The resolution cutoff, the shell table and the overall CC1/2 counted every unique reflection equally. The merge itself is inverse-variance weighted, so an observation from a frame the crystal barely diffracted on enters it at 1/G^2 of a good one - honestly, with its sigma - but a reflection measured only on such frames is scaled-up noise that then counts as much as a well-measured pair in every Pearson CC1/2 read off the merge. On a sweep where half the frames are weak the curve collapses at every resolution: the cut lands at 3.7 A on a P1 crystal whose good frames reach 1.5 A, and the UNUSABLE verdict fires (CC1/2 0.40 beside I/sigma 10). Each merged reflection now carries cc_weight: the precision its half-sets would have had with every observation at the run's typical frame scale, over the precision they have. G_ref = sum G^3 / sum G^2 over the usable observations is the precision-weighted typical scale, which the dead frames cannot drag down however many there are; the factor per observation is max(1, (G_ref/G)^2), with G the frame's total scale (partial scale, flux and the fulls' own G) taken before the correction surfaces and before collapsed frames are dropped, so nothing intensity- or resolution-dependent enters it. On a sweep without a weak stretch every weight is 1 and the CC1/2 is the plain Pearson it was. The cutoff fit, the shell table and the overall CC1/2 (and so the UNUSABLE verdict and the report's shell checks) all read the same weighted statistic. The two extra per-group sums are accumulated on both merge paths, the host loop and MergeAccumKernel, from one per-frame factor array; a host recompute of the device sums agrees to 1e-15 relative on every merge after the corrected corr is uploaded, and a host-merge run gives the same cut, space group, CC1/2 and ISa on five sets. Weighting by the half-set error variance alone (1/(v0+v1)) is not this: v grows with the intensity, so it weights the weak end of the intensity distribution and biases homogeneous data coarser. Measured (written resolution, together with the weighted outlier median): a P1 sweep with a long weak stretch 3.73 -> 1.40 A against a 1.63 A XDS reference, UNUSABLE withdrawn (overall CC1/2 0.40 -> 0.97); a second 3.61 -> 3.00 A; one with most of the sweep out of beam 7.35 -> 5.20 A. Lysozyme, thaumatin and two insulin sets unchanged to 0.01 A (one lysozyme sweep with a weak wedge 1.13 -> 1.16 A, from the median), same space groups throughout. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
409 lines
20 KiB
C++
409 lines
20 KiB
C++
// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
|
|
// SPDX-License-Identifier: GPL-3.0-only
|
|
|
|
#include <catch2/catch_all.hpp>
|
|
|
|
#include <random>
|
|
#include "../image_analysis/scale_merge/HKLKey.h"
|
|
#include "../image_analysis/scale_merge/Merge.h"
|
|
#include "../image_analysis/scale_merge/ResolutionCutoff.h"
|
|
#include "gemmi/reciproc.hpp"
|
|
|
|
TEST_CASE("HKLKey_NoSG_noMergeFriedel") {
|
|
HKLKeyGenerator hkl_key_gen(false, *gemmi::find_spacegroup_by_number(1));
|
|
CHECK(hkl_key_gen(-1, -2, -3) != hkl_key_gen(1,2,3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) == hkl_key_gen(-1,-2,-3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) != hkl_key_gen(1,-2,-3));
|
|
}
|
|
|
|
TEST_CASE("HKLKey_NoSG_MergeFriedel") {
|
|
HKLKeyGenerator hkl_key_gen(true, *gemmi::find_spacegroup_by_number(1));
|
|
CHECK(hkl_key_gen(-1, -2, -3) == hkl_key_gen(1,2,3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) == hkl_key_gen(-1,-2,-3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) != hkl_key_gen(1,-2,-3));
|
|
}
|
|
|
|
