From 9abbe9fe76c245ff9352902e47b408a719c0ac4b Mon Sep 17 00:00:00 2001 From: aditya0by0 Date: Sat, 8 Aug 2026 11:23:01 +0200 Subject: [PATCH 01/10] chebi aug variant with all props except node level --- .../preprocessing/datasets/__init__.py | 4 +++- .../datasets/augmentation_base.py | 7 ++++++ chebai_graph/preprocessing/datasets/chebi.py | 7 ++++++ .../chebi50_all_props_except_node_lvl.yml | 24 +++++++++++++++++++ 4 files changed, 41 insertions(+), 1 deletion(-) create mode 100644 configs/data/augmented/properties/chebi50_all_props_except_node_lvl.yml diff --git a/chebai_graph/preprocessing/datasets/__init__.py b/chebai_graph/preprocessing/datasets/__init__.py index 9ee9856..c1e0a23 100644 --- a/chebai_graph/preprocessing/datasets/__init__.py +++ b/chebai_graph/preprocessing/datasets/__init__.py @@ -1,4 +1,5 @@ from .chebi import ( + ChEBI25GraphProperties, ChEBI50_Atom_WGNOnly_GraphProp, ChEBI50_GN_WithAllNodes_FG_WithAtoms_FGE, ChEBI50_GN_WithAllNodes_FG_WithAtoms_NoFGE, @@ -9,6 +10,7 @@ ChEBI50_StaticGNI, ChEBI50_WFGE_NGN_GraphProp, ChEBI50_WFGE_WGN_AsPerNodeType, + ChEBI50_WFGE_WGN_ForAllPropsExceptNodeLevel, ChEBI50_WFGE_WGN_ForAtomAndFGLevelOnly, ChEBI50_WFGE_WGN_ForAtomLevelAndGraphNodeOnly, ChEBI50_WFGE_WGN_ForAtomLevelOnly, @@ -18,7 +20,6 @@ ChEBI50_WFGE_WGN_ForNodeLevelPropOnlyForAllNodes, ChEBI50_WFGE_WGN_GraphProp, ChEBI50GraphData, - ChEBI25GraphProperties, ChEBI50GraphProperties, ChEBI100GraphProperties, ) @@ -60,6 +61,7 @@ "ChEBI50_WFGE_WGN_ForAtomLevelAndGraphNodeOnly", "ChEBI50_WFGE_WGN_ForFGLevelAndGraphNodeOnly", "ChEBI50_WFGE_WGN_ForNodeLevelPropOnlyForAllNodes", + "ChEBI50_WFGE_WGN_ForAllPropsExceptNodeLevel", "BACE_WFGE_WGN_AsPerNodeType", "BBBP_WFGE_WGN_AsPerNodeType", "ClinTox_WFGE_WGN_AsPerNodeType", diff --git a/chebai_graph/preprocessing/datasets/augmentation_base.py b/chebai_graph/preprocessing/datasets/augmentation_base.py index 9bf6cdc..20ce564 100644 --- a/chebai_graph/preprocessing/datasets/augmentation_base.py +++ b/chebai_graph/preprocessing/datasets/augmentation_base.py @@ -177,3 +177,10 @@ def _fill_node_tensor_with_molecule_type_property( is_graph_node: torch.Tensor, ) -> torch.Tensor: return node_tensor + + +class GraphPropAllPropsExceptNodeLevel(GraphPropAsPerNodeType): + def _fill_node_tensor_with_all_node_type_property( + self, node_tensor: torch.Tensor, property_values: torch.Tensor, offset: int + ) -> torch.Tensor: + return node_tensor diff --git a/chebai_graph/preprocessing/datasets/chebi.py b/chebai_graph/preprocessing/datasets/chebi.py index 1962c31..c4ac4ed 100644 --- a/chebai_graph/preprocessing/datasets/chebi.py +++ b/chebai_graph/preprocessing/datasets/chebi.py @@ -25,6 +25,7 @@ from .augmentation_base import ( AugGraphPropMixIn_NoGraphNode, AugGraphPropMixIn_WithGraphNode, + GraphPropAllPropsExceptNodeLevel, GraphPropForAtomAndFGLevelOnly, GraphPropForAtomLevelAndGraphNodeOnly, GraphPropForAtomLevelOnly, @@ -204,6 +205,12 @@ class ChEBI50_WFGE_WGN_ForNodeLevelPropOnlyForAllNodes( READER = AtomFGReader_WithFGEdges_WithGraphNode +class ChEBI50_WFGE_WGN_ForAllPropsExceptNodeLevel( + GraphPropAllPropsExceptNodeLevel, ChEBIOver50 +): + READER = AtomFGReader_WithFGEdges_WithGraphNode + + # ---------- Final Augmentation: Different Thresholds ------------------------------ class ChEBI100_WFGE_WGN_AsPerNodeType(GraphPropAsPerNodeType, ChEBIOver100): READER = AtomFGReader_WithFGEdges_WithGraphNode diff --git a/configs/data/augmented/properties/chebi50_all_props_except_node_lvl.yml b/configs/data/augmented/properties/chebi50_all_props_except_node_lvl.yml new file mode 100644 index 0000000..a03da69 --- /dev/null +++ b/configs/data/augmented/properties/chebi50_all_props_except_node_lvl.yml @@ -0,0 +1,24 @@ +class_path: chebai_graph.preprocessing.datasets.ChEBI50_WFGE_WGN_ForAllPropsExceptNodeLevel +init_args: + properties: + # All Node type properties + - chebai_graph.preprocessing.properties.AtomNodeLevel + # Atom Node type properties + - chebai_graph.preprocessing.properties.AugAtomAromaticity + - chebai_graph.preprocessing.properties.AugAtomCharge + - chebai_graph.preprocessing.properties.AugAtomHybridization + - chebai_graph.preprocessing.properties.AugAtomNumHs + - chebai_graph.preprocessing.properties.AugAtomType + - chebai_graph.preprocessing.properties.AugNumAtomBonds + # FG Node type properties + - chebai_graph.preprocessing.properties.AtomFunctionalGroup + - chebai_graph.preprocessing.properties.IsHydrogenBondDonorFG + - chebai_graph.preprocessing.properties.IsHydrogenBondAcceptorFG + - chebai_graph.preprocessing.properties.IsFGAlkyl + # Graph Node type properties + - chebai_graph.preprocessing.properties.AugRDKit2DNormalized + # Bond properties + - chebai_graph.preprocessing.properties.BondLevel + - chebai_graph.preprocessing.properties.AugBondAromaticity + - chebai_graph.preprocessing.properties.AugBondInRing + - chebai_graph.preprocessing.properties.AugBondType From 05462dacf410bd216416aff568507cb100576a57 Mon Sep 17 00:00:00 2001 From: aditya0b0 Date: Mon, 10 Aug 2026 20:42:36 +0200 Subject: [PATCH 02/10] allow adding new tokens through augmented class for atom specific props --- chebai_graph/preprocessing/properties/base.