pytme 0.3b0__cp311-cp311-macosx_15_0_arm64.whl → 0.3.1__cp311-cp311-macosx_15_0_arm64.whl

scripts/postprocess.py

@@ -9,7 +9,7 @@ import argparse
 from sys import exit
 from os import getcwd
 from typing import Tuple, List
-from os.path import join, splitext
+from os.path import join, splitext, basename
 
 import numpy as np
 from numpy.typing import NDArray
@@ -17,7 +17,7 @@ from scipy.special import erfcinv
 
 from tme import Density, Structure, Orientations
 from tme.cli import sanitize_name, print_block, print_entry
-from tme.matching_utils import load_pickle, centered_mask, write_pickle
+from tme.matching_utils import load_pickle, center_slice, write_pickle
 from tme.matching_optimization import create_score_object, optimize_match
 from tme.rotations import euler_to_rotationmatrix, euler_from_rotationmatrix
 from tme.analyzer import (
@@ -50,15 +50,15 @@ def parse_args():
     additional_group = parser.add_argument_group("Additional Parameters")
 
     input_group.add_argument(
-        "--input_file",
-        "--input_files",
+        "--input-file",
+        "--input-files",
         required=True,
         nargs="+",
         help="Path to one or multiple runs of match_template.py.",
     )
     input_group.add_argument(
-        "--background_file",
-        "--background_files",
+        "--background-file",
+        "--background-files",
         required=False,
         nargs="+",
         default=[],
@@ -66,7 +66,7 @@ def parse_args():
         "For instance from --scramble_phases or a different template.",
     )
     input_group.add_argument(
-        "--target_mask",
+        "--target-mask",
         required=False,
         type=str,
         help="Path to an optional mask applied to template matching scores.",
@@ -81,12 +81,19 @@ def parse_args():
     )
 
     output_group.add_argument(
-        "--output_prefix",
-        required=True,
-        help="Output filename, extension will be added based on output_format.",
+        "--output-prefix",
+        required=False,
+        default=None,
+        help="Output prefix. Defaults to basename of first input. Extension is "
+        "added with respect to chosen output format.",
+    )
+    output_group.add_argument(
+        "--angles-clockwise",
+        action="store_true",
+        help="Report Euler angles in clockwise format expected by RELION.",
     )
     output_group.add_argument(
-        "--output_format",
+        "--output-format",
         choices=[
             "orientations",
             "relion4",
@@ -108,44 +115,44 @@ def parse_args():
     )
 
     peak_group.add_argument(
-        "--peak_caller",
+        "--peak-caller",
         choices=list(PEAK_CALLERS.keys()),
-        default="PeakCallerScipy",
+        default="PeakCallerMaximumFilter",
         help="Peak caller for local maxima identification.",
     )
     peak_group.add_argument(
-        "--minimum_score",
+        "--min-score",
         type=float,
         default=0.0,
         help="Minimum score from which peaks will be considered.",
     )
     peak_group.add_argument(
-        "--maximum_score",
+        "--max-score",
         type=float,
         default=None,
         help="Maximum score until which peaks will be considered.",
     )
     peak_group.add_argument(
-        "--min_distance",
+        "--min-distance",
         type=int,
         default=5,
         help="Minimum distance between peaks.",
     )
     peak_group.add_argument(
-        "--min_boundary_distance",
+        "--min-boundary-distance",
         type=int,
         default=0,
         help="Minimum distance of peaks to target edges.",
     )
     peak_group.add_argument(
-        "--mask_edges",
+        "--mask-edges",
         action="store_true",
         default=False,
         help="Whether candidates should not be identified from scores that were "
         "computed from padded densities. Superseded by min_boundary_distance.",
     )
     peak_group.add_argument(
-        "--num_peaks",
+        "--num-peaks",
         type=int,
         default=1000,
         required=False,
@@ -153,7 +160,7 @@ def parse_args():
         "If minimum_score is provided all peaks scoring higher will be reported.",
     )
     peak_group.add_argument(
-        "--peak_oversampling",
+        "--peak-oversampling",
         type=int,
         default=1,
         help="1 / factor equals voxel precision, e.g. 2 detects half voxel "
@@ -161,33 +168,33 @@ def parse_args():
     )
 