TEST_CASE("HKLKey_SG1_MergeFriedel") {
|
|
HKLKeyGenerator hkl_key_gen(true, *gemmi::find_spacegroup_by_number(1));
|
|
CHECK(hkl_key_gen(-1, -2, -3) == hkl_key_gen(1,2,3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) == hkl_key_gen(-1,-2,-3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) != hkl_key_gen(1,-2,-3));
|
|
}
|
|
|
|
TEST_CASE("HKLKey_SG1_NoMergeFriedel") {
|
|
HKLKeyGenerator hkl_key_gen(false, *gemmi::find_spacegroup_by_number(1));
|
|
CHECK(hkl_key_gen(-1, -2, -3) != hkl_key_gen(1,2,3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) == hkl_key_gen(-1,-2,-3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) != hkl_key_gen(1,-2,-3));
|
|
}
|
|
|
|
TEST_CASE("HKLKey_SG96_MergeFriedel") {
|
|
HKLKeyGenerator hkl_key_gen(true, *gemmi::find_spacegroup_by_number(96));
|
|
CHECK(hkl_key_gen(-1, -2, -3) == hkl_key_gen(1,2,3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) == hkl_key_gen(-1,-2,-3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-2,1,3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-1,-2,3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(2,-1,3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(1,-2,-3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-1,2,-3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(2,1,-3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-2, -1, -3));
|
|
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-2,-1,3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(2, 1, 3));
|
|
}
|
|
|
|
TEST_CASE("HKLKey_SG96_NoMergeFriedel") {
|
|
HKLKeyGenerator hkl_key_gen(false, *gemmi::find_spacegroup_by_number(96));
|
|
CHECK(hkl_key_gen(-1, -2, -3) != hkl_key_gen(1,2,3));
|
|
CHECK(hkl_key_gen(-1,-2,-3) == hkl_key_gen(-1,-2,-3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-2,1,3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-1,-2,3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(2,-1,3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(1,-2,-3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-1,2,-3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(2,1,-3));
|
|
CHECK(hkl_key_gen(1,2,3) == hkl_key_gen(-2, -1, -3));
|
|
|
|
CHECK(hkl_key_gen(1,2,3) != hkl_key_gen(-2,-1,3));
|
|
CHECK(hkl_key_gen(1,2,3) != hkl_key_gen(2, 1, 3));
|
|
}
|
|
|
|
TEST_CASE("HKLKey_pack_friedel") {
|
|
HKLKeyGenerator hkl_key_gen(false, *gemmi::find_spacegroup_by_number(1));
|
|
CHECK(hkl_key_gen(-1, -2, -3).pack() != hkl_key_gen(1,2,3).pack());
|
|
CHECK(hkl_key_gen(-1,-2,-3).pack() == hkl_key_gen(-1,-2,-3).pack());
|
|
CHECK(hkl_key_gen(-1,-2,-3).pack() != hkl_key_gen(1,-2,-3).pack());
|
|
}
|
|
|
|
TEST_CASE("HKLKey_pack_no_friedel") {
|
|
HKLKeyGenerator hkl_key_gen(true, *gemmi::find_spacegroup_by_number(1));
|
|
CHECK(hkl_key_gen(-1, -2, -3).pack() == hkl_key_gen(1,2,3).pack());
|
|
CHECK(hkl_key_gen(-1,-2,-3).pack() == hkl_key_gen(-1,-2,-3).pack());
|
|
CHECK(hkl_key_gen(-1,-2,-3).pack() != hkl_key_gen(1,-2,-3).pack());
|
|
}
|
|
|
|
|
|
TEST_CASE("HKLKey_sys_absence_P212121") {
|
|
HKLKeyGenerator hkl_key_gen(false, *gemmi::find_spacegroup_by_number(19));
|
|
CHECK(hkl_key_gen.IsSystematicallyAbsent(5,0,0));
|
|
CHECK(!hkl_key_gen.IsSystematicallyAbsent(6,0,0));
|
|
CHECK(hkl_key_gen.IsSystematicallyAbsent(0,5,0));
|
|
CHECK(hkl_key_gen.IsSystematicallyAbsent(0,0,5));
|
|
CHECK(!hkl_key_gen.IsSystematicallyAbsent(0,4,0));
|
|
CHECK(!hkl_key_gen.IsSystematicallyAbsent(5,5,5));
|
|
}
|
|
TEST_CASE("AcceptReflection_ResolutionLimits") {
|
|
Reflection r{};
|
|
r.I = 100.0f;
|
|
r.sigma = 5.0f;
|
|
r.prescaling_corr = 1.0f;
|
|
r.d = 20.0f;
|
|
|
|
// No limits: only the finiteness checks apply.
