Introduction to Pygenprop

An python library for interactive programatic usage of Genome Properties

InterProScan files used in this tutorial can be found at:



In [83]:

    
import requests
from io import StringIO
from pygenprop.results import GenomePropertiesResults
from pygenprop.database_file_parser import parse_genome_properties_flat_file
from pygenprop.assignment_file_parser import parse_interproscan_file, parse_genome_property_longform_file



In [84]:

    
# The Genome Properties is a flat file database that can be fount on Github.
# The latest release of the database can be found at the following URL.

genome_properties_database_url = 'https://raw.githubusercontent.com/ebi-pf-team/genome-properties/master/flatfiles/genomeProperties.txt'

# For this tutorial we will stream the file directly into the Jupyter notebook. Alternativly, 
# one could be downloaded the file with the unix wget or curl commands.

with requests.Session() as current_download:
    response = current_download.get(genome_properties_database_url, stream=True)
    tree = parse_genome_properties_flat_file(StringIO(response.text))



In [85]:

    
# There are 1286 properties in the Genome Properties tree.
len(tree)









    Out[85]:





1286



In [86]:

    
# Find all properties of type "GUILD".
for genome_property in tree:
    if genome_property.type == 'GUILD':
        print(genome_property.name)









    



Coenzyme F420 utilization
CRISPR region
Reduction of oxidized methionine
Phage: major features
Resistance to Reactive Oxygen Species (ROS)
tRNA aminoacylation
Toxin-antitoxin system, type II
Protein-coding palindromic elements
Flagellar components of unknown function
Bacillithiol utilization
Toxin-antitoxin system, type I
Toxin-antitoxin system, type III
Abortive infection proteins
Energy-coupling factor transporters
Initiator caspases of the apoptosis extrinsic pathway
Executor caspases of apoptosis



In [87]:

    
# Parse InterProScan files
with open('E_coli_K12.tsv') as ipr5_file_one:
    assignment_cache_1 = parse_interproscan_file(ipr5_file_one)



In [88]:

    
with open('E_coli_O157_H7.tsv') as ipr5_file_two:
    assignment_cache_2 = parse_interproscan_file(ipr5_file_two)



In [89]:

    
# Create results comparison object
results = GenomePropertiesResults(assignment_cache_1, assignment_cache_2, properties_tree=tree)



In [90]:

    
# Get property by identifier
virulence = tree['GenProp0074']



In [91]:

    
virulence









    Out[91]:





GenProp0074, Type: CATEGORY, Name: Virulence, Thresh: 0, References: False, Databases: False, Steps: True, Parents: True, Children: True, Public: False



In [92]:

    
# Iterate to get the identifiers of child properties of virulence
types_of_vir = [genprop.id for genprop in virulence.children]



In [93]:

    
# The property results property is used to compare two property assignments between samples.
results.property_results









    Out[93]:







  
    
      
      E_coli_K12
      E_coli_O157_H7
    
    
      Property_Identifier
      
      
    
  
  
    
      GenProp0724
      NO
      NO
    
    
      GenProp0757
      YES
      YES
    
    
      GenProp0809
      NO
      NO
    
    
      GenProp0853
      NO
      NO
    
    
      GenProp0861
      NO
      NO
    
    
      GenProp0901
      NO
      NO
    
    
      GenProp0919
      NO
      NO
    
    
      GenProp0920
      NO
      NO
    
    
      GenProp0921
      NO
      NO
    
    
      GenProp0936
      NO
      NO
    
    
      GenProp0945
      NO
      NO
    
    
      GenProp0954
      NO
      NO
    
    
      GenProp0955
      NO
      NO
    
    
      GenProp0956
      NO
      NO
    
    
      GenProp0962
      NO
      NO
    
    
      GenProp0967
      NO
      NO
    
    
      GenProp0982
      NO
      NO
    
    
      GenProp0984
      NO
      NO
    
    
      GenProp0991
      NO
      NO
    
    
      GenProp1000
      NO
      NO
    
    
      GenProp1002
      NO
      NO
    
    
      GenProp1003
      NO
      NO
    
    
      GenProp1037
      NO
      NO
    
    
      GenProp1052
      NO
      NO
    
    
      GenProp1062
      NO
      NO
    
    
      GenProp1065
      NO
      NO
    
    
      GenProp1078
      NO
      NO
    
    
      GenProp1083
      NO
      NO
    
    
      GenProp1084
      NO
      NO
    
    
      GenProp1090
      NO
      NO
    
    
      ...
      ...
      ...
    
