diff --git a/image_processing/build_dataset.py b/image_processing/build_dataset.py
index e2e0e8ad9d2d273f09825c014be7268aad2cc34b..1fa21bd2f65571c5ecfd8becc53aeee4142d36b1 100644
--- a/image_processing/build_dataset.py
+++ b/image_processing/build_dataset.py
@@ -6,6 +6,7 @@ import numpy as np
import matplotlib.image as mpimg
from build_image import build_image_ms1
+from image_processing.build_image import build_image_ms1_wiff
"""
find . -name '*.mzML' -exec cp -prv '{}' '/home/leo/PycharmProjects/pseudo_image/data/raw_data' ';'
@@ -98,6 +99,7 @@ antibiotic_enterrobacter_breakpoints = {
def create_antibio_dataset(path='../data/label_raw/230804_strain_peptides_antibiogram_Enterobacterales.xlsx',suffix='-d200'):
"""
Extract and build file name corresponding to each sample and transform antioresistance measurements to labels
+ :param suffix: file suffix
:param path: excel path
:return: dataframe
"""
@@ -144,7 +146,7 @@ def create_antibio_dataset(path='../data/label_raw/230804_strain_peptides_antibi
l = split_before_number(s)
species = l[0]
nb = l[1]
- return '{}-{}-{}{}.mzML'.format(species,nb,analyse,suffix)
+ return '{}-{}-{}{}.wiff'.format(species,nb,analyse,suffix)
df['path_ana'] = df['sample_name'].map(lambda x: create_fname(x,analyse='ANA'))
df['path_aer'] = df['sample_name'].map(lambda x: create_fname(x, analyse='AER'))
@@ -158,7 +160,7 @@ def create_dataset():
:return: None
"""
label = create_antibio_dataset(suffix='-d200')
- for path in glob.glob("../data/raw_data/**.mzML"):
+ for path in glob.glob("../data/raw_data/**.wiff"):
print(path)
species = None
#check if file exists in the label table
@@ -171,19 +173,21 @@ def create_dataset():
name = label[label['path_aer'] == path.split("/")[-1]]['sample_name'].values[0]
analyse = 'AER'
if species is not None: #save image in species specific dir
- directory_path_png = '../data/processed_data/png_image/{}'.format(species)
- directory_path_npy = '../data/processed_data/npy_image/{}'.format(species)
+ directory_path_png = '../data/processed_data_wiff/png_image/{}'.format(species)
+ directory_path_npy = '../data/processed_data_wiff/npy_image/{}'.format(species)
if not os.path.isdir(directory_path_png):
os.makedirs(directory_path_png)
if not os.path.isdir(directory_path_npy):
os.makedirs(directory_path_npy)
- mat = build_image_ms1(path, 1)
- mpimg.imsave(directory_path_png + "/" + name + '_' + analyse + '.png', mat)
- np.save(directory_path_npy + "/" + name + '_' + analyse + '.npy', mat)
+ if not os.path.isfile(directory_path_png + "/" + name + '_' + analyse + '.png'):
+ mat = build_image_ms1_wiff(path, 1)
+ mpimg.imsave(directory_path_png + "/" + name + '_' + analyse + '.png', mat)
+ np.save(directory_path_npy + "/" + name + '_' + analyse + '.npy', mat)
+ print('image create')
#reiterate for other kind of raw file
label = create_antibio_dataset(suffix='_100vW_100SPD')
- for path in glob.glob("../data/raw_data/**.mzML"):
+ for path in glob.glob("../data/raw_data/**.wiff"):
print(path)
species = None
if path.split("/")[-1] in label['path_ana'].values:
@@ -195,16 +199,18 @@ def create_dataset():
name = label[label['path_aer'] == path.split("/")[-1]]['sample_name'].values[0]
analyse = 'AER'
if species is not None:
- directory_path_png = '../data/processed_data/png_image/{}'.format(species)
- directory_path_npy = '../data/processed_data/npy_image/{}'.format(species)
+ directory_path_png = '../data/processed_data_wiff/png_image/{}'.format(species)
+ directory_path_npy = '../data/processed_data_wiff/npy_image/{}'.format(species)
if not os.path.isdir(directory_path_png):
os.makedirs(directory_path_png)
if not os.path.isdir(directory_path_npy):
os.makedirs(directory_path_npy)
- mat = build_image_ms1(path, 1)
- mpimg.imsave(directory_path_png + "/" + name + '_' + analyse + '.png', mat)
- np.save(directory_path_npy + "/" + name + '_' + analyse + '.npy', mat)
+ if not os.path.isfile(directory_path_png + "/" + name + '_' + analyse + '.png'):
+ mat = build_image_ms1_wiff(path, 1)
+ mpimg.imsave(directory_path_png + "/" + name + '_' + analyse + '.png', mat)