|
|
CHECK(AcceptReflection(r, std::nullopt, std::nullopt));
|
|
|
|
// Low-resolution limit rejects anything coarser than the limit, and is exclusive at it.
|
|
CHECK_FALSE(AcceptReflection(r, std::nullopt, std::optional<double>(15.0)));
|
|
CHECK(AcceptReflection(r, std::nullopt, std::optional<double>(20.0)));
|
|
CHECK(AcceptReflection(r, std::nullopt, std::optional<double>(50.0)));
|
|
|
|
// High-resolution limit still rejects anything finer, in the same direction as before.
|
|
CHECK_FALSE(AcceptReflection(r, std::optional<double>(25.0), std::nullopt));
|
|
CHECK(AcceptReflection(r, std::optional<double>(2.0), std::optional<double>(50.0)));
|
|
|
|
// The plain-double overload treats 0 as "no limit" at both ends.
|
|
CHECK(AcceptReflection(r, 0.0, 0.0));
|
|
CHECK_FALSE(AcceptReflection(r, 0.0, 15.0));
|
|
CHECK(AcceptReflection(r, 2.0, 50.0));
|
|
}
|
|
|
|
// --- Completeness denominator --------------------------------------------------------------------
|
|
|
|
namespace {
|
|
// A merged set built straight out of the reflections the cell and space group can give, so the
|
|
// test says exactly which of them were measured: every unique reflection between d_min and
|
|
// d_max_measured and none outside. Without Friedel merging an acentric contributes both hands.
|
|
std::vector<MergedReflection> MeasuredBetween(const gemmi::SpaceGroup &sg, const UnitCell &cell,
|
|
double d_min, double d_max_measured,
|
|
bool merge_friedel) {
|
|
const gemmi::UnitCell gemmi_cell = cell;
|
|
const gemmi::GroupOps gops = sg.operations();
|
|
std::vector<MergedReflection> out;
|
|
for (const auto &hkl: gemmi::make_miller_vector(gemmi_cell, &sg, d_min, d_max_measured, true)) {
|
|
MergedReflection r;
|
|
r.h = hkl[0];
|
|
r.k = hkl[1];
|
|
r.l = hkl[2];
|
|
r.d = static_cast<float>(gemmi_cell.calculate_d(hkl));
|
|
r.I = 100.0f;
|
|
r.sigma = 10.0f;
|
|
r.I_half[0] = 100.0f;
|
|
r.I_half[1] = 100.0f;
|
|
out.push_back(r);
|
|
if (!merge_friedel && !gops.is_reflection_centric(hkl)) {
|
|
r.h = -hkl[0];
|
|
r.k = -hkl[1];
|
|
r.l = -hkl[2];
|
|
out.push_back(r);
|
|
}
|
|
}
|
|
return out;
|
|
}
|
|
|
|
MergeStatistics StatsWithLowLimit(const gemmi::SpaceGroup &sg, const std::optional<UnitCell> &cell,
|
|
const std::vector<MergedReflection> &merged,
|
|
std::optional<double> low_limit, bool merge_friedel) {
|
|
DiffractionExperiment x;
|
|
x.SetSpaceGroup(sg);
|
|
ScalingSettings s = x.GetScalingSettings();
|
|
s.LowResolutionLimit_A(low_limit);
|
|
s.MergeFriedel(merge_friedel);
|
|
x.ImportScalingSettings(s);
|
|
|
|
MergeOnTheFly merge(x);
|
|
merge.ReferenceCell(cell);
|
|
return merge.MergeStats(merged, {});
|
|
}
|
|
|
|
double Completeness(const MergeStatisticsShell &s) {
|
|
return s.possible_unique_reflections > 0
|
|
? 100.0 * s.unique_reflections / s.possible_unique_reflections : 0.0;
|
|
}
|
|
|
|
const gemmi::SpaceGroup &TestSpaceGroup() { return gemmi::get_spacegroup_by_name("P 1 2 1"); }
|
|
constexpr UnitCell TEST_CELL{40, 45, 50, 90, 100, 90}; // synthetic; coarsest reflection ~49 A
|
|
}
|
|
|
|
// The low-resolution terms a beam stop ate must count as missing: the denominator is the declared
|
|
// range, so widening the declared range lowers completeness rather than leaving it alone.
