Generate a subgraph covering CbGpPWpGaD paths between bupropion and nicotine dependence



In [1]:

    
import random

import hetnetpy.readwrite
import hetnetpy.pathtools
import hetnetpy.stats



In [2]:

    
# Read Hetionet v1.0
url = 'https://github.com/hetio/hetionet/raw/{}/{}'.format(
    '00bf0b6f8886821d91cfdf00eadad145a7a1b6da',
    'hetnet/json/hetionet-v1.0.json.bz2',
)
graph = hetnetpy.readwrite.read_graph(url)
metagraph = graph.metagraph

Generate a subgraph covering CbGpPWpGaD paths between bupropion and nicotine dependence



In [3]:

    
# Specify compound and disease
compound_id = 'Compound', 'DB01156'  # Bupropion
disease_id = 'Disease', 'DOID:0050742'  # nicotine dependences
metapath = metagraph.metapath_from_abbrev('CbGpPWpGaD')



In [4]:

    
# Extract walks from compound to disease
paths = hetnetpy.pathtools.paths_between(
    graph, 
    source=graph.node_dict[compound_id],
    target=graph.node_dict[disease_id],
    metapath=metapath,
    duplicates=True,
)



In [5]:

    
metaedges = set(metapath)
nodes = set()
for path in paths:
    nodes.update(path.get_nodes())
    for edge in path:
        # Add incidental nodes along paths to enable correct DWWC/DWPC computations
        # for the CbGpPWpGaD metapath
        nodes.update(e.target for e in edge.source.get_edges(edge.metaedge))
        nodes.update(e.target for e in edge.target.get_edges(edge.metaedge.inverse))

# Add Gene-interacts-Gene metaedge (not essential but may be useful)
metaedges.add(metagraph.metapath_from_abbrev('GiG')[0])

# Get subgraph
subgraph = graph.get_subgraph(metaedges=metaedges, nodes=nodes)



In [6]:

    
# Metagraph size
subgraph.metagraph.n_nodes, subgraph.metagraph.n_edges









    Out[6]:





(4, 4)



In [7]:

    
# Graph size
subgraph.n_nodes, subgraph.n_edges









    Out[7]:





(3060, 18474)



In [8]:

    
# Metanode info
hetnetpy.stats.get_metanode_df(subgraph)









    Out[8]:







  
    
      
      metanode
      abbreviation
      metaedges
      nodes
      unconnected_nodes
    
  
  
    
      1
      Compound
      C
      1
      730
      730
    
    
      3
      Disease
      D
      1
      16
      16
    
    
      0
      Gene
      G
      4
      2226
      612
    
    
      2
      Pathway
      PW
      1
      88
      0



In [9]:

    
# Metaedge info
hetnetpy.stats.get_metaedge_df(subgraph)









    Out[9]:







  
    
      
      metaedge
      abbreviation
      edges
      source_nodes
      target_nodes
    
  
  
    
      0
      Compound - binds - Gene
      CbG
      5634
      730
      472
    
    
      1
      Disease - associates - Gene
      DaG
      937
      16
      557
    
    
      2
      Gene - interacts - Gene
      GiG
      5124
      1061
      1213
    
    
      3
      Gene - participates - Pathway
      GpPW
      6779
      2222
      88



In [10]:

    
# Export as JSON
hetnetpy.readwrite.write_graph(subgraph, 'bupropion-CbGpPWpGaD-subgraph.json.xz')

Random subgraph of ~100 nodes per metanode

Choose a different number of nodes per metanode to increase the liklihood rotten matrix operations cause misalignment.



In [11]:

    
metanode_to_nodes = graph.get_metanode_to_nodes()
n_nodes = 100
node_subset = list()
random.seed(0, version=2)
for metanode, nodes in sorted(metanode_to_nodes.items()):
    nodes = sorted(nodes)
    nodes = random.sample(nodes, n_nodes)
    node_subset.extend(nodes)
    n_nodes += 1



In [12]:

    
# Get subgraph
subgraph = graph.get_subgraph(nodes=node_subset)



In [13]:

    
# Metagraph size
subgraph.metagraph.n_nodes, subgraph.metagraph.n_edges









    Out[13]:





(11, 24)



In [14]:

    
# Graph size
subgraph.n_nodes, subgraph.n_edges









    Out[14]:





(1155, 3123)



In [15]:

    
# Metanode info
hetnetpy.stats.get_metanode_df(subgraph)









    Out[15]:







  
    
      
      metanode
      abbreviation
      metaedges
      nodes
      unconnected_nodes
    
  
  
    
      0
      Anatomy
      A
      4
      100
      7
    
    
      1
      Biological Process
      BP
      1
      101
      86
    
    
      2
      Cellular Component
      CC
      1
      102
      90
    
    
      3
      Compound
      C
      8
      103
      73
    
    
      4
      Disease
      D
      8
      104
      22
    
    
      5
      Gene
      G
      16
      105
      19
    
    
      6
      Molecular Function
      MF
      1
      106
      95
    
    
      7
      Pathway
      PW
      1
      107
      87
    
    
      8
      Pharmacologic Class
      PC
      1
      108
      108
    
    
      9
      Side Effect
      SE
      1
      109
      76
    
    
      10
      Symptom
      S
      1
      110
      14



In [16]:

