Dateien nach "ILP" hochladen

ILP/nmrSimilarity.py

@@ -1,3 +1,6 @@
+#Binning mostly for broader peaks?
+#
+
 import math
 import numpy as np
 
@@ -98,6 +101,17 @@ C17XANTHINE= {
     7: ([36.96], [1]),
 }
 
+CPARAXANTHINE = {
+1: ([26.7], [1]),
+2: ([32.9], [1]),
+3: ([151.1], [1]),
+4: ([106.5], [1]),
+5: ([147.4], [1]),
+6: ([155.3], [1]),
+7: ([143.0], [1]),
+}
+
+
 #Theobromine
 H37XANTHINE = {
     1: ([4.49], [3]),
@@ -116,13 +130,13 @@ C37XANTHINE= {
 }
 
 #Caffeine
-H37XANTHINE= {
+H137XANTHINE = {
     1: ([7.73], [1]),
     2: ([4.15], [3]),
     3: ([4.52], [3]),
     4: ([4.01], [3]),
 }
-C37XANTHINE= {
+C137XANTHINE = {
     1: ([163.66], [1]),
     2: ([166.66], [1]),
     3: ([122.03], [1]),
@@ -133,7 +147,29 @@ C37XANTHINE= {
     8: ([37.17], [1]),
 }
 
-#Neue Quelle für 13CNMR für beide
+CCAFFEINE = {
+    1: ([155.7], [1]),
+    2: ([148.8], [1]),
+    3: ([107.7], [1]),
+    4: ([152.2], [1]),
+    5: ([143.0], [1]),
+    6: ([27.2], [1]),
+    7: ([29.1], [1]),
+    8: ([32.9], [1]),
+}
+
+CCAFFEINE2 = {
+1: ([27.7], [1]),
+2: ([29.3], [1]),
+3: ([33.1], [1]),
+4: ([151.0], [1]),
+5: ([148.1], [1]),
+6: ([106.6], [1]),
+7: ([154.5], [1]),
+8: ([142.8], [1]),
+}
+
+
 #Experimental 7-Methylxanthine nmr
 HNMR1= {
     1: ([10.85], [1]),
@@ -142,6 +178,15 @@ HNMR1= {
     4: ([7.88], [1]),
 }
 
+CNMR1= {
+    1: ([155.85], [1]),
+    2: ([151.35], [1]),
+    3: ([149.30], [1]),
+    4: ([143.01], [1]),
+    5: ([106.90], [1]),
+    6: ([33.03], [1]),
+}
+
 
 
 #Experimental Theobromine nmr
@@ -181,12 +226,23 @@ def bin_array(spectra, highest_ppm, lowest_ppm, bin_width):
     normalizedbin = np.divide(bin, np.sum(bin))
     return normalizedbin
 
-def similarity_nmr(spectraref, spectranew, bin_width, highest_ppm, lowest_ppm):
+def define_border_values(spectraref, spectranew):
+    shifts = []
+    for _,(shift,_) in spectraref.items():
+        shifts.append(shift[0])
+    for _,(shift,_) in spectranew.items():
+        shifts.append(shift[0])
+    highest_ppm = math.ceil(max(shifts))
+    lowest_ppm = math.floor(min(shifts))
+    return (lowest_ppm, highest_ppm)
+
+def similarity_nmr(spectraref, spectranew, bin_width):
 
     #Maximize likelihood or minimize Deviation
     #Values for two spectra and optimize largest for both different?
     #Spectra in Nodes to allow maximize overlapp with both spectra or one spectra.
     #5.4.2 Eliminating X–H signals from 1H NMR spectra
+    lowest_ppm, highest_ppm = define_border_values(spectraref, spectranew)
     binref = bin_array(spectraref, highest_ppm, lowest_ppm, bin_width)
     binnew = bin_array(spectranew, highest_ppm, lowest_ppm, bin_width)
     crosscorr = overlap(binref, binnew)
@@ -196,9 +252,25 @@ def similarity_nmr(spectraref, spectranew, bin_width, highest_ppm, lowest_ppm):
     return(simidx)
 
 def main():
-    print(similarity_nmr(H1XANTHINE, HNMR1, 0.4, 13, 3))
+    positive = 0
-    print(similarity_nmr(H3XANTHINE, HNMR1, 0.4, 13, 3))
+    negative = 0
-    print(similarity_nmr(H7XANTHINE, HNMR1, 0.4, 13, 3))
+    bad_binwidth = []
+    
+    '''for i in [0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0, 1.2, 1.4, 1.6, 1.8, 2.0, 2.5, 3.0, 3.5, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 12.0, 14.0, 16.0, 18.0, 20.0, 25.0, 30.0, 35.0]:
+        print(similarity_nmr(CNMR1, CNMR2, i), i)
+        if(similarity_nmr(CCAFFEINE2, CCAFFEINE, i) - similarity_nmr(CPARAXANTHINE, CCAFFEINE, i) < 0):
+            negative += 1
+            bad_binwidth.append(i)
+        else:
+            positive += 1
+    print(f'Wrong similarity result: {negative} and Right similarity result: {positive}')
+    print(bad_binwidth)'''
+    for i in np.arange(0.01, 0.07, 0.01):
+        print(f'Increment i: {i}')
+        print(similarity_nmr(HNMR1, HNMR2, i))
+        print(similarity_nmr(H1XANTHINE, HNMR1, i))
+        print(similarity_nmr(H3XANTHINE, HNMR1, i))
+        print(similarity_nmr(H7XANTHINE, HNMR1, i))
 
 if __name__ == "__main__":
     main()