|
|
TEST_CASE("MergeStats_CompletenessFallsWhenTheLowBoundCrossesAMaskedRegion") {
|
|
const auto &sg = TestSpaceGroup();
|
|
// Nothing coarser than 20 A was measured - it is all behind the stop.
|
|
const auto merged = MeasuredBetween(sg, TEST_CELL, 2.0, 20.0, true);
|
|
REQUIRE(!merged.empty());
|
|
|
|
const auto at_20 = StatsWithLowLimit(sg, TEST_CELL, merged, 20.0, true);
|
|
const auto at_50 = StatsWithLowLimit(sg, TEST_CELL, merged, 50.0, true);
|
|
|
|
// Declared exactly where the data stop: everything possible was measured.
|
|
CHECK(Completeness(at_20.overall) > 99.0);
|
|
|
|
// Declared out to 50 A: the 20-50 A shell is in the denominator and in nothing else.
|
|
CHECK(at_50.overall.possible_unique_reflections > at_20.overall.possible_unique_reflections);
|
|
CHECK(at_50.overall.unique_reflections == at_20.overall.unique_reflections);
|
|
CHECK(Completeness(at_50.overall) < Completeness(at_20.overall));
|
|
// The innermost shell is where it bites.
|
|
CHECK(Completeness(at_50.shells.front()) < Completeness(at_20.shells.front()));
|
|
}
|
|
|
|
// No low-resolution limit means the whole sphere. The cell has no reflection coarser than 50 A, so
|
|
// freeing the 50 A limit must count the same set - the fix does not presuppose either default.
|
|
TEST_CASE("MergeStats_CompletenessWithNoDeclaredLowLimit") {
|
|
const auto &sg = TestSpaceGroup();
|
|
const auto merged = MeasuredBetween(sg, TEST_CELL, 2.0, 20.0, true);
|
|
|
|
const auto at_50 = StatsWithLowLimit(sg, TEST_CELL, merged, 50.0, true);
|
|
const auto unlimited = StatsWithLowLimit(sg, TEST_CELL, merged, std::nullopt, true);
|
|
|
|
CHECK(unlimited.overall.possible_unique_reflections == at_50.overall.possible_unique_reflections);
|
|
CHECK(Completeness(unlimited.overall) == Catch::Approx(Completeness(at_50.overall)));
|
|
// The shell table stays finite even though the bound is not.
|
|
CHECK(std::isfinite(unlimited.shells.front().d_max));
|
|
}
|
|
|
|
// Counting the two Bijvoet mates of an acentric separately doubles the denominator too, so a fully
|
|
// measured anomalous set is 100% complete and not 200%.
|
|
TEST_CASE("MergeStats_CompletenessNeverExceeds100") {
|
|
const auto &sg = TestSpaceGroup();
|
|
for (const bool merge_friedel: {true, false}) {
|
|
const auto merged = MeasuredBetween(sg, TEST_CELL, 2.0, 50.0, merge_friedel);
|
|
const auto stats = StatsWithLowLimit(sg, TEST_CELL, merged, 50.0, merge_friedel);
|
|
INFO("merge_friedel = " << merge_friedel);
|
|
CHECK(Completeness(stats.overall) <= 100.0);
|
|
CHECK(Completeness(stats.overall) > 99.0);
|
|
for (const auto &sh: stats.shells)
|
|
CHECK(Completeness(sh) <= 100.0);
|
|
}
|
|
}
|
|
|
|
// The shell grid and the denominator share their bounds, so every possible reflection lands in a
|
|
// shell: the shells sum to the overall, and the overall is the sphere the run declared.
