datasets

mzml_exploration.py

+import pandas as pd
 import pyopenms as oms
 import numpy as np
 import matplotlib.pyplot as plt
@@ -279,12 +280,23 @@ def check_energy(im):
                 l[i,f]=frag/prec
     return l
 
+def create_antibio_dataset(path='data/230804_strain_peptides_antibiogram_Enterobacterales.xlsx'):
+    df = pd.read_excel(path, header=1)
+    #sample_name : lien avec le fichier brut
+    #species : espèce => label de prédiction "simple"
+    #antibiogramme : disk + grand - résistant, vitek + grand + resistant, mic + grand + resistant
+    #AMC, AMK, AMP, AMX, ATM, CAZ, CHL, CIP, COL, CRO, CTX, CXM, CZA, CZT, ETP, FEP, FOS, FOX, GEN, IPM, LVX, MEC, MEM,
+    # NAL, NET, OFX, PIP, PRL, SXT, TCC, TEM, TGC, TIC, TOB, TZP (env x3) => 35 x 3 labels
+    pass
+
 if __name__ == "__main__":
-    e = oms.MSExperiment()
-    oms.MzMLFile().load("data/STAPH140.mzML", e)
-    im = build_image_frag(e, 2)
-    im2 = np.maximum(0,np.log(im+1))
-    np.save('data/mz_image/Staph140.npy',im2)
+    path = 'data/230804_strain_peptides_antibiogram_Enterobacterales.xlsx'
+    df = pd.read_excel(path, header=1)
+    # e = oms.MSExperiment()
+    # oms.MzMLFile().load("data/STAPH140.mzML", e)
+    # im = build_image_frag(e, 2)
+    # im2 = np.maximum(0,np.log(im+1))
+    # np.save('data/mz_image/Staph140.npy',im2)
 
     # norm = np.max(im2)
     # for i in range(im.shape[0]) :
@@ -301,5 +313,4 @@ if __name__ == "__main__":
     # b = [np.pad(array, (0, max_len - len(array)), mode='constant', constant_values=default_value) for array in res]
 
 
-s = oms.MSSpectrum