changed definitions. attempt to debug AF search. Has something to do …

…with configs

.gitignore

@@ -1,7 +1,7 @@
 ### POMEGRANATE ###
 structures/
-
-saved_graphs/*
+saved_graphs/
+graphs/
 
 
 # Byte-compiled / optimized / DLL files

pomegranate/app.py

@@ -6,30 +6,52 @@
 from distutils.log import debug
 import dash
 from dash import Dash, dcc, html, Input, Output
-from tabs.seeMotif import motifVisualisationTab, sidebarTab
+from tabs.seeMotif import motifVisualisationTab
 
 PROTEIN_ID = "default"
 
 external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
 
 app = Dash(__name__, external_stylesheets=external_stylesheets)
 
-# sidebar = html.Div(
-#     id="sidebar",
-#     children= [
-#         html.H3("Find a protein"),
-#         html.Hr(),
-#         html.P(
-#             "A placeholder for searching a protein of interest"
-#         ),
-#         html.Button("Button")
-#     ]
-# )
+'''
+Sidebar
+'''
+fnameDict = {'PDB': ['opt1_p', 'opt2_p', 'opt3_p'], 'SWISS_PROT': ['opt1_s', 'opt2_s'], 'AlphaFold': ['opt1_a']}
+
+names = list(fnameDict.keys())
+nestedOptions = fnameDict[names[0]]
 
 sidebar = html.Div(
     id="sidebar-container",
+    children=[
+        html.H3("Find a protein"),
+        html.Hr(),
+        dcc.Dropdown(
+            id='db-dropdown',
+            options=[{'label':name, 'value':name} for name in names],
+            value = list(fnameDict.keys())[0],
+            style={'width': '80%'},
+        ),
+        dcc.Input(
+            id="prot-input",
+            type="text",
+            #value="4hhb", # TODO: REMOVE THIS AFTER TESTING
+            placeholder="Protein ID",
+            style={'width': '80%'},
+            debounce=True,
+            persistence=True,
+            persistence_type='session'
+        ),
+        dcc.Store(id='intermediate-value-prot', storage_type='session'),
+        dcc.Store(id='intermediate-value-psites', storage_type='session'),
+        html.Div(id='input-show'), # DEBUGGING inputs
+    ],
 )
 
+'''
+Tabs
+'''
 tab_selected_style = {
     'borderTop': '3px solid #b52d37',
 }
@@ -46,13 +68,20 @@
     ]
 )
 
-app.layout = html.Div([
+base_page = html.Div([
     html.Img(src=app.get_asset_url('imgs/POMEGRANATE-LOGO.png'), style={'width': '40%'}),
     html.H2('PhOsphosite Motif Explorer -- GRAph Network Abstraction Through Embeddings'),
     html.Div(id="content-grid", children=[sidebar,content])
 
 ])
 
+app.layout = base_page
+
+app.validation_layout = html.Div([
+    base_page,
+    motifVisualisationTab()
+])
+
 @app.callback(Output('tab-container', 'children'),
               Input('tab-options', 'value'))
 def render_content(tab):
@@ -76,13 +105,6 @@ def render_content(tab):
     elif tab == 'documentation':
         return html.H3('Documentation')
 
-'''
-NOT SURE WHAT TO DO FOR INPUT
-'''
-@app.callback(Output('sidebar-container', 'children'),
-              Input('tab-options', 'value'))
-def render_content(tab):
-    return sidebarTab()
 
 
 

pomegranate/definitions.py

@@ -3,15 +3,14 @@
 # Pomegranate  root 
 source_dir = os.path.dirname(os.path.abspath(__file__))
 ROOT_DIR = os.path.dirname(source_dir)
-STRUCTURE_PATH = os.path.join(ROOT_DIR, 'structures')
-<<<<<<< HEAD
-=======
+STRUCTURE_PATH = os.path.join(ROOT_DIR, 'pomegranate/structures/')
 
 SAVED_GRAPHS_DIR = os.path.join(ROOT_DIR, "graphs")
 
+SAVED_PDB_DIR = os.path.join(ROOT_DIR, 'examples/pdbs/')
+
 STRUCTURE_HUMAN_PATH = os.path.join(STRUCTURE_PATH, 'human')
 
 EMBEDDINGS_FILENAME = "embeddings_output.csv" #'embeddings.csv'
 EMBEDDINGS_PATH = os.path.join(os.path.join(ROOT_DIR, 'embeddings'), EMBEDDINGS_FILENAME)
 
