Files
Jungfraujoch/common/IndexingSettings.cpp
T
leonarski_fandClaude Opus 5 926b68c658 indexing: a rotation lattice is accepted on the spots it explains, not the frames
The acceptance test counted frames: a frame indexed if at least six of its spots
and a fifth of them fell on the lattice, and a run was refused if fewer than ten of
sixty sampled frames did. That test comes from serial crystallography, where each
image is its own experiment. A rotation sweep is one crystal and one orientation
matrix, and its frames are not independent of each other - so what the count mostly
measured was how many spots happen to land on a frame. A sweep carrying four spots
an image cannot reach six on three frames in four however right the lattice is, and
one such run found the correct cell and threw it away at three frames of sixty.

Count the spots instead: the fraction of all spots in the sampled frames that the
lattice explains, against what the same lattice explains when each frame's spots are
put at another frame's angle. Same lattice, same spots, same detector, same
refinement - only the claim that these spots were seen at these angles is removed.
That difference is the evidence, and it carries no spots-per-frame number anywhere,
so nothing has to be chosen for a crystal that diffracts weakly.

Measured on the sparse sweeps this was found with: ninety-three per cent of spots
explained against nought point nought by chance, and they merge to 0.58 A with the
deposited cell. Over a hundred and three datasets the chance level never exceeds
2.6 per cent and the smallest true margin is seventeen points; ninety-nine of them
are byte-identical, because only the refusal is decided this way - every rescue and
every arbiter still counts frames.

The floor on --min-indexed-spots goes from six to four. Six was the serial gate's
number; four is where a lattice stops being fitted by any three spots.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011GxZqDiFP3KqriBhNdcR56
2026-09-14 00:20:01 +02:00

