Merge pull request #12 from fish-quant/release/v0.2.0

v0.2.0

LICENSE

@@ -1,21 +1,26 @@
-MIT License
+BSD 3-Clause License
 
-Copyright (c) 2018 Arthur Imbert
+Copyright © 2020, Arthur Imbert
+All rights reserved.
 
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+    * Neither the name of the copyright holder nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
 
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY
+DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

bigfish/classification/__init__.py

@@ -5,13 +5,20 @@
 patterns of the RNA.
 """
 
-# from .squeezenet import SqueezeNet0
+from .input_preparation import (prepare_coordinate_data,
+                                build_boundaries_layers, build_surface_layers,
+                                build_distance_layers, Generator)
+from .squeezenet import SqueezeNet0, SqueezeNet_qbi
 from .features import get_features, get_features_name
 
 # ### Load models ###
 
 _features = ["get_features", "get_features_name"]
 
-# _squeezenet = ["SqueezeNet0"]
+_input_preparation = ["prepare_coordinate_data", "build_boundaries_layers",
+                      "build_surface_layers", "build_distance_layers",
+                      "Generator"]
 
-__all__ = _features
+_squeezenet = ["SqueezeNet0", "SqueezeNet_qbi"]
+
+__all__ = _features + _input_preparation + _squeezenet

bigfish/classification/features.py

@@ -4,21 +4,20 @@
 Functions to craft features.
 """
 
-import bigfish.stack as stack
-
 import numpy as np
 from scipy import ndimage as ndi
 
-from skimage.measure import regionprops
 from skimage.morphology import binary_opening
 from skimage.morphology.selem import disk
 
+from .input_preparation import prepare_coordinate_data
+
+
 # TODO add sanity check functions
 # TODO add documentation
 # TODO allow to return intermediate results (distance map, etc.)
 # TODO round float results
 
-
 def get_features(cyt_coord, nuc_coord, rna_coord,
                  compute_distance=True,
                  compute_intranuclear=True,
@@ -233,112 +232,6 @@ def get_features_name(names_features_distance=True,
     return features_name
 