    
      GenProp0318
      NO
      NO
    
    
      GenProp0319
      NO
      NO
    
    
      GenProp0320
      PARTIAL
      PARTIAL
    
    
      GenProp0469
      PARTIAL
      PARTIAL
    
    
      GenProp0670
      NO
      NO
    
    
      GenProp0685
      NO
      NO
    
    
      GenProp0768
      PARTIAL
      PARTIAL
    
    
      GenProp0922
      PARTIAL
      PARTIAL
    
    
      GenProp1061
      NO
      NO
    
    
      GenProp1106
      PARTIAL
      PARTIAL
    
    
      GenProp1093
      NO
      NO
    
    
      GenProp2007
      NO
      NO
    
    
      GenProp1067
      PARTIAL
      PARTIAL
    
    
      GenProp2085
      NO
      NO
    
    
      GenProp2038
      NO
      NO
    
    
      GenProp2086
      NO
      NO
    
    
      GenProp2087
      NO
      NO
    
    
      GenProp2088
      NO
      NO
    
    
      GenProp2089
      NO
      NO
    
    
      GenProp2090
      NO
      NO
    
    
      GenProp2092
      NO
      NO
    
    
      GenProp2093
      NO
      NO
    
    
      GenProp2094
      NO
      NO
    
    
      GenProp2097
      NO
      NO
    
    
      GenProp2095
      NO
      NO
    
    
      GenProp2096
      NO
      NO
    
    
      GenProp2098
      NO
      NO
    
    
      GenProp2099
      NO
      NO
    
    
      GenProp1778
      NO
      NO
    
    
      GenProp0065
      PARTIAL
      PARTIAL
    
  

1286 rows × 2 columns



In [94]:

    
# The step results property is used to compare two step assignments between samples.
results.step_results









    Out[94]:







  
    
      
      
      E_coli_K12
      E_coli_O157_H7
    
    
      Property_Identifier
      Step_Number
      
      
    
  
  
    
      GenProp0724
      1
      NO
      NO
    
    
      2
      NO
      NO
    
    
      3
      NO
      NO
    
    
      4
      YES
      YES
    
    
      5
      YES
      YES
    
    
      6
      NO
      NO
    
    
      7
      YES
      YES
    
    
      8
      NO
      NO
    
    
      GenProp0077
      2
      NO
      NO
    
    
      3
      YES
      YES
    
    
      4
      NO
      NO
    
    
      5
      NO
      NO
    
    
      6
      NO
      NO
    
    
      7
      NO
      NO
    
    
      8
      NO
      NO
    
    
      9
      NO
      NO
    
    
      10
      NO
      NO
    
    
      11
      NO
      NO
    
    
      12
      NO
      NO
    
    
      13
      NO
      NO
    
    
      14
      NO
      NO
    
    
      15
      NO
      NO
    
    
      16
      NO
      NO
    
    
      17
      NO
      NO
    
    
      18
      NO
      NO
    
    
      19
      NO
      NO
    
    
      20
      NO
      NO
    
    
      21
      NO
      NO
    
    
      22
      NO
      NO
    
    
      23
      NO
      NO
    
    
      ...
      ...
      ...
      ...
    
