notebook.community

Edit and run

Parsing rare list

https://globalgenes.org/rarelist





In [3]:



    


# Fetch HTML using requests lib and feed to bs4
import requests

# note their SSL certificate is not verified. Be careful!
result = requests.get("https://globalgenes.org/rarelist", verify=False)

from bs4 import BeautifulSoup
from bs4 import NavigableString
soup = BeautifulSoup(result.content, 'html.parser')



    


















    






/usr/local/lib/python3.6/site-packages/urllib3/connectionpool.py:858: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
  InsecureRequestWarning)

















In [4]:



    


# check
soup.title



    


















    
Out[4]:








<title>Rare Disease List</title>

















In [5]:



    


# write formatted html to file
# (not used: this is just a useful side effect for exploration)
f=open('rarelist.html','w')
f.write(soup.prettify())
f.close()



    











In [6]:



    


# use bs4 to extract names from HTML

names = []  ## all disease names found
name2url = {}  ## mapping of names to URLs

h5s = soup.find_all("h5")
for h5 in h5s:
    ul = h5.find_next_sibling('ul')
    for li in ul.findAll('li'):
        if len(li.contents) == 0:
            continue
        n = li.contents[0]
        if n is None:
            print('BAD: {}'.format(li))
            continue
        if not isinstance(n, NavigableString):
            n = n.contents[0]
            if li.select('a'):
                url = li.a['href']
            
                name2url[n] = url
        names.append(n)
        
# show the first 20 for sanity checking
names[0:20]



    


















    
Out[6]:








['Aagenaes syndrome',
 'Aarskog syndrome',
 'Aase Smith syndrome',
 'ABCD syndrome',
 'Abderhalden Kaufmann Lignac syndrome',
 'Abdominal aortic aneurysm',
 'Abdominal chemodectomas with cutaneous angiolipomas',
 'Abdominal cystic lymphangioma',
 'Abdominal obesity metabolic syndrome',
 'Aberrant subclavian artery',
 'Abetalipoproteinemia',
 'Abidi X-linked mental retardation syndrome',
 'Ablepharon macrostomia syndrome',
 "Abrikosov's tumor",
 'Abruzzo Erickson syndrome',
 'Absence of fingerprints congenital milia',
 'Absence of gluteal muscle',
 'Absence of septum pellucidum',
 'Absence of Tibia',
 'Absence of tibia with polydactyly']

















In [7]:



    


## sanity check URL mapping
list(name2url.items())[0:10]



    


















    
Out[7]:








[('Acute disseminated encephalomyelitis', 'http://ulf.org/'),
 ('Acute hemorrhagic leukoencephalitis', 'http://ulf.org/'),
 ('Adrenoleukodystrophy X-linked', 'http://ulf.org/'),
 ('Adrenomyeloneuropathy', 'http://ulf.org/'),
 ('Aicardi-Goutieres syndrome', 'http://ulf.org/'),
 ('Alexander disease', 'http://ulf.org/'),
 ('Alkaptonuria', 'http://www.alkaptonuria.info/'),
 ('Alpers syndrome',
  'http://www.umdf.org/site/c.8qKOJ0MvF7LUG/b.7929671/k.BDF0/Home.htm'),
 ('Alzheimer disease familial', 'http://www.mitoaction.org/'),
 ('Alzheimer disease type 1', 'http://www.mitoaction.org/')]

















In [8]:



    


import csv
with open('rare-list.tsv', 'w', newline='') as csvfile:
    spamwriter = csv.writer(csvfile, delimiter='\t')
    for n in names:
        spamwriter.writerow([n, name2url.get(n)])



    











In [9]:



    


## use ontobio lib for fetching ontologies and lexical mapping
from ontobio import OntologyFactory



    


















    






/usr/local/lib/python3.6/site-packages/cachier/mongo_core.py:24: UserWarning: Cachier warning: pymongo was not found. MongoDB cores will not work.
  "Cachier warning: pymongo was not found. MongoDB cores will not work.")

