    
# Metaedge info
hetnetpy.stats.get_metaedge_df(subgraph)









    Out[16]:







  
    
      
      metaedge
      abbreviation
      edges
      source_nodes
      target_nodes
    
  
  
    
      0
      Anatomy - downregulates - Gene
      AdG
      173
      13
      64
    
    
      1
      Anatomy - expresses - Gene
      AeG
      735
      29
      80
    
    
      2
      Anatomy - upregulates - Gene
      AuG
      126
      13
      58
    
    
      6
      Compound - binds - Gene
      CbG
      10
      10
      1
    
    
      9
      Compound - causes - Side Effect
      CcSE
      170
      53
      33
    
    
      7
      Compound - downregulates - Gene
      CdG
      6
      6
      4
    
    
      4
      Compound - palliates - Disease
      CpD
      26
      16
      13
    
    
      3
      Compound - resembles - Compound
      CrC
      16
      14
      14
    
    
      5
      Compound - treats - Disease
      CtD
      37
      18
      26
    
    
      8
      Compound - upregulates - Gene
      CuG
      4
      3
      4
    
    
      12
      Disease - associates - Gene
      DaG
      62
      37
      24
    
    
      13
      Disease - downregulates - Gene
      DdG
      26
      18
      23
    
    
      10
      Disease - localizes - Anatomy
      DlA
      636
      95
      93
    
    
      15
      Disease - presents - Symptom
      DpS
      631
      96
      96
    
    
      11
      Disease - resembles - Disease
      DrD
      309
      81
      73
    
    
      14
      Disease - upregulates - Gene
      DuG
      28
      17
      20
    
    
      18
      Gene - covaries - Gene
      GcG
      1
      1
      1
    
    
      19
      Gene - interacts - Gene
      GiG
      2
      2
      2
    
    
      16
      Gene - participates - Biological Process
      GpBP
      33
      21
      15
    
    
      17
      Gene - participates - Cellular Component
      GpCC
      32
      23
      12
    
    
      21
      Gene - participates - Molecular Function
      GpMF
      13
      10
      11
    
    
      22
      Gene - participates - Pathway
      GpPW
      25
      15
      20
    
    
      20
      Gene > regulates > Gene
      Gr>G
      3
      3
      2
    
    
      23
      Pharmacologic Class - includes - Compound
      PCiC
      19
      13
      19



In [17]:

    
# Export as JSON
hetnetpy.readwrite.write_graph(subgraph, 'random-subgraph.json.xz')

	metaedge	abbreviation	edges	source_nodes	target_nodes
0	Compound - binds - Gene	CbG	5634	730	472
1	Disease - associates - Gene	DaG	937	16	557
2	Gene - interacts - Gene	GiG	5124	1061	1213
3	Gene - participates - Pathway	GpPW	6779	2222	88

	metanode	abbreviation	metaedges	nodes	unconnected_nodes
0	Anatomy	A	4	100	7
1	Biological Process	BP	1	101	86
2	Cellular Component	CC	1	102	90
3	Compound	C	8	103	73
4	Disease	D	8	104	22
5	Gene	G	16	105	19
6	Molecular Function	MF	1	106	95
7	Pathway	PW	1	107	87
8	Pharmacologic Class	PC	1	108	108
9	Side Effect	SE	1	109	76
10	Symptom	S	1	110	14

	metaedge	abbreviation	edges	source_nodes	target_nodes
0	Anatomy - downregulates - Gene	AdG	173	13	64
1	Anatomy - expresses - Gene	AeG	735	29	80
2	Anatomy - upregulates - Gene	AuG	126	13	58
6	Compound - binds - Gene	CbG	10	10	1
9	Compound - causes - Side Effect	CcSE	170	53	33
7	Compound - downregulates - Gene	CdG	6	6	4
4	Compound - palliates - Disease	CpD	26	16	13
3	Compound - resembles - Compound	CrC	16	14	14
5	Compound - treats - Disease	CtD	37	18	26
8	Compound - upregulates - Gene	CuG	4	3	4
12	Disease - associates - Gene	DaG	62	37	24
13	Disease - downregulates - Gene	DdG	26	18	23
10	Disease - localizes - Anatomy	DlA	636	95	93
15	Disease - presents - Symptom	DpS	631	96	96
11	Disease - resembles - Disease	DrD	309	81	73
14	Disease - upregulates - Gene	DuG	28	17	20
18	Gene - covaries - Gene	GcG	1	1	1
19	Gene - interacts - Gene	GiG	2	2	2
16	Gene - participates - Biological Process	GpBP	33	21	15
17	Gene - participates - Cellular Component	GpCC	32	23	12
21	Gene - participates - Molecular Function	GpMF	13	10	11
22	Gene - participates - Pathway	GpPW	25	15	20
20	Gene > regulates > Gene	Gr>G	3	3	2
23	Pharmacologic Class - includes - Compound	PCiC	19	13	19