selfies - pypi Package Compare versions

Comparing version 2.1.0 to 2.1.1

PKG-INFO

 Metadata-Version: 2.1
 Name: selfies
-Version: 2.1.0
+Version: 2.1.1
 Summary: SELFIES (SELF-referencIng Embedded Strings) is a general-purpose, sequence-based, robust representation of semantically constrained graphs.
@@ -24,2 +24,3 @@ Home-page: https://github.com/aspuru-guzik-group/selfies
         [Talk on youtube about SELFIES](https://www.youtube.com/watch?v=CaIyUmfGXDk).\
+        [A community paper with 31 authors on SELFIES and the future of molecular string representations](https://arxiv.org/abs/2204.00056).\
         [Blog explaining SELFIES in Japanese language](https://blacktanktop.hatenablog.com/entry/2021/08/12/115613)\
@@ -109,3 +110,16 @@ Major contributors of v1.0.n: _[Alston Lo](https://github.com/alstonlo) and [Seyone Chithrananda](https://github.com/seyonechithrananda)_\
         
+        #### Very simple creation of random valid molecules:
+        A key property of SELFIES is the possibility to create valid random molecules in a very simple way -- inspired by a tweet by [Rajarshi Guha](https://twitter.com/rguha/status/1543601839983284224):
         
+        ```python
+        import selfies as sf
+        import random
+        
+        alphabet=sf.get_semantic_robust_alphabet() # Gets the alphabet of robust symbols
+        rnd_selfies=''.join(random.sample(list(alphabet), 9))
+        rnd_smiles=sf.decoder(rnd_selfies)
+        print(rnd_smiles)
+        ```
+        These simple lines gives crazy molecules, but all are valid. Can be used as a start for more advanced filtering techniques or for machine learning models.
+        
         #### Integer and one-hot encoding SELFIES:
@@ -173,7 +187,4 @@
         print('Attribution:')
-        for smiles_token, a in attr:
+        for smiles_token in attr:
             print(smiles_token)
-            if a:
-                for j, selfies_token in a:
-                    print(f'\t{j}:{selfies_token}')
         
@@ -185,7 +196,7 @@ # output
         AttributionMap(index=0, token='C', attribution=[Attribution(index=0, token='[C]')])
-        AttributionMap(index=4, token='N', attribution=[Attribution(index=1, token='[N]')])
-        AttributionMap(index=6, token='C', attribution=[Attribution(index=2, token='[C]')])
-        AttributionMap(index=9, token='P', attribution=[Attribution(index=3, token='[Branch1]'), Attribution(index=5, token='[P]')])
-        AttributionMap(index=12, token='C', attribution=[Attribution(index=6, token='[C]')])
-        AttributionMap(index=14, token='C', attribution=[Attribution(index=7, token='[C]')])
+        AttributionMap(index=2, token='N', attribution=[Attribution(index=1, token='[N]')])
+        AttributionMap(index=3, token='C', attribution=[Attribution(index=2, token='[C]')])
+        AttributionMap(index=5, token='P', attribution=[Attribution(index=3, token='[Branch1]'), Attribution(index=5, token='[P]')])
+        AttributionMap(index=7, token='C', attribution=[Attribution(index=6, token='[C]')])
+        AttributionMap(index=8, token='C', attribution=[Attribution(index=7, token='[C]')])
         ```
@@ -192,0 +203,0 @@

README.md

@@ -16,2 +16,3 @@ # SELFIES
 [Talk on youtube about SELFIES](https://www.youtube.com/watch?v=CaIyUmfGXDk).\
+[A community paper with 31 authors on SELFIES and the future of molecular string representations](https://arxiv.org/abs/2204.00056).\
 [Blog explaining SELFIES in Japanese language](https://blacktanktop.hatenablog.com/entry/2021/08/12/115613)\
@@ -101,3 +102,16 @@ Major contributors of v1.0.n: _[Alston Lo](https://github.com/alstonlo) and [Seyone Chithrananda](https://github.com/seyonechithrananda)_\
 
+#### Very simple creation of random valid molecules:
+A key property of SELFIES is the possibility to create valid random molecules in a very simple way -- inspired by a tweet by [Rajarshi Guha](https://twitter.com/rguha/status/1543601839983284224):
 