->>>>>>> 699e6d4481baa3c2382dc4ff8a01d0654ff7e642

pomegranate/json_conversion/graphein_to_json.py

@@ -1,54 +1,7 @@
 import graphein.protein as gp
-<<<<<<< HEAD
-from graphein.testing import graphs_isomorphic
-import networkx.readwrite as nx
-import json
-# import sys # For cmd line debugging
-
-
-def g_to_json(g):
-
-    del g.graph["config"] # Remove the config from the graph as it's not easily serialisable
-
-    # Ensure graph data is in JSON format
-    for k, v in g.graph.items():
-        try:
-            g.graph[k] = v.to_json()
-        except AttributeError:
-            try:
-                g.graph[k] = v.tolist()
-            except AttributeError:
-                continue
-
-    # Ensure node data is in JSON format
-    for n, d in g.nodes(data=True):
-        for k, v in d.items():
-            try:
-                d[k] = v.to_json()
-            except AttributeError:
-                try:
-                    d[k] = v.tolist()
-                except AttributeError:
-                    continue
-
-    # Ensure edge data is in JSON format
-    for _, _, d in g.edges(data=True):
-        for k, v in d.items():
-            try:
-                d[k] = v.to_json()
-            except AttributeError:
-                try:
-                    d[k] = v.tolist()
-                except AttributeError:
-                    try:
-                        d[k] = list(v)
-                    except AttributeError:
-                        continue
-
-    j_graph = nx.json_graph.node_link_data(g)
-    return j_graph
-=======
 import networkx.readwrite as nx
+import pandas as pd
+import numpy as np
 import json
 
 from definitions import SAVED_GRAPHS_DIR 
@@ -107,7 +60,6 @@ def g_to_json(g, prot_id, db_name='PDB'):
             f.write(json.dumps(tmp))
 
         return j_graph
->>>>>>> 699e6d4481baa3c2382dc4ff8a01d0654ff7e642
     # print(json.dumps(j_graph))
     # # Write the graph to a JSON file
     # with open("test.json", 'w') as f:
@@ -123,6 +75,20 @@ def g_to_json(g, prot_id, db_name='PDB'):
 
     # assert graphs_isomorphic(g, h), "Graphs are not isomorphic"
 
+'''
+Get graph back from json
+'''
+def load_prot_graph (json_graph):
+
+    # Load general graph
+    g = nx.json_graph.node_link_graph(json.loads(json_graph))
+
+    # Convert specific fields from strings
+    g.graph["pdb_df"] = pd.read_json(g.graph["pdb_df"])
+    g.graph["coords"] = np.array(g.graph["coords"])
+
+    return g
+
 '''
 DEBUGGING
 '''

pomegranate/protein/interactions.py

@@ -0,0 +1,64 @@
+import networkx as nx
+
+from graphein.protein.utils import filter_dataframe
+from graphein.protein.edges.distance import compute_distmat, get_interacting_atoms
+
+
+'''
+From graphein.protein.edges.distance
+Modified by Naomi Warren
+'''
+def add_distance_threshold(
+    G: nx.Graph, long_interaction_threshold: int, threshold: float = 5.0
+):
+    """
+    Adds edges to any nodes within a given distance of each other.
+    Long interaction threshold is used to specify minimum separation in sequence
+    to add an edge between networkx nodes within the distance threshold
+    :param G: Protein Structure graph to add distance edges to
+    :type G: nx.Graph
+    :param long_interaction_threshold: minimum distance in sequence for two
+        nodes to be connected
+    :type long_interaction_threshold: int
+    :param threshold: Distance in angstroms, below which two nodes are connected
+    :type threshold: float
+    :return: Graph with distance-based edges added
+    """
+    pdb_df = filter_dataframe(
+        G.graph["pdb_df"], "node_id", list(G.nodes()), True
+    )
+    dist_mat = compute_distmat(pdb_df)
+    interacting_nodes = get_interacting_atoms(threshold, distmat=dist_mat)
+    interacting_nodes = list(zip(interacting_nodes[0], interacting_nodes[1]))
+
+    #log.info(f"Found: {len(interacting_nodes)} distance edges")
+    count = 0
+    for a1, a2 in interacting_nodes:
+
+        # Don't bother adding self-loops
+        if a1 == a2:
+            continue
+
+        n1 = pdb_df.at[a1, "node_id"]
+        n2 = pdb_df.at[a2, "node_id"]
+        n1_chain = pdb_df.at[a1, "chain_id"]
+        n2_chain = pdb_df.at[a2, "chain_id"]
+        n1_position =pdb_df.at[a1, "residue_number"]
+        n2_position = pdb_df.at[a2, "residue_number"]
+
+        condition_1 = n1_chain == n2_chain
+        condition_2 = (
+            abs(n1_position - n2_position) < long_interaction_threshold
+        )
+
+        if not (condition_1 and condition_2):
+            count += 1
+            if G.has_edge(n1, n2):
+                G.edges[n1, n2]["kind"].add("distance_threshold")
+            else:
+                G.add_edge(n1, n2, kind={"distance_threshold"})
+    # log.info(
+    #     f"Added {count} distance edges. ({len(list(interacting_nodes)) - count} removed by LIN)"
+    # )
+
+    return G