add ChEBI25 graph properties class

chebai_graph/preprocessing/datasets/__init__.py

@@ -11,13 +11,15 @@
     ChEBI50_WFGE_WGN_AsPerNodeType,
     ChEBI50_WFGE_WGN_GraphProp,
     ChEBI50GraphData,
+    ChEBI25GraphProperties,
     ChEBI50GraphProperties,
     ChEBI100GraphProperties,
 )
 from .pubchem import PubChemGraphProperties
 
 __all__ = [
     "ChEBI50GraphFGAugmentorReader",
+    "ChEBI25GraphProperties",
     "ChEBI50GraphProperties",
     "ChEBI100GraphProperties",
     "ChEBI50GraphData",

chebai_graph/preprocessing/datasets/chebi.py

@@ -9,6 +9,7 @@
 import torch
 import tqdm
 from chebai.preprocessing.datasets.chebi import (
+    ChEBIOver25,
     ChEBIOver50,
     ChEBIOver100,
     ChEBIOverX,
@@ -705,6 +706,12 @@ def load_processed_data_from_file(self, filename):
         return base_df[base_data[0].keys()].to_dict("records")
 
 
+class ChEBI25GraphProperties(GraphPropertiesMixIn, ChEBIOver25):
+    """ChEBIOver25 dataset with molecular property encodings."""
+
+    THRESHOLD = 25
+
+
 class ChEBI50GraphProperties(GraphPropertiesMixIn, ChEBIOver50):
     """ChEBIOver50 dataset with molecular property encodings."""
 

configs/data/chebi25_graph_properties.yml

@@ -0,0 +1,14 @@
+class_path: chebai_graph.preprocessing.datasets.ChEBI25GraphProperties
+init_args:
+  properties:
+      - chebai_graph.preprocessing.properties.AtomType
+      - chebai_graph.preprocessing.properties.NumAtomBonds
+      - chebai_graph.preprocessing.properties.AtomCharge
+      - chebai_graph.preprocessing.properties.AtomAromaticity
+      - chebai_graph.preprocessing.properties.AtomHybridization
+      - chebai_graph.preprocessing.properties.AtomNumHs
+      - chebai_graph.preprocessing.properties.BondType
+      - chebai_graph.preprocessing.properties.BondInRing
+      - chebai_graph.preprocessing.properties.BondAromaticity
+      #- chebai_graph.preprocessing.properties.MoleculeNumRings
+      - chebai_graph.preprocessing.properties.RDKit2DNormalized

configs/model/gat.yml

@@ -3,12 +3,13 @@ init_args:
   optimizer_kwargs:
     lr: 1e-3
   config:
-    in_channels: 158 # number of node/atom properties
+    in_channels: 161 # number of node/atom properties
     hidden_channels: 256
     out_channels: 512
     num_layers: 4
-    edge_dim: 7 # number of bond properties
+    edge_dim: 8 # number of bond properties
     heads: 8  # the number of heads should be divisible by output channels (hidden channels if output channel not given)
     v2: True  # This uses `torch_geometric.nn.conv.GATv2Conv` convolution layers, set False to use `GATConv`
+    dropout: 0
   n_molecule_properties: 0
   n_linear_layers: 1

configs/model/resgated.yml

@@ -3,11 +3,11 @@ init_args:
   optimizer_kwargs:
     lr: 1e-3
   config:
-    in_channels: 158 # number of node/atom properties
+    in_channels: 161 # number of node/atom properties
     hidden_channels: 256
     out_channels: 512
     num_layers: 4
-    edge_dim: 7 # number of bond properties
+    edge_dim: 8 # number of bond properties
     dropout: 0
   n_molecule_properties: 0
   n_linear_layers: 1