redefinition of agani class, working on secondary structures, error o…

…n preprocess

ugropy/__init__.py

@@ -7,11 +7,11 @@
 """
 
 from .core import instantiate_mol_object
-from .core.frag_classes.abdulelah_gani.abdulelah_gani_p import (
-    AbdulelahGaniPrimaryModel,
+from .core.frag_classes.abdulelah_gani.abdulelah_gani_pst import (
+    AbdulelahGaniPSTModel,
 )
-from .core.frag_classes.abdulelah_gani.abdulelah_gani_p_result import (
-    AGaniPFragmentationResult,
+from .core.frag_classes.abdulelah_gani.abdulelah_gani_pst_result import (
+    AGaniPSTFragmentationResult,
 )
 from .core.frag_classes.base.fragmentation_model import (
     FragmentationModel,
@@ -29,6 +29,7 @@
 from .core.ilp_solvers.ilp_solver import ILPSolver
 from .groups import Groups
 from .models.abdulelah_gani_pmod import abdulelah_gani_p
+from .models.abdulelah_gani_smod import abdulelah_gani_s
 from .models.jobackmod import joback
 from .models.psrkmod import psrk
 from .models.unifacmod import unifac
@@ -38,8 +39,8 @@
     "constants",
     "writers",
     "instantiate_mol_object",
-    "AbdulelahGaniPrimaryModel",
-    "AGaniPFragmentationResult",
+    "AbdulelahGaniPSTModel",
+    "AGaniPSTFragmentationResult",
     "FragmentationModel",
     "FragmentationResult",
     "GibbsModel",
@@ -48,6 +49,7 @@
     "JobackFragmentationResult",
     "Groups",
     "abdulelah_gani_p",
+    "abdulelah_gani_s",
     "joback",
     "unifac",
     "psrk",

ugropy/core/frag_classes/abdulelah_gani/__init__.py

@@ -1,6 +1,6 @@
 """Abdulelah-Gani frag classes module."""
 
-from . import abdulelah_gani_p, abdulelah_gani_p_result
+from . import abdulelah_gani_pst, abdulelah_gani_pst_result
 
 
-__all__ = ["abdulelah_gani_p", "abdulelah_gani_p_result"]
+__all__ = ["abdulelah_gani_pst", "abdulelah_gani_pst_result"]

ugropy/core/frag_classes/abdulelah_gani/abdulelah_gani_p.py → ugropy/core/frag_classes/abdulelah_gani/abdulelah_gani_pst.py

@@ -6,8 +6,8 @@
 
 from rdkit import Chem
 
-from ugropy.core.frag_classes.abdulelah_gani.abdulelah_gani_p_result import (
-    AGaniPFragmentationResult,
+from ugropy.core.frag_classes.abdulelah_gani.abdulelah_gani_pst_result import (
+    AGaniPSTFragmentationResult,
 )
 from ugropy.core.frag_classes.base.fragmentation_model import (
     FragmentationModel,
@@ -16,7 +16,7 @@
 from ugropy.core.ilp_solvers.ilp_solver import ILPSolver
 
 
-class AbdulelahGaniPrimaryModel(FragmentationModel):
+class AbdulelahGaniPSTModel(FragmentationModel):
     """Abdulelah-Gani model dedicated to properties estimation models.
 
     Class to construct the primary structures detector for the Abdulelah-Gani
@@ -48,13 +48,17 @@ def __init__(
         self,
         subgroups: pd.DataFrame,
         subgroups_info: pd.DataFrame,
+        allow_overlapping: bool = False,
+        allow_free_atoms: bool = False,
     ) -> None:
 
         super().__init__(
             subgroups=subgroups,
-            allow_overlapping=False,
-            fragmentation_result=AGaniPFragmentationResult,
+            allow_overlapping=allow_overlapping,
+            allow_free_atoms=allow_free_atoms,
+            fragmentation_result=AGaniPSTFragmentationResult,
         )
+
         self.subgroups_info = subgroups_info
 
     def get_groups(
@@ -63,7 +67,7 @@ def get_groups(
         identifier_type: str = "name",
         solver: ILPSolver = DefaultSolver,
         search_multiple_solutions: bool = False,
-    ) -> Union[AGaniPFragmentationResult, List[AGaniPFragmentationResult]]:
+    ) -> Union[AGaniPSTFragmentationResult, List[AGaniPSTFragmentationResult]]:
         """Get the groups of a molecule.
 
