Merge pull request #167 from hjkgrp/issue134

Issue134

molSimplify/Classes/mol3D.py

@@ -1609,7 +1609,7 @@ def getBondedAtomsBOMatrixAug(self, idx):
                 nats.append(i)
         return nats
 
-    def getBondCutoff(self, atom, ratom):
+    def getBondCutoff(self, atom: atom3D, ratom: atom3D) -> float:
         """
         Get cutoff based on two atoms.
 
@@ -1632,15 +1632,15 @@ def getBondCutoff(self, atom, ratom):
             distance_max = min(2.75, distance_max)  # 2.75 by 07/22/2021
         if ratom.symbol() == "C" and not atom.symbol() == "H":
             distance_max = min(2.75, distance_max)  # 2.75 by 07/22/2021
-        if ratom.symbol() == "H" and atom.ismetal:
+        if ratom.symbol() == "H" and atom.ismetal():
             # tight cutoff for metal-H bonds
             distance_max = 1.1 * (atom.rad + ratom.rad)
-        if atom.symbol() == "H" and ratom.ismetal:
+        if atom.symbol() == "H" and ratom.ismetal():
             # tight cutoff for metal-H bonds
             distance_max = 1.1 * (atom.rad + ratom.rad)
         return distance_max
 
-    def getBondedAtoms(self, idx):
+    def getBondedAtoms(self, idx: int) -> List[int]:
         """
         Gets atoms bonded to a specific atom. This is determined based on
         element-specific distance cutoffs, rather than predefined valences.

tests/helperFuncs.py

@@ -3,6 +3,7 @@
 import random
 import shutil
 import numpy as np
+from typing import List
 from molSimplify.Scripts.geometry import kabsch, distance
 from molSimplify.Scripts.generator import startgen
 from molSimplify.Classes.globalvars import (dict_oneempty_check_st,
@@ -14,7 +15,7 @@
 from pathlib import Path
 
 
-def is_number(s):
+def is_number(s: str) -> bool:
     """check whether the string is a integral/float/scientific"""
     try:
         float(s)
@@ -33,11 +34,11 @@ def working_directory(path: Path):
         os.chdir(prev_cwd)
 
 
-def fuzzy_equal(x1, x2, thresh):
+def fuzzy_equal(x1, x2, thresh: float) -> bool:
     return np.fabs(float(x1) - float(x2)) < thresh
 
 
-def fuzzy_compare_xyz(xyz1, xyz2, thresh):
+def fuzzy_compare_xyz(xyz1, xyz2, thresh: float) -> bool:
     fuzzyEqual = False
     mol1 = mol3D()
     mol1.readfromxyz(xyz1)
@@ -86,9 +87,7 @@ def getAllLigands(xyz):
     return ligands
 
 
-def getMetalLigBondLength(mymol3d):
-    # findMetal only returns 1 metal atom?
-    # TG: fixed findmetal to return a list
+def getMetalLigBondLength(mymol3d: mol3D) -> List[float]:
     mm = mymol3d.findMetal()[0]
     bonded = mymol3d.getBondedAtoms(mm)
     blength = []
@@ -98,39 +97,43 @@ def getMetalLigBondLength(mymol3d):
     return blength
 
 
-def compareNumAtoms(xyz1, xyz2):
+def compareNumAtoms(xyz1, xyz2) -> bool:
     """Compare number of atoms"""
     print("Checking total number of atoms")
     mol1 = mol3D()
     mol1.readfromxyz(xyz1)
     mol2 = mol3D()
-    mol2.readfromxyz(xyz1)
+    mol2.readfromxyz(xyz2)
     # Compare number of atoms
     passNumAtoms = (mol1.natoms == mol2.natoms)
     print("Pass total number of atoms check: ", passNumAtoms)
     return passNumAtoms
 
