MASSA-Algorithm 0.9.3__py3-none-any.whl → 0.9.4__py3-none-any.whl

MASSA_Algorithm/MASSAdescriptors.py

@@ -1,7 +1,8 @@
 import pandas as pd
 from rdkit.Chem import Descriptors
-from rdkit.Chem import rdMolDescriptors
-from rdkit.DataStructs import cDataStructs
+from rdkit.Chem import AllChem
+# from rdkit.Chem import rdMolDescriptors
+# from rdkit.DataStructs import cDataStructs
 
 def physicochemical_descriptors(file):
 	NumHAcceptors = {}
@@ -33,9 +34,25 @@ def physicochemical_descriptors(file):
 def atompairs_fingerprint(file):
 	FP_dict = {}
 	for i in file['molecules']:
-		FPasBitVect = rdMolDescriptors.GetHashedAtomPairFingerprintAsBitVect(i, nBits=1024) # Determine the fingerprint of the molecule using AtomPairs Fingerprint.
-		FPasBinary = cDataStructs.BitVectToText(FPasBitVect) # Convert fingerprint to text.
-		BinaryAsList = list(FPasBinary) # Each bit of fingerprint will be a string item of a list.
+		# Updated AtomPair Fingerprint (without count).
+		# To use AtomPairCount use the function (fpgen.GetCountFingerprintAsNumPy).
+		# 1) Determine the fingerprint generator using AtomPairs Fingerprint.
+		# 2) Generate the numpy array fingerprint using the generator.
+		# 3) Transform the np.array in list.
+		fpgen = AllChem.GetAtomPairGenerator(fpSize=1024)  # 1
+		FPasBinary = fpgen.GetFingerprintAsNumPy(i)  # 2
+		BinaryAsList = list(FPasBinary)  # 3
+
+		# DEPRECATED (by RDKit):
+		# 1) Determine the fingerprint of the molecule using AtomPairs Fingerprint.
+		# 2) Convert fingerprint to text.
+		# 3) Each bit of fingerprint will be a string item of a list.
+		# FPasBitVect = rdMolDescriptors.GetHashedAtomPairFingerprintAsBitVect(
+		# i, nBits=1024
+		# ) # 1
+		# FPasBinary = cDataStructs.BitVectToText(FPasBitVect) # 2
+		# BinaryAsList = list(FPasBinary) # 3
+
 		BinaryAsNewList = []
 		for a in BinaryAsList:
 			b = int(a) # Each bit of fingerprint will be a int item of a list.

MASSA_Algorithm/MASSAlogos.py

@@ -20,7 +20,7 @@ def initial_print():
        ██░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░█
      ██░░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓░░░░█                                 MASSA Algorithm:
    ████░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░█████          Molecular data set sampling  —  Training-Test Separation
-  █▓▓▓███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░███▓▓▓█                            Version: v. 0.9.3
+  █▓▓▓███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░███▓▓▓█                            Version: v. 0.9.4
  █▒▓▓▒▒▒████░░░░░░░░░░░░░░░░░░░░░░░░░░░░████▒▒▓▓▒█
  ██▓▒▒▒▓▓▓▓██████████████████████████████▓▓▓▒▒▒▒▓█                Developed by: Gabriel Corrêa Veríssimo
  ██▒▒▒▓▓▒▒▒▒▓▓▒▒▒▒▓▓▒▒▒▒▒▒▒▒▒▒▒▒▓▓▒▒▒▒▓▓▒▒▒▓▓▒▒██                           LICENSE: AGPL-3.0

{MASSA_Algorithm-0.9.3.dist-info → MASSA_Algorithm-0.9.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: MASSA-Algorithm
-Version: 0.9.3
+Version: 0.9.4
 Summary: MASSA Algorithm is a Python package to separate data sets of molecules into training and test sets, considering the diversity of structural, physicochemical and biological characteristics of these molecules.
 Home-page: https://github.com/gcverissimo/MASSA_Algorithm
 Author: Gabriel Corrêa Veríssimo
@@ -18,13 +18,13 @@ Classifier: Topic :: Scientific/Engineering :: Chemistry
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy <2.0
+Requires-Dist: numpy (<2.0)
 Requires-Dist: rdkit
 Requires-Dist: pandas
-Requires-Dist: matplotlib >=3.2
-Requires-Dist: scipy >=1.6
-Requires-Dist: scikit-learn >0.24
-Requires-Dist: kmodes >=0.10
+Requires-Dist: matplotlib (>=3.2)
+Requires-Dist: scipy (>=1.6)
+Requires-Dist: scikit-learn (>0.24)
+Requires-Dist: kmodes (>=0.10)
 
 # MASSA Algorithm
 MASSA Algorithm: A tool for separating data sets of molecules into training and test sets. Developed with the objective of preparing data sets for the generation of prediction models in cheminformatics.

