Files
Jungfraujoch/tests/RefineOnlyTest.cpp
T
leonarski_f a218c0bec8 rugnux --mode refine: refine a model against merged structure factors, nothing processed
rugnux --mode refine --model model.cif -o out data.mtz

The input is an MTZ or a structure-factor mmCIF, gzipped or not, by content
(writer/RugnuxReflectionFile: parsing in the file layer, the library reads no file). Columns are
found, not named: F/SIGF-like amplitudes (calculated amplitudes and map coefficients passed over),
else intensities made into amplitudes by French-Wilson, else the mean of the anomalous pairs; the
free set from a FreeR_flag-like column (0 the test set, or the minority value), else rugnux's own
5 % set. RunRefineOnly (rugnux/RugnuxRefine) runs RefineModel; the outputs are --refine's
(_refined_model.cif, _refined_maps.mtz, _blobs.json) and a report with the REFINE_ keys, the input's
REFINE_FRENCH_WILSON / REFINE_FREE_FLAGS, and every term of the start score under REFINE_SCORE_
(also in --refine's section). --refine-score-only scores the model as given; --refine-d-min cuts
the resolution.

tools/battery/refine_parity.py runs REFMAC 5.8 at 0 cycles and rugnux --refine-score-only on the
same files and prints the terms side by side, with R by resolution from both programs' model
amplitudes on the same reflections.

Tests: [refine_only] - column choice (observed over map coefficients, intensities, 1-marks-free
flags, no flags, no usable column), an MTZ read from its bytes, and the mode end to end on a
synthetic cell (French-Wilson, generated flags, score-only, the report keys).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015CeEGgpKdfkCTJb3YNMJcu
(cherry picked from commit 63ee830c39c988588cffb8c9d4638a678815ec2c)
(cherry picked from commit d7397311e6ce0d3bb37ac91e8973b6052e38589f)
2026-10-26 01:38:24 +01:00