 
-def compareMLBL(xyz1, xyz2, thresh):
+def compareMLBL(xyz1, xyz2, thresh: float) -> bool:
     """Compare Metal Ligand Bond Length"""
     print("Checking metal-ligand bond length")
     mol1 = mol3D()
     mol1.readfromxyz(xyz1)
     mol2 = mol3D()
-    mol2.readfromxyz(xyz1)
+    mol2.readfromxyz(xyz2)
     bl1 = getMetalLigBondLength(mol1)
     bl2 = getMetalLigBondLength(mol2)
     passMLBL = True
-    for i in range(0, len(bl1)):
-        if not fuzzy_equal(bl1[i], bl2[i], thresh):
-            print("Error! Metal-Ligand bondlength mismatch for bond # ", i)
-            passMLBL = False
+    if len(bl1) != len(bl2):
+        print("Error! Number of metal-ligand bonds is different")
+        passMLBL = False
+    else:
+        for i in range(0, len(bl1)):
+            if not fuzzy_equal(bl1[i], bl2[i], thresh):
+                print("Error! Metal-Ligand bondlength mismatch for bond # ", i)
+                passMLBL = False
     print("Pass metal-ligand bond length check: ", passMLBL)
     print("Threshold for bondlength difference: ", thresh)
     return passMLBL
 
 
-def compareLG(xyz1, xyz2, thresh):
+def compareLG(xyz1, xyz2, thresh: float) -> bool:
     """Compare Ligand Geometry"""
     print("Checking the Ligand Geometries")
     passLG = True
@@ -152,7 +155,7 @@ def compareLG(xyz1, xyz2, thresh):
     return passLG
 
 
-def compareOG(xyz1, xyz2, thresh):
+def compareOG(xyz1, xyz2, thresh: float) -> bool:
     print("Checking the overall geometry")
     passOG = fuzzy_compare_xyz(xyz1, xyz2, thresh)
     print("Pass overall geometry check: ", passOG)

tests/inputs/molcas_caspt2.in

@@ -14,7 +14,7 @@
 -oxstate II
 -lig water
 -smicat 0
--ff mmff94
+-ff uff
 -keepHs True
 -qccode MOLCAS
 -method CASPT2

tests/inputs/molcas_casscf.in

@@ -14,7 +14,7 @@
 -oxstate II
 -lig water
 -smicat 0
--ff mmff94
+-ff uff
 -keepHs True
 -qccode MOLCAS
 -method CASSCF

tests/inputs/orca_ccsdt.in

@@ -14,9 +14,9 @@
 -oxstate II
 -lig N1C=CC=C1
 -runtyp Opt
--smicat 0
+-smicat 1
 -qccode orca
 -ff mmff94
 -ffoption ba
--keepHs True
+-keepHs False
 -qoption REL DKH2

tests/inputs/orca_dft.in

@@ -15,9 +15,9 @@
 -oxstate II
 -lig N1C=CC=C1
 -runtyp Opt
--smicat 0
+-smicat 1
 -qccode orca
 -ff mmff94
--keepHs True
+-keepHs False
 -qoption REL DKH2
 -qoption HFX 0.2

tests/inputs/tutorial_09_part_one.in

@@ -7,3 +7,4 @@
 -oxstate II
 -spin 1
 -geometry tbp
+-ffoption L

tests/inputs/tutorial_09_part_two.in

@@ -5,3 +5,4 @@
 -replig true
 -oxstate II
 -spin 1
+-ffoption BA

tests/inputs/tutorial_10_part_one.in

@@ -2,3 +2,4 @@
 -ligocc 3
 -smicat 3,4
 -skipANN true
+-ffoption L

tests/inputs/tutorial_10_part_two.in

@@ -2,3 +2,4 @@
 -ligocc 1 1 1
 -smicat 3,4
 -skipANN true
+-ffoption L

tests/refs/orca_ccsdt.report

@@ -2,25 +2,25 @@ Bad structure?, False
 Min_dist (A), 1000
 Was ANN used?, True
 geo_label, 1
-geo_prob, 0.9946129322052002
-geo_LSE, 0.6930601425111972
+geo_prob, 0.9413718581199646
+geo_LSE, 0.6739948349985794
 geo_label_trust, very low
 sc_label, 1
-sc_prob, 0.8634330630302429
-sc_LSE, 0.6931470250647405
+sc_prob, 0.6407925486564636
+sc_LSE, 0.5110593378625077
 sc_label_trust, very low
-split, 47.12842958921388
-split_dist, 18.91462055450386
+split, -13.827394459438906
+split_dist, 8.552455363508885
 This spin, 5
-ANN_ground_state, 1
-homo, -15.494993125140807
-gap, 3.746240116650166
-homo_dist, 0.68992805
-gap_dist, 0.26609284
-ANN_bondl, [2.0098842331388456, 2.0098842331388456, 2.0098842331388456, 2.0098842331388456, 1.9381185776891228, 2.0859009557197328]
+ANN_ground_state, 5
+homo, -13.793439866573024
+gap, 3.4514513871141346
+homo_dist, 0.44729072
+gap_dist, 0.18568888
+ANN_bondl, [2.3605745803152858, 2.3605745803152858, 2.3605745803152858, 2.3605745803152858, 2.2763077827004237, 2.2302417433371216]
 homo_trust, high
 gap_trust, high
 split_trust, very low
 Was Catalytic ANN used?, False
 Catalytic ANN reason, False
-ML-bl (database, A), 1.62
+ML-bl (database, A), 2.1

