mx/Jungfraujoch
2
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 67 Wiki Activity

Remove sample identities from the repository; document the rule

Browse Source 
Datasets may be confidential; sample names and measured unit cells committed to
the repo can leak outside the group working on them. Scrub existing occurrences
and add a "No sample identities in the repository" section to CLAUDE.md
(forbidden: sample/dataset names, internal codes, measured cells tied to a
sample; fine: space group / lattice / twinning descriptors).

- Comments: replace internal dataset codes and protein names with the
  crystallographic situation they illustrate (centred vs pseudo-symmetric,
  holohedral, cubic, F-cubic/hexagonal, ...).
- Docs: same, in the analysis/writer/stream references and example configs.
- Tests: rename sample-named identifiers, TEST_CASE names, file prefixes and
  asserted labels to neutral crystallographic names (e.g. tetragonal_uc);
  behaviour unchanged. Reduce the CrystFEL reference PDB to a bare CRYST1 cell
  file (cell.pdb) and rename the reference data file.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
leonarski_f
2026-07-15 17:19:43 +02:00
co-authored by Claude Opus 4.8
parent 0f3ccda779
commit abbee2d4dc
27 changed files with 159 additions and 4079 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/IndexingUnitTest.cpp
+43 -43
View File
@@ -246,14 +246,14 @@ TEST_CASE("FFTIndexer","[Indexing]") {
logger.Info("Time: {} ms", std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count());
}
TEST_CASE("PostIndexingRefinement_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]") {
Logger logger("PostIndexingRefinement_MultiLattice_TwoLysozymes_BraggPrediction");
TEST_CASE("PostIndexingRefinement_MultiLattice_TwoCrystals_BraggPrediction","[Indexing]") {
Logger logger("PostIndexingRefinement_MultiLattice_TwoCrystals_BraggPrediction");
UnitCell lysozyme_uc{36.9, 78.95, 78.95, 90.0, 90.0, 90.0};
CrystalLattice lysozyme_base(lysozyme_uc);
UnitCell tetragonal_uc{36.9, 78.95, 78.95, 90.0, 90.0, 90.0};
CrystalLattice tetragonal_base(tetragonal_uc);
CrystalLattice lysozyme_rot_1 = RotateLattice(lysozyme_base, MakeRotation(10.0f, 18.0f, 27.0f));
CrystalLattice lysozyme_rot_2 = RotateLattice(lysozyme_base, MakeRotation(66.0f, -14.0f, 101.0f));
CrystalLattice crystal_rot_1 = RotateLattice(tetragonal_base, MakeRotation(10.0f, 18.0f, 27.0f));
CrystalLattice crystal_rot_2 = RotateLattice(tetragonal_base, MakeRotation(66.0f, -14.0f, 101.0f));
DiffractionExperiment experiment(DetJF4M());
experiment.DetectorDistance_mm(75)
@@ -272,8 +272,8 @@ TEST_CASE("PostIndexingRefinement_MultiLattice_TwoLysozymes_BraggPrediction","[I
.mosaicity_multiplier = 4.0f
};
const auto spots_1 = BuildPredictedReciprocalSpots(experiment, lysozyme_rot_1, pred_settings);
const auto spots_2 = BuildPredictedReciprocalSpots(experiment, lysozyme_rot_2, pred_settings);
const auto spots_1 = BuildPredictedReciprocalSpots(experiment, crystal_rot_1, pred_settings);
const auto spots_2 = BuildPredictedReciprocalSpots(experiment, crystal_rot_2, pred_settings);
logger.Info("Predicted spots lattice 1: {}", spots_1.size());
logger.Info("Predicted spots lattice 2: {}", spots_2.size());
@@ -300,9 +300,9 @@ TEST_CASE("PostIndexingRefinement_MultiLattice_TwoLysozymes_BraggPrediction","[I
oCell(idx * 3 + 2, 2) = lattice.Vec2().z;
};
put_lattice(0, lysozyme_rot_1);
put_lattice(1, lysozyme_rot_2);
put_lattice(2, lysozyme_rot_1); // duplicate to verify overlap rejection
put_lattice(0, crystal_rot_1);
put_lattice(1, crystal_rot_2);
put_lattice(2, crystal_rot_1); // duplicate to verify overlap rejection
// Keep bootstrap scores tiny to disable candidate drift in iterative re-fitting.