+```python
+import selfies as sf
+import random
+
+alphabet=sf.get_semantic_robust_alphabet() # Gets the alphabet of robust symbols
+rnd_selfies=''.join(random.sample(list(alphabet), 9))
+rnd_smiles=sf.decoder(rnd_selfies)
+print(rnd_smiles)
+```
+These simple lines gives crazy molecules, but all are valid. Can be used as a start for more advanced filtering techniques or for machine learning models.
+
 #### Integer and one-hot encoding SELFIES:
@@ -165,7 +179,4 @@
 print('Attribution:')
-for smiles_token, a in attr:
+for smiles_token in attr:
     print(smiles_token)
-    if a:
-        for j, selfies_token in a:
-            print(f'\t{j}:{selfies_token}')
 
@@ -177,7 +188,7 @@ # output
 AttributionMap(index=0, token='C', attribution=[Attribution(index=0, token='[C]')])
-AttributionMap(index=4, token='N', attribution=[Attribution(index=1, token='[N]')])
-AttributionMap(index=6, token='C', attribution=[Attribution(index=2, token='[C]')])
-AttributionMap(index=9, token='P', attribution=[Attribution(index=3, token='[Branch1]'), Attribution(index=5, token='[P]')])
-AttributionMap(index=12, token='C', attribution=[Attribution(index=6, token='[C]')])
-AttributionMap(index=14, token='C', attribution=[Attribution(index=7, token='[C]')])
+AttributionMap(index=2, token='N', attribution=[Attribution(index=1, token='[N]')])
+AttributionMap(index=3, token='C', attribution=[Attribution(index=2, token='[C]')])
+AttributionMap(index=5, token='P', attribution=[Attribution(index=3, token='[Branch1]'), Attribution(index=5, token='[P]')])
+AttributionMap(index=7, token='C', attribution=[Attribution(index=6, token='[C]')])
+AttributionMap(index=8, token='C', attribution=[Attribution(index=7, token='[C]')])
 ```
@@ -184,0 +195,0 @@

selfies.egg-info/PKG-INFO

 Metadata-Version: 2.1
 Name: selfies
-Version: 2.1.0
+Version: 2.1.1
 Summary: SELFIES (SELF-referencIng Embedded Strings) is a general-purpose, sequence-based, robust representation of semantically constrained graphs.
@@ -24,2 +24,3 @@ Home-page: https://github.com/aspuru-guzik-group/selfies
         [Talk on youtube about SELFIES](https://www.youtube.com/watch?v=CaIyUmfGXDk).\
+        [A community paper with 31 authors on SELFIES and the future of molecular string representations](https://arxiv.org/abs/2204.00056).\
         [Blog explaining SELFIES in Japanese language](https://blacktanktop.hatenablog.com/entry/2021/08/12/115613)\
@@ -109,3 +110,16 @@ Major contributors of v1.0.n: _[Alston Lo](https://github.com/alstonlo) and [Seyone Chithrananda](https://github.com/seyonechithrananda)_\
         
+        #### Very simple creation of random valid molecules:
+        A key property of SELFIES is the possibility to create valid random molecules in a very simple way -- inspired by a tweet by [Rajarshi Guha](https://twitter.com/rguha/status/1543601839983284224):
         
+        ```python
+        import selfies as sf
+        import random
+        
+        alphabet=sf.get_semantic_robust_alphabet() # Gets the alphabet of robust symbols
+        rnd_selfies=''.join(random.sample(list(alphabet), 9))
+        rnd_smiles=sf.decoder(rnd_selfies)
+        print(rnd_smiles)
+        ```
+        These simple lines gives crazy molecules, but all are valid. Can be used as a start for more advanced filtering techniques or for machine learning models.
+        
         #### Integer and one-hot encoding SELFIES:
@@ -173,7 +187,4 @@
         print('Attribution:')
-        for smiles_token, a in attr:
+        for smiles_token in attr:
             print(smiles_token)
-            if a:
-                for j, selfies_token in a:
-                    print(f'\t{j}:{selfies_token}')
         
@@ -185,7 +196,7 @@ # output
         AttributionMap(index=0, token='C', attribution=[Attribution(index=0, token='[C]')])
-        AttributionMap(index=4, token='N', attribution=[Attribution(index=1, token='[N]')])
-        AttributionMap(index=6, token='C', attribution=[Attribution(index=2, token='[C]')])