tests/refs/orca_ccsdt.xyz

@@ -1,63 +1,57 @@
-61
+55
 02/06/2019 11:09, XYZ structure generated by mol3D Class, molSimplify
 Fe 	0.000000	0.000000	0.000000
-N 	-0.710450	0.905404	-0.942135
-C 	-2.086092	0.653124	-1.098946
-C 	-2.802413	1.781697	-0.781450
-C 	-1.872837	2.737795	-0.435990
-C 	-0.622386	2.158343	-0.552520
-H 	-0.116353	0.625454	-1.734749
-H 	-2.507151	-0.290452	-1.420309
-H 	-3.878665	1.886215	-0.806866
-H 	-2.070885	3.756987	-0.132677
-H 	0.309869	2.668255	-0.351586
-N 	3.091620	-2.646483	0.044745
-C 	2.320645	-3.526091	0.708713
-C 	2.134527	-3.096748	2.006446
-C 	2.824190	-1.908414	2.130531
-C 	3.402500	-1.658630	0.903315
-H 	3.392803	-2.717926	-0.952191
-H 	1.913992	-4.429877	0.274465
-H 	1.560655	-3.594725	2.776285
-H 	2.897089	-1.293143	3.017041
-H 	4.015705	-0.803045	0.652473
-N 	-1.887583	-1.859670	1.175941
-C 	-3.119868	-2.362594	1.369665
-C 	-3.288409	-3.493150	0.597455
-C 	-2.107525	-3.678967	-0.091830
-C 	-1.265694	-2.654278	0.286712
-H 	-1.487948	-1.009458	1.629729
-H 	-3.856858	-1.932885	2.034989
-H 	-4.173470	-4.112736	0.542749
-H 	-1.885590	-4.472543	-0.792575
-H 	-0.256645	-2.498096	-0.068930
-N 	-3.181000	2.600173	2.667607
-C 	-2.324879	2.849241	3.674525
-C 	-2.028750	1.675379	4.335321
-C 	-2.734109	0.675756	3.698238
-C 	-3.434012	1.279099	2.674121
-H 	-3.576004	3.302370	2.003991
-H 	-1.937618	3.829895	3.917384
-H 	-1.372462	1.560786	5.186893
-H 	-2.737465	-0.375453	3.952795
-H 	-4.091380	0.780875	1.973868
-N 	1.622876	1.431753	3.894954
-C 	2.862443	1.953048	3.865710
-C 	3.281754	2.085788	2.558545
-C 	2.251046	1.625257	1.766302
-C 	1.242300	1.230238	2.620626
-H 	1.062017	1.222117	4.749491
-H 	3.431885	2.221798	4.745590
-H 	4.232929	2.474260	2.220314
-H 	2.240260	1.582105	0.686917
-H 	0.286199	0.817350	2.328196
-N 	2.863843	-0.907697	-4.361222
-C 	4.008098	-0.259645	-4.077501
-C 	3.948790	0.253401	-2.798174
-C 	2.716289	-0.100128	-2.289852
-C 	2.072198	-0.815629	-3.277572
-H 	2.633034	-1.392491	-5.256495
-H 	4.840804	-0.164529	-4.761934
-H 	4.717754	0.821569	-2.292262
-H 	2.330956	0.135947	-1.308416
-H 	1.081149	-1.244338	-3.207618
+N 	0.000000	2.360575	0.000000
+C 	-1.035788	3.192277	0.085736
+C 	-0.643421	4.510582	0.038070
+C 	0.743144	4.470086	-0.077885
+C 	1.079671	3.131116	-0.093238
+H 	-2.053859	2.834210	0.195040
+H 	-1.272514	5.379877	0.082074
+H 	1.415864	5.310455	-0.139639
+H 	2.076832	2.719004	-0.181012
+N 	2.360575	0.000000	0.000000
+C 	3.127732	-0.143112	-1.087315
+C 	4.468459	-0.063830	-0.781307
+C 	4.531334	0.033282	0.594336
+C 	3.225998	0.103080	1.017031
+H 	2.712594	-0.281119	-2.073654
+H 	5.296854	-0.103185	-1.473983
+H 	5.415281	0.067060	1.215491
+H 	2.913250	0.226033	2.043499
+N 	0.000000	-2.360575	0.000000
+C 	0.192850	-3.127647	-1.079157
+C 	0.083736	-4.468103	-0.780911
+C 	-0.100858	-4.531712	0.585622
+C 	-0.188203	-3.226274	1.003762
+H 	0.393839	-2.711751	-2.054473
+H 	0.157469	-5.295719	-1.471497
+H 	-0.182679	-5.415980	1.201590
+H 	-0.374463	-2.911942	2.020304
+N 	-2.360575	0.000000	0.000000
+C 	-3.146744	0.610592	-0.887598
+C 	-4.475194	0.403300	-0.591083
+C 	-4.488687	-0.444346	0.507268
+C 	-3.168394	-0.698140	0.798476
+H 	-2.731623	1.201389	-1.695534
+H 	-5.327958	0.808217	-1.116916
+H 	-5.352374	-0.842062	1.021054
+H 	-2.782647	-1.346045	1.574617
+N 	0.000000	0.000000	2.276308
+C 	-0.796690	0.836404	2.986431
+C 	-0.516315	0.556546	4.312459
+C 	0.470965	-0.484681	4.342641
+C 	0.774482	-0.815638	3.033991
+H 	-1.455299	1.528309	2.488289
+H 	-0.963294	1.046319	5.168393
+H 	0.910129	-0.931297	5.226080
+H 	1.450709	-1.522446	2.580292
+N 	0.000000	0.000000	-2.230242
+C 	-0.817279	-0.692005	-3.028553
+C 	-0.529141	-0.458721	-4.354299
+C 	0.428078	0.543987	-4.356027
+C 	0.639646	0.854835	-3.031705
+H 	-1.555827	-1.372443	-2.622531
+H 	-0.976958	-0.942071	-5.210385
+H 	0.892624	1.009475	-5.213171
+H 	1.283841	1.626647	-2.632723

