leonarski_fandClaude Opus 4.8
abbee2d4dc
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>
325 lines
16 KiB
C++
325 lines
16 KiB
C++
// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
|
|
// SPDX-License-Identifier: GPL-3.0-only
|
|
|
|
#include "ModelValidation.h"
|
|
|
|
#include <cmath>
|
|
#include <complex>
|
|
#include <array>
|
|
#include <vector>
|
|
#include <unordered_map>
|
|
|
|
#include <gemmi/pdb.hpp> // read_pdb
|
|
#include <gemmi/gz.hpp> // MaybeGzipped
|
|
#include <gemmi/it92.hpp> // IT92 x-ray form factors
|
|
#include <gemmi/dencalc.hpp> // DensityCalculator
|
|
#include <gemmi/fourier.hpp> // transform_map_to_f_phi, get_f_phi_on_grid, transform_f_phi_grid_to_map
|
|
#include <gemmi/solmask.hpp> // SolventMasker
|
|
#include <gemmi/scaling.hpp> // Scaling (bulk solvent + anisotropic B)
|
|
#include <gemmi/ccp4.hpp> // Ccp4 map I/O
|
|
#include <gemmi/mtz.hpp> // Mtz (map-coefficient output)
|
|
|
|
#include "../common/Logger.h"
|
|
#include "../image_analysis/scale_merge/ReindexAmbiguity.h" // ReindexReflections
|
|
|
|
namespace {
|
|
|
|
using Table = gemmi::IT92<float>;
|
|
|
|
// Stable key for a Miller index reduced into the ASU (indices are small, well within +/-512).
|
|
long hkl_key(const gemmi::Miller &h) {
|
|
return (h[0] + 512L) * 1048576 + (h[1] + 512L) * 1024 + (h[2] + 512L);
|
|
}
|
|
|
|
// Write an FFT of ASU map coefficients as a CCP4 map; return its RMS (for reporting / sigma units).
|
|
double write_ccp4(gemmi::AsuData<std::complex<float>> &coef, const std::string &path) {
|
|
coef.ensure_sorted();
|
|
std::array<int, 3> size = gemmi::get_size_for_hkl(coef, {{0, 0, 0}}, 3.0);
|
|
gemmi::Grid<float> map =
|
|
gemmi::transform_f_phi_grid_to_map(gemmi::get_f_phi_on_grid<float>(coef, size, true));
|
|
gemmi::Ccp4<float> ccp4;
|
|
ccp4.grid = map;
|
|
ccp4.update_ccp4_header(2);
|
|
ccp4.write_ccp4_map(path);
|
|
return ccp4.hstats.rms;
|
|
}
|
|
|
|
} // namespace
|
|
|
|
ModelValidationResult ValidateAgainstModel(const std::vector<MergedReflection> &merged,
|
|
const UnitCell &cell,
|
|
const std::string &model_path,
|
|
const std::string &output_prefix,
|
|
Logger &logger,
|
|
std::optional<int> data_space_group_number,
|
|
bool probe_indexing_ambiguity) {
|
|
ModelValidationResult result;
|
|
|
|
// --- read the atomic model ---
|
|
gemmi::Structure st;
|
|
try {
|
|
st = gemmi::read_pdb(gemmi::MaybeGzipped(model_path));
|
|
} catch (const std::exception &e) {
|
|
logger.Error("Model validation: cannot read model {}: {}", model_path, e.what());
|
|
return result;
|
|
}
|
|
if (st.models.empty() || !st.cell.is_crystal()) {
|
|
logger.Error("Model validation: model {} has no atoms or no unit cell", model_path);
|
|
return result;
|
|
}
|
|
const gemmi::SpaceGroup *sg = st.find_spacegroup();
|
|
if (!sg) {
|
|
logger.Error("Model validation: model {} has no usable space group", model_path);
|
|
return result;
|
|
}
|
|
|
|
// If the data was indexed in the enantiomorph of the model's space group (e.g. data P4(1)2(1)2,
|
|
// model P4(3)2(1)2 - the merged intensities cannot tell them apart), reindex the observed
|
|
// reflections into the model's hand so the two settings agree. This does not change the
|
|
// R-factors (which use |F|), but keeps the observed data consistent with the model.
