fixes to update to rdkit-2023.9.1

CDDLeiden · Jan 18, 2024 · d23b312 · d23b312
1 parent 1b1aea9
commit d23b312
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 4 deletions.
diff --git a/qsprpred/data/test_files/data/test_data_large.tsv b/qsprpred/data/test_files/data/test_data_large.tsv
@@ -77,7 +77,7 @@ Dobesilic acid	88-46-0	O=S(=O)(O)c1c(O)ccc(O)c1	0.12	0.87		2.41	2.01	G. Franke,
 Repinotan	144980-29-0	O=C1N(CCCCNC[C@H]2CCc3ccccc3O2)S(=O)(=O)c4ccccc14	0.21	2.2		1.6	1.2	Heining R,  Sundaresan P, Shah A and Boettcher M (2005) Effect of Gender and Age on the Pharmacokinetics of Repinotan.  Clin. Drug. Invest. 25: 125-134.  			1992	400.49	6	1	75.7	7	cationic	3.9	3.5
 CEP-18770	847499-27-8	C(N[C@H](C(N[C@@H](CC(C)C)[B](O)O)=O)[C@@H](C)O)(=O)C(=NC(=C1)C(=C2)C=CC=C2)C=C1	0.87	0.29		50.6	42.1	Sala F et al. Development and validation of a high-performance liquid chromatography–tandemmass spectrometry method for the determination of the novel proteasome inhibitor CEP-18770 in human plasma and its application in a clinical pharmacokinetic study. J. Mass. Spectrom. 2010, 45, 1299–1305	Data digitized from figure 4	Delanzomib. Data received by Dr. M. Zucchetti, Mario Negri Research Institute, Milan, Italy.  See also Gallerani, Zucchetti et al. Eur. J.  Cancer 2013, 49, 290-296.	2005	413.28	8	5	131.8	9	neutral	1.9	1.9
 Bumecaine	30103-44-7	CCCCN1CCCC1C(=O)Nc2c(cc(cc2C)C)C	1.73	19.19		1.51	1.58	Piotrovskii, V. K.; Blagodatskikh, S. V.; Ryabokon, O. S.; Metelitsa, V. I.; Smirnov, V. K.; Gorshkov, V. A.; Mazur, N. A.; Pryanishnikova, N. T.  Clinical pharmacokinetics of pyromecaine. I. Single intravenous administration Khimiko-Farmatsevticheskii Zhurnal (1983), 17(12), 1427-32	Pyromecaine. N=10 all male patients, 100 mg iv dose. MRT from reported clearance and VDss.		1970	288.43	3	1	32.3	5	cationic	4.0	3.3
-Carboplatin	41575-94-4	N[Pt+2]1(N)[O-]C(=O)C2(CCC2)C(=O)[O-]1	0.26	1.5	1.0	3.0	2.0	Elferink F, van der Vijgh WJ, Klein I, Vermorken JB, Gall HE, and Pinedo HM (1987) Pharmacokinetics of carboplatin after i.v. administration.    Cancer Treatment Rep.  71: 1231-1237.  Gaver RC, George AM, and Deeb G (1987) In vitro stability, plasma protein binding and blood cell partitioning of 14C-carboplatin.  Cancer Chemother. Pharmacol. 20: 271-276.	Used 1.6 m2 = 60 kg since the study was done in all females.		1982	369.24	6	2	108.8	0			
+Carboplatin	41575-94-4	N[X]1(N)[O-]C(=O)C2(CCC2)C(=O)[O-]1	0.26	1.5	1.0	3.0	2.0	Elferink F, van der Vijgh WJ, Klein I, Vermorken JB, Gall HE, and Pinedo HM (1987) Pharmacokinetics of carboplatin after i.v. administration.    Cancer Treatment Rep.  71: 1231-1237.  Gaver RC, George AM, and Deeb G (1987) In vitro stability, plasma protein binding and blood cell partitioning of 14C-carboplatin.  Cancer Chemother. Pharmacol. 20: 271-276.	Used 1.6 m2 = 60 kg since the study was done in all females.		1982	369.24	6	2	108.8	0
 Disopyramide	3737-09-5	CC(C)N(CCC(C(=O)N)(c1ccccc1)c2ccccn2)C(C)C	0.52	0.9	0.16	9.6	7.0	Lima JJ, Haughey DB, and Leier CV (1984) Disopyramide pharmacokinetics and bioavailability following the simultaneous administration of disopyramide and 14C-disopyramide.  J. Pharmacokinet. Biopharm. 12: 289-313.			1962	339.47	4	1	59.2	8	cationic	2.2	-0.11
 LY2090314	603288-22-8	C1(C2C3C(N(C(C=3C(N=C(N3C=CC4)C=4)=C3)=O)[H])=O)[C@@H](N(C=2)C2)[C@@H](C=C(C=1)F)CN(C2)C(=O)N(CCCC1)C1	1.2	10.3	0.02	1.9	2.7	Pharmacokinetics, metabolism, and excretion of the GSK-3 inhibitor LY2090314 in rats, dogs, and humans: A case study in rapid clearance by extensive metabolism with low circulating metabolite exposures. Maciej J. Zamek-Gliszczynski, Trent L. Abraham, Jeffrey J. Alberts, Palaniappan Kulanthaivel, Kimberley A. Jackson, Kay H. Chow, Denis J. McCann, Haitao Hu, Shelby Anderson, Nathan A. Furr, Robert J. Barbuch, and Kenneth C. Cassidy. Drug Metabolism & Disposition (2013), 41(4), 714-726	N=12 across dose range from 10 to 120 mg. 70 kg assumed as average weight. N=2 per dose group.		2003	514.55	9	1	90.3	2	neutral	3.5	3.5
 Atomoxetine	83015-26-3	CNCC[C@@H](Oc1ccccc1C)c2ccccc2	0.85	9.3	0.02	1.5	5.2	Strattera Product Label	CYP2D6 EM data MRT is calculated as VD/CL; CL was calculated as CLpo/F (F=63%)		1982	255.35	2	1	21.3	6	cationic	3.6	1.5