In [10]:



    


ofa = OntologyFactory()



    











In [11]:



    


hp = ofa.create('obo:hp')



    











In [12]:



    


mondo = ofa.create('obo:mondo')



    











In [13]:



    


from ontobio.lexmap import LexicalMapEngine
lexmap = LexicalMapEngine()



    











In [14]:



    


# Quick hack to make a degenerate 'ontology' from the list of names
from ontobio import Ontology

def ont_from_names(names):
    ont = Ontology(id='rare')
    for n in names:
        ## use name as ID
        ont.add_node(n, n)
    return ont
        
rare = ont_from_names(names)
rare



    


















    
Out[14]:








rare handle: None meta: None

















In [15]:



    


## quick inspection
rare.nodes()[0:10]



    


















    
Out[15]:








['Aagenaes syndrome',
 'Aarskog syndrome',
 'Aase Smith syndrome',
 'ABCD syndrome',
 'Abderhalden Kaufmann Lignac syndrome',
 'Abdominal aortic aneurysm',
 'Abdominal chemodectomas with cutaneous angiolipomas',
 'Abdominal cystic lymphangioma',
 'Abdominal obesity metabolic syndrome',
 'Aberrant subclavian artery']

















In [16]:



    


## index the 3 ontologies
lexmap.index_ontology(hp)
lexmap.index_ontology(mondo)
lexmap.index_ontology(rare)



    


















    






WARNING:root:Incomplete syn: HP:0000991 "" hasRelatedSynonym None [] 1.0
WARNING:root:Incomplete syn: HP:0012377 "" hasRelatedSynonym None [] 1.0
WARNING:root:Incomplete syn: HP:0000510 "" hasRelatedSynonym None [] 1.0
WARNING:root:Ignoring suspicous synonym: UBERON:0002722 "4" hasBroadSynonym None ['http://uri.neuinfo.org/nif/nifstd/birnlex_1488', 'NIFSTD:NeuroNames_abbrevSource'] 1.0
WARNING:root:Ignoring suspicous synonym: UBERON:0001715 "3" hasBroadSynonym None ['http://uri.neuinfo.org/nif/nifstd/birnlex_1240', 'NIFSTD:NeuroNames_abbrevSource'] 1.0

















In [17]:



    


## CONFIGURE
## we will map R to mondo and hp separately
lexmap.ontology_pairs = [(rare.id, mondo.id), (rare.id, hp.id)]



    











In [18]:



    


# align
g = lexmap.get_xref_graph()



    











In [19]:



    


# get a dataframe from the mapping graph
df=lexmap.as_dataframe(g)
df



    


















    
Out[19]:











  
    

      
      left
      left_label
      right
      right_label
      left_match_type
      right_match_type
      left_match_val
      right_match_val
      score
      left_simscore
      ...
      conditional_pr_equiv
      pr_subClassOf
      pr_superClassOf
      pr_equivalentTo
      pr_other
      left_novel
      right_novel
      left_consistent
      right_consistent
      equiv_clique_size
    

  
  
    

      3287
      11-beta-hydroxylase deficiency
      11-beta-hydroxylase deficiency
      MONDO:0008729
      congenital adrenal hyperplasia due to 11-beta-...
      label
      hasRelatedSynonym
      11-beta-hydroxylase deficiency
      11-Beta-Hydroxylase Deficiency
      50.0
      1.000000
      ...
      1.000000
      0.061581
      0.061581
      0.799654
      0.077184
      True
      True
      False
      False
      7
    

    

      2199
      15q13.3 microdeletion syndrome
      15q13.3 microdeletion syndrome
      MONDO:0012774
      chromosome 15q13.3 microdeletion syndrome
      label
      hasExactSynonym
      15q13.3 microdeletion syndrome
      15q13.3 microdeletion syndrome
      90.0
      1.000000
      ...
      1.000000
      0.029969
      0.029969
      0.918763
      0.021299
      True
      True
      False
      False
      6
    

    

      3339
      17-alpha-hydroxylase deficiency
      17-alpha-hydroxylase deficiency
      MONDO:0008730
      congenital adrenal hyperplasia due to 17-alpha...
      label
      hasRelatedSynonym
      17-alpha-hydroxylase deficiency
      17-Alpha-Hydroxylase Deficiency
      50.0
      1.000000
      ...
      1.000000
      0.061581
      0.061581
      0.799654
      0.077184
      True
      True
      False
      False
      5
    

    