scores(0) = 1e-6f;
@@ -324,12 +324,12 @@ TEST_CASE("PostIndexingRefinement_MultiLattice_TwoLysozymes_BraggPrediction","[I
REQUIRE(refined.size() >= 2);
int lysozyme_count = 0;
int crystal_count = 0;
for (const auto &lattice : refined) {
if (MatchesCellLengths(lattice.GetUnitCell(), lysozyme_uc))
++lysozyme_count;
if (MatchesCellLengths(lattice.GetUnitCell(), tetragonal_uc))
++crystal_count;
}
CHECK(lysozyme_count >= 2);
CHECK(crystal_count >= 2);
int64_t count_0 = 0;
int64_t count_1 = 0;
@@ -346,14 +346,14 @@ TEST_CASE("PostIndexingRefinement_MultiLattice_TwoLysozymes_BraggPrediction","[I
}
/*
TEST_CASE("FFTIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]") {
Logger logger("FFTIndexer_MultiLattice_TwoLysozymes_BraggPrediction");
TEST_CASE("FFTIndexer_MultiLattice_TwoCrystals_BraggPrediction","[Indexing]") {
Logger logger("FFTIndexer_MultiLattice_TwoCrystals_BraggPrediction");
UnitCell lysozyme_uc{36.9, 78.95, 78.95, 90.0, 90.0, 90.0};
CrystalLattice lysozyme_base(lysozyme_uc);
UnitCell tetragonal_uc{36.9, 78.95, 78.95, 90.0, 90.0, 90.0};
CrystalLattice tetragonal_base(tetragonal_uc);
CrystalLattice lysozyme_rot_1 = RotateLattice(lysozyme_base, MakeRotation(10.0f, 18.0f, 27.0f));
CrystalLattice lysozyme_rot_2 = RotateLattice(lysozyme_base, MakeRotation(66.0f, -14.0f, 101.0f));
CrystalLattice crystal_rot_1 = RotateLattice(tetragonal_base, MakeRotation(10.0f, 18.0f, 27.0f));
CrystalLattice crystal_rot_2 = RotateLattice(tetragonal_base, MakeRotation(66.0f, -14.0f, 101.0f));
DiffractionExperiment experiment(DetJF4M());
experiment.DetectorDistance_mm(75)
@@ -372,8 +372,8 @@ TEST_CASE("FFTIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]") {
.mosaicity_multiplier = 4.0f
};
auto spots_1 = BuildPredictedReciprocalSpots(experiment, lysozyme_rot_1, pred_settings);
auto spots_2 = BuildPredictedReciprocalSpots(experiment, lysozyme_rot_2, pred_settings);
auto spots_1 = BuildPredictedReciprocalSpots(experiment, crystal_rot_1, pred_settings);
auto spots_2 = BuildPredictedReciprocalSpots(experiment, crystal_rot_2, pred_settings);
logger.Info("Predicted spots lattice 1: {}", spots_1.size());
logger.Info("Predicted spots lattice 2: {}", spots_2.size());
@@ -389,7 +389,7 @@ TEST_CASE("FFTIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]") {
.FFT_HighResolution_A(2.0f)
.FFT_NumVectors(1024);
experiment.ImportIndexingSettings(settings)
.SetUnitCell(lysozyme_uc);
.SetUnitCell(tetragonal_uc);
REQUIRE(experiment.GetIndexingAlgorithm() == IndexingAlgorithmEnum::FFT);
@@ -404,20 +404,20 @@ TEST_CASE("FFTIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]") {
const float tolerance = experiment.GetIndexingSettings().GetTolerance();
int lysozyme_count = 0;
int crystal_count = 0;
for (size_t i = 0; i < result.lattice.size(); ++i) {
auto uc = result.lattice[i].GetUnitCell();
int64_t indexed_count = 0;
BuildIndexedMask(spots, result.lattice[i], tolerance, indexed_count);
logger.Info("Lattice {} cell ({:.1f} {:.1f} {:.1f}) indexes {} spots",
i, uc.a, uc.b, uc.c, indexed_count);
if (MatchesCellLengths(uc, lysozyme_uc))
++lysozyme_count;
if (MatchesCellLengths(uc, tetragonal_uc))
++crystal_count;
}
CHECK(lysozyme_count >= 2);
CHECK(crystal_count >= 2);
// Verify the two best lysozyme lattices are distinct (low overlap)
