Files
Jungfraujoch/tests/MolecularReplacementTest.cpp
T
leonarski_fandClaude Opus 5.5 2a3d60fb82 rugnux --af-model: anomalous veto on the enantiomorph, search on the GPU, cheaper rescoring
- An MR ENANTIOMORPH decision is taken into the answer's label only as --model takes a model's
  enantiomorph: ValidateAgainstModel runs on the placed model (in a scratch directory, removed after)
  and its adopted_model_enantiomorph - fit over its null, anomalous map at the atoms not inverted -
  decides; otherwise ENANTIOMORPH_VETOED. The hand-check numbers go to the MODEL PRIOR section.
- Rotation and translation functions on the GPU (MolecularReplacementGPU.cu): one block per
  orientation for the rotation function; per orientation the copies, the bin weights, a gather of the
  Crowther-Blow coefficients (CSR lists, fixed order, no atomics) and a cuFFT C2R, block-reduced
  statistics finished on the host in a fixed order. The CPU path (FFTW) is unchanged in what it
  computes; the orientation-independent part of the translation function (TranslationSetup) is now
  built once per group on either path.
- Rescoring: a placement clashing with its mates over twice the limit is not refined, one rigid-body
  engine per group, and the null is built only for the candidate the choice falls on.

Measured MR step on the RTX 5080 (before -> after, seconds; hand check extra where it runs):
3r6o 1.77 -> 0.67, neg 2.14 -> 0.37, 11if 1.20 -> 0.51 (+0.6 hand check), 7ris 1.46 -> 0.56 (+0.6),
9zmu 4.71 -> 1.07 (+0.9). Rotation 0.50 -> 0.02 s and translation 1.17 -> 0.13 s on 9zmu.
Mirrored-detector runs of two anomalous lysozyme sets: the hand check vetoes (map inverted at the
model's atoms); the unmirrored runs adopt.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-11 17:10:48 +02:00

207 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 <gemmi/dencalc.hpp>
#include <gemmi/it92.hpp>
#include "../image_analysis/structure_refinement/ModelFFT.h"
#include "../image_analysis/structure_refinement/MolecularReplacement.h"
#ifdef JFJOCH_USE_CUDA
#include "../common/CUDAWrapper.h"
#include "../image_analysis/structure_refinement/MolecularReplacementGPU.h"
#endif
namespace {
// A synthetic body: carbon atoms scattered in a 12 A sphere, centroid at the origin.
SearchModel synthetic_model() {
SearchModel m;
std::mt19937 rng(7);
std::uniform_real_distribution<double> u(-12.0, 12.0);
gemmi::Model model(1);
gemmi::Chain chain("A");
gemmi::Residue res;
res.name = "UNK";
res.seqid = gemmi::SeqId(1, ' ');
std::vector<gemmi::Vec3> pos;
while (pos.size() < 300) {
const gemmi::Vec3 p(u(rng), u(rng), u(rng));
if (p.length() < 12.0)
pos.push_back(p);
}
gemmi::Vec3 c;
for (const auto &p : pos)
c += p;
c *= 1.0 / pos.size();
for (const auto &p : pos) {
gemmi::Atom a;
a.name = "C";
a.element = gemmi::El::C;
a.pos = gemmi::Position(p - c);
a.b_iso = 15.0f;
a.occ = 1.0f;
res.atoms.push_back(a);
m.radius_A = std::max(m.radius_A, (p - c).length());
}
chain.residues.push_back(res);
model.chains.push_back(chain);
m.st.models.push_back(model);
m.residues_read = m.residues_kept = 1;
m.mass_da = 3600;
return m;
}
gemmi::Mat33 axis_angle(gemmi::Vec3 axis, double deg) {
axis = axis.normalized();
const double k = deg * M_PI / 180.0, s = std::sin(k), c1 = 1.0 - std::cos(k);
const double x = axis.x, y = axis.y, z = axis.z;
return {1 + c1 * (x * x - 1), -s * z + c1 * x * y, s * y + c1 * x * z,
s * z + c1 * x * y, 1 + c1 * (y * y - 1), -s * x + c1 * y * z,
-s * y + c1 * x * z, s * x + c1 * y * z, 1 + c1 * (z * z - 1)};
}
// |F|^2 of the placed crystal to 4 A, as merged reflections.