    
      GenProp2095
      6
      NO
      NO
    
    
      7
      NO
      NO
    
    
      8
      NO
      NO
    
    
      9
      NO
      NO
    
    
      GenProp2097
      1
      NO
      NO
    
    
      2
      NO
      NO
    
    
      3
      NO
      NO
    
    
      4
      NO
      NO
    
    
      GenProp2096
      1
      NO
      NO
    
    
      2
      NO
      NO
    
    
      4
      NO
      NO
    
    
      5
      NO
      NO
    
    
      6
      NO
      NO
    
    
      GenProp2098
      1
      NO
      NO
    
    
      2
      NO
      NO
    
    
      4
      NO
      NO
    
    
      5
      NO
      NO
    
    
      6
      NO
      NO
    
    
      7
      NO
      NO
    
    
      GenProp2099
      1
      NO
      NO
    
    
      2
      NO
      NO
    
    
      3
      YES
      YES
    
    
      4
      NO
      NO
    
    
      5
      NO
      NO
    
    
      6
      NO
      NO
    
    
      7
      NO
      NO
    
    
      8
      NO
      NO
    
    
      9
      NO
      NO
    
    
      10
      NO
      NO
    
    
      11
      NO
      NO
    
  

6525 rows × 2 columns



In [95]:

    
# Get properties with differing assignments
results.differing_property_results









    Out[95]:







  
    
      
      E_coli_K12
      E_coli_O157_H7
    
    
      Property_Identifier
      
      
    
  
  
    
      GenProp0111
      YES
      PARTIAL
    
    
      GenProp1032
      YES
      PARTIAL
    
    
      GenProp0183
      YES
      PARTIAL
    
    
      GenProp1695
      NO
      PARTIAL
    
    
      GenProp1331
      PARTIAL
      YES
    
    
      GenProp1388
      NO
      YES
    
    
      GenProp0051
      NO
      YES
    
    
      GenProp0232
      PARTIAL
      YES
    
    
      GenProp0236
      PARTIAL
      YES
    
    
      GenProp0455
      YES
      PARTIAL
    
    
      GenProp0687
      YES
      PARTIAL
    
    
      GenProp0686
      YES
      PARTIAL
    
    
      GenProp0139
      NO
      PARTIAL
    
    
      GenProp1365
      YES
      PARTIAL
    
    
      GenProp0283
      YES
      NO
    
    
      GenProp1297
      YES
      PARTIAL
    
    
      GenProp1326
      YES
      PARTIAL
    
    
      GenProp1501
      PARTIAL
      NO
    
    
      GenProp1402
      YES
      PARTIAL
    
    
      GenProp1299
      YES
      PARTIAL
    
    
      GenProp1463
      YES
      PARTIAL
    
    
      GenProp1568
      YES
      NO
    
    
      GenProp1374
      YES
      PARTIAL
    
    
      GenProp1556
      YES
      PARTIAL
    
    
      GenProp1566
      YES
      PARTIAL
    
    
      GenProp0938
      YES
      PARTIAL
    
    
      GenProp0052
      NO
      PARTIAL
    
    
      GenProp0059
      NO
      YES
    
    
      GenProp0735
      NO
      YES
    
    
      GenProp1074
      NO
      YES
    
    
      GenProp0961
      NO
      YES
    
    
      GenProp0820
      PARTIAL
      YES
    
    
      GenProp0323
      PARTIAL
      YES
    
    
      GenProp1120
      YES
      NO
    
    
      GenProp1133
      YES
      NO
    
    
      GenProp1189
      YES
      NO
    
    
      GenProp0176
      YES
      NO
    
    
      GenProp1094
      NO
      PARTIAL



In [96]:

    
# Get property assignments for virulence properties
results.get_results(*types_of_vir, steps=False)









    Out[96]:







  
    
      
      E_coli_K12
      E_coli_O157_H7
    
    
      Property_Identifier
      
      
    
  
  
    
      GenProp0052
      NO
      PARTIAL
    
    
      GenProp0648
      YES
      YES
    
    
      GenProp0707
      NO
      NO



In [97]:

    
# Get step assignments for virulence properties
results.get_results(*types_of_vir, steps=True)









    Out[97]:







  
    
      
      
      E_coli_K12
      E_coli_O157_H7
    
    
      Property_Identifier
      Step_Number
      
      
    
  
  