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/chebai_graph/preprocessing/properties/base.py b/chebai_graph/preprocessing/properties/base.py index f148df8..1f2e0aa 100644 --- a/chebai_graph/preprocessing/properties/base.py +++ b/chebai_graph/preprocessing/properties/base.py @@ -209,8 +209,8 @@ def on_finish(self) -> None: hasattr(self.encoder, "cache") and len(self.encoder.cache) > self.encoder.index_length_start ): - raise ValueError( - f"{self.__class__.__name__} attempted to add new tokens " + print( + f"{self.__class__.__name__} added new tokens " f"to a frozen encoder at {self.encoder.index_path}" ) super().on_finish() From d26b9b9e04179b0ce851c75f74c47ec6e221d7f0 Mon Sep 17 00:00:00 2001 From: aditya0b0 Date: Mon, 10 Aug 2026 20:42:52 +0200 Subject: [PATCH 03/10] BACE dataset tokens --- .../bin/bace/AtomCharge/indices_one_hot.txt | 3 ++ .../AtomFunctionalGroup/indices_one_hot.txt | 44 +++++++++++++++++++ .../AtomHybridization/indices_one_hot.txt | 3 ++ .../bace/AtomNodeLevel/indices_one_hot.txt | 3 ++ .../bin/bace/AtomNumHs/indices_one_hot.txt | 4 ++ .../bin/bace/AtomType/indices_one_hot.txt | 8 ++++ .../bin/bace/BondLevel/indices_one_hot.txt | 4 ++ .../bin/bace/BondType/indices_one_hot.txt | 4 ++ .../bin/bace/NumAtomBonds/indices_one_hot.txt | 4 ++ 9 files changed, 77 insertions(+) create mode 100644 chebai_graph/preprocessing/bin/bace/AtomCharge/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bace/AtomFunctionalGroup/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bace/AtomHybridization/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bace/AtomNodeLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bace/AtomNumHs/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bace/AtomType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bace/BondLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bace/BondType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bace/NumAtomBonds/indices_one_hot.txt diff --git a/chebai_graph/preprocessing/bin/bace/AtomCharge/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/AtomCharge/indices_one_hot.txt new file mode 100644 index 0000000..d7e52d1 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/AtomCharge/indices_one_hot.txt @@ -0,0 +1,3 @@ +0 +1 +-1 diff --git a/chebai_graph/preprocessing/bin/bace/AtomFunctionalGroup/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/AtomFunctionalGroup/indices_one_hot.txt new file mode 100644 index 0000000..b621c2a --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/AtomFunctionalGroup/indices_one_hot.txt @@ -0,0 +1,44 @@ +RING_6 +difluoromethyl +RING_5 +ether +alkyne +alkyl +primary_amine +fluoro +amide +graph_fg +NO_FG +alkene +tertiary_carbon +alkene_carbon +nitrile +trifluoromethyl +ketone +chloro +quaternary_carbon +sulfonyl +hydroxyl +bromo +secondary_amine +ester +aldoxime +sulfide +iodo +tertiary_amine +RING_4 +secondary_ketimine +ketoxime +RING_3 +carboxylate +acetal +sulfinyl +RING_7 +RING_16 +RING_15 +nitro +primary_ketimine +sulfonate_ester +RING_8 +RING_14 +RING_13 diff --git a/chebai_graph/preprocessing/bin/bace/AtomHybridization/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/AtomHybridization/indices_one_hot.txt new file mode 100644 index 0000000..7c99da3 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/AtomHybridization/indices_one_hot.txt @@ -0,0 +1,3 @@ +SP2 +SP3 +SP diff --git a/chebai_graph/preprocessing/bin/bace/AtomNodeLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/AtomNodeLevel/indices_one_hot.txt new file mode 100644 index 0000000..2d65776 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/AtomNodeLevel/indices_one_hot.txt @@ -0,0 +1,3 @@ +atom_node_lvl +fg_node_lvl +graph_node_level diff --git a/chebai_graph/preprocessing/bin/bace/AtomNumHs/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/AtomNumHs/indices_one_hot.txt new file mode 100644 index 0000000..c4b216a --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/AtomNumHs/indices_one_hot.txt @@ -0,0 +1,4 @@ +0 +1 +3 +2 diff --git a/chebai_graph/preprocessing/bin/bace/AtomType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/AtomType/indices_one_hot.txt new file mode 100644 index 0000000..6da4980 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/AtomType/indices_one_hot.txt @@ -0,0 +1,8 @@ +6 +7 +8 +9 +17 +16 +35 +53 diff --git a/chebai_graph/preprocessing/bin/bace/BondLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/BondLevel/indices_one_hot.txt new file mode 100644 index 0000000..6b48d66 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/BondLevel/indices_one_hot.txt @@ -0,0 +1,4 @@ +within_atoms_lvl +atom_fg_lvl +within_fg_lvl +to_graphNode_lvl diff --git a/chebai_graph/preprocessing/bin/bace/BondType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/BondType/indices_one_hot.txt