      3481
      17-beta hydroxysteroid dehydrogenase 3 deficiency
      17-beta hydroxysteroid dehydrogenase 3 deficiency
      MONDO:0009916
      46,XY disorder of sex development due to 17-be...
      label
      hasExactSynonym
      17-beta hydroxysteroid dehydrogenase 3 deficiency
      17-beta-hydroxysteroid dehydrogenase 3 deficiency
      58.0
      1.000000
      ...
      1.000000
      0.205965
      0.205965
      0.392394
      0.195675
      True
      True
      False
      False
      7
    

    

      2592
      17q21.31 microdeletion syndrome
      17q21.31 microdeletion syndrome
      MONDO:0012496
      Koolen de Vries syndrome
      label
      hasExactSynonym
      17q21.31 microdeletion syndrome
      17q21.31 microdeletion syndrome
      90.0
      1.000000
      ...
      0.473684
      0.168017
      0.055554
      0.749591
      0.026839
      True
      True
      False
      False
      8
    

    

      2593
      17q21.31 microdeletion syndrome
      17q21.31 microdeletion syndrome
      MONDO:0018216
      17q21.31 microdeletion syndrome
      label
      label
      17q21.31 microdeletion syndrome
      17q21.31 microdeletion syndrome
      100.0
      1.000000
      ...
      0.526316
      0.051671
      0.108232
      0.824734
      0.015363
      True
      True
      False
      False
      8
    

    

      2987
      18 Hydroxylase deficiency
      18 Hydroxylase deficiency
      MONDO:0008751
      Corticosterone methyloxidase type 1 deficiency
      label
      hasRelatedSynonym
      18 Hydroxylase deficiency
      18-Hydroxylase Deficiency
      32.0
      1.000000
      ...
      0.355556
      0.232996
      0.289482
      0.283582
      0.193941
      True
      True
      False
      False
      6
    

    

      2986
      18 Hydroxylase deficiency
      18 Hydroxylase deficiency
      MONDO:0020489
      familial hyperreninemic hypoaldosteronism type 1
      label
      hasExactSynonym
      18 Hydroxylase deficiency
      18-hydroxylase deficiency
      58.0
      1.000000
      ...
      0.644444
      0.292046
      0.210145
      0.309167
      0.188643
      True
      True
      False
      False
      6
    

    

      1960
      1q21.1 microdeletion syndrome
      1q21.1 microdeletion syndrome
      MONDO:0012914
      chromosome 1q21.1 deletion syndrome
      label
      hasExactSynonym
      1q21.1 microdeletion syndrome
      1q21.1 microdeletion syndrome
      90.0
      1.000000
      ...
      1.000000
      0.030109
      0.030109
      0.923042
      0.016740
      True
      True
      False
      False
      6
    

    

      1428
      2 4-Dienoyl-CoA reductase deficiency
      2 4-Dienoyl-CoA reductase deficiency
      MONDO:0014464
      progressive encephalopathy with leukodystrophy...
      label
      hasExactSynonym
      2 4-Dienoyl-CoA reductase deficiency
      2,4-dienoyl-CoA reductase deficiency
      58.0
      1.000000
      ...
      1.000000
      0.200803
      0.200803
      0.382559
      0.215835
      True
      True
      False
      False
      5
    

    

      4514
      2-Hydroxyglutaric aciduria
      2-Hydroxyglutaric aciduria
      MONDO:0016001
      2-hydroxyglutaric aciduria
      label
      label
      2-Hydroxyglutaric aciduria
      2-hydroxyglutaric aciduria
      100.0
      1.000000
      ...
      1.000000
      0.028758
      0.028758
      0.925963
      0.016522
      True
      True
      False
      False
      7
    

    

      1888
      2-methyl-3-hydroxybutyric aciduria
      2-methyl-3-hydroxybutyric aciduria
      MONDO:0010327
      HSD10 disease
      label
      hasExactSynonym
      2-methyl-3-hydroxybutyric aciduria
      2-methyl-3-hydroxybutyric aciduria
      90.0
      1.000000
      ...
      1.000000
      0.029969
      0.029969
      0.918763
      0.021299
      True
      True
      False
      False
      5
    

    

      1202
      2-methylbutyryl-CoA dehydrogenase deficiency
      2-methylbutyryl-CoA dehydrogenase deficiency
      MONDO:0012392
      2-methylbutyryl-CoA dehydrogenase deficiency
      label
      label
      2-methylbutyryl-CoA dehydrogenase deficiency
      2-methylbutyryl-CoA dehydrogenase deficiency
      100.0
      1.000000
      ...
      1.000000
      0.028795
      0.028795
      0.927169
      0.015241
      True
      True
      False
      False
      7
    