std::vector<MergedReflection> observed(const gemmi::Structure &crystal) {
gemmi::DensityCalculator<gemmi::IT92<float>, float> dc;
dc.d_min = 3.5;
dc.rate = 1.5;
dc.set_grid_cell_and_spacegroup(crystal);
dc.put_model_density_on_grid(crystal.models[0]);
const auto f = MapToFPhi(dc.grid).prepare_asu_data(3.5, 0, false, false, false);
std::vector<MergedReflection> out;
for (const auto &hv : f.v) {
MergedReflection r;
r.h = hv.hkl[0];
r.k = hv.hkl[1];
r.l = hv.hkl[2];
r.I = std::norm(hv.value);
r.sigma = 1;
r.F = std::abs(hv.value);
r.d = 1.0 / std::sqrt(crystal.cell.calculate_1_d2(hv.hkl));
out.push_back(r);
}
return out;
}
}
TEST_CASE("MolecularReplacement_UniformRotationsCoverSO3", "[MolecularReplacement]") {
const auto rotations = UniformRotations(6.0);
const double step = 6.0 * M_PI / 180.0;
// 8 pi^2 is the volume of SO(3) in the measure a 6 deg cube of Euler-like angles samples.
const double expected = 8 * M_PI * M_PI / (step * step * step);
CHECK(rotations.size() > 0.8 * expected);
CHECK(rotations.size() < 1.2 * expected);
// Every rotation has a sampled one nearby.
std::mt19937 rng(11);
std::normal_distribution<double> g;
const std::vector<gemmi::Mat33> identity{gemmi::Mat33()};
double worst = 0;
for (int i = 0; i < 100; i++) {
const gemmi::Mat33 r = axis_angle({g(rng), g(rng), g(rng)}, std::uniform_real_distribution<double>(0, 180)(rng));
double best = 180;
for (const auto &s : rotations)
best = std::min(best, RotationDistanceDeg(r, s, identity));
worst = std::max(worst, best);
}
CHECK(worst < 6.0);
}
TEST_CASE("MolecularReplacement_RotationAsu", "[MolecularReplacement]") {
const gemmi::UnitCell cell(40, 40, 60, 90, 90, 90);
const auto pg = CartesianPointGroup(gemmi::get_spacegroup_by_name("P 41 2 2"), cell);
REQUIRE(pg.size() == 8);
const auto all = UniformRotations(10.0);
const auto asu = RotationAsu(all, pg);
// One class in eight, give or take the boundaries.
CHECK(asu.size() > all.size() / 8 * 0.9);
CHECK(asu.size() < all.size() / 8 * 1.3);
// Every sampled rotation has a class member in the ASU close by.
for (size_t i = 0; i < all.size(); i += 37) {
double best = 180;
for (const auto &s : asu)
best = std::min(best, RotationDistanceDeg(s, all[i], pg));
CHECK(best < 10.0);
}
}
TEST_CASE("MolecularReplacement_SameRotationGroups", "[MolecularReplacement]") {
const auto groups = SameRotationGroups(gemmi::get_spacegroup_by_name("P 41"));
REQUIRE(groups.size() == 4);
CHECK(groups[0].xhm() == "P 41");
const auto i = SameRotationGroups(gemmi::get_spacegroup_by_name("I 41 2 2"));
CHECK(i.size() == 2); // I 4 2 2, I 41 2 2
}
TEST_CASE("MolecularReplacement_SyntheticPlacement", "[MolecularReplacement]") {
const SearchModel model = synthetic_model();
const gemmi::UnitCell cell(42, 50, 58, 90, 90, 90);
const gemmi::SpaceGroup &sg = gemmi::get_spacegroup_by_name("P 21 21 21");
const gemmi::Mat33 truth = axis_angle({1, 2, 3}, 50);
const gemmi::Fractional t(0.17, 0.31, 0.09);
const gemmi::Structure crystal = PlaceSearchModel(model, truth, t, cell, sg);
const auto merged = observed(crystal);
const SearchReflections refl = MakeSearchReflections(merged, cell, sg, 4.0, 12.0);
REQUIRE(refl.hkl.size() > 300);
const MolecularTransform ft(model, 4.0, 4);
// The rotation function's best orientation is the true one, to the sampling.