208 lines
8.6 KiB
C++

// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include <catch2/catch_all.hpp>
#include <cmath>
#include <random>
#include <string>
#include <vector>
#include <gemmi/dencalc.hpp>
#include <gemmi/fourier.hpp>
#include <gemmi/it92.hpp>
#include <gemmi/mtz.hpp>
#include "../common/Logger.h"
#include "../rugnux/ResultReport.h"
#include "../rugnux/RugnuxRefine.h"
#include "../writer/RugnuxReflectionFile.h"
namespace {
// A small synthetic orthorhombic cell (no real sample) and its reflections h, k, l = 1..6.
const gemmi::UnitCell test_cell(31.0, 37.0, 43.0, 90.0, 90.0, 90.0);
// An MTZ of `columns` (label, type), every row the hkl followed by values from `value(h, k, l, column)`.
gemmi::Mtz MakeMtz(const std::vector<std::pair<std::string, char>> &columns,
float (*value)(int h, int k, int l, size_t column)) {
gemmi::Mtz mtz(true);
mtz.spacegroup = gemmi::find_spacegroup_by_name("P 21 21 21");
mtz.set_cell_for_all(test_cell);
mtz.add_dataset("test").wavelength = 0.9;
for (const auto &[label, type] : columns)
mtz.add_column(label, type, -1, -1, false);
for (int h = 1; h <= 6; h++)
for (int k = 1; k <= 6; k++)
for (int l = 1; l <= 6; l++) {
mtz.data.insert(mtz.data.end(), {float(h), float(k), float(l)});
for (size_t c = 0; c < columns.size(); c++)
mtz.data.push_back(value(h, k, l, c));
mtz.nreflections++;
}
return mtz;
}
bool InTestSet(int h, int k, int l) { return (h * 7 + k * 13 + l * 17) % 10 == 0; }
} // namespace
TEST_CASE("RugnuxReflectionsFromMtz takes observed amplitudes over map coefficients", "[refine_only]") {
// FWT comes first and is an amplitude with a phase after it; FP/SIGFP is what is observed.
const gemmi::Mtz mtz = MakeMtz({{"FWT", 'F'}, {"PHWT", 'P'}, {"FP", 'F'}, {"SIGFP", 'Q'}, {"FreeR_flag", 'I'}},
[](int h, int k, int l, size_t c) -> float {
switch (c) {
case 0: return 999.0f;
case 1: return 10.0f;
case 2: return 100.0f + h;
case 3: return 2.0f;
default: return InTestSet(h, k, l) ? 0.0f : float(1 + (h + k + l) % 19);
}
});
const RugnuxReflections r = RugnuxReflectionsFromMtz(mtz, "synthetic.mtz");
CHECK(r.amplitudes);
CHECK(r.value_column == "FP");
CHECK(r.sigma_column == "SIGFP");
CHECK(r.free_column == "FreeR_flag");
CHECK(r.wavelength_A == Catch::Approx(0.9));
REQUIRE(r.reflections.size() == 216);
int n_free = 0;
for (const MergedReflection &m : r.reflections) {
CHECK(m.F == Catch::Approx(100.0 + m.h));
CHECK(m.rfree_flag == InTestSet(m.h, m.k, m.l));
n_free += m.rfree_flag;
}
CHECK(r.n_free == n_free);
}
TEST_CASE("RugnuxReflectionsFromMtz falls back to intensities and reads a 1-marks-free flag", "[refine_only]") {
const gemmi::Mtz mtz = MakeMtz({{"IMEAN", 'J'}, {"SIGIMEAN", 'Q'}, {"R-free-flags", 'I'}},
[](int h, int k, int l, size_t c) -> float {
if (c == 0) return 50.0f * h;
if (c == 1) return 5.0f;
return InTestSet(h, k, l) ? 1.0f : 0.0f;
});
const RugnuxReflections r = RugnuxReflectionsFromMtz(mtz, "synthetic.mtz");
CHECK_FALSE(r.amplitudes);
CHECK(r.value_column == "IMEAN");
CHECK(r.free_column == "R-free-flags");
for (const MergedReflection &m : r.reflections) {
CHECK(m.I == Catch::Approx(50.0 * m.h));
CHECK(std::isnan(m.F));
CHECK(m.rfree_flag == InTestSet(m.h, m.k, m.l));
}
}
TEST_CASE("RugnuxReflectionsFromMtz without free flags, and without any value column", "[refine_only]") {
const gemmi::Mtz plain = MakeMtz({{"F", 'F'}, {"SIGF", 'Q'}},
[](int h, int, int, size_t c) -> float { return c == 0 ? 10.0f * h : 1.0f; });
const RugnuxReflections r = RugnuxReflectionsFromMtz(plain, "synthetic.mtz");
CHECK(r.value_column == "F");
CHECK(r.free_column.empty());
CHECK(r.n_free == 0);
