Repository navigation
Fix solvation energy, Boltz-2 token alignment, report and AF3 parser issues - #32
Merged
DimaMolod merged 5 commits intoSep 28, 2026
Conversation
ProSurf skipped the per-atom accessible-area calculation for atoms with no partner-chain atom in reach, leaving their SAS at 0 even when a sibling atom of the same residue was at the interface. The solvation energy types charged groups (Arg NE/NH1/NH2, His ND1/NE2, carboxylate O1/O2) by comparing SAS between those siblings, so a residue straddling the cutoff could be typed charged in one state and neutral in the other. SAS is now computed for every atom of any residue with an atom near the other side, as PISA does for the atoms that matter here. Residues wholly away from the interface still keep SAS 0; their terms are identical in the free and bound states and cancel. On the six CCP4 references int_solv_en moves from +0.02..+1.09 kcal/mol off PISA to within 1e-4, so the test tolerance drops from 1.2 to 1e-3. Buried area, interface residues, H-bonds and salt bridges are unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Boltz-2 gives each ligand atom its own token, and the parser kept the leading N x N block of the PAE (and the first N pLDDT values) and read pair_chains_iptm by position among the scored chains. That is only right when every ligand chain follows the proteins; a ligand chain first or in between shifted every PAE entry and could return another pair's ipTM, the same class of error #30 fixed for AF3x. The token layout is rebuilt from the structure (one token per standard residue, one per atom for ligands and modified residues, whose scored token is the CA/C1' atom's as for AF3), and PAE/pLDDT are selected by it when the sizes match. pair_chains_iptm is recorded against the structure's chain order and dropped with a warning when its size does not match. The centre-atom token rule moves to BaseParser so AF3 and Boltz-2 share it. The bundled 6OGE run (crosslinker chains last) is unchanged; the new test_boltz.py covers ligand-first, ligand-between and mis-sized matrices and fails on the previous code. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- _find_pae_png built "*<model>*" globs from the raw model name: an empty
name made the invalid pattern "**PAE*plot*.png" (ValueError on Python
3.10-3.12, crashing generate_aggregate_report), and characters such as
"[" were read as glob syntax. The name is now escaped, and without one
only the ranked_0 PAE plot is considered.
- The per-interface caption said "10 metascore features"; it now counts
META_SCORE_FEATURES (11).
- The aggregate cover's median took the upper middle value for an even
number of interfaces; it now uses statistics.median.
- Appendix pages were numbered "A.<model name>", which the heading cuts
to eight characters ("A.model…"); they are now A.1, A.2, ... with the
model name kept in the title.
Each has a test that fails on the previous code.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The cache shared by interface area, H-bonds, salt bridges and solvation energy was keyed on each residue's full_id and first-atom coordinate. Every structure is parsed under the id "complex", so another model of the same chain pair whose residues start at the same N atoms (e.g. a side-chain repack) hit the stale result: a model with the second chain's side chains moved 50 A away reported the original 2717.28 A^2. The key now covers every residue id and name, atom name and element, and all coordinates. The cache keeps the four most recent results rather than up to 33 (which also held their structures in memory); one interface's four scores are computed back to back. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- _read_csv_order sorted rows on float(ranking_score) with NaN for a missing or unparsable score, and NaN keys leave Python's sort order arbitrary, so the "best" model could be wrong. Unscored rows now rank last and the rest keep their order. - The flat-layout structure lookup globbed "*seed-1_sample-1*", which also matches "..._sample-10_model.cif" and sorts it first. Glob hits must now carry the model name not followed by another digit. - process() indexed run.order[0] in best mode and raised IndexError when the ranking file listed no models; it now takes order[:1] and writes the explained empty CSV, as "all" mode already did. - Drop the unused model_dir in load_model and the private _find_existing in favour of BaseParser._first_existing. Tidy the mid-file imports in test_parsers_and_runner.py. Each behaviour change has a test that fails on the previous code. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Base automatically changed from
30-simplify
to
30-alphajudge-pae-handling-for-af3x-outputs-cross-linker-tokens
September 28, 2026 12:18
DimaMolod
marked this pull request as ready for review
September 28, 2026 12:18
DimaMolod
merged commit Sep 28, 2026
1d07261
into
30-alphajudge-pae-handling-for-af3x-outputs-cross-linker-tokens
12 checks passed
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a9963477e3
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| def rank(row: dict) -> float: | ||
| # A missing score ranks last; a NaN sort key would scramble the order. | ||
| value = score(row) | ||
| return -np.inf if np.isnan(value) else value |
There was a problem hiding this comment.
When ranking_scores.csv contains inf (for example from an overflowed upstream score), float() accepts it and this key ranks it above every finite model, so --models_to_analyse best selects an invalid model. This also conflicts with the subsequent np.isfinite check, which deliberately omits that model from scores; treat all non-finite values as unscored when constructing the sort key.
Useful? React with 👍 / 👎.
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.
These are fixes for the problems found while reviewing #31, plus a check of
parsers/af3.py. There is one commit per fix, and each behaviour change has a test that fails on the previous code.This PR is stacked on #31, so it targets
30-simplify. GitHub will retarget it to the #30 branch once #31 is merged.Fixes
a9774d6).int_solv_enwas off by +0.02 to +1.09 kcal/mol and now agrees to within 1e-4. The test tolerance drops fromabs=1.2to1e-3. Area, H-bonds and salt bridges are unchanged.69c9f1b).pair_chains_iptmby position among the scored chains. That is only right when every ligand chain comes after the proteins, which is the same class of bug as AlphaJudge PAE handling for AF3x outputs (cross-linker tokens) #30.test_boltz.pycovers the ligand-first and ligand-between cases.15cf721).model_used: it crashed the aggregate report through the invalid**glob on Python 3.10–3.12. Model names are now matched literally in PAE image lookup.A.<model>cut to eight characters; they are now numberedA.1,A.2, ….92ed184).full_idplus its first-atom coordinate, and every structure is loaded as"complex". A model whose side chains moved 50 Å still returned the cached 2717.28 Ų.a996347).ranking_scoregave a NaN sort key, which scrambles the order, so "best" could be the wrong model. Unscored rows now rank last.seed-1_sample-1matched and preferredseed-1_sample-10's structure.bestmode this raisedIndexError; it now writes the explained empty CSV.model_dirand the duplicate_find_existinghelper.Verification
pytest test/withALPHAJUDGE_RUN_SLOW_SC_REFERENCE=1: 103/103 pass (92 existing + 11 new regression tests).interface_solv_en(99 values, max |Δ| 1.085 kcal/mol) andinterface_meta_score(99 values, max |Δ| 0.0012) change; every other column is identical. All 32 PAE PNGs are byte-identical; 10 of 11 PDFs change, as expected from the metascore and report-text fixes.Worth knowing
interface_solv_enpercentile ladder was built with the previous solvation values. The correction is small next to its decile spacing (roughly 3–5 kcal/mol in the lower half). A recalibration run on the benchmark would make the ladder exact.interface_solv_enor the metascore were computed with the old solvation code.🤖 Generated with Claude Code