|
|
std::vector<MergedReflection> reindexed;
|
|
const std::vector<MergedReflection> *obs_ptr = &merged;
|
|
if (data_space_group_number && *data_space_group_number != sg->number) {
|
|
const gemmi::SpaceGroup *dsg = gemmi::find_spacegroup_by_number(*data_space_group_number);
|
|
if (dsg && dsg->is_enantiomorphic() && sg->is_enantiomorphic()) {
|
|
gemmi::GroupOps eops = dsg->operations();
|
|
eops.change_basis_forward(dsg->change_of_hand_op());
|
|
const gemmi::SpaceGroup *enant = gemmi::find_spacegroup_by_ops(eops);
|
|
if (enant && enant->number == sg->number) {
|
|
reindexed = ReindexReflections(merged, dsg->change_of_hand_op());
|
|
obs_ptr = &reindexed;
|
|
logger.Info("Model validation: data space group {} is the enantiomorph of the model {}; "
|
|
"reindexed the observed reflections into the model's hand",
|
|
dsg->short_name(), sg->hm);
|
|
}
|
|
}
|
|
}
|
|
const std::vector<MergedReflection> &obs = *obs_ptr;
|
|
|
|
// Resolution limit from the data (the merged set is already resolution-trimmed).
|
|
double d_min = 0.0;
|
|
for (const MergedReflection &r : obs)
|
|
if (r.d > 0 && (d_min == 0.0 || r.d < d_min))
|
|
d_min = r.d;
|
|
if (d_min <= 0.0) {
|
|
logger.Error("Model validation: merged reflections carry no resolution");
|
|
return result;
|
|
}
|
|
|
|
// Re-fractionalize the model into the data cell (rigid cell adjustment; no refinement).
|
|
const gemmi::UnitCell data_cell = cell; // UnitCell -> gemmi::UnitCell
|
|
if (data_cell.is_crystal()) {
|
|
gemmi::UnitCell old = st.cell;
|
|
for (gemmi::Model &m : st.models)
|
|
for (gemmi::Chain &ch : m.chains)
|
|
for (gemmi::Residue &r : ch.residues)
|
|
for (gemmi::Atom &a : r.atoms)
|
|
a.pos = data_cell.orthogonalize(old.fractionalize(a.pos));
|
|
st.cell = data_cell;
|
|
}
|
|
st.setup_cell_images();
|
|
const gemmi::UnitCell &ucell = st.cell;
|
|
|
|
logger.Info("Model validation: {} atoms, cell a={:.2f} b={:.2f} c={:.2f}, sg {}, to {:.2f} A",
|
|
gemmi::count_atom_sites(st.models[0]), ucell.a, ucell.b, ucell.c, sg->hm, d_min);
|
|
|
|
// --- Fcalc (atomic) via electron density on a grid + FFT ---
|
|
gemmi::DensityCalculator<Table, float> dc;
|
|
dc.d_min = d_min;
|
|
dc.rate = 1.5;
|
|
dc.set_grid_cell_and_spacegroup(st);
|
|
dc.set_refmac_compatible_blur(st.models[0]);
|
|
dc.put_model_density_on_grid(st.models[0]);
|
|
gemmi::AsuData<std::complex<float>> fcalc =
|
|
gemmi::transform_map_to_f_phi(dc.grid, true).prepare_asu_data(dc.d_min, dc.blur, false, false, false);
|
|
|
|
// --- flat bulk-solvent mask -> Fmask ---
|
|
// Refmac radii give a slightly lower R than the Cctbx set on our test cases, at no cost.