+ np.save(directory_path_npy + "/" + name + '_' + analyse + '.npy', mat)
+ print('image create')
if __name__ =='__main__' :
- df = create_antibio_dataset()
\ No newline at end of file
+ create_dataset()
\ No newline at end of file
diff --git a/image_processing/build_image.py b/image_processing/build_image.py
index f390b40eef5d0ecd1d105aa6d76b79878b8e6766..7c4934c70d489e0bd92b87d7e5d63928f20ea594 100644
--- a/image_processing/build_image.py
+++ b/image_processing/build_image.py
@@ -2,29 +2,38 @@ import numpy as np
import matplotlib.pyplot as plt
import matplotlib.colors as colors
import pyopenms as oms
+from pyRawMSDataReader.pyRawMSDataReader.WiffFileReader_py import WiffFileReader
-def plot_spectra_2d(exp, ms_level=1, marker_size=5, out_path='temp.png'):
- exp.updateRanges()
- for spec in exp:
- if spec.getMSLevel() == ms_level:
- mz, intensity = spec.get_peaks()
- p = intensity.argsort() # sort by intensity to plot highest on top
- rt = np.full([mz.shape[0]], spec.getRT(), float)
- plt.scatter(
- rt,
- mz[p],
- c=intensity[p],
- cmap="afmhot_r",
- s=marker_size,
- norm=colors.LogNorm(
- exp.getMinIntensity() + 1, exp.getMaxIntensity()
- ),
- )
- plt.clim(exp.getMinIntensity() + 1, exp.getMaxIntensity())
- plt.xlabel("time (s)")
- plt.ylabel("m/z")
- plt.colorbar()
- plt.savefig(out_path) # slow for larger data sets
+
+def build_image_ms1_wiff(path, bin_mz):
+ #load raw data
+ rawFile = WiffFileReader(path)
+ max_cycle=0
+ for scanNumber in range (rawFile.GetLastSpectrumNumber()):
+ if rawFile.GetMSOrderForScanNum(scanNumber) == 1 :
+ ms1_start_mz = rawFile.source.ScanInfos[scanNumber].LowMz
+ ms1_end_mz = rawFile.source.ScanInfos[scanNumber].HighMz
+ max_cycle+=1
+
+ # print('start', ms1_start_mz, 'end', ms1_end_mz)
+ total_ms1_mz = ms1_end_mz - ms1_start_mz
+
+ n_bin_ms1 = int(total_ms1_mz // bin_mz)
+ size_bin_ms1 = total_ms1_mz / n_bin_ms1
+ im = np.zeros([max_cycle, n_bin_ms1])
+
+ cycle = 0
+ for scanNumber in range(rawFile.GetLastSpectrumNumber()):
+ if rawFile.GetMSOrderForScanNum(scanNumber) == 1:
+ masses, intensities = rawFile.GetCentroidMassListFromScanNum(scanNumber)
+ line = np.zeros(n_bin_ms1)
+ if len(masses) > 0:
+ for k in range(len(masses)):
+ line[int((masses[k] - ms1_start_mz) // size_bin_ms1)] += intensities[k]
+ im[cycle, :] = line
+ cycle += 1
+
+ return im
def build_image_ms1(path, bin_mz):
diff --git a/image_ref/dataset_ref.py b/image_ref/dataset_ref.py
index 3472d627e5a61a4c7d5f2a7f0768486c80081375..f2bd8fcca265441697a533676454d0c2fb071592 100644
--- a/image_ref/dataset_ref.py
+++ b/image_ref/dataset_ref.py
@@ -170,9 +170,11 @@ def load_data_duo(base_dir_train, base_dir_test, batch_size, shuffle=True, noise
ref_transform = transforms.Compose(
[transforms.Resize((224, 224)),
- Threshold_noise(noise_threshold),
+ Threshold_noise(0),
Log_normalisation(),
- transforms.Normalize(0.5, 0.5)])
+ transforms.Normalize(0.5, 0.5)
+ ])
+
print('Default val transform')
train_dataset = ImageFolderDuo(root=base_dir_train, transform=train_transform, ref_dir = ref_dir, positive_prop=positive_prop, ref_transform=ref_transform)
diff --git a/image_ref/grad_cam.py b/image_ref/grad_cam.py
index 091753e669109e76ef24628d48a0d7ab0f600ac6..139bcd234d064d44ec834977b553b751176588c1 100644
--- a/image_ref/grad_cam.py
+++ b/image_ref/grad_cam.py
@@ -112,4 +112,24 @@ def compute_class_activation_map():
return heatmap
if __name__ =='__main__':
- compute_class_activation_map()
\ No newline at end of file
+ # compute_class_activation_map()
+
+ transform = transforms.Compose(
+ [transforms.Resize((224, 224)),
+ Threshold_noise(500),
+ Log_normalisation(),
+ transforms.Normalize(0.5, 0.5)])
+
+ ref_transform = transforms.Compose(
+ [transforms.Resize((224, 224)),
+ Threshold_noise(0),
+ Log_normalisation(),
+ transforms.Normalize(0.5, 0.5)
+ ])
+
+ path_ref = '../image_ref/img_ref/Enterobacter hormaechei.npy' # negative
+ tensor_ref = npy_loader(path_ref)
+
+ ref_base = tensor_ref.squeeze()
+ ref_false = transform(tensor_ref).squeeze()
+ ref_true = ref_transform(tensor_ref).squeeze()
\ No newline at end of file