         Parameters

ugropy/core/frag_classes/abdulelah_gani/abdulelah_gani_p_result.py → ugropy/core/frag_classes/abdulelah_gani/abdulelah_gani_pst_result.py

@@ -9,7 +9,7 @@
 )
 
 
-class AGaniPFragmentationResult(FragmentationResult):
+class AGaniPSTFragmentationResult(FragmentationResult):
     """Abdulelah-Gani primary group contribution properties estimator.
 
     Parameters

ugropy/core/frag_classes/base/fragmentation_model.py

@@ -54,10 +54,12 @@ def __init__(
         self,
         subgroups: pd.DataFrame,
         allow_overlapping: bool = False,
+        allow_free_atoms: bool = False,
         fragmentation_result: FragmentationResult = FragmentationResult,
     ) -> None:
         self.subgroups = subgroups
         self.allow_overlapping = allow_overlapping
+        self.allow_free_atoms = allow_free_atoms
         self.fragmentation_result = fragmentation_result
 
         # Instantiate all de mol object from their SMARTS representation
@@ -122,7 +124,7 @@ def get_groups(
         )
 
         # If there is free atoms in the molecule can't fragment with the model
-        if np.size(free_atoms) > 0:
+        if np.size(free_atoms) > 0 and not self.allow_free_atoms:
             return self.set_fragmentation_result(
                 mol, [{}], search_multiple_solutions, **kwargs
             )

