBAD added; CMV deliberately excluded pending a canonical-length consensus. Co-Authored-By: Claude <noreply@anthropic.com>9c2665c
-
Commit the real 3-dataset benchmark result
Tengo GzirishviliFirst genuine multi-dataset run: BLAT_ECOLX_Stiffler2015 (n=4996, rho=0.5165), PABP_YEAST_Melamed2013 (n=1188, rho=0.4998), DLG4_RAT_McLaughlin2012 (n=1577, rho=0.5246). Computed live on the Space via /api/admin/run-benchmarks against dee/data/dms_fixtures/.461718a
-
Two more real, validated DMS assays — clears the commons k-anonymity floor
Tengo Gzirishvili +1: Claude Sonnet 5Adds PABP_YEAST_Melamed2013 (1,188 mutants, PABP RRM2 domain, binding enrichment) and DLG4_RAT_McLaughlin2012 (1,660 mutants, PSD-95 PDZ3 domain, CRIPT-peptide binding) to dee/data/dms_fixtures/ — both from debbiemarkslab/DeepSequence's own bundled reference examples (the repository behind Riesselman et al. 2018 Nature Methods), same trust tier as the existing BLAT_ECOLX fixture. Full-length canonical UniProt sequences (P04147, P31016); every one of the 2,848 combined mutations cross-validated against those sequences (100% wild-type-residue match, UniProt numbering used directly — no offset needed, unlike BLAT_ECOLX) before being committed. This is the actual point: the Field Atlas seed (dee.core.dms_seed) requires >= MIN_USERS=3 INDEPENDENT assays before any substitution type clears the k-anonymity floor. With only BLAT_ECOLX, /api/admin/seed-commons correctly, honestly returned 0 rows. With 3 independent assays now bundled, most of the 380 possible substitution types are measured by…5194826 -
Commit the first real benchmark result + fix a self-invalidating test
Tengo Gzirishvili +1: Claude Sonnet 5Pulled the live result from /api/admin/run-benchmarks (run by the founder against the bundled BLAT_ECOLX fixture on the actual Space, real ESM-2 small): median Spearman rho 0.5165, top-decile precision 47.8%, across all 4,996 real mutations. This is now the permanent, committed state, so it survives future redeploys instead of resetting to the empty placeholder. Also fixes test_benchmarks_route_public_and_honest_empty, which asserted the bundled file is ALWAYS empty — true when it was written, but wrong the moment a real run legitimately populates it (which just happened). Replaced with a shape-only assertion (the route never fabricates, whatever the current file state is) plus a separate test that the honest-empty behavior still holds when the file is genuinely absent. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>5dc55c5 -
Admin endpoints to run the real validation + seed against bundled DMS
Tengo Gzirishvili +1: Claude Sonnet 5Closes the loop on the "no fabricated numbers" promise: these are the two routes that actually produce real data, running IN the Space where ESM-2 and the Supabase credentials already live (this dev machine is an Intel Mac — PyTorch dropped x86_64 macOS wheels after 2.2.2, so real ESM-2 can only run where the Space already runs it, not here). - dee/data/dms_fixtures/ — one real, rigorously validated public DMS dataset: TEM-1 beta-lactamase (Stiffler/Ranganathan 2015 Cell), 4,996 single mutants, the SAME reference example bundled with facebookresearch/esm for the exact zero-shot scoring scheme our scorer.py implements. Every single mutation was cross-validated against the reconstructed reference sequence (100% wild-type-residue match) before being committed — the numbering in the original paper is absolute (offset 24), renumbered to local 1-indexed positions matching the bundled sequence, verified twice. - dee.core.benchmark.predict_additive — sum-of-single-site ΔLL predi…598a072
-
Receipts + seed: validation harness, DMS→commons seeding, evidence UI
Tengo Gzirishvili +1: Claude Opus 4.8Turns the glass-box thesis from claims into proof — and gives the empty commons a path to real data. Honest by construction: no benchmark number is ever hand-entered; the app serves only what a real run produced, and ships an explicit "pending" state until then (this sandbox has no torch/ESM, so the numbers get made on a box with the weights). - dee/core/benchmark.py — validation harness: average-rank Spearman ρ + top-decile precision ("of your top picks, how many are genuinely high- fitness?") + cross-dataset medians. Pure numpy, predictions injected → unit-testable without ESM. - dee/core/dms_seed.py — turns published DMS assays into de-identified substitution-prior rows via the SAME k-anonymized aggregate machinery user data uses (each assay = one contributor; a substitution needs ≥ MIN_USERS independent studies to survive). ESM-free, so it can seed the commons with real, citable data on day one; user results refine it after. - scripts/run_benchmarks.py + scripts/seed…8d1e644