|
|
gemmi::SolventMasker masker(gemmi::AtomicRadiiSet::Refmac);
|
|
gemmi::Grid<float> mask_grid;
|
|
mask_grid.unit_cell = dc.grid.unit_cell;
|
|
mask_grid.spacegroup = dc.grid.spacegroup;
|
|
mask_grid.set_size_from_spacing(dc.requested_grid_spacing(), gemmi::GridSizeRounding::Up);
|
|
masker.put_mask_on_grid(mask_grid, st.models[0]);
|
|
gemmi::AsuData<std::complex<float>> fmask =
|
|
gemmi::transform_map_to_f_phi(mask_grid, true).prepare_asu_data(dc.d_min, 0);
|
|
|
|
gemmi::GroupOps gops = sg->operations();
|
|
gemmi::ReciprocalAsu asu(sg);
|
|
|
|
// --- fit the (scaled, solvent-corrected) model to one observed set and score it ---
|
|
// Factored into a lambda so we can probe indexing (merohedral) ambiguities: run the same scale +
|
|
// R computation on each reindexing of the observed reflections and keep the lowest-R-free one.
|
|
struct Fit {
|
|
gemmi::AsuData<std::complex<float>> fmodel, map2fofc, mapfofc;
|
|
std::unordered_map<long, std::pair<double, bool>> obs_by_hkl; // hkl -> (Fobs, is_free)
|
|
double r_work = 1, r_free = 1, k_sol = 0, b_sol = 0, k_overall = 0;
|
|
int n_w = 0, n_f = 0;
|
|
};
|
|
auto fit_model = [&](const std::vector<MergedReflection> &obs_in) -> Fit {
|
|
Fit out;
|
|
out.fmodel = fcalc; // copy the atomic structure factors; scaling mutates them in place
|
|
|
|
// --- observed amplitudes into the model ASU, keyed by hkl (also remember free flag) ---
|
|
// Observed amplitudes are the French-Wilson |F| already computed at the end of the merge
|
|
// (MergedReflection.F), so the model R-free / maps use exactly the same amplitudes as the
|
|
// written reflection file.
|
|
gemmi::AsuData<gemmi::ValueSigma<float>> fobs;
|
|
fobs.unit_cell_ = ucell;
|
|
fobs.spacegroup_ = sg;
|
|
for (const MergedReflection &r : obs_in) {
|
|
if (std::isnan(r.F)) continue;
|
|
gemmi::Miller h{{r.h, r.k, r.l}};
|
|
if (!asu.is_in(h)) h = asu.to_asu(h, gops).first;
|
|
fobs.v.push_back({h, {r.F, 1.0f}});
|
|
out.obs_by_hkl[hkl_key(h)] = {r.F, r.rfree_flag};
|
|
}
|
|
fobs.ensure_asu();
|
|
fobs.ensure_sorted();
|
|
|
|
// --- scale Fmodel(+solvent) to Fobs: k_overall, anisotropic B, k_sol, b_sol ---
|
|
gemmi::Scaling<float> scaling(ucell, sg);
|
|
scaling.use_solvent = true;
|
|
scaling.prepare_points(out.fmodel, fobs, &fmask);
|
|
scaling.fit_isotropic_b_approximately();
|
|
scaling.fit_parameters();
|
|
scaling.scale_data(out.fmodel, &fmask); // out.fmodel now holds the scaled, solvent-corrected Fmodel
|
|
out.k_sol = scaling.k_sol;
|
|
out.b_sol = scaling.b_sol;
|
|
out.k_overall = scaling.k_overall;
|
|
|
|
// The model is scaled to the data with an overall scale, an anisotropic B and a flat bulk
|
|
// solvent only - the standard, few-parameter model that refinement programs use. A dataset-
|
|
// specific free-form per-resolution-shell rescale would lower this dataset's R a little, but
|
|
// it reshapes each map's radial amplitude profile differently, so a batch of maps would no
|
|
// longer be directly comparable. For a fragment-screening / PanDDA campaign, comparable maps
|
|
// across datasets matter more than the last bit of per-dataset R, so it is deliberately omitted.