     additional_group.add_argument(
-        "--extraction_box_size",
+        "--extraction-box-size",
         type=int,
         default=None,
         help="Box size of extracted subtomograms, defaults to the centered template.",
     )
     additional_group.add_argument(
-        "--mask_subtomograms",
+        "--mask-subtomograms",
         action="store_true",
         default=False,
         help="Whether to mask subtomograms using the template mask. The mask will be "
         "rotated according to determined angles.",
     )
     additional_group.add_argument(
-        "--invert_target_contrast",
+        "--invert-target-contrast",
         action="store_true",
         default=False,
         help="Whether to invert the target contrast.",
     )
     additional_group.add_argument(
-        "--n_false_positives",
+        "--n-false-positives",
         type=int,
         default=None,
         required=False,
         help="Number of accepted false-positives picks to determine minimum score.",
     )
     additional_group.add_argument(
-        "--local_optimization",
+        "--local-optimization",
         action="store_true",
         required=False,
         help="[Experimental] Perform local optimization of candidates. Useful when the "
@@ -196,6 +203,9 @@ def parse_args():
 
     args = parser.parse_args()
 
+    if args.output_prefix is None:
+        args.output_prefix = splitext(basename(args.input_file[0]))[0]
+
     if args.orientations is not None:
         args.orientations = Orientations.from_file(filename=args.orientations)
 
@@ -310,7 +320,7 @@ def normalize_input(foregrounds: Tuple[str], backgrounds: Tuple[str]) -> Tuple:
 
         # We could normalize to unit sdev, but that might lead to unexpected
         # results for flat background distributions
-        scores -= scores.mean()
+        # scores -= scores.mean()
         indices = tuple(slice(0, x) for x in scores.shape)
 
         indices_update = scores > scores_out[indices]
@@ -361,7 +371,8 @@ def normalize_input(foregrounds: Tuple[str], backgrounds: Tuple[str]) -> Tuple:
         data_norm = load_matching_output(background)
 
         scores = data_norm[0]
-        scores -= scores.mean()
+        # scores -= scores.mean()
+
         indices = tuple(slice(0, x) for x in scores.shape)
         indices_update = scores > scores_norm[indices]
         scores_norm[indices][indices_update] = scores[indices_update]
@@ -370,8 +381,9 @@ def normalize_input(foregrounds: Tuple[str], backgrounds: Tuple[str]) -> Tuple:
     update = tuple(slice(0, int(x)) for x in np.minimum(out_shape, scores.shape))
     scores_out = np.full(out_shape, fill_value=0, dtype=np.float32)
     scores_out[update] = data[0][update] - scores_norm[update]
-    scores_out[update] = np.divide(scores_out[update], 1 - scores_norm[update])
-    np.fmax(scores_out, 0, out=scores_out)
+
+    # scores_out[update] = np.divide(scores_out[update], 1 - scores_norm[update])
+    scores_out = np.fmax(scores_out, 0, out=scores_out)
     data[0] = scores_out
 
     fg, bg = simple_stats(data[0]), simple_stats(scores_norm)
@@ -421,6 +433,10 @@ def main():
 
     data, entities = normalize_input(args.input_file, args.background_file)
 
+    if args.output_format == "pickle":
+        write_pickle(data, f"{args.output_prefix}.pickle")
+        exit(0)
+
     if args.target_mask:
         target_mask = Density.from_file(args.target_mask, use_memmap=True).data
         if target_mask.shape != data[0].shape:
@@ -433,11 +449,15 @@ def main():
 
     target_origin, _, sampling_rate, cli_args = data[-1]
 