 
-# ### Prepare the data ###
-
-def from_coord_to_matrix(cyt_coord, nuc_coord):
-    # get size of the frame
-    max_y = cyt_coord[:, 0].max() + stack.get_offset_value() * 2
-    max_x = cyt_coord[:, 1].max() + stack.get_offset_value() * 2
-    image_shape = (max_y, max_x)
-
-    # cytoplasm
-    cyt = np.zeros(image_shape, dtype=bool)
-    cyt[cyt_coord[:, 0] + stack.get_offset_value(),
-        cyt_coord[:, 1] + stack.get_offset_value()] = True
-
-    # nucleus
-    nuc = np.zeros(image_shape, dtype=bool)
-    nuc[nuc_coord[:, 0] + stack.get_offset_value(),
-        nuc_coord[:, 1] + stack.get_offset_value()] = True
-
-    return cyt, nuc
-
-
-def get_centroid_surface(mask):
-    # get centroid
-    region = regionprops(mask.astype(np.uint8))[0]
-    centroid = np.array(region.centroid, dtype=np.int64)
-
-    return centroid
-
-
-def get_centroid_rna(rna_coord):
-    # get rna centroids
-    centroid_rna = np.mean(rna_coord[:, :3], axis=0, dtype=np.int64)
-    return centroid_rna
-
-
-def get_centroid_distance_map(centroid_coordinate, mask_cyt):
-    if centroid_coordinate.size == 3:
-        centroid_coordinate_2d = centroid_coordinate[1:]
-    else:
-        centroid_coordinate_2d = centroid_coordinate.copy()
-
-    # get mask centroid
-    mask_centroid = np.zeros_like(mask_cyt)
-    mask_centroid[centroid_coordinate_2d[0], centroid_coordinate_2d[1]] = True
-
-    # compute distance map
-    distance_map = ndi.distance_transform_edt(~mask_centroid)
-    distance_map[mask_cyt == 0] = 0
-    distance_map = distance_map.astype(np.float32)
-
-    return distance_map
-
-
-def prepare_coordinate_data(cyt_coord, nuc_coord, rna_coord):
-    # get a binary representation of the coordinates
-    cyt, nuc = from_coord_to_matrix(cyt_coord, nuc_coord)
-    rna_coord[:, 1:3] += stack.get_offset_value()
-
-    # fill in masks
-    mask_cyt, mask_nuc = stack.get_surface_layers(cyt, nuc, cast_float=False)
-
-    # get mask cytoplasm outside nucleus
-    mask_cyt_out = mask_cyt.copy()
-    mask_cyt_out[mask_nuc] = False
-
-    # compute distance maps for the cytoplasm and the nucleus
-    distance_cyt, distance_nuc = stack.get_distance_layers(cyt, nuc,
-                                                           normalized=False)
-
-    # normalize distance maps between 0 and 1
-    distance_cyt_normalized = distance_cyt / distance_cyt.max()
-    distance_cyt_normalized = stack.cast_img_float32(distance_cyt_normalized)
-    distance_nuc_normalized = distance_nuc / distance_nuc.max()
-    distance_nuc_normalized = stack.cast_img_float32(distance_nuc_normalized)
-
-    # get rna outside nucleus
-    mask_rna_in = mask_nuc[rna_coord[:, 1], rna_coord[:, 2]]
-    rna_coord_out = rna_coord[~mask_rna_in]
-
-    # get centroids
-    centroid_cyt = get_centroid_surface(mask_cyt)
-    centroid_nuc = get_centroid_surface(mask_nuc)
-    centroid_rna = get_centroid_rna(rna_coord)
-    if len(rna_coord_out) == 0:
-        centroid_rna_out = centroid_cyt.copy()
-    else:
-        centroid_rna_out = get_centroid_rna(rna_coord_out)
-
-    # get centroid distance maps
-    distance_cyt_centroid = get_centroid_distance_map(centroid_cyt, mask_cyt)
-    distance_nuc_centroid = get_centroid_distance_map(centroid_nuc, mask_cyt)
-    distance_rna_out_centroid = get_centroid_distance_map(centroid_rna_out,
-                                                          mask_cyt)
-
-    prepared_inputs = (mask_cyt, mask_nuc, mask_cyt_out,
-                       distance_cyt, distance_nuc,
-                       distance_cyt_normalized, distance_nuc_normalized,
-                       rna_coord_out,
-                       centroid_cyt, centroid_nuc,
-                       centroid_rna, centroid_rna_out,
-                       distance_cyt_centroid, distance_nuc_centroid,
-                       distance_rna_out_centroid)
-
-    return prepared_inputs
-
-
 # ### Other features ###
 
 def features_distance(rna_coord_out, distance_cyt, distance_nuc, mask_cyt_out):
@@ -376,6 +269,11 @@ def features_distance(rna_coord_out, distance_cyt, distance_nuc, mask_cyt_out):
 
 
 def features_in_out_nucleus(rna_coord, rna_coord_out):
+    # case where no mRNAs outside the nucleus are detected
+    if len(rna_coord) == 0:
+        features = [0, 0, 0]
+        return features
+
     # number of mRNAs outside and inside nucleus
     nb_rna_out = len(rna_coord_out)
     nb_rna_in = len(rna_coord) - nb_rna_out
@@ -509,7 +407,7 @@ def features_topography(rna_coord, rna_coord_out, mask_cyt, mask_nuc,
     nb_rna_out = len(rna_coord_out)
 
     # case where no mRNAs outside the nucleus are detected
-    if nb_rna_out == 0:
+    if nb_rna == 0 or nb_rna_out == 0:
         features = [0., 0.]
         features += [0., 0.] * 5
         features += [0., 0.] * 6