const auto pg = CartesianPointGroup(sg, cell);
const auto rotations = RotationAsu(UniformRotations(6.0), pg);
const auto rf = RotationFunction(ft, refl, cell, sg, rotations, 4);
size_t best = 0;
for (size_t i = 1; i < rf.size(); i++)
if (rf[i] > rf[best])
best = i;
CHECK(RotationDistanceDeg(rotations[best], truth, pg) < 6.0);
// At the true orientation the translation function peaks at the true position, up to the
// origins P 21 21 21 allows (a half in each coordinate), and stands far out of its own noise.
const TranslationPeak peak = TranslationFunction(ft, MakeTranslationSetup(refl, cell, sg), truth);
CHECK(peak.z > 10.0);
for (double d : {peak.t.x - t.x, peak.t.y - t.y, peak.t.z - t.z}) {
const double half = 2 * d - std::round(2 * d);
CHECK(std::fabs(half) < 0.06);
}
}
#ifdef JFJOCH_USE_CUDA
TEST_CASE("MolecularReplacement_GPUMatchesCPU", "[MolecularReplacement]") {
if (get_gpu_count() == 0)
SKIP("no GPU");
const SearchModel model = synthetic_model();
const gemmi::UnitCell cell(42, 50, 58, 90, 90, 90);
const gemmi::SpaceGroup &sg = gemmi::get_spacegroup_by_name("P 21 21 21");
const gemmi::Mat33 truth = axis_angle({1, 2, 3}, 50);
const gemmi::Fractional t(0.17, 0.31, 0.09);
const auto merged = observed(PlaceSearchModel(model, truth, t, cell, sg));
const SearchReflections refl = MakeSearchReflections(merged, cell, sg, 4.0, 12.0);
const MolecularTransform ft(model, 4.0, 4);
MolecularReplacementGPU gpu(ft);
const auto rotations = RotationAsu(UniformRotations(15.0), CartesianPointGroup(sg, cell));
const auto rf_cpu = RotationFunction(ft, refl, cell, sg, rotations, 4);
const auto rf_gpu = gpu.RotationFunction(refl, cell, sg, rotations);
REQUIRE(rf_gpu.size() == rf_cpu.size());
for (size_t i = 0; i < rf_cpu.size(); i++)
CHECK(std::fabs(rf_gpu[i] - rf_cpu[i]) < 1e-4);
const TranslationSetup setup = MakeTranslationSetup(refl, cell, sg);
std::vector<gemmi::Mat33> orientations{truth, rotations[3], rotations[17]};
const auto tf_gpu = gpu.TranslationFunction(setup, orientations);
for (size_t i = 0; i < orientations.size(); i++) {
const TranslationPeak cpu = TranslationFunction(ft, setup, orientations[i]);
CHECK(std::fabs(tf_gpu[i].z - cpu.z) < 1e-3);
if (i == 0) { // the solution's peak is unique; noise peaks can tie between grid points
CHECK(tf_gpu[i].t.x == Catch::Approx(cpu.t.x));
CHECK(tf_gpu[i].t.y == Catch::Approx(cpu.t.y));
CHECK(tf_gpu[i].t.z == Catch::Approx(cpu.t.z));
}
}
}
#endif