Add bayer macrocycle datasets

openfe_benchmarks/data/benchmark_system_indexing.yml

@@ -3,6 +3,9 @@
 # This file provides tags for benchmark systems based on the files available, e.g., protein or cofactor.
 # Other tags indicate experimental data present, labeled as exp_bfe and exp_sfe appropriately.
 
+bayer_macrocycles:
+  brd4: ["protein","bfe"]
+  ftase: ["protein", "cofactor", "bfe"]
 charge_annihilation_set:
   cdk2: ["protein","bfe"]
   dlk: ["protein", "bfe"]

openfe_benchmarks/data/benchmark_systems/bayer_macrocycles/brd4/PREPARATION_DETAILS.md

@@ -0,0 +1,27 @@
+# Preperation of systems
+
+Done by J. Bluck
+
+<ol type="1">
+<li>Read in original inputs from the repo
+<li>Duplicate the input, to ensure there is a reference to comapre to
+<li>Check the sequence to see if it contains any non-natural amino acids
+<li>Check all caps to see if any need to be charged or not.
+<li>Open the Protein preparation wizard (Schrodinger 2024-2)
+<li>Run only step 3 - "Preprocess". The only three options activated are:
+   <ul type="disc">
+    <li>Cap termini
+    <li>Convert selomethionines to methionines
+    <li>Include peptides when capping termini
+    </ul>
+<li>Convert SER back to a charged terminus, to reflect the Schrodinger input
+<li>Change the cap names if not NME:
+   <ul type="disc">
+    <li>Highlight all waters
+    <li>Builder > Other Edits > Change Atom Properties > Property: Residue/Chain Name
+    <li>Residue name "NME"
+    </ul>
+<li>Export outputs, named "ligand.sdf", "protein.pdb" and optionally "cofactors.sdf"
+<li>Run input through validation script
+<li>Scrub files of sensitive information
+</ol>

openfe_benchmarks/data/benchmark_systems/bayer_macrocycles/brd4/experimental_binding_data.json

@@ -0,0 +1,35 @@
+{
+    "61a": {
+        "dg": {
+            "magnitude": -12.0,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c2c(c(c1N([H])S(=O)(=O)C([H])([H])C([H])([H])[H])[H])C3=C(N(C(=O)C(=C3OC(C(C(C(c4c(c(c(c(c4O2)F)[H])F)[H])([H])[H])([H])[H])([H])[H])([H])[H])[H])C([H])([H])[H])[H])[H]",
+        "inchikey": "BYFSQAHWOPJWRA-UHFFFAOYNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "25e": {
+        "dg": {
+            "magnitude": -11.300000190734863,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1N([H])S(=O)(=O)C([H])([H])C([H])([H])[H])[H])C2=C(N(C(=O)C(=C2OC([H])([H])C([H])([H])[H])[H])C([H])([H])[H])[H])Oc3c(c(c(c(c3F)[H])F)[H])[H])[H]",
+        "inchikey": "GLXOAGUUYVCIFE-UHFFFAOYNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    },
+    "11": {
+        "dg": {
+            "magnitude": -8.199999809265137,
+            "unit": "kilocalories_per_mole",
+            ":is_custom:": true,
+            "pint_unit_registry": "openff_units"
+        },
+        "canonical_smiles": "[H]c1c(c(c(c(c1[H])[H])Oc2c(c(c(c(c2C3=NN(C(=O)C(=C3OC([H])([H])[H])[H])C([H])([H])[H])[H])[H])[H])[H])[H])[H]",
+        "inchikey": "MDTCYTNEBYQKFC-UHFFFAOYNA-N",
+        "reference": "https://doi.org/10.1038/s42004-023-01019-9"
+    }
+}