|
|
TEST_CASE("MergeStats_PossibleSumsOverTheShellsToTheDeclaredSphere") {
|
|
const auto &sg = TestSpaceGroup();
|
|
const auto merged = MeasuredBetween(sg, TEST_CELL, 2.0, 20.0, true);
|
|
const auto stats = StatsWithLowLimit(sg, TEST_CELL, merged, 50.0, true);
|
|
|
|
int sum = 0;
|
|
for (const auto &sh: stats.shells)
|
|
sum += sh.possible_unique_reflections;
|
|
CHECK(sum == stats.overall.possible_unique_reflections);
|
|
|
|
// Counted independently over the same declared range - nothing is lost between the two.
|
|
const gemmi::UnitCell gemmi_cell = TEST_CELL;
|
|
const int expected = gemmi::count_reflections(gemmi_cell, &sg, stats.overall.d_min * 0.999, 50.0, true);
|
|
CHECK(stats.overall.possible_unique_reflections == expected);
|
|
}
|
|
|
|
// Without a reference cell there is no set to count against; completeness stays unmeasured rather
|
|
// than becoming a number, with or without a declared low limit.
|
|
TEST_CASE("MergeStats_NoReferenceCellLeavesCompletenessUnmeasured") {
|
|
const auto &sg = TestSpaceGroup();
|
|
const auto merged = MeasuredBetween(sg, TEST_CELL, 2.0, 20.0, true);
|
|
|
|
for (const std::optional<double> low_limit: {std::optional<double>(50.0), std::optional<double>()}) {
|
|
const auto stats = StatsWithLowLimit(sg, std::nullopt, merged, low_limit, true);
|
|
CHECK(stats.overall.possible_unique_reflections == 0);
|
|
CHECK(stats.overall.unique_reflections > 0);
|
|
CHECK(Completeness(stats.overall) == 0.0);
|
|
}
|
|
}
|
|
|
|
// The reference-range table (--report-resolution) is binned over the range it is GIVEN, whether or
|
|
// not the data reach it: its last shell ends at the declared d_min, and past the run's own limit
|
|
// nothing is read from anywhere - the reflections the run did not keep count as missing.
|
|
TEST_CASE("MergeStats_ReferenceRangeIsBinnedOverTheDeclaredRange") {
|
|
const auto &sg = TestSpaceGroup();
|
|
const auto merged = MeasuredBetween(sg, TEST_CELL, 2.0, 20.0, true); // what the run kept
|
|
DiffractionExperiment x;
|
|
x.SetSpaceGroup(sg);
|
|
MergeOnTheFly merge(x);
|
|
merge.ReferenceCell(TEST_CELL);
|
|
const auto own = merge.MergeStats(merged, {});
|
|
|
|
// A range coarser than the run's own: a complete subset, on a grid ending at the declared bound.
|
|
const auto within = merge.MergeStats(merged, {}, {}, std::nullopt, ReportResolutionRange{3.0, 50.0});
|
|
CHECK(within.shells.back().d_min == Catch::Approx(3.0));
|
|
CHECK(within.shells.front().d_max == Catch::Approx(50.0));
|
|
int coarser_than_3 = 0;
|
|
for (const auto &m: merged)
|
|
if (m.d > 3.0f) ++coarser_than_3;
|
|
CHECK(within.overall.unique_reflections == coarser_than_3);
|
|
CHECK(within.overall.unique_reflections < own.overall.unique_reflections);
|
|
CHECK(Completeness(within.overall) > 99.0);
|
|
|
|
// A range finer than the run kept: the grid still ends at 1.5 A, the outer shell is empty and its
|
|
// possible reflections are in the denominator, and the measured range says where the data stop.
