readme note

README.md

@@ -11,6 +11,8 @@ This package includes tools for:
 
 Data used for training, models and binding pocket visualizations available [here](http://csb.cs.mcgill.ca/RNAmigos/). 
 
+NOTE: The user friendly API is currently being built and tested. Sample usage described below is still being improved.
+
 ## Requirements
 
 * Python 3.6+
@@ -21,8 +23,25 @@ Data used for training, models and binding pocket visualizations available [here
 
 ## Building Pocket Graph Dataset
 
+### Extracting binding pockets
+
+The `get_binding` function extracts all binding pockts from a PDB and writes a new PDB for each ligand in the PDB.
+
+```python
+>>> from RNAmigos.binding_pockets import get_binding
+>>> pdb_path = '/path/to/pdbs/'
+>>> get_binding(pdb_path, '1aju.pdb')
+
+```
+
+### Building Graph Representations of Binding pockets
+
+The function `build_graph` from `pocket_graph` builds a newtorkx graph from a CSV of binding pocket residues.
+
+
 ## Pocket Graph Drawing
 
+From a graph object, or a pickled graph we can draw the graph.
 
 ```python
 >>> G = nx.read_gpickle('../Data/sample_graphs/3ds7_GNG_P.nxpickle')
@@ -75,16 +94,35 @@ You can convert this output to a distance matrix and a list indicating the graph
 >>> DM, L, graphlist = data_prepare(geds, fps)
 ```
 
-The distance matrix can be passed to a prototype selector.
+The distance matrix can be passed to a prototype selector to get the indices in the DM selected as prototypes.
 
 ```python
 >>> from RNAmigos.dissimilarity_embed import prototype_select
->>> prototypes = prototype_select(DM, 20)
+>>> prototypes = prototype_select(DM, 20, heuristic='spanning')
 ```
 
+### Embedding a full dataset
 
+To embed the graphs used in the GED comparisons and select prototypes in one call to get a matrix of size N x r where N is the nubmer of graphs in DM and r is the number of prototypes used.
 
-## Fingerprint Prediction
+```python
+>>> from RNAmigos.dissimilarity_embed import full_embed
+>>> embedding = full_embed(graphlist, 20, DM=DM, dist_mat=True, heuristic='k-centers')
+```
+
+The vector embedding of the third graph in our dataset:
+
+```python
+>>> embedding[2]
+array([ 8., 10., 10.,  8., 22., 10.,  6.,  8.,  8., 18., 20.,  8., 10.,
+       10., 24., 16.,  6., 16., 12., 18.])
+```
+
+### Embedding a single graph
 
+User-friendly API coming soon.
 
 
+## Fingerprint Prediction
+
+User-friendly API coming soon.

RNAmigos/dissimilarity_embed.py

@@ -14,14 +14,14 @@ import cProfile
 import pstats
 import uuid
 import random
+import pickle
 
 
 import networkx as nx
 import numpy as np
 from numpy.linalg import eig
 
-from spectral_distance import *
-
+from rna_ged import ged
 
 logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
 
@@ -42,10 +42,6 @@ def dummy(args):
     cProfile.runctx('row_compute(args)', globals(), locals(),\
         f'prof_{random.randint(0,20)}.prof')
 
-def graph_eigen(G):
-    L = graph_laplacian(G)
-    return eig(L)
-    
 def distance_matrix_para(D):
     eigens = []
     #compute list of eigendecompositions for each graph.
@@ -196,7 +192,7 @@ def prototypes(DM,m, heuristic='spanning'):
         return random_proto(DM, m)
     pass
 
-def graph_embed(args):
+def graph_embed(G, prototypes):
     """
     Embed graph G given prototype set P.
 
@@ -204,8 +200,14 @@ def graph_embed(args):
 
     `array`: numpy array representing embedding vector.
     """
-    i,G,P, = args
-    return (i, np.array([graph_distance(G, p) for p in P]))
+    embedding = np.zeros(len(prototypes))
+    for p in prototypes:
+        g = pickle.load(open(G, 'rb'))
+        p  = pickle.load(open(p, 'rb'))
+        ops,_,_ = ged((g1,p), source_only=True)
+        embedding.append(ops.cost)
+    return embedding
+
 def full_embed(D, m, DM=None, dist_mat=None, heuristic='spanning'):
     """
     For a dataset of graphs D, perform prototype selection and embedding.
@@ -215,22 +217,12 @@ def full_embed(D, m, DM=None, dist_mat=None, heuristic='spanning'):
     """
     if dist_mat == None:
         DM = distance_matrix_para(D)
-    P_idx = prototypes(D, m, DM, heuristic=heuristic)
-    print(P_idx)
+    P_idx = prototypes(DM,m, heuristic=heuristic)
     logging.info("Embedding graphs.")
-    # embeddings = [graph_embed(g, P) for g in D]
-    # embeddings = [graph_embed(g, P) for g in D]
-    # todo = ((i,g,P) for i,g in enumerate(D))
     embeddings = np.zeros((len(D), m))
 
     for i, g in enumerate(D):
         embeddings[i] =  DM[i][P_idx]
-    
-    # with multiprocessing.Pool(PROCS) as pool:
-        # for e in pool.map(graph_embed, todo):
-            # i,embed = e
-            # embeddings[i] = embed
-        
     return embeddings
 
 if __name__ == "__main__":

RNAmigos/post_ged.py

@@ -89,6 +89,7 @@ def prepare_data(geds_path, fps_path, non_redundant=True):
     if non_redundant:
         print(DM, L)
         DM, L, ind = no_redundants(DM, L)
+        return (DM, L, [g for i, g in enumerate(graphlist) if i in ind])
     return (DM, L, graphlist)
 
 if __name__ == "__main__":