+    # Backwards compatibility with pre v0.3.0b
+    if hasattr(cli_args, "no_centering"):
+        cli_args.centering = not cli_args.no_centering
+
     _, template_extension = splitext(cli_args.template)
     ret = load_template(
         filepath=cli_args.template,
         sampling_rate=sampling_rate,
-        centering=not cli_args.no_centering,
+        centering=cli_args.centering,
     )
     template, center_of_mass, translation, template_is_density = ret
 
@@ -461,10 +481,6 @@ def main():
         max_shape = np.max(template.shape)
         args.min_boundary_distance = np.ceil(np.divide(max_shape, 2))
 
-    if args.output_format == "pickle":
-        write_pickle(data, f"{args.output_prefix}.pickle")
-        exit(0)
-
     orientations = args.orientations
     if orientations is None:
         translations, rotations, scores, details = [], [], [], []
@@ -477,7 +493,10 @@ def main():
         ).astype(int)
 
         if args.min_boundary_distance > 0:
-            scores = centered_mask(scores, new_shape=cropped_shape)
+            _scores = np.zeros_like(scores)
+            subset = center_slice(scores.shape, cropped_shape)
+            _scores[subset] = scores[subset]
+            scores = _scores
 
         if args.n_false_positives is not None:
             # Rickgauer et al. 2017
@@ -496,11 +515,11 @@ def main():
             )
             print(f"Determined minimum score cutoff: {minimum_score}.")
             minimum_score = max(minimum_score, 0)
-            args.minimum_score = minimum_score
+            args.min_score = minimum_score
 
         args.batch_dims = None
-        if hasattr(cli_args, "target_batch"):
-            args.batch_dims = cli_args.target_batch
+        if hasattr(cli_args, "batch_dims"):
+            args.batch_dims = cli_args.batch_dims
 
         peak_caller_kwargs = {
             "shape": scores.shape,
@@ -508,8 +527,8 @@ def main():
             "min_distance": args.min_distance,
             "min_boundary_distance": args.min_boundary_distance,
             "batch_dims": args.batch_dims,
-            "minimum_score": args.minimum_score,
-            "maximum_score": args.maximum_score,
+            "min_score": args.min_score,
+            "max_score": args.max_score,
         }
 
         peak_caller = PEAK_CALLERS[args.peak_caller](**peak_caller_kwargs)
@@ -518,7 +537,7 @@ def main():
             state,
             scores,
             rotation_matrix=np.eye(template.data.ndim),
-            mask=template.data,
+            mask=template_mask.data,
             rotation_mapping=rotation_mapping,
             rotations=rotation_array,
         )
@@ -553,12 +572,12 @@ def main():
             details=details,
         )
 
-    if args.minimum_score is not None and len(orientations.scores):
-        keep = orientations.scores >= args.minimum_score
+    if args.min_score is not None and len(orientations.scores):
+        keep = orientations.scores >= args.min_score
         orientations = orientations[keep]
 
-    if args.maximum_score is not None and len(orientations.scores):
-        keep = orientations.scores <= args.maximum_score
+    if args.max_score is not None and len(orientations.scores):
+        keep = orientations.scores <= args.max_score
         orientations = orientations[keep]
 
     if args.peak_oversampling > 1:
@@ -602,6 +621,9 @@ def main():
             orientations.rotations[index] = angles
             orientations.scores[index] = score * -1
 
+    if args.angles_clockwise:
+        orientations.rotations *= -1
+
     if args.output_format in ("orientations", "relion4", "relion5"):
         file_format, extension = "text", "tsv"
 
