Add exp bfe data

openfe_benchmarks/data/_benchmark_systems.py

@@ -211,6 +211,9 @@ class BenchmarkData:
     ligand_networks : dict[str, Path] | None
         Dictionary of available ligand networks where the key is the filename, '*network.json',
         and the value is a Path to a ligand network file.
+    reference_data : dict[str, Path] | None
+        Dictionary of available reference data files where the key is the filename 'experimental*data.json',
+        and the value is a Path to a reference data file.
     details : str
         Information available in the preparation_details.md file
     """
@@ -221,6 +224,7 @@ class BenchmarkData:
     ligands: dict[str, Path]
     cofactors: dict[str, Path] | None
     ligand_networks: dict[str, Path] | None
+    reference_data: dict[str, Path] | None
     details: str
 
     def __repr__(self):
@@ -231,6 +235,7 @@ def __repr__(self):
             f"ligands={list(self.ligands.keys())}, "
             f"cofactors={list(self.cofactors.keys()) if self.cofactors is not None else 'None'}, "
             f"ligand_network={list(self.ligand_networks.keys()) if self.ligand_networks is not None else 'None'}"
+            f"reference_data={list(self.reference_data.keys()) if self.reference_data is not None else 'None'})"
         )
 
 
@@ -263,6 +268,7 @@ def _validate_and_load_data_system(
     ligands = {}
     cofactors = {}
     ligand_networks = {}
+    reference_data = {}
     details = None
 
     # Track all files for validation
@@ -341,6 +347,13 @@ def _validate_and_load_data_system(
             logger.debug(f"Found ligand network: {filename}")
             continue
 
+        # check for reference data file (experimental*data.json)
+        if filename.startswith("experimental") and filename.endswith("data.json"):
+            reference_data[file_path.stem] = file_path
+            categorized_files.add(file_path)
+            logger.debug(f"Found reference data: {filename}")
+            continue
+
     # Check for uncategorized files
     uncategorized = set(all_files) - categorized_files
     for file_path in uncategorized:
@@ -411,6 +424,7 @@ def _validate_and_load_data_system(
         ligands=ligands,
         cofactors=cofactors,
         ligand_networks=ligand_networks,
+        reference_data=reference_data,
         details=details,
     )
 

openfe_benchmarks/data/benchmark_system_indexing.yml

@@ -4,73 +4,74 @@
 # Other tags indicate experimental data present, labeled as exp_bfe and exp_sfe appropriately.
 