|
|
const auto beyond = merge.MergeStats(merged, {}, {}, std::nullopt, ReportResolutionRange{1.5, 50.0});
|
|
CHECK(beyond.shells.back().d_min == Catch::Approx(1.5));
|
|
CHECK(beyond.overall.unique_reflections == own.overall.unique_reflections);
|
|
CHECK(beyond.overall.possible_unique_reflections > own.overall.possible_unique_reflections);
|
|
CHECK(Completeness(beyond.overall) < Completeness(own.overall));
|
|
CHECK(beyond.shells.back().unique_reflections == 0);
|
|
CHECK(beyond.shells.back().possible_unique_reflections > 0);
|
|
CHECK(beyond.overall.d_min == Catch::Approx(own.overall.d_min));
|
|
|
|
// A range the data never reach at all is still a grid, not an error.
|
|
const auto empty = merge.MergeStats(merged, {}, {}, std::nullopt, ReportResolutionRange{1.0, 1.5});
|
|
CHECK(empty.overall.unique_reflections == 0);
|
|
CHECK(empty.overall.possible_unique_reflections > 0);
|
|
CHECK(empty.overall.d_min == 0.0f);
|
|
}
|
|
|
|
// ---------------------------------------------------------------- the automatic resolution cutoff
|
|
namespace {
|
|
// Half-set pairs spread uniformly in s = 1/d^2 over [s_from, s_to), either correlated with each
|
|
// other (signal) or drawn independently (noise, CC1/2 ~ 0), so a whole CC1/2 curve can be built
|
|
// band by band.
|
|
void AddBand(std::vector<MergedReflection> &v, std::mt19937 &rng,
|
|
double s_from, double s_to, int n, bool correlated, double sigma = 1.0) {
|
|
std::normal_distribution<double> g(0.0, sigma);
|
|
for (int j = 0; j < n; ++j) {
|
|
MergedReflection m;
|
|
m.d = static_cast<float>(1.0 / std::sqrt(s_from + (j + 0.5) * (s_to - s_from) / n));
|
|
const double a = g(rng), b = g(rng);
|
|
m.I_half[0] = static_cast<float>(a);
|
|
m.I_half[1] = static_cast<float>(correlated ? a : b);
|
|
// The pair's weight in a CC1/2: the precision it would have had at the typical frame scale
|
|
// over the precision it has - 1/sigma^2 for a band scaled up by sigma from dead frames.
|
|
m.cc_weight = static_cast<float>(1.0 / (sigma * sigma));
|
|
v.push_back(m);
|
|
}
|
|
}
|
|
}
|
|
|
|
// A clean fall-off: CC1/2 crosses the target where the signal stops, and the cut is written one
|
|
// shell past it.
|
|
TEST_CASE("ResolutionCutoff_CleanFallOff") {
|
|
Logger logger("test");
|
|
std::mt19937 rng(12345);
|
|
std::vector<MergedReflection> merged;
|
|
AddBand(merged, rng, 0.01, 0.25, 480, true); // signal to 1/sqrt(0.25) = 2.00 A
|
|
AddBand(merged, rng, 0.25, 0.51, 520, false); // noise beyond it
|
|
|
|
const auto rc = ComputeCCHalfLogisticCutoff(merged, 0.30, logger);
|
|
REQUIRE(rc.d_fit);
|
|
CHECK(*rc.d_fit == Catch::Approx(2.0).margin(0.15));
|
|
REQUIRE(rc.d_cut);
|
|
CHECK(*rc.d_cut < *rc.d_fit); // the deliberate one-shell extension
|
|
CHECK(*rc.d_cut == Catch::Approx(1.92).margin(0.15));
|
|
}
|
|
|
|
// A sweep with a long stretch where the crystal barely diffracted: the reflections measured only there
|
|
// are noise scaled up by 1/G, sigmas with them, and there are many of them at every resolution. Counted
|
|
// by the information they carry they must not hide where the well-measured reflections stop.