const gemmi::Mtz calculated = MakeMtz({{"FC", 'F'}, {"PHIC", 'P'}},
[](int, int, int, size_t) -> float { return 1.0f; });
CHECK_THROWS(RugnuxReflectionsFromMtz(calculated, "synthetic.mtz"));
}
TEST_CASE("ParseRugnuxReflections reads an MTZ from its bytes", "[refine_only]") {
const gemmi::Mtz mtz = MakeMtz({{"F", 'F'}, {"SIGF", 'Q'}, {"FreeR_flag", 'I'}},
[](int h, int k, int l, size_t c) -> float {
if (c == 0) return 10.0f * h;
if (c == 1) return 1.0f;
return InTestSet(h, k, l) ? 0.0f : 1.0f;
});
std::string bytes;
mtz.write_to_string(bytes);
const RugnuxReflections r = ParseRugnuxReflections(bytes, "synthetic.mtz");
CHECK(r.source == "MTZ");
CHECK(r.space_group == "P 21 21 21");
CHECK(r.reflections.size() == 216);
CHECK(r.free_column == "FreeR_flag");
}
TEST_CASE("RunRefineOnly scores a model against intensities, with amplitudes and free flags made for it",
"[refine_only]") {
// Atoms scattered over the cell; the data are their own |F|^2, so the model as given scores well.
const gemmi::SpaceGroup *sg = gemmi::find_spacegroup_by_name("P 21 21 21");
gemmi::Structure st;
st.cell = test_cell;
st.spacegroup_hm = sg->xhm();
st.setup_cell_images();
gemmi::Model model(1);
gemmi::Chain chain("A");
std::mt19937 rng(7);
std::uniform_real_distribution<double> frac(0.0, 1.0);
for (int i = 0; i < 120; i++) {
gemmi::Residue res;
res.name = "HOH";
res.seqid = gemmi::SeqId(i + 1, ' ');
res.het_flag = 'H';
gemmi::Atom a;
a.name = "O";
a.element = gemmi::El::O;
a.pos = test_cell.orthogonalize(gemmi::Fractional(frac(rng), frac(rng), frac(rng)));
a.b_iso = 15.0f;
a.occ = 1.0f;
res.atoms.push_back(a);
chain.residues.push_back(res);
}
model.chains.push_back(chain);
st.models.push_back(model);
gemmi::DensityCalculator<gemmi::IT92<float>, float> dc;
dc.d_min = 2.0;
dc.grid.unit_cell = test_cell;
dc.grid.spacegroup = sg;
dc.set_refmac_compatible_blur(st.models[0]);
dc.put_model_density_on_grid(st.models[0]);
const gemmi::AsuData<std::complex<float>> f =
gemmi::transform_map_to_f_phi(dc.grid, true).prepare_asu_data(2.0, dc.blur);
RugnuxReflections data;
data.name = "synthetic.mtz";
data.source = "MTZ";
data.cell = test_cell;
data.space_group = sg->xhm();
data.amplitudes = false;
for (const auto &hv : f.v) {
if (hv.hkl == gemmi::Miller{{0, 0, 0}})
continue;
const double fc = std::abs(hv.value);
MergedReflection m;
m.h = hv.hkl[0];
m.k = hv.hkl[1];
m.l = hv.hkl[2];
m.d = static_cast<float>(test_cell.calculate_d(hv.hkl));
m.I = static_cast<float>(fc * fc);
m.sigma = static_cast<float>(0.02 * fc * fc + 1.0);
data.reflections.push_back(m);
}
RefinementSettings settings;
settings.score_only = true;
settings.gpu = false;
settings.nthreads = 2;
Logger logger("RefineOnlyTest");
const RefineOnlyResult r = RunRefineOnly(data, st, 2.5, settings, logger);
REQUIRE(r.refinement.ok);
CHECK(r.french_wilson);
CHECK(r.free_flags_generated);
CHECK(r.free_reflections > 0);
CHECK(r.d_min_limit == 2.5);
CHECK(r.refinement.d_min >= 2.5);
CHECK(r.refinement.r_work_start < 0.15);
CHECK(r.refinement.score_start.r_work == Catch::Approx(r.refinement.r_work_start));
CHECK(r.refinement.score_start.shells.size() == 20);
CHECK_FALSE(r.refinement.restrained);
const ReportDocument doc = BuildRefineReportDocument("out", "synthetic.mtz", "model.cif", r);
CHECK(doc.verdict == "OK");
const std::string text = RenderReportText(doc, true);
CHECK(text.find("REFINE= PERFORMED") != std::string::npos);
CHECK(text.find("REFINE_SCORE_R_WORK=") != std::string::npos);
CHECK(text.find("REFINE_FREE_FLAGS= GENERATED") != std::string::npos);
CHECK(text.find("REFINE_FRENCH_WILSON= TRUE") != std::string::npos);
}