|
|
|
|
// --- R-work / R-free and map coefficients (2Fo-Fc and Fo-Fc, model phases) ---
|
|
out.map2fofc.unit_cell_ = ucell; out.map2fofc.spacegroup_ = sg;
|
|
out.mapfofc.unit_cell_ = ucell; out.mapfofc.spacegroup_ = sg;
|
|
double num_w = 0, den_w = 0, num_f = 0, den_f = 0;
|
|
for (const auto &hv : out.fmodel.v) {
|
|
auto it = out.obs_by_hkl.find(hkl_key(hv.hkl));
|
|
if (it == out.obs_by_hkl.end()) continue;
|
|
double Fo = it->second.first;
|
|
double Fc = std::abs(hv.value);
|
|
double phi = std::arg(hv.value);
|
|
if (it->second.second) { num_f += std::fabs(Fo - Fc); den_f += Fo; ++out.n_f; }
|
|
else { num_w += std::fabs(Fo - Fc); den_w += Fo; ++out.n_w; }
|
|
std::complex<float> ph = std::polar(1.0f, static_cast<float>(phi));
|
|
out.map2fofc.v.push_back({hv.hkl, static_cast<float>(2 * Fo - Fc) * ph});
|
|
out.mapfofc.v.push_back({hv.hkl, static_cast<float>(Fo - Fc) * ph});
|
|
}
|
|
out.r_work = den_w > 0 ? num_w / den_w : 1;
|
|
out.r_free = den_f > 0 ? num_f / den_f : 1;
|
|
return out;
|
|
};
|
|
|
|
// --- indexing (merohedral) ambiguity ---
|
|
// When a reference MTZ was supplied, the data were already reindexed to agree with the reference
|
|
// intensities (at the merge stage for rotation data, per image in stills scaling), and that
|
|
// choice is authoritative - we keep it. Only with a model and NO reference do we resolve the
|
|
// ambiguity here, as a fallback, by fitting each candidate reindexing and keeping the lowest
|
|
// R-free. A no-op either way for a holohedral crystal (no twin laws). The
|
|
// enantiomorph/screw ambiguity is never probed by R-free: |Fcalc| is the same for both hands, so
|
|
// it cannot distinguish them - that is taken from the model hand above.
|
|
Fit best = fit_model(obs);
|
|
if (probe_indexing_ambiguity) {
|
|
const auto reindex_ops = ReindexAmbiguityOperators(cell, sg->number);
|
|
bool did_reindex = false;
|
|
for (const auto &op : reindex_ops) {
|
|
Fit cand = fit_model(ReindexReflections(obs, op));
|
|
if (cand.r_free < best.r_free) { best = std::move(cand); did_reindex = true; }
|
|
}
|
|
if (!reindex_ops.empty())
|
|
logger.Info("Model validation: no reference - probed {} indexing solution(s) against the model; "
|
|
"{} (R-free {:.4f})", reindex_ops.size() + 1,
|
|
did_reindex ? "reindexed to the lower-R-free solution" : "kept the current indexing",
|
|
best.r_free);
|
|
}
|
|
|
|
gemmi::AsuData<std::complex<float>> &fmodel = best.fmodel;
|
|
gemmi::AsuData<std::complex<float>> &map2fofc = best.map2fofc;
|
|
gemmi::AsuData<std::complex<float>> &mapfofc = best.mapfofc;
|
|
std::unordered_map<long, std::pair<double, bool>> &obs_by_hkl = best.obs_by_hkl;
|
|
|
|
result.r_work = best.r_work;
|
|
result.r_free = best.r_free;
|
|
result.n_work = best.n_w;
|
|
result.n_free = best.n_f;
|
|
result.k_sol = best.k_sol;
|
|
result.b_sol = best.b_sol;
|
|
result.k_overall = best.k_overall;
|
|
|
|
// --- write the maps and score the 2Fo-Fc map at atom centres (a real map peaks there) ---
|
|
const std::string p2 = output_prefix + "_2fofc.ccp4";
|
|
const std::string pd = output_prefix + "_fofc.ccp4";
|
|
double rms2 = write_ccp4(map2fofc, p2);
|
|
write_ccp4(mapfofc, pd);
|
|
|
|
// Recompute the 2Fo-Fc real-space grid once more to sample it at atom positions.