|
|
TEST_CASE("ResolutionCutoff_ScaledUpNoiseDoesNotHideTheFallOff") {
|
|
Logger logger("test");
|
|
std::mt19937 rng(12345);
|
|
std::vector<MergedReflection> merged;
|
|
AddBand(merged, rng, 0.01, 0.25, 480, true);
|
|
AddBand(merged, rng, 0.25, 0.51, 520, false);
|
|
AddBand(merged, rng, 0.01, 0.51, 300, false, 50.0);
|
|
|
|
const auto rc = ComputeCCHalfLogisticCutoff(merged, 0.30, logger);
|
|
REQUIRE(rc.d_fit);
|
|
CHECK(*rc.d_fit == Catch::Approx(2.0).margin(0.15));
|
|
|
|
// Counted as equals, the same reflections hide it: the curve reads noise from the first bin on.
|
|
for (auto &m : merged) m.cc_weight = 1.0f;
|
|
const auto unweighted = ComputeCCHalfLogisticCutoff(merged, 0.30, logger);
|
|
CHECK((!unweighted.d_fit || *unweighted.d_fit > 3.0));
|
|
}
|
|
|
|
// The frame factor of the CC1/2 weight is 1 on a sweep whose frames all sit at one scale, however that
|
|
// scale is spread over the frames, and 1 for any frame brighter than typical.
|
|
TEST_CASE("CCHalfFrameFactors_UniformScaleIsOne") {
|
|
const auto f = CCHalfFrameFactors({1.7, 1.7, 1.7, 1.7}, {100, 3, 250, 0});
|
|
for (double x : f) CHECK(x == 1.0);
|
|
const auto g = CCHalfFrameFactors({1.0, 2.0}, {100, 100});
|
|
CHECK(g[1] == 1.0);
|
|
CHECK(g[0] == Catch::Approx(9.0 / 5.0 * 9.0 / 5.0)); // G_ref = (1 + 8) / (1 + 4)
|
|
}
|
|
|
|
// Most of the sweep at 2% of the good frames' scale: the typical scale is still the good frames', not
|
|
// the run median, and an observation from a dead frame carries 2500x the variance of a good one.
|
|
TEST_CASE("CCHalfFrameFactors_DeadStretchDoesNotSetTheTypicalScale") {
|
|
std::vector<double> scale;
|
|
std::vector<int64_t> n;
|
|
for (int f = 0; f < 100; ++f) {
|
|
scale.push_back(f < 60 ? 0.02 : 1.0);
|
|
n.push_back(50);
|
|
}
|
|
scale.push_back(NAN); // a frame without a scale counts as G = 1
|
|
n.push_back(50);
|
|
const auto factor = CCHalfFrameFactors(scale, n);
|
|
CHECK(factor[0] == Catch::Approx(2500.0).epsilon(0.01));
|
|
CHECK(factor[99] == Catch::Approx(1.0).epsilon(1e-3));
|
|
CHECK(factor[100] == Catch::Approx(1.0).epsilon(1e-3));
|
|
}
|
|
|
|
// A fall-off region a logistic cannot follow: CC1/2 drops through the target and comes straight back
|
|
// up. The fitted crossing is then an extrapolation far past the bins it was made over, and reading
|
|
// the cut off it writes the data deep into the noise; the crossing the bins themselves show is where
|
|
// the signal stopped, and that is what must be used.
|
|
TEST_CASE("ResolutionCutoff_RaggedFallOffIsReadOffTheBins") {
|
|
Logger logger("test");
|
|
std::mt19937 rng(12345);
|
|
std::vector<MergedReflection> merged;
|
|
AddBand(merged, rng, 0.01, 0.13, 240, true); // signal to 1/sqrt(0.13) = 2.77 A
|
|
AddBand(merged, rng, 0.13, 0.17, 80, false); // a hole below the target
|
|
AddBand(merged, rng, 0.17, 0.25, 160, true); // correlated again - not a fall-off
|
|
AddBand(merged, rng, 0.25, 0.51, 520, false);
|
|
|
|
const auto rc = ComputeCCHalfLogisticCutoff(merged, 0.30, logger);
|
|
REQUIRE(rc.d_fit);
|
|
CHECK(*rc.d_fit == Catch::Approx(2.77).margin(0.20));
|
|
REQUIRE(rc.d_cut);
|
|
CHECK(*rc.d_cut > 2.30); // coarser than the band that correlates again
|
|
}
|