    
      GenProp0052
      1
      NO
      NO
    
    
      2
      NO
      NO
    
    
      3
      NO
      NO
    
    
      4
      NO
      NO
    
    
      5
      NO
      NO
    
    
      6
      NO
      YES
    
    
      7
      NO
      NO
    
    
      8
      NO
      YES
    
    
      9
      NO
      NO
    
    
      10
      YES
      YES
    
    
      11
      NO
      NO
    
    
      12
      NO
      NO
    
    
      13
      NO
      YES
    
    
      14
      NO
      YES
    
    
      15
      NO
      NO
    
    
      16
      NO
      YES
    
    
      17
      NO
      NO
    
    
      18
      NO
      NO
    
    
      19
      NO
      YES
    
    
      21
      NO
      NO
    
    
      22
      YES
      YES
    
    
      24
      NO
      YES
    
    
      25
      NO
      NO
    
    
      26
      NO
      YES
    
    
      27
      NO
      YES
    
    
      28
      NO
      YES
    
    
      29
      NO
      NO
    
    
      30
      NO
      NO
    
    
      31
      NO
      YES
    
    
      32
      NO
      YES
    
    
      33
      NO
      NO
    
    
      34
      NO
      NO
    
    
      35
      NO
      YES
    
    
      36
      NO
      NO
    
    
      37
      NO
      YES
    
    
      38
      NO
      YES
    
    
      39
      NO
      YES
    
    
      40
      NO
      YES
    
    
      41
      NO
      YES
    
    
      42
      NO
      YES
    
    
      43
      NO
      NO
    
    
      44
      NO
      NO
    
    
      GenProp0648
      1
      YES
      YES
    
    
      2
      YES
      YES
    
    
      3
      YES
      YES
    
    
      4
      YES
      YES
    
    
      5
      YES
      YES
    
    
      6
      YES
      YES
    
    
      7
      YES
      YES
    
    
      GenProp0707
      1
      NO
      NO
    
    
      2
      NO
      NO
    
    
      3
      NO
      NO
    
    
      4
      NO
      NO
    
    
      5
      NO
      NO
    
    
      6
      NO
      NO



In [98]:

    
# Get counts of virulence properties assigned YES, NO, and PARTIAL per organism
results.get_results_summary(*types_of_vir, steps=False, normalize=False)









    Out[98]:







  
    
      
      E_coli_K12
      E_coli_O157_H7
    
  
  
    
      NO
      2.0
      1
    
    
      PARTIAL
      0.0
      1
    
    
      YES
      1.0
      1



In [99]:

    
# Get counts of virulence steps assigned YES, NO, and PARTIAL per organism
results.get_results_summary(*types_of_vir, steps=True, normalize=False)









    Out[99]:







  
    
      
      E_coli_K12
      E_coli_O157_H7
    
  
  
    
      NO
      46
      27
    
    
      YES
      9
      28



In [100]:

    
# Get percentages of virulence steps assigned YES, NO, and PARTIAL per organism
results.get_results_summary(*types_of_vir, steps=True, normalize=True)









    Out[100]:







  
    
      
      E_coli_K12
      E_coli_O157_H7
    
  
  
    
      NO
      83.636364
      49.090909
    
    
      YES
      16.363636
      50.909091



In [ ]:

	E_coli_K12	E_coli_O157_H7
Property_Identifier
GenProp0724	NO	NO
GenProp0757	YES	YES
GenProp0809	NO	NO
GenProp0853	NO	NO
GenProp0861	NO	NO
GenProp0901	NO	NO
GenProp0919	NO	NO
GenProp0920	NO	NO
GenProp0921	NO	NO
GenProp0936	NO	NO
GenProp0945	NO	NO
GenProp0954	NO	NO
GenProp0955	NO	NO
GenProp0956	NO	NO
GenProp0962	NO	NO
GenProp0967	NO	NO
GenProp0982	NO	NO
GenProp0984	NO	NO
GenProp0991	NO	NO
GenProp1000	NO	NO
GenProp1002	NO	NO
GenProp1003	NO	NO
GenProp1037	NO	NO
GenProp1052	NO	NO
GenProp1062	NO	NO
GenProp1065	NO	NO
GenProp1078	NO	NO
GenProp1083	NO	NO
GenProp1084	NO	NO
GenProp1090	NO	NO
...	...	...
GenProp0318	NO	NO
GenProp0319	NO	NO
GenProp0320	PARTIAL	PARTIAL
GenProp0469	PARTIAL	PARTIAL
GenProp0670	NO	NO
GenProp0685	NO	NO
GenProp0768	PARTIAL	PARTIAL
GenProp0922	PARTIAL	PARTIAL
GenProp1061	NO	NO
GenProp1106	PARTIAL	PARTIAL
GenProp1093	NO	NO
GenProp2007	NO	NO
GenProp1067	PARTIAL	PARTIAL
GenProp2085	NO	NO
GenProp2038	NO	NO
GenProp2086	NO	NO
GenProp2087	NO	NO
GenProp2088	NO	NO
GenProp2089	NO	NO
GenProp2090	NO	NO
GenProp2092	NO	NO
GenProp2093	NO	NO
GenProp2094	NO	NO
GenProp2097	NO	NO
GenProp2095	NO	NO
GenProp2096	NO	NO
GenProp2098	NO	NO
GenProp2099	NO	NO
GenProp1778	NO	NO
GenProp0065	PARTIAL	PARTIAL