    

      3288
      21-hydroxylase deficiency
      21-hydroxylase deficiency
      MONDO:0008728
      classic congenital adrenal hyperplasia due to ...
      label
      hasRelatedSynonym
      21-hydroxylase deficiency
      21-Hydroxylase Deficiency
      50.0
      1.000000
      ...
      1.000000
      0.061581
      0.061581
      0.799654
      0.077184
      True
      True
      False
      False
      5
    

    

      3507
      22q11.2 deletion syndrome
      22q11.2 deletion syndrome
      MONDO:0008644
      velocardiofacial syndrome
      label
      hasExactSynonym
      22q11.2 deletion syndrome
      deletion 22q11.2 syndrome
      58.0
      1.000000
      ...
      0.134754
      0.179472
      0.287938
      0.282070
      0.250520
      True
      True
      False
      False
      41
    

    

      2964
      22q11.2 deletion syndrome
      22q11.2 deletion syndrome
      MONDO:0018923
      22q11.2 deletion syndrome
      label
      label
      22q11.2 deletion syndrome
      22q11.2 deletion syndrome
      100.0
      0.166667
      ...
      0.115075
      0.092223
      0.035954
      0.841716
      0.030107
      True
      True
      False
      False
      41
    

    

      1721
      3 methylglutaconic aciduria type I
      3 methylglutaconic aciduria type I
      MONDO:0009610
      3-methylglutaconic aciduria type 1
      label
      label
      3 methylglutaconic aciduria type I
      3-methylglutaconic aciduria type 1
      64.0
      1.000000
      ...
      1.000000
      0.200803
      0.200803
      0.382559
      0.215835
      True
      True
      False
      False
      9
    

    

      1720
      3 methylglutaconic aciduria type IV
      3 methylglutaconic aciduria type IV
      MONDO:0009611
      3-methylglutaconic aciduria type 4
      label
      label
      3 methylglutaconic aciduria type IV
      3-methylglutaconic aciduria type 4
      64.0
      1.000000
      ...
      1.000000
      0.200803
      0.200803
      0.382559
      0.215835
      True
      True
      False
      False
      8
    

    

      2580
      3 methylglutaconic aciduria type V
      3 methylglutaconic aciduria type V
      MONDO:0012435
      3-methylglutaconic aciduria type 5
      label
      label
      3 methylglutaconic aciduria type V
      3-methylglutaconic aciduria type 5
      64.0
      1.000000
      ...
      1.000000
      0.198342
      0.198342
      0.377872
      0.225444
      True
      True
      False
      False
      7
    

    

      1877
      3-Hydroxyisobutyric aciduria
      3-Hydroxyisobutyric aciduria
      MONDO:0009371
      3-hydroxyisobutyric aciduria
      label
      label
      3-Hydroxyisobutyric aciduria
      3-hydroxyisobutyric aciduria
      100.0
      1.000000
      ...
      1.000000
      0.028795
      0.028795
      0.927169
      0.015241
      True
      True
      False
      False
      8
    

    

      3289
      3-beta-hydroxysteroid dehydrogenase deficiency
      3-beta-hydroxysteroid dehydrogenase deficiency
      MONDO:0008727
      congenital adrenal hyperplasia due to 3-beta-h...
      label
      hasRelatedSynonym
      3-beta-hydroxysteroid dehydrogenase deficiency
      3-Beta-Hydroxysteroid Dehydrogenase Deficiency
      50.0
      1.000000
      ...
      1.000000
      0.061581
      0.061581
      0.799654
      0.077184
      True
      True
      False
      False
      5
    

    

      3670
      3-methylglutaconic aciduria type III
      3-methylglutaconic aciduria type III
      MONDO:0009787
      3-methylglutaconic aciduria type 3
      label
      hasExactSynonym
      3-methylglutaconic aciduria type III
      3-methylglutaconic aciduria type III
      90.0
      1.000000
      ...
      1.000000
      0.029969
      0.029969
      0.918763
      0.021299
      True
      True
      False
      False
      8
    

    

