update notebooks

DeepRank · Sep 22, 2023 · 702f1ed · 702f1ed
1 parent 3516edf
commit 702f1ed
Show file tree

Hide file tree

Showing 3 changed files with 24 additions and 17 deletions.
diff --git a/tests/data/hdf5/_generate_testdata.ipynb b/tests/data/hdf5/_generate_testdata.ipynb
@@ -102,7 +102,8 @@
     "models_folder_name = 'exp_nmers_all_HLA_quantitative'\n",
     "data = 'pMHCI'\n",
     "resolution = 'residue' # either 'residue' or 'atom'\n",
-    "distance_cutoff = 15 # max distance in Å between two interacting residues/atoms of two proteins\n",
+    "interaction_radius = 15 # max distance in Å between two interacting residues/atoms of two proteins\n",
+    "max_edge_distance = 15 # max distance in Å between to create an edge\n",
     "\n",
     "csv_file_path = f'{project_folder}data/external/processed/I/{csv_file_name}'\n",
     "models_folder_path = f'{project_folder}data/{data}/features_input_folder/{models_folder_name}'\n",
@@ -130,7 +131,8 @@
     "            pdb_path = pdb_files[i],\n",
     "            resolution = \"residue\",\n",
     "            chain_ids = [\"M\", \"P\"],\n",
-    "            distance_cutoff = distance_cutoff,\n",
+    "            interaction_radius = interaction_radius,\n",
+    "            max_edge_distance = max_edge_distance,\n",
     "            targets = {\n",
     "                'binary': int(float(bas[i]) <= 500), # binary target value\n",
     "                'BA': bas[i], # continuous target value\n",

diff --git a/tutorials/data_generation_ppi.ipynb b/tutorials/data_generation_ppi.ipynb
@@ -162,8 +162,9 @@
     "- A `.pdb` file, representing the protein-protein structural complex.\n",
     "- The resolution (`\"residue\"` or `\"atom\"`), i.e. whether each node should represent an amino acid residue or an atom.\n",
     "- The ids of the two chains composing the complex. In our use case, \"M\" indicates the MHC protein chain and \"P\" the peptide chain.\n",
-    "- The distance cutoff, which represents the maximum distance in Ångström between two interacting residues/atoms of the two proteins.\n",
+    "- The interaction radius, which determines the threshold distance (in Ångström) for residues/atoms surrounding the interface that will be included in the graph.\n",
     "- The target values associated with the query. For each query/data point, in the use case demonstrated in this tutorial will add two targets: \"BA\" and \"binary\". The first represents the actual BA value of the complex in nM, while the second represents its binary mapping, being 0 (BA > 500 nM) a not-binding complex and 1 (BA <= 500 nM) a binding one.\n",
+    "- The max edge distance, which is the maximum distance between two nodes to generate an edge between them.\n",
     "- Optional: The correspondent [Position-Specific Scoring Matrices (PSSMs)](https://en.wikipedia.org/wiki/Position_weight_matrix), in the form of .pssm files. PSSMs are optional and will not be used in this tutorial."
    ]
   },
@@ -183,7 +184,8 @@
    "source": [
     "queries = QueryCollection()\n",
     "\n",
-    "interface_distance_cutoff = 8  # max distance in Å between two interacting residues/atoms of two proteins\n",
+    "interaction_radius = 8  # max distance in Å between two interacting residues/atoms of two proteins\n",
+    "max_edge_distance = 8\n",
     "\n",
     "print(f'Adding {len(pdb_files)} queries to the query collection ...')\n",
     "count = 0\n",
@@ -193,7 +195,8 @@
     "\t\t\tpdb_path = pdb_files[i],\n",
     "\t\t\tresolution = \"residue\",\n",
     "\t\t\tchain_ids = [\"M\", \"P\"],\n",
-    "\t\t\tdistance_cutoff = interface_distance_cutoff,\n",
+    "\t\t\tinteraction_radius = interaction_radius,\n",
+    "\t\t\tmax_edge_distance = max_edge_distance,\n",
     "\t\t\ttargets = {\n",
     "\t\t\t\t'binary': int(float(bas[i]) <= 500), # binary target value\n",
     "\t\t\t\t'BA': bas[i], # continuous target value\n",
@@ -416,7 +419,8 @@
    "source": [
     "queries = QueryCollection()\n",
     "\n",
-    "interface_distance_cutoff = 5  # max distance in Å between two interacting residues/atoms of two proteins\n",
+    "interaction_radius = 5  # max distance in Å between two interacting residues/atoms of two proteins\n",
+    "max_edge_distance = 5\n",
     "\n",
     "print(f'Adding {len(pdb_files)} queries to the query collection ...')\n",
     "count = 0\n",
@@ -426,7 +430,8 @@
     "\t\t\tpdb_path = pdb_files[i],\n",
     "\t\t\tresolution = \"atom\",\n",
     "\t\t\tchain_ids = [\"M\",\"P\"],\n",
-    "\t\t\tdistance_cutoff = interface_distance_cutoff,\n",
+    "\t\t\tinteraction_radius = interaction_radius,\n",
+    "\t\t\tmax_edge_distance = max_edge_distance,\n",
     "\t\t\ttargets = {\n",
     "\t\t\t\t'binary': int(float(bas[i]) <= 500), # binary target value\n",
     "\t\t\t\t'BA': bas[i], # continuous target value\n",