@@ -623,7 +645,7 @@ def main():
         orientations.to_file(
             filename=f"{args.output_prefix}.{extension}",
             file_format=file_format,
-            source_path=cli_args.target,
+            source_path=basename(cli_args.target),
             version=version,
         )
         exit(0)
@@ -708,7 +730,7 @@ def main():
     template, center, *_ = load_template(
         filepath=cli_args.template,
         sampling_rate=sampling_rate,
-        centering=not cli_args.no_centering,
+        centering=cli_args.centering,
     )
 
     for index, (translation, angles, *_) in enumerate(orientations):

scripts/preprocess.py

@@ -11,7 +11,7 @@ import numpy as np
 from tme import Density, Structure
 from tme.cli import print_entry
 from tme.backends import backend as be
-from tme.filters import BandPassFilter
+from tme.filters import BandPassReconstructed
 
 
 def parse_args():
@@ -24,7 +24,6 @@ def parse_args():
     io_group.add_argument(
         "-m",
         "--data",
-        dest="data",
         type=str,
         required=True,
         help="Path to a file in PDB/MMCIF, CCP4/MRC, EM, H5 or a format supported by "
@@ -34,7 +33,6 @@ def parse_args():
     io_group.add_argument(
         "-o",
         "--output",
-        dest="output",
         type=str,
         required=True,
         help="Path the output should be written to.",
@@ -42,22 +40,19 @@ def parse_args():
 
     box_group = parser.add_argument_group("Box")
     box_group.add_argument(
-        "--box_size",
-        dest="box_size",
+        "--box-size",
         type=int,
         required=False,
         help="Box size of the output. Defaults to twice the required box size.",
     )
     box_group.add_argument(
-        "--sampling_rate",
-        dest="sampling_rate",
+        "--sampling-rate",
         type=float,
         required=True,
         help="Sampling rate of the output file.",
     )
     box_group.add_argument(
-        "--input_sampling_rate",
-        dest="input_sampling_rate",
+        "--input-sampling-rate",
         type=float,
         required=False,
         help="Sampling rate of the input file. Defaults to header for volume "
@@ -66,15 +61,13 @@ def parse_args():
 
     modulation_group = parser.add_argument_group("Modulation")
     modulation_group.add_argument(
-        "--invert_contrast",
-        dest="invert_contrast",
+        "--invert-contrast",
         action="store_true",
         required=False,
         help="Inverts the template contrast.",
     )
     modulation_group.add_argument(
         "--lowpass",
-        dest="lowpass",
         type=float,
         required=False,
         default=None,
@@ -82,14 +75,12 @@ def parse_args():
         "A value of 0 disables the filter.",
     )
     modulation_group.add_argument(
-        "--no_centering",
-        dest="no_centering",
+        "--no-centering",
         action="store_true",
         help="Assumes the template is already centered and omits centering.",
     )
     modulation_group.add_argument(
         "--backend",
-        dest="backend",
         type=str,
         default=None,
         choices=be.available_backends(),
@@ -98,15 +89,13 @@ def parse_args():
 
     alignment_group = parser.add_argument_group("Modulation")
     alignment_group.add_argument(
-        "--align_axis",
-        dest="align_axis",
+        "--align-axis",
         type=int,
         required=False,
         help="Align template to given axis, e.g. 2 for z-axis.",
     )
     alignment_group.add_argument(
-        "--align_eigenvector",
-        dest="align_eigenvector",
+        "--align-eigenvector",
         type=int,
         required=False,
         default=0,
@@ -114,8 +103,7 @@ def parse_args():
         "with numerically largest eigenvalue.",
     )
     alignment_group.add_argument(
-        "--flip_axis",
-        dest="flip_axis",
+        "--flip-axis",
         action="store_true",
         required=False,
         help="Align the template to -axis instead of axis.",
@@ -185,12 +173,11 @@ def main():
     bpf_mask = 1
     lowpass = 2 * args.sampling_rate if args.lowpass is None else args.lowpass
     if args.lowpass != 0:
-        bpf_mask = BandPassFilter(
+        bpf_mask = BandPassReconstructed(
             lowpass=lowpass,
             highpass=None,
             use_gaussian=True,
             return_real_fourier=True,
-            shape_is_real_fourier=False,
             sampling_rate=data.sampling_rate,
         )(shape=data.shape)["data"]
         bpf_mask = be.to_backend_array(bpf_mask)