-        AttributionMap(index=9, token='P', attribution=[Attribution(index=3, token='[Branch1]'), Attribution(index=5, token='[P]')])
-        AttributionMap(index=12, token='C', attribution=[Attribution(index=6, token='[C]')])
-        AttributionMap(index=14, token='C', attribution=[Attribution(index=7, token='[C]')])
+        AttributionMap(index=2, token='N', attribution=[Attribution(index=1, token='[N]')])
+        AttributionMap(index=3, token='C', attribution=[Attribution(index=2, token='[C]')])
+        AttributionMap(index=5, token='P', attribution=[Attribution(index=3, token='[Branch1]'), Attribution(index=5, token='[P]')])
+        AttributionMap(index=7, token='C', attribution=[Attribution(index=6, token='[C]')])
+        AttributionMap(index=8, token='C', attribution=[Attribution(index=7, token='[C]')])
         ```
@@ -192,0 +203,0 @@

selfies/__init__.py

@@ -28,3 +28,3 @@ #!/usr/bin/env python
 
-__version__ = "2.0.0"
+__version__ = "2.1.0"
 
@@ -31,0 +31,0 @@ __all__ = [

selfies/encoder.py

@@ -187,2 +187,6 @@ from selfies.exceptions import EncoderError, SMILESParserError
             else:
+                # start, end are so we can go back and
+                # correct offset from branch symbol in
+                # branch tokens
+                start = len(attribution_maps)
                 branch = _fragment_to_selfies(
@@ -195,7 +199,5 @@ mol, bond, bond.dst, attribution_maps, len(derived))
                 )
+                end = len(attribution_maps)
 
                 derived.append(branch_symbol)
-                attribution_maps.append(AttributionMap(
-                    len(derived) - 1 + attribution_index,
-                    branch_symbol, mol.get_attribution(bond)))
                 for symbol in Q_as_symbols:
@@ -206,2 +208,10 @@ derived.append(symbol)
                         symbol, mol.get_attribution(bond)))
+
+                # account for branch symbol because it is inserted after
+                for j in range(start, end):
+                    attribution_maps[j].index += len(Q_as_symbols) + 1
+                attribution_maps.append(AttributionMap(
+                    len(derived) - 1 + attribution_index,
+                    branch_symbol, mol.get_attribution(bond)))
+
                 derived.extend(branch)
@@ -212,3 +222,2 @@
             break
-
     return derived
@@ -215,0 +224,0 @@

selfies/utils/smiles_utils.py

@@ -427,3 +427,3 @@ import enum
             derived, mol, root, ring_log, attribution_maps, attribution_index)
-        attribution_index += len(derived)
+        attribution_index += _strlen(derived)
         fragments.append("".join(derived))
@@ -436,2 +436,6 @@ # trim attribution map of empty tokens
 
+def _strlen(slist: List[str]) -> int:
+    return len(''.join(slist))
+
+
 def _derive_smiles_from_fragment(
@@ -447,3 +451,3 @@ derived,
     attribution_maps.append(AttributionMap(
-        len(derived) - 1 + attribution_index,
+        _strlen(derived) - 1 + attribution_index,
         token, mol.get_attribution(curr_atom)))
@@ -457,3 +461,3 @@
             attribution_maps.append(AttributionMap(
-                len(derived) - 1 + attribution_index,
+                _strlen(derived) - 1 + attribution_index,
                 token, mol.get_attribution(bond)))
@@ -473,3 +477,3 @@ ends = (min(bond.src, bond.dst), max(bond.src, bond.dst))
             attribution_maps.append(AttributionMap(
-                len(derived) - 1 + attribution_index,
+                _strlen(derived) - 1 + attribution_index,
                 token, mol.get_attribution(bond)))
@@ -476,0 +480,0 @@ _derive_smiles_from_fragment(

setup.py

@@ -10,3 +10,3 @@ #!/usr/bin/env python
     name="selfies",
-    version="2.1.0",
+    version="2.1.1",
     author="Mario Krenn, Alston Lo, and many other contributors",
@@ -13,0 +13,0 @@ author_email="[e-mail], [e-mail]",

Alert delta unavailable

Currently unable to show alert delta for PyPI packages.

Improved metrics

Total package byte prevSize

124295

2.29%

Lines of code

1821

0.55%