Add GPCR sets

openfe_benchmarks/data/benchmark_system_indexing.yml

@@ -26,6 +26,11 @@ fragments:
   mup1: ["protein", "bfe", "ross"]
   p38: ["protein", "bfe", "ross"]
   t4_lysozyme: ["protein", "bfe", "ross"]
+gpcrs:
+  a2a: ["protein", "bfe", "ross"]
+  p2y1_meta: ["protein", "bfe", "ross"]
+  p2y1_ortho: ["protein", "bfe", "ross"]
+  ox2: ["protein", "bfe", "ross"]
 jacs_set:
   bace: ["protein", "bfe", "ross"]
   cdk2: ["protein", "bfe", "ross"]

openfe_benchmarks/data/benchmark_systems/gpcrs/a2a/PREPARATION_DETAILS.md

@@ -0,0 +1,11 @@
+- Prepared solvated protein-membrane complex was taken from https://github.com/schrodinger/public_binding_free_energy_benchmark/tree/main/fep_benchmark_inputs/fep_plus_inputs/gpcrs/a2a_hip278.fmp
+- The .fmp file was loaded into maestro and the lipids, solvent, and protein were saved separately as PDB files.
+- The individual components were then combined into a single PDB file using openmm
+- Box vectors were taken from the .fmp file and stored in the CRYST1 record in the PDB file
+- Ligands were taken from https://github.com/schrodinger/public_binding_free_energy_benchmark/tree/main/fep_benchmark_inputs/structure_inputs/gpcrs/a2a_hip278_ligands.sdf
+- For ligands with multiple binding modes, the binding mode was retained that Ross et al. found to be more potent (present in this table https://github.com/schrodinger/public_binding_free_energy_benchmark/blob/main/21_4_results/ligand_predictions/gpcrs/a2a_hip278_sbpkacorr_out.csv)
+- For ligands with multiple protonation states, the neutral form was retained
+
+Lomap network was generated using the generate_lomap_networks.py
+
+Ligand partial charges were obtained using the charge_molecules.py script in the conda-lock environment.

openfe_benchmarks/data/benchmark_systems/gpcrs/a2a/experimental_binding_data.json