249 lines
8.4 KiB
C++

// SPDX-FileCopyrightText: 2025 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include "IndexingSettings.h"
#include "JFJochException.h"
#include "CUDAWrapper.h"
#include <cmath>
#define check_max(param, val, max) if ((val) > (max)) throw JFJochException(JFJochExceptionCategory::InputParameterAboveMax, param)
#define check_min(param, val, min) if ((val) < (min)) throw JFJochException(JFJochExceptionCategory::InputParameterBelowMin, param)
#define check_finite(param, val) if (!std::isfinite(val)) throw JFJochException(JFJochExceptionCategory::InputParameterInvalid, param)
IndexingSettings::IndexingSettings() {
if (get_gpu_count() > 0)
algorithm = IndexingAlgorithmEnum::FFBIDX;
else
algorithm = IndexingAlgorithmEnum::None;
}
IndexingSettings &IndexingSettings::ViableCellMinSpots(int64_t input) {
// Four, not the default six: six is the stills frame gate's number, and a rotation run is no longer
// accepted or refused on it (the pooled spot test in the first pass decides that), so it has no
// business being a hard minimum. Four is where the number stops being a convention and becomes a
// fact - three spots fit any lattice at all (see MIN_SPOT_COUNT), and the cell and orientation
// refinements this same setting bounds need more observations than parameters.
check_min("ViableCellMinSpots", input, 4);
viable_cell_min_spots = input;
return *this;
}
int64_t IndexingSettings::GetViableCellMinSpots() const {
return viable_cell_min_spots;
}
IndexingSettings &IndexingSettings::Algorithm(IndexingAlgorithmEnum input) {
switch (input) {
case IndexingAlgorithmEnum::Auto:
case IndexingAlgorithmEnum::FFBIDX:
case IndexingAlgorithmEnum::FFT:
case IndexingAlgorithmEnum::FFTW:
case IndexingAlgorithmEnum::None:
algorithm = input;
break;
default:
throw JFJochException(JFJochExceptionCategory::InputParameterInvalid,
"Invalid value for indexing algorithm enum parameter");
}
return *this;
}
// The accepted range, not the default (which stays 500 A - see IndexingSettings.h). The FFT can
// only recover a basis vector up to this length, so the ceiling is exactly the longest cell the
// indexer can ever find; at 500 it excluded 1091 of the PDB's 206950 X-ray entries (0.53%) outright.
// 1200 A leaves 8. Nothing pays for the wider range: the histogram is sized from the VALUE in use,
// and only a caller that asks for more - a given cell that needs it, or the long-axis rescue - gets
// a longer transform.
IndexingSettings &IndexingSettings::FFT_MaxUnitCell_A(float input) {
check_finite("FFT indexing max unit cell (A)", input);
check_min("FFT indexing max unit cell (A)", input, 50);
check_max("FFT indexing max unit cell (A)", input, fft_max_unit_cell_limit_A);
fft_max_unit_cell_A = input;
return *this;
}
IndexingSettings &IndexingSettings::FFT_MinUnitCell_A(float input) {
check_finite("FFT indexing min unit cell (A)", input);
check_min("FFT indexing min unit cell (A)", input, fft_min_unit_cell_limit_A);
check_max("FFT indexing min unit cell (A)", input, 40);
fft_min_unit_cell_A = input;
return *this;
}
IndexingSettings & IndexingSettings::FFT_MaxAngle_deg(float input) {
check_finite("FFT indexing max angle (deg)", input);
check_min("FFT indexing max angle (deg)", input, 0);
check_max("FFT indexing max angle (deg)", input, 180);
fft_max_angle_deg = input;
return *this;
}
IndexingSettings & IndexingSettings::FFT_MinAngle_deg(float input) {
check_finite("FFT indexing min angle (deg)", input);
check_min("FFT indexing min angle (deg)", input, 0);
check_max("FFT indexing min angle (deg)", input, 180);
fft_min_angle_deg = input;
return *this;
}
float IndexingSettings::GetFFT_MinAngle_deg() const {
return fft_min_angle_deg;
}
float IndexingSettings::GetFFT_MaxAngle_deg() const {
return fft_max_angle_deg;
}
IndexingSettings &IndexingSettings::FFT_NumVectors(int64_t input) {
check_min("FFT indexing number of search vectors", input, 128);
fft_num_vectors = input;
return *this;
}
IndexingSettings &IndexingSettings::FFT_HighResolution_A(float input) {
check_finite("FFT indexing high resolution (A)", input);
check_min("FFT indexing high resolution (A)", input, 0.5);
check_max("FFT indexing high resolution (A)", input, 6.0);
fft_high_resolution_A = input;
return *this;
}
IndexingAlgorithmEnum IndexingSettings::GetAlgorithm() const {
return algorithm;
}
float IndexingSettings::GetFFT_MaxUnitCell_A() const {
return fft_max_unit_cell_A;
}
float IndexingSettings::GetFFT_MinUnitCell_A() const {
return fft_min_unit_cell_A;
}
int64_t IndexingSettings::GetFFT_NumVectors() const {
return fft_num_vectors;
}
float IndexingSettings::GetFFT_HighResolution_A() const {
return fft_high_resolution_A;
}
IndexingSettings &IndexingSettings::Tolerance(float input) {
check_min("Indexing tolerance", input, 0.0);
check_max("Indexing tolerance", input, 0.5);
indexing_tolerance = input;
return *this;
}
float IndexingSettings::GetTolerance() const {
return indexing_tolerance;
}
int64_t IndexingSettings::GetIndexingThreads() const {
return indexing_threads;
}
IndexingSettings &IndexingSettings::IndexingThreads(int64_t input) {
check_min("Indexing thread count", input, 1);
check_max("Indexing thread count", input, 64);
indexing_threads = input;
return *this;
}
int64_t IndexingSettings::GetRefineThreads() const {
return refine_threads;
}
IndexingSettings &IndexingSettings::RefineThreads(int64_t input) {
check_min("Candidate-cell refinement thread count", input, 1);
check_max("Candidate-cell refinement thread count", input, MAX_REFINE_THREADS);
refine_threads = input;
return *this;
}
IndexingSettings &IndexingSettings::UnitCellDistTolerance(float input) {
check_min("Relative unit cell distance tolerance vs. reference", input, 0.0001);
check_max("Relative unit cell distance tolerance vs. reference", input, 0.2001);
unit_cell_dist_tolerance_vs_reference = input;
return *this;
}
float IndexingSettings::GetUnitCellDistTolerance() const {
return unit_cell_dist_tolerance_vs_reference;
}
float IndexingSettings::GetUnitCellAngleTolerance_deg() const {
return unit_cell_angle_tolerance_deg;
}
GeomRefinementAlgorithmEnum IndexingSettings::GetGeomRefinementAlgorithm() const {
return refinement;
}
IndexingSettings &IndexingSettings::GeomRefinementAlgorithm(GeomRefinementAlgorithmEnum input) {
refinement = input;
return *this;
}
IndexingSettings & IndexingSettings::IndexIceRings(bool input) {
index_ice_rings = input;
return *this;
}
IndexingSettings & IndexingSettings::RotationIndexing(bool input) {
enable_rotation_indexing = input;
return*this;
}
IndexingSettings & IndexingSettings::RotationIndexingMinAngularRange_deg(float input) {
check_finite("Rotation indexing minimum angular range (deg.)", input);
check_min("Rotation indexing minimum angular range (deg.)", input, 1.0);
rotation_indexing_min_angular_range_deg = input;
return *this;
}
IndexingSettings & IndexingSettings::RotationIndexingAngularStride_deg(float input) {
check_finite("Rotation indexing angular stride (deg.)", input);
check_min("Rotation indexing angular stride (deg.)", input, 0.0);
rotation_indexing_angular_stride_deg = input;
return *this;
}
bool IndexingSettings::GetRotationIndexing() const {
return enable_rotation_indexing;
}
float IndexingSettings::GetRotationIndexingMinAngularRange_deg() const {
return rotation_indexing_min_angular_range_deg;
}
float IndexingSettings::GetRotationIndexingAngularStride_deg() const {
return rotation_indexing_angular_stride_deg;
}
bool IndexingSettings::GetIndexIceRings() const {
return index_ice_rings;
}
bool IndexingSettings::GetBlockingBehavior() const {
return blocking_behavior;
}
IndexingSettings &IndexingSettings::BlockingBehavior(bool input) {
blocking_behavior = input;
return *this;
}
int64_t IndexingSettings::GetMaxExtraLattices() const {
return max_extra_lattices;
}
IndexingSettings &IndexingSettings::MaxExtraLattices(int64_t input) {
check_min("Max extra lattices", input, 0);
check_max("Max extra lattices", input, 10);
max_extra_lattices = input;
return *this;
}