diff --git a/tutorials/data_generation_srv.ipynb b/tutorials/data_generation_srv.ipynb
@@ -186,9 +186,9 @@
     "- The insertion code, used when two residues have the same numbering. The combination of residue numbering and insertion code defines the unique residue.\n",
     "- The wildtype amino acid. \n",
     "- The variant amino acid. \n",
-    "- The radius, which determines the threshold distance (in Ångström) for residues/atoms surrounding the mutation that will be included in the graph.\n",
-    "- The distance cutoff, which represents the maximum distance in Ångström between two interacting residues/atoms.\n",
+    "- The interaction radius, which determines the threshold distance (in Ångström) for residues/atoms surrounding the mutation that will be included in the graph.\n",
     "- The target values associated with the query. For each query/data point, in the use case demonstrated in this tutorial will add a 0 if the SRV belongs to the benign class, and 1 if it belongs to the pathogenic one. \n",
+    "- The max edge distance, which is the maximum distance between two nodes to generate an edge between them.\n",
     "- Optional: The correspondent [Position-Specific Scoring Matrices (PSSMs)](https://en.wikipedia.org/wiki/Position_weight_matrix), per chain identifier, in the form of .pssm files. PSSMs are optional and will not be used in this tutorial."
    ]
   },
@@ -208,8 +208,8 @@
    "source": [
     "queries = QueryCollection()\n",
     "\n",
-    "radius = 10.0 # radius to select the local neighborhood around the SRV\n",
-    "distance_cutoff = 4.5 # ??\n",
+    "interaction_radius = 10.0 # radius to select the local neighborhood around the SRV\n",
+    "max_edge_distance = 4.5 # ??\n",
     "\n",
     "print(f'Adding {len(pdb_files)} queries to the query collection ...')\n",
     "count = 0\n",
@@ -223,8 +223,8 @@
     "\t\twildtype_amino_acid = aa_dict[res_wildtypes[i]],\n",
     "\t\tvariant_amino_acid = aa_dict[res_variants[i]],\n",
     "\t\ttargets = {'binary': targets[i]},\n",
-    "\t\tradius = radius,\n",
-    "\t\tdistance_cutoff = distance_cutoff,\n",
+    "\t\tinteraction_radius = interaction_radius,\n",
+    "\t\tmax_edge_distance = max_edge_distance,\n",
     "\t\t))\n",
     "\tcount +=1\n",
     "\tif count % 20 == 0:\n",
@@ -452,8 +452,8 @@
    "source": [
     "queries = QueryCollection()\n",
     "\n",
-    "radius = 10.0 # radius to select the local neighborhood around the SRV\n",
-    "distance_cutoff = 4.5 # ??\n",
+    "interaction_radius = 10.0 # radius to select the local neighborhood around the SRV\n",
+    "max_edge_distance = 4.5 # ??\n",
     "\n",
     "print(f'Adding {len(pdb_files)} queries to the query collection ...')\n",
     "count = 0\n",
@@ -467,8 +467,8 @@
     "\t\twildtype_amino_acid = aa_dict[res_wildtypes[i]],\n",
     "\t\tvariant_amino_acid = aa_dict[res_variants[i]],\n",
     "\t\ttargets = {'binary': targets[i]},\n",
-    "\t\tradius = radius,\n",
-    "\t\tdistance_cutoff = distance_cutoff,\n",
+    "\t\tinteraction_radius = interaction_radius,\n",
+    "\t\tmax_edge_distance = max_edge_distance,\n",
     "\t\t))\n",
     "\tcount +=1\n",
     "\tif count % 20 == 0:\n",