@@ -0,0 +1,189 @@
+{
+    "4g": {
+        "dg": {
+            "magnitude": -11.064042091369627,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([C]([H])([H])[H])[n][c]([C]([H])([H])[H])[c]2[H])[c]([H])[c]1[H]",
+        "inchikey": "SORFNYWLKDSNNF-HVXXBKQBNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4h": {
+        "dg": {
+            "magnitude": -10.654767990112305,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([C]([H])([H])[H])[n][c]([C]([H])([H])[H])[c]2[H])[c]([H])[c]([H])[c]1[F]",
+        "inchikey": "NEYZTILMBRSITP-DZQCGVKKNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4jS": {
+        "dg": {
+            "magnitude": -10.886690139770508,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c]([F])[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([C]([H])([H])[H])[n][c]([C]([H])([H])[H])[c]2[H])[c]1[H]",
+        "inchikey": "LYVNVEJCGRVTLE-DZQCGVKKNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4kU": {
+        "dg": {
+            "magnitude": -11.541528701782228,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([C]([H])([H])[H])[n][c]([C]([F])([F])[F])[c]2[H])[c]([H])[c]1[H]",
+        "inchikey": "NDFNRBWLVZWETQ-HPHMPNDVNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4lD": {
+        "dg": {
+            "magnitude": -11.377819061279297,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([C]([H])([H])[H])[n][c]([C]([F])([F])[F])[c]2[H])[c]([H])[c]([H])[c]1[F]",
+        "inchikey": "GIFJFWNMMFGQLP-QVUQFMIFNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4i": {
+        "dg": {
+            "magnitude": -10.313706398010254,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([F])[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([C]([H])([H])[H])[n][c]([C]([H])([H])[H])[c]2[H])[c]([H])[c]1[F]",
+        "inchikey": "ZEBNSCYTUBSYES-SDRQFZCRNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4a": {
+        "dg": {
+            "magnitude": -9.41330337524414,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c]([H])[c](-[c]2[n][n][c]([N]([H])[H])[n][c]2-[c]2[c]([H])[c]([H])[c]([H])[c]([H])[c]2[H])[c]([H])[c]1[H]",
+        "inchikey": "NZRHOWNFGASHMN-ZHLVXTBQNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4b D": {
+        "dg": {
+            "magnitude": -9.959002494812012,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([H])[c]([H])[c]([Cl])[c]2[H])[c]([H])[c]1[H]",
+        "inchikey": "KRDHDDNWMDQZBH-HVXXBKQBNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4c": {
+        "dg": {
+            "magnitude": -11.459673881530762,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([Cl])[c]([H])[c]([Cl])[c]2[H])[c]([H])[c]1[H]",
+        "inchikey": "HMAOALRIGFSFDY-DZQCGVKKNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4d": {
+        "dg": {
+            "magnitude": -10.504701614379885,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([C]([H])([H])[H])[c]([H])[c]([C]([H])([H])[H])[c]2[H])[c]([H])[c]1[H]",
+        "inchikey": "UDTRKUCMSDMFIR-DZQCGVKKNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4o": {
+        "dg": {
+            "magnitude": -11.35667324066162,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][O][c]1[c]([H])[c]([H])[c](-[c]2[n][n][c]([N]([H])[H])[n][c]2-[c]2[c]([H])[c]([H])[c]([H])[c]([H])[c]2[H])[c]([H])[c]1[H]",
+        "inchikey": "JJNHLIQRVKGACC-ZHLVXTBQNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4f": {
+        "dg": {
+            "magnitude": -11.44603157043457,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][O][c]1[c]([C]([H])([H])[H])[c]([H])[c](-[c]2[n][n][c]([N]([H])[H])[n][c]2-[c]2[c]([H])[c]([H])[c]([H])[c]([H])[c]2[H])[c]([H])[c]1[C]([H])([H])[H]",
+        "inchikey": "DSCUJHKNOYFIAC-DZQCGVKKNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4e D": {
+        "dg": {
+            "magnitude": -12.073585510253906,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][O][c]1[c]([H])[c]([H])[c](-[c]2[n][n][c]([N]([H])[H])[n][c]2-[c]2[c]([H])[c]([H])[c]([H])[c]([H])[c]2[H])[c]([H])[c]1[Cl]",
+        "inchikey": "ZHUZHTHIEMXLRA-HVXXBKQBNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4m D": {
+        "dg": {
+            "magnitude": -10.550403594970703,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[n][c]([Cl])[c]([H])[c](-[c]2[n][n][c]([N]([H])[H])[n][c]2-[c]2[c]([H])[c]([H])[c]([H])[c]([H])[c]2[H])[c]1[H]",
+        "inchikey": "HCVRXRUXNXGAJZ-ZHLVXTBQNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4q": {
+        "dg": {
+            "magnitude": -8.886704444885254,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[n][c]([H])[c]([H])[c](-[c]2[n][n][c]([N]([H])[H])[n][c]2-[c]2[c]([H])[c]([H])[c]([H])[c]([H])[c]2[H])[c]1[H]",
+        "inchikey": "CTRSWEIROKNMCC-YHSKDTNENA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4n": {
+        "dg": {
+            "magnitude": -11.550395965576172,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([Cl])[n][c]([Cl])[c]2[H])[c]([H])[c]1[H]",
+        "inchikey": "VPYMIAUKWOSXCL-HVXXBKQBNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4r U": {
+        "dg": {
+            "magnitude": -11.461993217468262,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H][c]1[c]([H])[c](-[c]2[n][c]([N]([H])[H])[n][n][c]2-[c]2[c]([H])[c]([Cl])[n][c]([C]([F])([F])[F])[c]2[H])[c]([H])[c]([H])[c]1[F]",
+        "inchikey": "LGWZYEYBDVFUJX-QVUQFMIFNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    }
+}