|
|
{
|
|
map2fofc.ensure_sorted();
|
|
std::array<int, 3> size = gemmi::get_size_for_hkl(map2fofc, {{0, 0, 0}}, 3.0);
|
|
gemmi::Grid<float> grid =
|
|
gemmi::transform_f_phi_grid_to_map(gemmi::get_f_phi_on_grid<float>(map2fofc, size, true));
|
|
double s = 0; int n = 0;
|
|
for (gemmi::Model &m : st.models)
|
|
for (gemmi::Chain &ch : m.chains)
|
|
for (gemmi::Residue &r : ch.residues)
|
|
for (gemmi::Atom &a : r.atoms) { s += grid.interpolate_value(a.pos); ++n; }
|
|
result.mean_atom_density_sigma = (n > 0 && rms2 > 0) ? (s / n) / rms2 : 0;
|
|
}
|
|
|
|
// --- MTZ of map coefficients so the maps can be re-opened / rebuilt in Coot etc. ---
|
|
try {
|
|
gemmi::Mtz mtz(true);
|
|
mtz.spacegroup = sg;
|
|
mtz.set_cell_for_all(ucell);
|
|
mtz.add_dataset("model_validation");
|
|
mtz.add_column("FP", 'F', -1, -1, false);
|
|
mtz.add_column("FC", 'F', -1, -1, false);
|
|
mtz.add_column("PHIC", 'P', -1, -1, false);
|
|
mtz.add_column("FWT", 'F', -1, -1, false);
|
|
mtz.add_column("PHWT", 'P', -1, -1, false);
|
|
mtz.add_column("DELFWT", 'F', -1, -1, false);
|
|
mtz.add_column("PHDELWT", 'P', -1, -1, false);
|
|
mtz.add_column("FREE", 'I', -1, -1, false);
|
|
std::vector<float> data;
|
|
int nref = 0;
|
|
for (const auto &hv : fmodel.v) {
|
|
auto it = obs_by_hkl.find(hkl_key(hv.hkl));
|
|
if (it == obs_by_hkl.end()) continue;
|
|
double Fo = it->second.first;
|
|
double Fc = std::abs(hv.value);
|
|
double phi_deg = gemmi::phase_in_angles(hv.value);
|
|
data.insert(data.end(), {static_cast<float>(hv.hkl[0]), static_cast<float>(hv.hkl[1]),
|
|
static_cast<float>(hv.hkl[2]),
|
|
static_cast<float>(Fo), static_cast<float>(Fc),
|
|
static_cast<float>(phi_deg),
|
|
static_cast<float>(2 * Fo - Fc), static_cast<float>(phi_deg),
|
|
static_cast<float>(Fo - Fc), static_cast<float>(phi_deg),
|
|
it->second.second ? 0.0f : 1.0f});
|
|
++nref;
|
|
}
|
|
mtz.nreflections = nref;
|
|
mtz.data = std::move(data);
|
|
mtz.write_to_file(output_prefix + "_maps.mtz");
|
|
} catch (const std::exception &e) {
|
|
logger.Warning("Model validation: could not write map MTZ: {}", e.what());
|
|
}
|
|
|
|
result.ok = true;
|
|
result.maps_prefix = output_prefix;
|
|
logger.Info("Model validation: R-work={:.4f} ({} refl) R-free={:.4f} ({} refl) "
|
|
"[overall + anisotropic B + bulk solvent]",
|
|
result.r_work, result.n_work, result.r_free, result.n_free);
|
|
logger.Info("Model validation: bulk solvent k_sol={:.3f} b_sol={:.1f}, k_overall={:.3f}",
|
|
result.k_sol, result.b_sol, result.k_overall);
|
|
logger.Info("Model validation: mean 2Fo-Fc density at atom centres = {:.2f} sigma", result.mean_atom_density_sigma);
|
|
logger.Info("Model validation: wrote {}_2fofc.ccp4, {}_fofc.ccp4, {}_maps.mtz",
|
|
output_prefix, output_prefix, output_prefix);
|
|
return result;
|
|
}
|