{MASSA_Algorithm-0.9.3.dist-info → MASSA_Algorithm-0.9.4.dist-info}/RECORD

@@ -1,18 +1,18 @@
 MASSA_Algorithm/MASSA.py,sha256=PltTwmOsK-_q6MzmCxqY1AQMTXM-5XKB-3S6Yqe_VTo,9196
 MASSA_Algorithm/MASSAargs.py,sha256=MCOBlRm6sx6TUQHLwJrW-ktdSNiQltyFjyfJbS-1dVc,6777
 MASSA_Algorithm/MASSAcluster.py,sha256=orRK3rqEpH4j-C4LiS2rp3z4f1gM_rvsjgqiljvtlUI,11293
-MASSA_Algorithm/MASSAdescriptors.py,sha256=502A3NPxYMikXfSVsOz8u8p22hu5hgmZR5_4Am-8X5s,2141
+MASSA_Algorithm/MASSAdescriptors.py,sha256=3wd4MXfqTJU6w-sUolEhsCKIOCS2ye1tSkXvOXwFn2c,2716
 MASSA_Algorithm/MASSAextraction.py,sha256=bADEWtpEE5P0hg9O-8piD659GrPfHUeqyyaAYCWlsAs,4976
-MASSA_Algorithm/MASSAlogos.py,sha256=h12kNzcQFWNMIZM-S7Pt3KaDquwmjkuNFSv0wQ-QaIE,3528
+MASSA_Algorithm/MASSAlogos.py,sha256=gu5suAiFlp1Dfn-Zcvl80oDEq4sVsdXSjfrduXvZ_mU,3528
 MASSA_Algorithm/MASSAmoloutput.py,sha256=LsyeCvIc9SPiFjVXTOQ3GVXDzhB9sc-MYWGGvIbOcwQ,2512
 MASSA_Algorithm/MASSAod.py,sha256=y0tizbYYtw34iJEf8c_5XPfQHHxF9RSRGjbmSZ0qRWk,487
 MASSA_Algorithm/MASSAopen_files.py,sha256=aPYCBNSmSPasL1wyuYvM7Nd1mTyGG9GMcyDdOAYQ3GE,1600
 MASSA_Algorithm/MASSApreparation.py,sha256=I4JpddMfBX1btYomNI5vflN1gyllJKodbQgtYf9imWY,3208
 MASSA_Algorithm/MASSAsplit.py,sha256=qsZgvXAat4UleaF0Qaa4Y-CtsMQU_NaIJvK-ypOzkbw,5330
 MASSA_Algorithm/__init__.py,sha256=yY3Tbs-t4HSl4I0Ev0RcHMnHU7SwljlWRveiRJkeCB8,10
-MASSA_Algorithm-0.9.3.dist-info/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
-MASSA_Algorithm-0.9.3.dist-info/METADATA,sha256=IRbwh48vKeRgQGxbJn9iZLhovV8hPBocSzZ8anP2gO4,6542
-MASSA_Algorithm-0.9.3.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-MASSA_Algorithm-0.9.3.dist-info/entry_points.txt,sha256=oMtqswy07Di-w2uIYAEvenBKl0ovsr9AYm_yxn6LGtU,63
-MASSA_Algorithm-0.9.3.dist-info/top_level.txt,sha256=IZyttJ20RSD8w9nAcaTHWAvkvxHV5FGaVGB7mDrw9Cc,16
-MASSA_Algorithm-0.9.3.dist-info/RECORD,,
+MASSA_Algorithm-0.9.4.dist-info/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
+MASSA_Algorithm-0.9.4.dist-info/METADATA,sha256=_bGdINXx2Z0BpgKn7uo8W49wvnWfDfwZLGQtL1huBpc,6552
+MASSA_Algorithm-0.9.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+MASSA_Algorithm-0.9.4.dist-info/entry_points.txt,sha256=oMtqswy07Di-w2uIYAEvenBKl0ovsr9AYm_yxn6LGtU,63
+MASSA_Algorithm-0.9.4.dist-info/top_level.txt,sha256=IZyttJ20RSD8w9nAcaTHWAvkvxHV5FGaVGB7mDrw9Cc,16
+MASSA_Algorithm-0.9.4.dist-info/RECORD,,

{MASSA_Algorithm-0.9.3.dist-info → MASSA_Algorithm-0.9.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.41.2)
+Generator: bdist_wheel (0.38.4)
 Root-Is-Purelib: true
 Tag: py3-none-any