ugropy/groupscsv/abdulelah_gani/secondary/info.csv

@@ -0,0 +1,131 @@
+group|group_number
+(CH3)2CH|221
+(CH3)3C|222
+CH(CH3)CH(CH3)|223
+CH(CH3)C(CH3)2|224
+C(CH3)2C(CH3)2|225
+CHn=CHm-CHp=CHk (k,m,n,p in 0..2)|226
+CH3-CHm=CHn (m,n in 0..2)|227
+CH2-CHm=CHn (m,n in 0..2)|228
+CHp-CHm=CHn (m,n in 0..2; p in 0..1)|229
+CHCHO or CCHO|230
+CH3COCH2|231
+CH3COCH or CH3COC|232
+CHCOOH or CCOOH|233
+CH3COOCH or CH3COOC|234
+CO-O-CO|235
+CHOH|236
+COH|237
+CH3COCHnOH (n in 0..2)|238
+NCCHOH or NCCOH|239
+OH-CHn-COO (n in 0..2)|240
+CHm(OH)CHn(OH) (m,n in 0..2)|241
+CHm(OH)CHn(NHp) (m,n,p in 0..2)|242
+CHm(NH2)CHn(NH2) (m,n in 0..2)|243
+CHm(NH)CHn(NH2) (m,n in 1..2)|244
+H2NCOCHnCHmCONH2 (m,n in 1..2)|245
+CHm(NHn)-COOH (m,n in 0..2)|246
+HOOC-CHn-COOH (n in 1..2)|247
+HOOC-CHn-CHm-COOH (n, m in 1..2)|248
+HO-CHn-COOH (n in 1..2)|249
+NH2-CHn-CHm-COOH (n, m in 1..2)|250
+CH3-O-CHn-COOH (n in 1..2)|251
+HS-CH-COOH|252
+HS-CHn-CHm-COOH (n, m in 1..2)|253
+NC-CHn-CHm-CN (n, m in 1..2)|254
+OH-CHn-CHm-CN (n, m in 1..2)|255
+HS-CHn-CHm-SH (n, m in 1..2)|256
+COO-CHn-CHm-OOC (n, m in 1..2)|257
+OOC-CHm-CHm-COO (n, m in 1..2)|258
+NC-CHn-COO (n in 1..2)|259
+COCHnCOO (n in 1..2)|260
+CHm-O-CHn=CHp (m,n,p in 0..3)|261
+CHm=CHn-F (m,n in 0..2)|262
+CHm=CHn-Br (m,n in 0..2)|263
+CHm=CHn-I (m,n in 0..2)|264
+CHm=CHn-Cl (m,n in 0..2)|265
+CHm=CHn-CN (m,n in 0..2)|266
+CHn=CHm-COO-CHp (m,n,p in 0..3)|267
+CHm=CHn-CHO (m,n in 0..2)|268
+CHm=CHn-COOH (m,n in 0..2)|269
+aC-CHn-X (n in 1..2) X: Halogen|270
+aC-CHn-NHm (n in 1..2; m in 0..2))|271
+aC-CHn-O- (n in 1..2)|272
+aC-CHn-OH (n in 1..2)|273
+aC-CHn-CN (n in 1..2)|274
+aC-CHn-CHO (n in 1..2)|275
+aC-CHn-SH (n in 1..2)|276
+aC-CHn-COOH (n in 1..2)|277
+aC-CHn-CO- (n in 1..2)|278
+aC-CHn-S- (n in 1..2)|279
+aC-CHn-OOC-H (n in 1..2)|280
+aC-CHm-NO2 (n in 1..2)|281
+aC-CHn-CONH2 (n in 1..2)|282
+aC-CHn-OOC (n in 1..2)|283
+aC-CHn-COO (n in 1..2)|284
+aC-SO2-OH|285
+aC-CH(CH3)2|286
+aC-C(CH3)3|287
+aC-CF3|288
+(CHn=C)(cyc)-CHO (n in 0..2)|289
+(CHn=C)cyc-COO-CHm (n,m in 0..3)|290
+(CHn=C)cyc-CO- (n in 0..2)|291
+(CHn=C)cyc-CH3 (n in 0..2)|292
+(CHn=C)cyc-CH2 (n in 0..2)|293
+(CHn=C)cyc-CN (n in 0..2)|294
+(CHn=C)cyc-Cl (n in 0..2)|295
+CHcyc-CH3|296
+CHcyc-CH2|297
+CHcyc-CH|298
+CHcyc-C|299
+CHcyc-CH=CHn (n in 1..2)|300
+CHcyc-C=CHn (n in 1..2)|301
+CHcyc-Cl|302
+CHcyc-F|303
+CHcyc-OH|304
+CHcyc-NH2|305
+CHcyc-NH-CHn (n in 0..3)|306
+CHcyc-N-CHn (n in 0..3)|307
+CHcyc-SH|308
+CHcyc-CN|309
+CHcyc-COOH|310
+CHcyc-CO|311
+CHcyc-NO2|312
+CHcyc-S-|313
+CHcyc-CHO|314
+CHcyc-O-|315
+CHcyc-OOCH|316
+CHcyc-COO|317
+CHcyc-OOC|318
+Ccyc-CH3|319
+Ccyc-CH2|320
+Ccyc-OH|321
+>Ncyc-CH3|322
+>Ncyc-CH2|323
+AROMRINGs1s2|324
+AROMRINGs1s3|325
+AROMRINGs1s4|326
+AROMRINGs1s2s3|327
+AROMRINGs1s2s4|328
+AROMRINGs1s3s5|329
+AROMRINGs1s2s3s4|330
+AROMRINGs1s2s3s5|331
+AROMRINGs1s2s4s5|332
+PYRIDINEs2|333
+PYRIDINEs3|334
+PYRIDINEs4|335
+PYRIDINEs2s3|336
+PYRIDINEs2s4|337
+PYRIDINEs2s5|338
+PYRIDINEs2s6|339
+PYRIDINEs3s4|340
+PYRIDINEs3s5|341
+PYRIDINEs2s3s6|342
+(CHn=CHm)cyc-COOH|343
+AROMRINGs1s2s3s4s5|344
+aC-NHCOCH2N|345
+(N=C)cyc-CH3|346
+aC-CONH(CH2)2N|347
+aC-SO2NHn (n>=0;n<3)|348
+aC-SO2NHn (n>=0;n<3)|349
+aC-SO2NHn (n>=0;n<3)|350