 charge_annihilation_set:
-  cdk2: ["protein",]
-  dlk: ["protein",]
-  egfr: ["protein",]
-  ephx2: ["protein",]
-  irak4_s2: ["protein",]
-  irak4_s3: ["protein",]
-  itk: ["protein",]
-  jak1: ["protein",]
-  jnk1: ["protein",]
-  ptp1b: ["protein",]
-  thrombin: ["protein", "cofactor"]
-  tyk2: ["protein",]
+  cdk2: ["protein","bfe"]
+  dlk: ["protein", "bfe"]
+  egfr: ["protein", "bfe"]
+  ephx2: ["protein", "bfe"]
+  irak4_s2: ["protein", "bfe"]
+  irak4_s3: ["protein", "bfe"]
+  itk: ["protein", "bfe"]
+  jak1: ["protein", "bfe"]
+  jnk1: ["protein", "bfe"]
+  ptp1b: ["protein", "bfe"]
+  thrombin: ["protein", "cofactor", "bfe"]
+  tyk2: ["protein", "bfe"]
 fragments:
-  hsp90_2rings: ["protein",]
-  hsp90_single_ring: ["protein",]
-  jak2_set1: ["protein",]
-  jak2_set2: ["protein",]
-  liga: ["protein",]
-  mcl1: ["protein",]
-  mup1: ["protein",]
-  p38: ["protein",]
-  t4_lysozyme: ["protein",]
+  hsp90_2rings: ["protein", "bfe"]
+  hsp90_single_ring: ["protein", "bfe"]
+  jak2_set1: ["protein", "bfe"]
+  jak2_set2: ["protein", "bfe"]
+  liga: ["protein", "bfe"]
+  mcl1: ["protein", "bfe"]
+  mup1: ["protein", "bfe"]
+  p38: ["protein", "bfe"]
+  t4_lysozyme: ["protein", "bfe"]
 jacs_set:
-  bace: ["protein",]
-  cdk2: ["protein",]
-  jnk1: ["protein",]
-  mcl1: ["protein",]
-  p38: ["protein",]
-  ptp1b: ["protein",]
-  thrombin: ["protein",]
-  tyk2: ["protein",]
+  bace: ["protein", "bfe"]
+  cdk2: ["protein", "bfe"]
+  jnk1: ["protein", "bfe"]
+  mcl1: ["protein", "bfe"]
+  p38: ["protein", "bfe"]
+  ptp1b: ["protein", "bfe"]
+  thrombin: ["protein", "bfe"]
+  tyk2: ["protein", "bfe"]
 janssen_bace:
-  bace_ciordia_prospective: ["protein",]
-  bace_p3_arg368_in: ["protein",]
-  ciordia_retro: ["protein",]
-  keranen_p2: ["protein",]
+  bace_ciordia_prospective: ["protein", "bfe"]
+  bace_p3_arg368_in: ["protein", "bfe"]
+  ciordia_retro: ["protein", "bfe"]
+  keranen_p2: ["protein", "bfe"]
 mcs_docking_set:
-  hne: ["protein", "cofactor"]
-  renin: ["protein",]
+  hne: ["protein", "cofactor", "bfe"]
+  renin: ["protein", "bfe"]
 merck:
-  cdk8: ["protein",]
-  cmet: ["protein",]
-  eg5: ["protein",]
-  hif2a: ["protein",]
-  pfkfb3: ["protein", "cofactor"]
-  shp2: ["protein",]
-  syk: ["protein",]
-  tnks2: ["protein", "cofactor"]
+  cdk8: ["protein", "bfe"]
+  cmet: ["protein", "bfe"]
+  eg5: ["protein", "bfe"]
+  hif2a: ["protein", "bfe"]
+  pfkfb3: ["protein", "cofactor", "bfe"]
+  shp2: ["protein", "bfe"]
+  syk: ["protein", "bfe"]
+  tnks2: ["protein", "cofactor", "bfe"]
 miscellaneous_set:
-  btk: ["protein",]
-  cdk8: ["protein",]
-  faah: ["protein",]
-  galectin: ["protein",]
-  hiv1_protease: ["protein",]
+  btk: ["protein", "bfe"]
+  cdk8: ["protein", "bfe"]
+  faah: ["protein", "bfe"]
+  galectin: ["protein", "bfe"]
+  hiv1_protease: ["protein", "bfe"]
 water_set:
-  brd4: ["protein",]
-  chk1: ["protein",]
-  hsp90_kung: ["protein",]
-  hsp90_woodhead: ["protein", "cofactor"]
-  scyt_dehyd: ["protein",]
-  taf12: ["protein",]
-  thrombin: ["protein",]
-  urokinase: ["protein",]
+  brd4: ["protein", "bfe"]
+  chk1: ["protein", "bfe"]
+  hsp90_kung: ["protein", "bfe"]
+  hsp90_woodhead: ["protein", "cofactor", "bfe"]
+  scyt_dehyd: ["protein", "bfe"]
+  taf12: ["protein", "bfe"]
+  thrombin: ["protein", "bfe"]
+  urokinase: ["protein", "bfe"]
 metadata:
-  last_updated: "2026-02-02"
+  last_updated: "2026-02-13"
   notes:
     - "Systems may or may not include cofactor files"
     - "All systems can be used for ASFEs and RSFEs"
+    - "bfe tag indicates that experimental binding free energy data is available for this system"
     - "Systems with proteins can also be used for RBFE and ABFE calculations"
     - "Systems with ligands and cofactors could potentially be used for RBFE and ABFE calculations"

openfe_benchmarks/data/benchmark_systems/charge_annihilation_set/cdk2/experimental_binding_data.json