tests/refs/orca_dft.report

@@ -2,25 +2,25 @@ Bad structure?, False
 Min_dist (A), 1000
 Was ANN used?, True
 geo_label, 1
-geo_prob, 0.9946129322052002
-geo_LSE, 0.6930601425111972
+geo_prob, 0.9413718581199646
+geo_LSE, 0.6739948349985794
 geo_label_trust, very low
 sc_label, 1
-sc_prob, 0.8634330630302429
-sc_LSE, 0.6931470250647405
+sc_prob, 0.6407925486564636
+sc_LSE, 0.5110593378625077
 sc_label_trust, very low
-split, 47.12842958921388
-split_dist, 18.91462055450386
+split, -13.827394459438906
+split_dist, 8.552455363508885
 This spin, 5
-ANN_ground_state, 1
-homo, -15.494993125140807
-gap, 3.746240116650166
-homo_dist, 0.68992805
-gap_dist, 0.26609284
-ANN_bondl, [2.0098842331388456, 2.0098842331388456, 2.0098842331388456, 2.0098842331388456, 1.9381185776891228, 2.0859009557197328]
+ANN_ground_state, 5
+homo, -13.793439866573024
+gap, 3.4514513871141346
+homo_dist, 0.44729072
+gap_dist, 0.18568888
+ANN_bondl, [2.3605745803152858, 2.3605745803152858, 2.3605745803152858, 2.3605745803152858, 2.2763077827004237, 2.2302417433371216]
 homo_trust, high
 gap_trust, high
 split_trust, very low
 Was Catalytic ANN used?, False
 Catalytic ANN reason, False
-ML-bl (database, A), 1.62
+ML-bl (database, A), 2.1