		E_coli_K12	E_coli_O157_H7
Property_Identifier	Step_Number
GenProp0724	1	NO	NO
	2	NO	NO
	3	NO	NO
	4	YES	YES
	5	YES	YES
	6	NO	NO
	7	YES	YES
	8	NO	NO
GenProp0077	2	NO	NO
	3	YES	YES
	4	NO	NO
	5	NO	NO
	6	NO	NO
	7	NO	NO
	8	NO	NO
	9	NO	NO
	10	NO	NO
	11	NO	NO
	12	NO	NO
	13	NO	NO
	14	NO	NO
	15	NO	NO
	16	NO	NO
	17	NO	NO
	18	NO	NO
	19	NO	NO
	20	NO	NO
	21	NO	NO
	22	NO	NO
	23	NO	NO
...	...	...	...
GenProp2095	6	NO	NO
	7	NO	NO
	8	NO	NO
	9	NO	NO
GenProp2097	1	NO	NO
	2	NO	NO
	3	NO	NO
	4	NO	NO
GenProp2096	1	NO	NO
	2	NO	NO
	4	NO	NO
	5	NO	NO
	6	NO	NO
GenProp2098	1	NO	NO
	2	NO	NO
	4	NO	NO
	5	NO	NO
	6	NO	NO
	7	NO	NO
GenProp2099	1	NO	NO
	2	NO	NO
	3	YES	YES
	4	NO	NO
	5	NO	NO
	6	NO	NO
	7	NO	NO
	8	NO	NO
	9	NO	NO
	10	NO	NO
	11	NO	NO

	E_coli_K12	E_coli_O157_H7
Property_Identifier
GenProp0111	YES	PARTIAL
GenProp1032	YES	PARTIAL
GenProp0183	YES	PARTIAL
GenProp1695	NO	PARTIAL
GenProp1331	PARTIAL	YES
GenProp1388	NO	YES
GenProp0051	NO	YES
GenProp0232	PARTIAL	YES
GenProp0236	PARTIAL	YES
GenProp0455	YES	PARTIAL
GenProp0687	YES	PARTIAL
GenProp0686	YES	PARTIAL
GenProp0139	NO	PARTIAL
GenProp1365	YES	PARTIAL
GenProp0283	YES	NO
GenProp1297	YES	PARTIAL
GenProp1326	YES	PARTIAL
GenProp1501	PARTIAL	NO
GenProp1402	YES	PARTIAL
GenProp1299	YES	PARTIAL
GenProp1463	YES	PARTIAL
GenProp1568	YES	NO
GenProp1374	YES	PARTIAL
GenProp1556	YES	PARTIAL
GenProp1566	YES	PARTIAL
GenProp0938	YES	PARTIAL
GenProp0052	NO	PARTIAL
GenProp0059	NO	YES
GenProp0735	NO	YES
GenProp1074	NO	YES
GenProp0961	NO	YES
GenProp0820	PARTIAL	YES
GenProp0323	PARTIAL	YES
GenProp1120	YES	NO
GenProp1133	YES	NO
GenProp1189	YES	NO
GenProp0176	YES	NO
GenProp1094	NO	PARTIAL