// Verify the two best crystal lattices are distinct (low overlap)
if (result.lattice.size() >= 2) {
int64_t count_0 = 0, count_1 = 0;
auto mask_0 = BuildIndexedMask(spots, result.lattice[0], tolerance, count_0);
@@ -429,14 +429,14 @@ TEST_CASE("FFTIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]") {
}
}
TEST_CASE("FFBIDXIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]") {
Logger logger("FFBIDXIndexer_MultiLattice_TwoLysozymes_BraggPrediction");
TEST_CASE("FFBIDXIndexer_MultiLattice_TwoCrystals_BraggPrediction","[Indexing]") {
Logger logger("FFBIDXIndexer_MultiLattice_TwoCrystals_BraggPrediction");
UnitCell lysozyme_uc{36.9, 78.95, 78.95, 90.0, 90.0, 90.0};
CrystalLattice lysozyme_base(lysozyme_uc);
UnitCell tetragonal_uc{36.9, 78.95, 78.95, 90.0, 90.0, 90.0};
CrystalLattice tetragonal_base(tetragonal_uc);
CrystalLattice lysozyme_rot_1 = RotateLattice(lysozyme_base, MakeRotation(10.0f, 18.0f, 27.0f));
CrystalLattice lysozyme_rot_2 = RotateLattice(lysozyme_base, MakeRotation(66.0f, -14.0f, 101.0f));
CrystalLattice crystal_rot_1 = RotateLattice(tetragonal_base, MakeRotation(10.0f, 18.0f, 27.0f));
CrystalLattice crystal_rot_2 = RotateLattice(tetragonal_base, MakeRotation(66.0f, -14.0f, 101.0f));
DiffractionExperiment experiment(DetJF4M());
experiment.DetectorDistance_mm(75)
@@ -455,8 +455,8 @@ TEST_CASE("FFBIDXIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]"
.mosaicity_multiplier = 4.0f
};
auto spots_1 = BuildPredictedReciprocalSpots(experiment, lysozyme_rot_1, pred_settings);
auto spots_2 = BuildPredictedReciprocalSpots(experiment, lysozyme_rot_2, pred_settings);
auto spots_1 = BuildPredictedReciprocalSpots(experiment, crystal_rot_1, pred_settings);
auto spots_2 = BuildPredictedReciprocalSpots(experiment, crystal_rot_2, pred_settings);
logger.Info("Predicted spots lattice 1: {}", spots_1.size());
logger.Info("Predicted spots lattice 2: {}", spots_2.size());
@@ -466,7 +466,7 @@ TEST_CASE("FFBIDXIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]"
spots.insert(spots.end(), spots_1.begin(), spots_1.end());
spots.insert(spots.end(), spots_2.begin(), spots_2.end());
experiment.SetUnitCell(lysozyme_uc);
experiment.SetUnitCell(tetragonal_uc);
experiment.IndexingAlgorithm(IndexingAlgorithmEnum::FFBIDX);
REQUIRE(experiment.GetIndexingAlgorithm() == IndexingAlgorithmEnum::FFBIDX);
@@ -482,20 +482,20 @@ TEST_CASE("FFBIDXIndexer_MultiLattice_TwoLysozymes_BraggPrediction","[Indexing]"
const float tolerance = experiment.GetIndexingSettings().GetTolerance();
int lysozyme_count = 0;
int crystal_count = 0;
for (size_t i = 0; i < result.lattice.size(); ++i) {
auto uc = result.lattice[i].GetUnitCell();
int64_t indexed_count = 0;
BuildIndexedMask(spots, result.lattice[i], tolerance, indexed_count);
logger.Info("Lattice {} cell ({:.1f} {:.1f} {:.1f}) indexes {} spots",
i, uc.a, uc.b, uc.c, indexed_count);
if (MatchesCellLengths(uc, lysozyme_uc))
++lysozyme_count;
if (MatchesCellLengths(uc, tetragonal_uc))
++crystal_count;
}
CHECK(lysozyme_count >= 2);
CHECK(crystal_count >= 2);
// Verify the two best lysozyme lattices are distinct (low overlap)
// Verify the two best crystal lattices are distinct (low overlap)
if (result.lattice.size() >= 2) {
int64_t count_0 = 0, count_1 = 0;
auto mask_0 = BuildIndexedMask(spots, result.lattice[0], tolerance, count_0);