@@ -0,0 +1,35 @@
+{
+    "39charg": {
+        "dg": {
+            "magnitude": -8.369999885559082,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1C(=O)[O-])[H])[H])N([H])c2nc3c(c(n2)OC([H])([H])C4(C(C(C(C(C4([H])[H])([H])[H])([H])[H])([H])[H])([H])[H])[H])N=C(N3[H])[H])[H]",
+        "inchikey": "TVEHBRDXVINFRZ-RHMRERFDNA-M",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "34": {
+        "dg": {
+            "magnitude": -9.880000114440918,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1C(=O)N([H])[H])[H])[H])N([H])c2nc3c(c(n2)OC([H])([H])C4(C(C(C(C(C4([H])[H])([H])[H])([H])[H])([H])[H])([H])[H])[H])N=C(N3[H])[H])[H]",
+        "inchikey": "RUUOIINPNMNPIU-GJCIOOLPNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "25": {
+        "dg": {
+            "magnitude": -9.829999923706056,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1N([H])c2nc3c(c(n2)OC([H])([H])C4(C(C(C(C(C4([H])[H])([H])[H])([H])[H])([H])[H])([H])[H])[H])N=C(N3[H])[H])[H])[H])O[H])[H]",
+        "inchikey": "RFSDQDHHBKYQOD-BDGWVKIONA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    }
+}

openfe_benchmarks/data/benchmark_systems/charge_annihilation_set/dlk/experimental_binding_data.json

@@ -0,0 +1,57 @@
+{
+    "9": {
+        "dg": {
+            "magnitude": -8.729999542236328,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(nc(c(c1C#N)[H])N([H])C2=NN(C(=C2[H])C3(C(C(N(C(C3([H])[H])([H])[H])C(=O)C([H])([H])[H])([H])[H])([H])[H])[H])C([H])(C([H])([H])[H])C([H])([H])[H])[H]",
+        "inchikey": "CBLJTUXDZXYAMM-QWOVJGMINA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "17charg": {
+        "dg": {
+            "magnitude": -10.4399995803833,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(nc(c(c1C#N)[H])N([H])C2=NN(C(=C2[H])[C@]3(C(C([N@@+](C3([H])[H])([H])C4(C(OC4([H])[H])([H])[H])[H])([H])[H])([H])[H])[H])C5(C(C(C(C5([H])[H])([H])[H])([H])[H])([H])[H])[H])[H]",
+        "inchikey": "HPCAFTNDPHAAGH-WNJPLXHJNA-O",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "4charg": {
+        "dg": {
+            "magnitude": -9.329999923706056,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(nc(c(c1C#N)[H])N([H])C2=NN(C(=C2[H])C3(C(C([N+](C(C3([H])[H])([H])[H])([H])[H])([H])[H])([H])[H])[H])C([H])(C([H])([H])[H])C([H])([H])[H])[H]",
+        "inchikey": "PZXSYKGUMOGQBI-ZFSSJWKENA-O",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "18": {
+        "dg": {
+            "magnitude": -9.979999542236328,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(nc(c(c1C#N)[H])N([H])C2=NN(C(=C2[H])[C@]3(C(C(OC3([H])[H])([H])[H])([H])[H])[H])C4(C(C(C(C4([H])[H])([H])[H])([H])[H])([H])[H])[H])[H]",
+        "inchikey": "ZBHXJFIKXIBKBY-JAIDSPQONA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "8": {
+        "dg": {
+            "magnitude": -10.510000228881836,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(nc(c(c1C#N)[H])N([H])C2=NN(C(=C2[H])C3(C(C([N+](C(C3([H])[H])([H])[H])([H])[H])([H])[H])([H])[H])[H])C4(C(C(C(C4([H])[H])([H])[H])([H])[H])([H])[H])[H])[H]",
+        "inchikey": "VOBBPVMLJJZDTQ-UDEMLUNXNA-O",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    }
+}

openfe_benchmarks/data/benchmark_systems/charge_annihilation_set/egfr/experimental_binding_data.json