diff --git a/qsprpred/data/tests.py b/qsprpred/data/tests.py
@@ -1382,16 +1382,18 @@ def testRDKitDescs(self):
         """Test the rdkit descriptors calculator."""
         desc_calc = MoleculeDescriptorsCalculator([RDKitDescs()])
         self.dataset.addDescriptors(desc_calc)
+        rdkit_desc_count = len(set(Descriptors._descList))
         self.assertEqual(
-            self.dataset.X.shape, (len(self.dataset), len(Descriptors._descList))
+            self.dataset.X.shape,
+            (len(self.dataset), rdkit_desc_count)
         )
         self.assertTrue(self.dataset.X.any().any())
         self.assertTrue(self.dataset.X.any().sum() > 1)
         # with 3D
         desc_calc = MoleculeDescriptorsCalculator([RDKitDescs(compute_3Drdkit=True)])
         self.dataset.addDescriptors(desc_calc, recalculate=True)
         self.assertEqual(
-            self.dataset.X.shape, (len(self.dataset), len(Descriptors._descList) + 10)
+            self.dataset.X.shape, (len(self.dataset), rdkit_desc_count + 10)
         )
 
     def testSmilesDesc(self):

diff --git a/qsprpred/data/utils/descriptor_utils/rdkitdescriptors.py b/qsprpred/data/utils/descriptor_utils/rdkitdescriptors.py
@@ -26,7 +26,8 @@ def __init__(
         #     self.descriptors = list(self.available.values())
         self.descriptors = (
             rdkit_descriptors
-            if rdkit_descriptors is not None else [x[0] for x in Descriptors._descList]
+            if rdkit_descriptors is not None
+            else sorted(list(set([x[0] for x in Descriptors._descList])))
         )
         if compute_3Drdkit:
             self.descriptors = [