feat: add level of theory

OpenBioML · Oct 16, 2023 · 705fb48 · 705fb48
1 parent 8acd238
commit 705fb48
Show file tree

Hide file tree

Showing 2 changed files with 58 additions and 24 deletions.
diff --git a/data/tabular/RedDB/meta.yaml b/data/tabular/RedDB/meta.yaml
@@ -1,7 +1,7 @@
 ---
 name: RedDB
 description: |-
-    RedDB: a computational database that contains 31,618 molecules
+    RedDB: a computational database that contains 30861 molecules
     from two prominent classes of organic electroactive compounds, quinones and aza-aromatics,
     has been presented. RedDB incorporates miscellaneous physicochemical property information
     of the compounds that can potentially be employed as battery performance descriptors.
@@ -40,67 +40,68 @@ targets:
       units: kT
       type: numeric
       names:
-          - noun: cavity formation energy
+          - noun: cavity formation energy at the PBE level of theory
     - id: gasEnergy
       description: Total energy of a molecule in the gas phase
       units: Hartree
       type: numeric
       names:
-          - noun: gas-phase molecular energy
+          - noun: gas-phase molecular energy at the PBE level of theory
     - id: gasHomo
       description: Highest Occupied Molecular Orbital (HOMO) energy of a gas-phase molecule
       units: Hartree
       type: numeric
       names:
-          - noun: gaseous phase HOMO energy
+          - noun: gaseous phase HOMO energy at the PBE level of theory
     - id: gasLumo
       description: Lowest Unoccupied Molecular Orbital (LUMO) energy of a gas-phase molecule
       units: Hartree
       type: numeric
       names:
-          - noun: gaseous phase LUMO energy
+          - noun: gaseous phase LUMO energy at the PBE level of theory
     - id: solutionEnergy
       description: Total energy of a molecule in a solution
       units: Hartree
       type: numeric
       names:
-          - noun: aqueous phase molecular energy
+          - noun: aqueous phase molecular energy at the PBE level of theory
     - id: solutionHomo
       description: Highest Occupied Molecular Orbital (HOMO) energy in a solution
       units: Hartree
       type: numeric
       names:
-          - noun: aqueous phase HOMO energy
+          - noun: aqueous phase HOMO energy at the PBE level of theory
     - id: solutionLumo
       description: Lowest Unoccupied Molecular Orbital (LUMO) energy in a solution
       units: Hartree
       type: numeric
       names:
-          - noun: aqueous phase LUMO energy
+          - noun: aqueous phase LUMO energy at the PBE level of theory
     - id: nuclearRepulsionEnergy
       description: Electrostatic repulsion energy between atomic nuclei in a molecule
       units: Hartree
       type: numeric
       names:
-          - noun: nuclear repulsion energy
+          - noun: nuclear repulsion energy at the PBE level of theory
     - id: optGasEnergy
       description: Total energy of an optimized gas-phase molecule
       units: Hartree
       type: numeric
       names:
-          - noun: optimized gas-phase molecular energy
+          - noun: optimized gas-phase molecular energy at the PBE level of theory
     - id: optGasHomo
       description: Highest Occupied Molecular Orbital (HOMO) energy of an optimized gas-phase molecule
       units: Hartree
       type: numeric
       names:
-          - noun: optimized gas-phase HOMO energy
+          - noun: optimized gas-phase HOMO energy at the PBE level of theory
     - id: optGasLumo
       description: Lowest Unoccupied Molecular Orbital (LUMO) energy of an optimized gas-phase molecule
       units: Hartree
       type: numeric
       names:
-          - noun: optimized gas-phase LUMO energy
+          - noun: optimized gas-phase LUMO energy calculated at the PBE level of theory
+          - noun: optimized gas-phase LUMO energy calculated with DFT at the PBE level of theory
 identifiers:
     - id: SMILES
       type: SMILES