new file mode 100644 index 0000000..f1a2ce5 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/BondType/indices_one_hot.txt @@ -0,0 +1,4 @@ +SINGLE +AROMATIC +TRIPLE +DOUBLE diff --git a/chebai_graph/preprocessing/bin/bace/NumAtomBonds/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bace/NumAtomBonds/indices_one_hot.txt new file mode 100644 index 0000000..cf286d6 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bace/NumAtomBonds/indices_one_hot.txt @@ -0,0 +1,4 @@ +3 +2 +4 +1 From 1ce48efaba747c6e84938c5a78ade85800ebae46 Mon Sep 17 00:00:00 2001 From: aditya0b0 Date: Tue, 11 Aug 2026 23:59:57 +0200 Subject: [PATCH 04/10] check len of base_df after merge, to avoid memory blow due to duplicated entries leading to cross merge --- chebai_graph/preprocessing/datasets/base.py | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/chebai_graph/preprocessing/datasets/base.py b/chebai_graph/preprocessing/datasets/base.py index 4e8e6c3..84d42be 100644 --- a/chebai_graph/preprocessing/datasets/base.py +++ b/chebai_graph/preprocessing/datasets/base.py @@ -462,6 +462,7 @@ def load_processed_data( base_data = super().load_processed_data(kind, filename) base_df = pd.DataFrame(base_data) base_df["ident"] = base_df["ident"].astype(str) + len_base_df_before_merge = len(base_df) props_categories = { "AllNodeTypeProperties": [], "FGNodeTypeProperties": [], @@ -524,11 +525,21 @@ def load_processed_data( ) property_df = pd.DataFrame(property_data) + assert len(property_df) == len(property_df["ident"].unique()), ( + f"Duplicate entries found in property {property.name} data. " + f"Unique entries {len(property_df['ident'].unique())}. " + f"Total entries {len(property_df)}. " + ) property_df["ident"] = property_df["ident"].astype(str) property_df.rename( columns={property.name: f"{property.name}"}, inplace=True ) + base_df = base_df.merge(property_df, on="ident", how="left") + assert len(base_df) == len_base_df_before_merge, ( + f"Length mismatch after merging property {property.name}. " + f"Expected {len_base_df_before_merge}, got {len(base_df)}" + ) base_df["features"] = base_df.apply( lambda row: self._merge_props_into_base( From f590aebb32fcc2a7549680f41896fcc32588ca2e Mon Sep 17 00:00:00 2001 From: aditya0b0 Date: Wed, 12 Aug 2026 13:56:52 +0200 Subject: [PATCH 05/10] BBBP tokens --- .../bin/bbbp/AtomCharge/indices_one_hot.txt | 4 + .../AtomFunctionalGroup/indices_one_hot.txt | 80 +++++++++++++++++++ .../AtomHybridization/indices_one_hot.txt | 4 + .../bbbp/AtomNodeLevel/indices_one_hot.txt | 3 + .../bin/bbbp/AtomNumHs/indices_one_hot.txt | 4 + .../bin/bbbp/AtomType/indices_one_hot.txt | 13 +++ .../bin/bbbp/BondLevel/indices_one_hot.txt | 4 + .../bin/bbbp/BondType/indices_one_hot.txt | 4 + .../bin/bbbp/NumAtomBonds/indices_one_hot.txt | 5 ++ 9 files changed, 121 insertions(+) create mode 100644 chebai_graph/preprocessing/bin/bbbp/AtomCharge/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bbbp/AtomFunctionalGroup/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bbbp/AtomHybridization/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bbbp/AtomNodeLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bbbp/AtomNumHs/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bbbp/AtomType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bbbp/BondLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bbbp/BondType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/bbbp/NumAtomBonds/indices_one_hot.txt diff --git a/chebai_graph/preprocessing/bin/bbbp/AtomCharge/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/AtomCharge/indices_one_hot.txt new file mode 100644 index 0000000..7b6a00a --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/AtomCharge/indices_one_hot.txt @@ -0,0 +1,4 @@ +0 +1 +-1 +2 diff --git a/chebai_graph/preprocessing/bin/bbbp/AtomFunctionalGroup/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/AtomFunctionalGroup/indices_one_hot.txt new file mode 100644 index 0000000..d2ee211 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/AtomFunctionalGroup/indices_one_hot.txt @@ -0,0 +1,80 @@ +alkyl +ester +chloro +RING_6 +tertiary_amine +graph_fg +tertiary_carbon +primary_amine +dichloromethyl +sulfonyl +ketone +secondary_amine +hydroxyl +ether +quaternary_carbon +amide +NO_FG +carboxyl +nitro +alkene +alkene_carbon +secondary_ketimine +secondary_aldimine +carboxylate +iodo +aldoxime +bromo +alkyne +fluoro +carbamate +trifluoromethyl +sulfide +trichloromethyl +hemiacetal +primary_ketimine +azide +4_ammonium_ion +sulfonate_ester +ketoxime +nitroso +sulfhydryl +difluoromethyl +fluorochloromethyl +chlorobromomethyl +phosphono +carbodithio +disulfide +difluorochloromethyl +carbonate_ester +phosphate +RING_5 +thiolester +RING_7 +nitrile +phosphoryl +aldehyde +sulfinyl +thioketone +acetal +RING_4 +sulfonic_acid +imide +RING_14 +RING_24 +amidine +RING_3 +RING_9 +RING_19 +RING_16 +RING_8 +isonitrile +RING_23 +RING_12 +RING_21 +RING_17 +RING_30 +RING_33 +RING_36 +azo +RING_15 diff --git a/chebai_graph/preprocessing/bin/bbbp/AtomHybridization/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/AtomHybridization/indices_one_hot.txt new file mode 100644 index 0000000..0e4a9aa --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/AtomHybridization/indices_one_hot.txt @@ -0,0 +1,4 @@ +SP3 +SP2 +S +SP diff --git a/chebai_graph/preprocessing/bin/bbbp/AtomNodeLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/AtomNodeLevel/indices_one_hot.txt new file mode 100644 index 0000000..2d65776 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/AtomNodeLevel/indices_one_hot.txt @@ -0,0 +1,3 @@ +atom_node_lvl +fg_node_lvl +graph_node_level diff --git a/chebai_graph/preprocessing/bin/bbbp/AtomNumHs/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/AtomNumHs/indices_one_hot.txt new file mode 100644 index 0000000..35f5032 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/AtomNumHs/indices_one_hot.txt @@ -0,0 +1,4 @@ +2 +0 +1 +3 diff --git a/chebai_graph/preprocessing/bin/bbbp/AtomType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/AtomType/indices_one_hot.txt new file mode 100644 index 0000000..9500570 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/AtomType/indices_one_hot.txt @@ -0,0 +1,13 @@ +6 +17 +8 +7 +16 +11 +53 +35 +9 +1 +15 +5 +20 diff --git a/chebai_graph/preprocessing/bin/bbbp/BondLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/BondLevel/indices_one_hot.txt new file mode 100644 index 0000000..6b48d66 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/BondLevel/indices_one_hot.txt @@ -0,0 +1,4 @@ +within_atoms_lvl +atom_fg_lvl +within_fg_lvl +to_graphNode_lvl diff --git a/chebai_graph/preprocessing/bin/bbbp/BondType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/BondType/indices_one_hot.txt new file mode 100644 index 0000000..a134437 --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/BondType/indices_one_hot.txt @@ -0,0 +1,4 @@ +DOUBLE +SINGLE +AROMATIC +TRIPLE diff --git a/chebai_graph/preprocessing/bin/bbbp/NumAtomBonds/indices_one_hot.txt b/chebai_graph/preprocessing/bin/bbbp/NumAtomBonds/indices_one_hot.txt new file mode 100644 index 0000000..5d07eee --- /dev/null +++ b/chebai_graph/preprocessing/bin/bbbp/NumAtomBonds/indices_one_hot.txt @@ -0,0 +1,5 @@ +2 +4 +1 +3 +0 From f4cb1ace533ddbbebcb2a40d046c59bb4317ef37 Mon Sep 17 00:00:00 2001 From: aditya0b0 Date: Wed, 12 Aug 2026 14:27:20 +0200 Subject: [PATCH 06/10] hiv tokens --- .../bin/hiv/AtomCharge/indices_one_hot.txt | 9 ++ .../AtomFunctionalGroup/indices_one_hot.txt | 122 ++++++++++++++++++ .../hiv/AtomHybridization/indices_one_hot.txt | 7 + .../bin/hiv/AtomNodeLevel/indices_one_hot.txt | 3 + .../bin/hiv/AtomNumHs/indices_one_hot.txt | 5 + .../bin/hiv/AtomType/indices_one_hot.txt | 54 ++++++++ .../bin/hiv/BondLevel/indices_one_hot.txt | 0 .../bin/hiv/BondType/indices_one_hot.txt | 0 .../bin/hiv/NumAtomBonds/indices_one_hot.txt | 0 9 files changed, 200 insertions(+) create mode 100644 chebai_graph/preprocessing/bin/hiv/AtomCharge/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/hiv/AtomFunctionalGroup/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/hiv/AtomHybridization/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/hiv/AtomNodeLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/hiv/AtomNumHs/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/hiv/AtomType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/hiv/BondLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/hiv/BondType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/hiv/NumAtomBonds/indices_one_hot.txt diff --git a/chebai_graph/preprocessing/bin/hiv/AtomCharge/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/AtomCharge/indices_one_hot.txt new file mode 100644 index 0000000..22aacd7 --- /dev/null +++ b/chebai_graph/preprocessing/bin/hiv/AtomCharge/indices_one_hot.txt @@ -0,0 +1,9 @@ +0 +1 +-1 +3 +-4 +-3 +-2 +2 +-5 diff --git a/chebai_graph/preprocessing/bin/hiv/AtomFunctionalGroup/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/AtomFunctionalGroup/indices_one_hot.txt new file mode 100644 index 0000000..e5b33d4 --- /dev/null +++ b/chebai_graph/preprocessing/bin/hiv/AtomFunctionalGroup/indices_one_hot.txt @@ -0,0 +1,122 @@ +alkyl +RING_6 +chloro +NO_FG +secondary_amine +graph_fg +carboxyl +primary_amine +sulfonic_acid +nitro +ketone +hydroxyl +sulfonyl +ester +nitroso +sulfhydryl +tertiary_carbon +tertiary_amine +dichloromethyl +nitrile +primary_ketimine +alkyne +alkene +ether +iodo +sulfide +secondary_aldimine +phosphoryl +thioketone +alkene_carbon +secondary_ketimine +nitrate +4_ammonium_ion +ketoxime +amide +amidine +trichloromethyl +fluoro +quaternary_carbon +hydrazone +disulfide +thiocyanate +carbamate +trifluoromethyl +phosphate +sulfonate_ester +sulfinyl +azo +bromo +imide +carbodithioic_acid +carbodithio +sulfino +silyl_ether +aldehyde +phosphono +azide +aldoxime +phosphino +trimethylsilyl +thionoester +thiolester +isonitrile +acetal +difluorochloromethyl +dibromomethyl +ketal +diiodomethyl +borono +isothiocyanate +difluoromethyl +tribromomethyl +carbonate_ester +hemiacetal +phosphodiester +carboxylate +orthoester +isocyanate +primary_aldimine +hemiketal +borinate +RING_5 +cyanate +RING_4 +RING_24 +RING_3 +thial +RING_7 +RING_12 +RING_9 +RING_16 +hydroperoxy +RING_15 +RING_18 +RING_8 +RING_35 +RING_10 +RING_19 +RING_17 +RING_29 +RING_23 +RING_27 +RING_11 +RING_14 +RING_20 +RING_33 +RING_13 +RING_31 +RING_21 +RING_28 +RING_22 +RING_30 +RING_34 +RING_54 +RING_38 +RING_36 +RING_26 +RING_32 +carboxylic_anhydride +RING_25 +carbothioic_S-acid +RING_40 diff --git a/chebai_graph/preprocessing/bin/hiv/AtomHybridization/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/AtomHybridization/indices_one_hot.txt new file mode 100644 index 0000000..cdc6985 --- /dev/null +++ b/chebai_graph/preprocessing/bin/hiv/AtomHybridization/indices_one_hot.txt @@ -0,0 +1,7 @@ +SP3 +SP2 +SP +S +SP3D2 +SP3D +UNSPECIFIED diff --git a/chebai_graph/preprocessing/bin/hiv/AtomNodeLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/AtomNodeLevel/indices_one_hot.txt new file mode 100644 index 0000000..2d65776 --- /dev/null +++ b/chebai_graph/preprocessing/bin/hiv/AtomNodeLevel/indices_one_hot.txt @@ -0,0 +1,3 @@ +atom_node_lvl +fg_node_lvl +graph_node_level diff --git a/chebai_graph/preprocessing/bin/hiv/AtomNumHs/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/AtomNumHs/indices_one_hot.txt new file mode 100644 index 0000000..df4a3e9 --- /dev/null +++ b/chebai_graph/preprocessing/bin/hiv/AtomNumHs/indices_one_hot.txt @@ -0,0 +1,5 @@ +3 +1 +0 +2 +4 diff --git a/chebai_graph/preprocessing/bin/hiv/AtomType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/AtomType/indices_one_hot.txt new file mode 100644 index 0000000..95c9cba --- /dev/null +++ b/chebai_graph/preprocessing/bin/hiv/AtomType/indices_one_hot.txt @@ -0,0 +1,54 @@ +6 +17 +8 +7 +15 +16 +33 +53 +9 +35 +14 +11 +34 +79 +50 +80 +32 +51 +82 +5 +19 +3 +83 +29 +67 +44 +65 +74 +27 +55 +25 +26 +75 +42 +78 +47 +24 +46 +89 +20 +31 +12 +30 +28 +77 +1 +40 +81 +45 +22 +52 +64 +92 +23 diff --git a/chebai_graph/preprocessing/bin/hiv/BondLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/BondLevel/indices_one_hot.txt new file mode 100644 index 0000000..e69de29 diff --git a/chebai_graph/preprocessing/bin/hiv/BondType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/BondType/indices_one_hot.txt new file mode 100644 index 0000000..e69de29 diff --git a/chebai_graph/preprocessing/bin/hiv/NumAtomBonds/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/NumAtomBonds/indices_one_hot.txt new file mode 100644 index 0000000..e69de29 From d2b439dfd8a3fa0eb38e94d5bcb839b2e4f8566e Mon Sep 17 00:00:00 2001 From: aditya0b0 Date: Wed, 12 Aug 2026 15:02:52 +0200 Subject: [PATCH 07/10] clintox tokens --- .../clin_tox/AtomCharge/indices_one_hot.txt | 6 ++ .../AtomFunctionalGroup/indices_one_hot.txt | 84 +++++++++++++++++++ .../AtomHybridization/indices_one_hot.txt | 7 ++ .../AtomNodeLevel/indices_one_hot.txt | 3 + .../clin_tox/AtomNumHs/indices_one_hot.txt | 4 + .../bin/clin_tox/AtomType/indices_one_hot.txt | 30 +++++++ .../clin_tox/BondLevel/indices_one_hot.txt | 4 + .../bin/clin_tox/BondType/indices_one_hot.txt | 5 ++ .../clin_tox/NumAtomBonds/indices_one_hot.txt | 6 ++ 9 files changed, 149 insertions(+) create mode 100644 chebai_graph/preprocessing/bin/clin_tox/AtomCharge/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/clin_tox/AtomFunctionalGroup/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/clin_tox/AtomHybridization/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/clin_tox/AtomNodeLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/clin_tox/AtomNumHs/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/clin_tox/AtomType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/clin_tox/BondLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/clin_tox/BondType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/clin_tox/NumAtomBonds/indices_one_hot.txt diff --git a/chebai_graph/preprocessing/bin/clin_tox/AtomCharge/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/AtomCharge/indices_one_hot.txt new file mode 100644 index 0000000..374de68 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/AtomCharge/indices_one_hot.txt @@ -0,0 +1,6 @@ +0 +-1 +1 +3 +2 +-2 diff --git a/chebai_graph/preprocessing/bin/clin_tox/AtomFunctionalGroup/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/AtomFunctionalGroup/indices_one_hot.txt new file mode 100644 index 0000000..36bc343 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/AtomFunctionalGroup/indices_one_hot.txt @@ -0,0 +1,84 @@ +alkyl +chloro +RING_6 +ether +secondary_amine +fluoro +graph_fg +tertiary_carbon +hydroxyl +ketone +sulfonyl +carboxylate +RING_5 +NO_FG +amide +sulfide +RING_4 +quaternary_carbon +alkyne +alkene +primary_amine +carboxyl +trifluoromethyl +ester +alkene_carbon +RING_20 +sulfhydryl +nitrile +RING_3 +RING_29 +RING_7 +4_ammonium_ion +acetal +RING_9 +iodo +RING_38 +sulfinyl +difluoromethyl +imide +RING_16 +tertiary_amine +nitro +RING_8 +secondary_ketimine +nitrate +sulfonic_acid +carbamate +secondary_aldimine +bromo +thioketone +RING_14 +azo +RING_33 +trichloromethyl +RING_15 +ketoxime +phosphodiester +RING_24 +RING_22 +aldehyde +RING_18 +RING_21 +nitroso +dichloromethyl +carbonate_ester +silyl_ether +thiolester +borono +aldoxime +sulfonate_ester +RING_23 +RING_19 +RING_25 +carbodithio +disulfide +RING_36 +RING_31 +fluorochloromethyl +RING_12 +phosphate +azide +chlorobromomethyl +bromodifluoromethyl +phosphino diff --git a/chebai_graph/preprocessing/bin/clin_tox/AtomHybridization/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/AtomHybridization/indices_one_hot.txt new file mode 100644 index 0000000..a96b9b3 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/AtomHybridization/indices_one_hot.txt @@ -0,0 +1,7 @@ +SP3 +SP2 +SP +S +SP3D2 +UNSPECIFIED +SP3D diff --git a/chebai_graph/preprocessing/bin/clin_tox/AtomNodeLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/AtomNodeLevel/indices_one_hot.txt new file mode 100644 index 0000000..2d65776 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/AtomNodeLevel/indices_one_hot.txt @@ -0,0 +1,3 @@ +atom_node_lvl +fg_node_lvl +graph_node_level diff --git a/chebai_graph/preprocessing/bin/clin_tox/AtomNumHs/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/AtomNumHs/indices_one_hot.txt new file mode 100644 index 0000000..1127527 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/AtomNumHs/indices_one_hot.txt @@ -0,0 +1,4 @@ +3 +0 +2 +1 diff --git a/chebai_graph/preprocessing/bin/clin_tox/AtomType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/AtomType/indices_one_hot.txt new file mode 100644 index 0000000..2c8a324 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/AtomType/indices_one_hot.txt @@ -0,0 +1,30 @@ +6 +17 +7 +8 +9 +16 +15 +53 +80 +1 +13 +35 +79 +0 +27 +22 +78 +33 +34 +30 +14 +5 +29 +24 +81 +43 +83 +25 +20 +26 diff --git a/chebai_graph/preprocessing/bin/clin_tox/BondLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/BondLevel/indices_one_hot.txt new file mode 100644 index 0000000..6b48d66 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/BondLevel/indices_one_hot.txt @@ -0,0 +1,4 @@ +within_atoms_lvl +atom_fg_lvl +within_fg_lvl +to_graphNode_lvl diff --git a/chebai_graph/preprocessing/bin/clin_tox/BondType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/BondType/indices_one_hot.txt new file mode 100644 index 0000000..bdc90d7 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/BondType/indices_one_hot.txt @@ -0,0 +1,5 @@ +SINGLE +AROMATIC +DOUBLE +TRIPLE +DATIVE diff --git a/chebai_graph/preprocessing/bin/clin_tox/NumAtomBonds/indices_one_hot.txt b/chebai_graph/preprocessing/bin/clin_tox/NumAtomBonds/indices_one_hot.txt new file mode 100644 index 0000000..3c2db51 --- /dev/null +++ b/chebai_graph/preprocessing/bin/clin_tox/NumAtomBonds/indices_one_hot.txt @@ -0,0 +1,6 @@ +1 +3 +2 +4 +0 +6 From 3a8b8ed3370ee628d3ef1ce0717135a9a95f6260 Mon Sep 17 00:00:00 2001 From: aditya0b0 Date: Wed, 12 Aug 2026 15:03:55 +0200 Subject: [PATCH 08/10] sider tokens --- .../bin/sider/AtomCharge/indices_one_hot.txt | 6 ++ .../AtomFunctionalGroup/indices_one_hot.txt | 93 +++++++++++++++++++ .../AtomHybridization/indices_one_hot.txt | 6 ++ .../sider/AtomNodeLevel/indices_one_hot.txt | 3 + .../bin/sider/AtomNumHs/indices_one_hot.txt | 5 + .../bin/sider/AtomType/indices_one_hot.txt | 40 ++++++++ .../bin/sider/BondLevel/indices_one_hot.txt | 4 + .../bin/sider/BondType/indices_one_hot.txt | 4 + .../sider/NumAtomBonds/indices_one_hot.txt | 6 ++ 9 files changed, 167 insertions(+) create mode 100644 chebai_graph/preprocessing/bin/sider/AtomCharge/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/sider/AtomFunctionalGroup/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/sider/AtomHybridization/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/sider/AtomNodeLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/sider/AtomNumHs/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/sider/AtomType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/sider/BondLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/sider/BondType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/sider/NumAtomBonds/indices_one_hot.txt diff --git a/chebai_graph/preprocessing/bin/sider/AtomCharge/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/AtomCharge/indices_one_hot.txt new file mode 100644 index 0000000..6f89a5d --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/AtomCharge/indices_one_hot.txt @@ -0,0 +1,6 @@ +0 +1 +-1 +3 +2 +-2 diff --git a/chebai_graph/preprocessing/bin/sider/AtomFunctionalGroup/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/AtomFunctionalGroup/indices_one_hot.txt new file mode 100644 index 0000000..6fbc2c2 --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/AtomFunctionalGroup/indices_one_hot.txt @@ -0,0 +1,93 @@ +alkyl +RING_6 +carboxyl +alkene +fluoro +sulfinyl +RING_5 +graph_fg +tertiary_carbon +secondary_amine +ketone +primary_amine +primary_ketimine +NO_FG +sulfide +hydroxyl +sulfonic_acid +bromo +4_ammonium_ion +chloro +quaternary_carbon +ether +carboxylate +tertiary_amine +amide +RING_3 +trifluoromethyl +ester +nitro +sulfonyl +iodo +secondary_ketimine +RING_7 +aldehyde +phosphono +alkyne +nitrile +carbamate +alkene_carbon +carbonate_ester +RING_4 +RING_18 +RING_24 +RING_14 +imide +sulfonate_ester +RING_81 +RING_20 +RING_8 +nitroso +RING_29 +RING_16 +RING_12 +RING_21 +sulfhydryl +thiolester +difluoromethyl +thioketone +RING_25 +RING_78 +RING_68 +RING_77 +nitrate +azo +RING_36 +phosphate +ketoxime +secondary_aldimine +dichloromethyl +carboxylic_anhydride +RING_33 +borono +RING_15 +diiodomethyl +RING_23 +carbodithio +disulfide +acetal +RING_40 +phosphodiester +fluorochloromethyl +RING_22 +RING_10 +RING_9 +azide +phosphino +RING_31 +RING_28 +RING_53 +RING_56 +RING_41 +RING_43 +RING_35 diff --git a/chebai_graph/preprocessing/bin/sider/AtomHybridization/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/AtomHybridization/indices_one_hot.txt new file mode 100644 index 0000000..e9958eb --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/AtomHybridization/indices_one_hot.txt @@ -0,0 +1,6 @@ +SP3 +SP2 +S +SP3D +SP +SP3D2 diff --git a/chebai_graph/preprocessing/bin/sider/AtomNodeLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/AtomNodeLevel/indices_one_hot.txt new file mode 100644 index 0000000..2d65776 --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/AtomNodeLevel/indices_one_hot.txt @@ -0,0 +1,3 @@ +atom_node_lvl +fg_node_lvl +graph_node_level diff --git a/chebai_graph/preprocessing/bin/sider/AtomNumHs/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/AtomNumHs/indices_one_hot.txt new file mode 100644 index 0000000..df4a3e9 --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/AtomNumHs/indices_one_hot.txt @@ -0,0 +1,5 @@ +3 +1 +0 +2 +4 diff --git a/chebai_graph/preprocessing/bin/sider/AtomType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/AtomType/indices_one_hot.txt new file mode 100644 index 0000000..384eb37 --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/AtomType/indices_one_hot.txt @@ -0,0 +1,40 @@ +6 +8 +9 +16 +7 +35 +17 +11 +64 +15 +24 +53 +47 +49 +1 +25 +29 +20 +62 +3 +19 +78 +39 +43 +31 +26 +5 +12 +38 +79 +33 +30 +56 +98 +34 +32 +27 +88 +81 +57 diff --git a/chebai_graph/preprocessing/bin/sider/BondLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/BondLevel/indices_one_hot.txt new file mode 100644 index 0000000..6b48d66 --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/BondLevel/indices_one_hot.txt @@ -0,0 +1,4 @@ +within_atoms_lvl +atom_fg_lvl +within_fg_lvl +to_graphNode_lvl diff --git a/chebai_graph/preprocessing/bin/sider/BondType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/BondType/indices_one_hot.txt new file mode 100644 index 0000000..f14a241 --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/BondType/indices_one_hot.txt @@ -0,0 +1,4 @@ +SINGLE +DOUBLE +AROMATIC +TRIPLE diff --git a/chebai_graph/preprocessing/bin/sider/NumAtomBonds/indices_one_hot.txt b/chebai_graph/preprocessing/bin/sider/NumAtomBonds/indices_one_hot.txt new file mode 100644 index 0000000..dfb5c6d --- /dev/null +++ b/chebai_graph/preprocessing/bin/sider/NumAtomBonds/indices_one_hot.txt @@ -0,0 +1,6 @@ +1 +2 +3 +4 +0 +6 From 13234d125ac7674e72131531ab3c37118e1be4cb Mon Sep 17 00:00:00 2001 From: aditya0by0 Date: Wed, 12 Aug 2026 17:31:41 +0200 Subject: [PATCH 09/10] HIV tokens --- .../bin/hiv/BondLevel/indices_one_hot.txt | 4 ++++ .../bin/hiv/BondType/indices_one_hot.txt | 5 +++++ .../bin/hiv/NumAtomBonds/indices_one_hot.txt | 11 +++++++++++ 3 files changed, 20 insertions(+) diff --git a/chebai_graph/preprocessing/bin/hiv/BondLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/BondLevel/indices_one_hot.txt index e69de29..6b48d66 100644 --- a/chebai_graph/preprocessing/bin/hiv/BondLevel/indices_one_hot.txt +++ b/chebai_graph/preprocessing/bin/hiv/BondLevel/indices_one_hot.txt @@ -0,0 +1,4 @@ +within_atoms_lvl +atom_fg_lvl +within_fg_lvl +to_graphNode_lvl diff --git a/chebai_graph/preprocessing/bin/hiv/BondType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/BondType/indices_one_hot.txt index e69de29..58c0a5c 100644 --- a/chebai_graph/preprocessing/bin/hiv/BondType/indices_one_hot.txt +++ b/chebai_graph/preprocessing/bin/hiv/BondType/indices_one_hot.txt @@ -0,0 +1,5 @@ +SINGLE +DOUBLE +AROMATIC +TRIPLE +DATIVE diff --git a/chebai_graph/preprocessing/bin/hiv/NumAtomBonds/indices_one_hot.txt b/chebai_graph/preprocessing/bin/hiv/NumAtomBonds/indices_one_hot.txt index e69de29..88ddb48 100644 --- a/chebai_graph/preprocessing/bin/hiv/NumAtomBonds/indices_one_hot.txt +++ b/chebai_graph/preprocessing/bin/hiv/NumAtomBonds/indices_one_hot.txt @@ -0,0 +1,11 @@ +1 +2 +3 +4 +0 +5 +6 +9 +7 +8 +10 From 185b78d7f5afe966257497820e33888b64d3355a Mon Sep 17 00:00:00 2001 From: aditya0by0 Date: Thu, 13 Aug 2026 12:18:36 +0200 Subject: [PATCH 10/10] muv tokens --- .../bin/muv/AtomCharge/indices_one_hot.txt | 3 + .../AtomFunctionalGroup/indices_one_hot.txt | 68 +++++++++++++++++++ .../muv/AtomHybridization/indices_one_hot.txt | 3 + .../bin/muv/AtomNodeLevel/indices_one_hot.txt | 3 + .../bin/muv/AtomNumHs/indices_one_hot.txt | 4 ++ .../bin/muv/AtomType/indices_one_hot.txt | 7 ++ .../bin/muv/BondLevel/indices_one_hot.txt | 4 ++ .../bin/muv/BondType/indices_one_hot.txt | 4 ++ .../bin/muv/NumAtomBonds/indices_one_hot.txt | 4 ++ 9 files changed, 100 insertions(+) create mode 100644 chebai_graph/preprocessing/bin/muv/AtomCharge/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/muv/AtomFunctionalGroup/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/muv/AtomHybridization/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/muv/AtomNodeLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/muv/AtomNumHs/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/muv/AtomType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/muv/BondLevel/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/muv/BondType/indices_one_hot.txt create mode 100644 chebai_graph/preprocessing/bin/muv/NumAtomBonds/indices_one_hot.txt diff --git a/chebai_graph/preprocessing/bin/muv/AtomCharge/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/AtomCharge/indices_one_hot.txt new file mode 100644 index 0000000..d7e52d1 --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/AtomCharge/indices_one_hot.txt @@ -0,0 +1,3 @@ +0 +1 +-1 diff --git a/chebai_graph/preprocessing/bin/muv/AtomFunctionalGroup/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/AtomFunctionalGroup/indices_one_hot.txt new file mode 100644 index 0000000..c55dc92 --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/AtomFunctionalGroup/indices_one_hot.txt @@ -0,0 +1,68 @@ +primary_amine +RING_6 +ketone +carboxyl +alkyl +tertiary_carbon +secondary_amine +graph_fg +hydroxyl +alkene +thioketone +bromo +fluoro +ester +ether +tertiary_amine +NO_FG +chloro +sulfonyl +difluoromethyl +quaternary_carbon +nitro +amide +alkyne +trifluoromethyl +aldoxime +alkene_carbon +nitrile +sulfide +secondary_aldimine +ketoxime +carbodithio +secondary_ketimine +thionoester +thiolester +sulfinyl +carbamate +thiocyanate +aldehyde +sulfonate_ester +amidine +trichloromethyl +sulfhydryl +sulfonic_acid +RING_5 +nitroso +acetal +carbonate_ester +imide +azo +primary_ketimine +dichloromethyl +RING_7 +RING_3 +RING_8 +hydrazone +RING_4 +RING_15 +RING_12 +azide +RING_13 +RING_18 +difluorochloromethyl +RING_14 +RING_9 +RING_11 +disulfide +4_ammonium_ion diff --git a/chebai_graph/preprocessing/bin/muv/AtomHybridization/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/AtomHybridization/indices_one_hot.txt new file mode 100644 index 0000000..7c99da3 --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/AtomHybridization/indices_one_hot.txt @@ -0,0 +1,3 @@ +SP2 +SP3 +SP diff --git a/chebai_graph/preprocessing/bin/muv/AtomNodeLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/AtomNodeLevel/indices_one_hot.txt new file mode 100644 index 0000000..2d65776 --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/AtomNodeLevel/indices_one_hot.txt @@ -0,0 +1,3 @@ +atom_node_lvl +fg_node_lvl +graph_node_level diff --git a/chebai_graph/preprocessing/bin/muv/AtomNumHs/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/AtomNumHs/indices_one_hot.txt new file mode 100644 index 0000000..52db5ae --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/AtomNumHs/indices_one_hot.txt @@ -0,0 +1,4 @@ +2 +1 +0 +3 diff --git a/chebai_graph/preprocessing/bin/muv/AtomType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/AtomType/indices_one_hot.txt new file mode 100644 index 0000000..c36ddc7 --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/AtomType/indices_one_hot.txt @@ -0,0 +1,7 @@ +7 +6 +8 +35 +9 +16 +17 diff --git a/chebai_graph/preprocessing/bin/muv/BondLevel/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/BondLevel/indices_one_hot.txt new file mode 100644 index 0000000..6b48d66 --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/BondLevel/indices_one_hot.txt @@ -0,0 +1,4 @@ +within_atoms_lvl +atom_fg_lvl +within_fg_lvl +to_graphNode_lvl diff --git a/chebai_graph/preprocessing/bin/muv/BondType/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/BondType/indices_one_hot.txt new file mode 100644 index 0000000..f14a241 --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/BondType/indices_one_hot.txt @@ -0,0 +1,4 @@ +SINGLE +DOUBLE +AROMATIC +TRIPLE diff --git a/chebai_graph/preprocessing/bin/muv/NumAtomBonds/indices_one_hot.txt b/chebai_graph/preprocessing/bin/muv/NumAtomBonds/indices_one_hot.txt new file mode 100644 index 0000000..94ebaf9 --- /dev/null +++ b/chebai_graph/preprocessing/bin/muv/NumAtomBonds/indices_one_hot.txt @@ -0,0 +1,4 @@ +1 +2 +3 +4