Merge pull request #29 from OpenDrugDiscovery/add_func

Merge Add_func branch

src/openqdc/__init__.py

@@ -7,9 +7,32 @@
 
 # Dictionary of objects to lazily import; maps the object's name to its module path
 
-_lazy_imports_obj = {}
+_lazy_imports_obj = {
+    "ANI1": "openqdc.datasets.ani",
+    "ANI1CCX": "openqdc.datasets.ani",
+    "ANI1X": "openqdc.datasets.ani",
+    "Spice": "openqdc.datasets.spice",
+    "GEOM": "openqdc.datasets.geom",
+    "QMugs": "openqdc.datasets.qmugs",
+    "ISO17": "openqdc.datasets.iso_17",
+    "COMP6": "openqdc.datasets.comp6",
+    "GDML": "openqdc.datasets.gdml",
+    "Molecule3D": "openqdc.datasets.molecule3d",
+    "OrbnetDenali": "openqdc.datasets.orbnet_denali",
+    "SN2RXN": "openqdc.datasets.sn2_rxn",
+    "QM7X": "openqdc.datasets.qm7x",
+    "DESS": "openqdc.datasets.dess",
+    "NablaDFT": "openqdc.datasets.nabladft",
+    "SolvatedPeptides": "openqdc.datasets.solvated_peptides",
+    "WaterClusters": "openqdc.datasets.waterclusters3_30",
+    "TMQM": "openqdc.datasets.tmqm",
+    "Dummy": "openqdc.datasets.dummy",
+    "PCQM_B3LYP": "openqdc.datasets.pcqm",
+    "PCQM_PM6": "openqdc.datasets.pcqm",
+    "Transition1X": "openqdc.datasets.transition1x",
+}
 
-_lazy_imports_mod = {"datasets": "openqdc.datamodule", "utils": "openqdc.utils"}
+_lazy_imports_mod = {"datasets": "openqdc.datasets", "utils": "openqdc.utils"}
 
 
 def __getattr__(name):

src/openqdc/datasets/ani.py

@@ -39,6 +39,12 @@ class ANI1(BaseDataset):
     def root(self):
         return p_join(get_local_cache(), "ani")
 
+    def __smiles_converter__(self, x):
+        """util function to convert string to smiles: useful if the smiles is
+        encoded in a different format than its display format
+        """
+        return "-".join(x.decode("ascii").split("-")[:-1])
+
     @property
     def preprocess_path(self):
         path = p_join(self.root, "preprocessed", self.__name__)
@@ -89,6 +95,12 @@ class ANI1CCX(ANI1):
     __force_methods__ = []
     force_target_names = []
 
+    def __smiles_converter__(self, x):
+        """util function to convert string to smiles: useful if the smiles is
+        encoded in a different format than its display format
+        """
+        return x
+
 
 class ANI1X(ANI1):
     """
@@ -145,3 +157,9 @@ class ANI1X(ANI1):
 
     def convert_forces(self, x):
         return super().convert_forces(x) * 0.529177249  # correct the Dataset error
+
+    def __smiles_converter__(self, x):
+        """util function to convert string to smiles: useful if the smiles is
+        encoded in a different format than its display format
+        """
+        return x