diff --git a/data/tabular/RedDB/transform.py b/data/tabular/RedDB/transform.py
@@ -30,7 +30,7 @@ def read_dataset():
     # create meta yaml
     meta = {
         "name": "RedDB",  # unique identifier, we will also use this for directory names
-        "description": """RedDB: a computational database that contains 31,618 molecules
+        "description": f"""RedDB: a computational database that contains {len(hf_data)} molecules
 from two prominent classes of organic electroactive compounds, quinones and aza-aromatics,
 has been presented. RedDB incorporates miscellaneous physicochemical property information
 of the compounds that can potentially be employed as battery performance descriptors.
@@ -73,77 +73,110 @@ def read_dataset():
                 "description": "Energy associated with the formation of cavities in a molecular structure",
                 "units": "kT",
                 "type": "numeric",
-                "names": [{"noun": "cavity formation energy"}],
+                "names": [
+                    {"noun": "cavity formation energy at the PBE level of theory"}
+                ],
             },
             {
                 "id": "gasEnergy",
                 "description": "Total energy of a molecule in the gas phase",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "gas-phase molecular energy"}],
+                "names": [
+                    {"noun": "gas-phase molecular energy at the PBE level of theory"}
+                ],
             },
             {
                 "id": "gasHomo",
                 "description": "Highest Occupied Molecular Orbital (HOMO) energy of a gas-phase molecule",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "gaseous phase HOMO energy"}],
+                "names": [
+                    {"noun": "gaseous phase HOMO energy at the PBE level of theory"}
+                ],
             },
             {
                 "id": "gasLumo",
                 "description": "Lowest Unoccupied Molecular Orbital (LUMO) energy of a gas-phase molecule",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "gaseous phase LUMO energy"}],
+                "names": [
+                    {"noun": "gaseous phase LUMO energy at the PBE level of theory"}
+                ],
             },
             {
                 "id": "solutionEnergy",
                 "description": "Total energy of a molecule in a solution",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "aqueous phase molecular energy"}],
+                "names": [
+                    {
+                        "noun": "aqueous phase molecular energy at the PBE level of theory"
+                    }
+                ],
             },
             {
                 "id": "solutionHomo",
                 "description": "Highest Occupied Molecular Orbital (HOMO) energy in a solution",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "aqueous phase HOMO energy"}],
+                "names": [
+                    {"noun": "aqueous phase HOMO energy at the PBE level of theory"}
+                ],
             },
             {
                 "id": "solutionLumo",
                 "description": "Lowest Unoccupied Molecular Orbital (LUMO) energy in a solution",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "aqueous phase LUMO energy"}],
+                "names": [
+                    {"noun": "aqueous phase LUMO energy at the PBE level of theory"}
+                ],
             },
             {
                 "id": "nuclearRepulsionEnergy",
                 "description": "Electrostatic repulsion energy between atomic nuclei in a molecule",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "nuclear repulsion energy"}],
+                "names": [
+                    {"noun": "nuclear repulsion energy at the PBE level of theory"}
+                ],
             },
             {
                 "id": "optGasEnergy",
                 "description": "Total energy of an optimized gas-phase molecule",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "optimized gas-phase molecular energy"}],
+                "names": [
+                    {
+                        "noun": "optimized gas-phase molecular energy at the PBE level of theory"
+                    }
+                ],
             },
             {
                 "id": "optGasHomo",
                 "description": "Highest Occupied Molecular Orbital (HOMO) energy of an optimized gas-phase molecule",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "optimized gas-phase HOMO energy"}],
+                "names": [
+                    {
+                        "noun": "optimized gas-phase HOMO energy at the PBE level of theory"
+                    }
+                ],
             },
             {
                 "id": "optGasLumo",
                 "description": "Lowest Unoccupied Molecular Orbital (LUMO) energy of an optimized gas-phase molecule",
                 "units": "Hartree",
                 "type": "numeric",
-                "names": [{"noun": "optimized gas-phase LUMO energy"}],
+                "names": [
+                    {
+                        "noun": "optimized gas-phase LUMO energy calculated at the PBE level of theory"
+                    },
+                    {
+                        "noun": "optimized gas-phase LUMO energy calculated with DFT at the PBE level of theory"
+                    },
+                ],
             },
         ],
         "identifiers": [