@@ -0,0 +1,57 @@
+{
+    "21": {
+        "dg": {
+            "magnitude": -9.88,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1[H])[H])C([H])([H])C(=O)N([H])c2c(c(c(c(c2[H])C3=C(N4C(=C(SC4=N3)[H])[H])c5c(c(nc(n5)N([H])c6c(c(c(c(c6[H])[H])N7C(C(OC(C7([H])[H])([H])[H])([H])[H])([H])[H])[H])[H])[H])[H])[H])[H])[H])[H])[H]",
+        "inchikey": "BFTPDUXUTFGDLP-QQYWGXKINA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "27chargR": {
+        "dg": {
+            "magnitude": -9.94,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1[H])[H])C([H])([H])C(=O)N([H])c2c(c(c(c(c2[H])C3=C(N4C(=C(SC4=N3)[H])[H])c5c(c(nc(n5)N([H])c6c(c(c7c(c6[H])C([N@+](C(C7([H])[H])([H])[H])([H])C([H])([H])[H])([H])[H])[H])[H])[H])[H])[H])[H])[H])[H])[H]",
+        "inchikey": "PVKPCQULPTYIRN-RRKCJBJINA-O",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "28charg": {
+        "dg": {
+            "magnitude": -10.7,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1[H])[H])C([H])([H])C(=O)N([H])c2c(c(c(c(c2[H])C3=C(N4C(=C(SC4=N3)[H])[H])c5c(c(nc(n5)N([H])c6c(c(c(c(c6[H])[H])N7C(C([N+](C(C7([H])[H])([H])[H])([H])C([H])([H])C([H])([H])[H])([H])[H])([H])[H])[H])[H])[H])[H])[H])[H])[H])[H])[H]",
+        "inchikey": "MBYBHGUQPPLBRD-XUHMWGPANA-O",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "29charg": {
+        "dg": {
+            "magnitude": -10.46,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1[H])[H])C([H])([H])C(=O)N([H])c2c(c(c(c(c2[H])C3=C(N4C(=C(SC4=N3)[H])[H])c5c(c(nc(n5)N([H])c6c(c(c(c(c6[H])C([H])([H])C([H])([H])[N+]([H])(C([H])([H])[H])C([H])([H])[H])[H])[H])[H])[H])[H])[H])[H])[H])[H])[H]",
+        "inchikey": "JPSXZEQQHPNTNX-UPNFYDLJNA-O",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "30charg": {
+        "dg": {
+            "magnitude": -11.25,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1[H])[H])C([H])([H])C(=O)N([H])c2c(c(c(c(c2[H])C3=C(N4C(=C(SC4=N3)[H])[H])c5c(c(nc(n5)N([H])c6c(c(c7c(c6[H])C([N+](C(C7([H])[H])([H])[H])([H])[H])([H])[H])[H])[H])[H])[H])[H])[H])[H])[H])[H]",
+        "inchikey": "KEOFEULIBILKAL-NSQPPVFJNA-O",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    }
+}

openfe_benchmarks/data/benchmark_systems/charge_annihilation_set/ephx2/experimental_binding_data.json

@@ -0,0 +1,46 @@
+{
+    "47charg": {
+        "dg": {
+            "magnitude": -11.25,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1C(=O)[O-])[H])[H])OC2(C(C(N(C(C2([H])[H])([H])[H])C(=O)N([H])C([H])([H])c3c(c(c(c(c3Cl)[H])Cl)[H])[H])([H])[H])([H])[H])[H])[H]",
+        "inchikey": "SJFWZPJFJSGSAB-BGLXQYIQNA-M",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "19charg": {
+        "dg": {
+            "magnitude": -8.239999771118164,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1C([H])([H])N([H])C(=O)N2C(C(C(C(C2([H])[H])([H])[H])([H])C(=O)[O-])([H])[H])([H])[H])Cl)[H])Cl)[H]",
+        "inchikey": "YYEDYEHCUJGPOP-ZVXBUSEHNA-M",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "20": {
+        "dg": {
+            "magnitude": -9.140000343322754,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1C([H])([H])N([H])C(=O)N2C(C(C(C(C2([H])[H])([H])[H])([H])C(=O)N([H])[H])([H])[H])([H])[H])Cl)[H])Cl)[H]",
+        "inchikey": "UUCMRBUYLOLCHH-VRGMUVNCNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "33": {
+        "dg": {
+            "magnitude": -10.739999771118164,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1C([H])([H])N([H])C(=O)N2C(C(C(C(C2([H])[H])([H])[H])([H])Oc3nc(c(c(n3)[H])[H])[H])([H])[H])([H])[H])Cl)[H])Cl)[H]",
+        "inchikey": "UZEPPAOAIDTLTK-QWOVJGMINA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    }
+}