      755
      4-hydroxyphenylacetic aciduria
      4-hydroxyphenylacetic aciduria
      HP:0003607
      4-Hydroxyphenylacetic aciduria
      label
      label
      4-hydroxyphenylacetic aciduria
      4-Hydroxyphenylacetic aciduria
      100.0
      1.000000
      ...
      1.000000
      0.028891
      0.028891
      0.930268
      0.011949
      True
      True
      False
      False
      2
    

    

      3680
      46 XX testicular disorder of sex development
      46 XX testicular disorder of sex development
      MONDO:0010766
      46,XX testicular disorder of sex development
      label
      label
      46 XX testicular disorder of sex development
      46,XX testicular disorder of sex development
      64.0
      1.000000
      ...
      1.000000
      0.198342
      0.198342
      0.377872
      0.225444
      True
      True
      False
      False
      6
    

    

      3136
      47 XXX syndrome
      47 XXX syndrome
      MONDO:0018066
      trisomy X
      label
      hasExactSynonym
      47 XXX syndrome
      47,XXX syndrome
      58.0
      1.000000
      ...
      1.000000
      0.226493
      0.185437
      0.392394
      0.195675
      True
      True
      False
      False
      5
    

    

      3166
      47 XYY syndrome
      47 XYY syndrome
      MONDO:0019339
      47,XYY syndrome
      label
      label
      47 XYY syndrome
      47,XYY syndrome
      64.0
      1.000000
      ...
      1.000000
      0.226493
      0.185437
      0.392394
      0.195675
      True
      True
      False
      False
      5
    

    

      4164
      49 XXXXX syndrome
      49 XXXXX syndrome
      MONDO:0015228
      pentasomy X
      label
      hasExactSynonym
      49 XXXXX syndrome
      49,XXXXX syndrome
      58.0
      1.000000
      ...
      1.000000
      0.205965
      0.205965
      0.392394
      0.195675
      True
      True
      False
      False
      5
    

    

      4531
      49 XXXXY syndrome
      49 XXXXY syndrome
      MONDO:0019929
      49,XXXXY syndrome
      label
      label
      49 XXXXY syndrome
      49,XXXXY syndrome
      64.0
      1.000000
      ...
      1.000000
      0.219001
      0.179303
      0.379414
      0.222282
      True
      True
      False
      False
      6
    

    

      710
      5-oxoprolinase deficiency
      5-oxoprolinase deficiency
      MONDO:0009825
      5-oxoprolinase deficiency (disease)
      label
      hasExactSynonym
      5-oxoprolinase deficiency
      5-oxoprolinase deficiency
      90.0
      1.000000
      ...
      1.000000
      0.030109
      0.030109
      0.923042
      0.016740
      True
      True
      False
      False
      7
    

    

      709
      5-oxoprolinase deficiency
      5-oxoprolinase deficiency
      HP:0040142
      5-oxoprolinase deficiency
      label
      label
      5-oxoprolinase deficiency
      5-oxoprolinase deficiency
      100.0
      1.000000
      ...
      1.000000
      0.028891
      0.028891
      0.930268
      0.011949
      True
      True
      False
      False
      7
    

    

      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    

    

      2067
      Wrinkly skin syndrome
      Wrinkly skin syndrome
      MONDO:0010208
      Wrinkly skin syndrome
      label
      label
      Wrinkly skin syndrome
      Wrinkly skin syndrome
      100.0
      1.000000
      ...
      1.000000
      0.028758
      0.028758
      0.925963
      0.016522
      True
      True
      False
      False
      7
    

    

      2105
      X-linked adrenal hypoplasia congenita
      X-linked adrenal hypoplasia congenita
      MONDO:0010264
      X-linked adrenal hypoplasia congenita
      label
      label
      X-linked adrenal hypoplasia congenita
      X-linked adrenal hypoplasia congenita
      100.0
      1.000000
      ...
      1.000000
      0.028738
      0.028738
      0.925323
      0.017201
      True
      True
      False
      False
      7
    

    

      1552
      X-linked hypohidrotic ectodermal dysplasia
      X-linked hypohidrotic ectodermal dysplasia
      MONDO:0010585
      X-linked hypohidrotic ectodermal dysplasia
      label
      label
      X-linked hypohidrotic ectodermal dysplasia
      X-linked hypohidrotic ectodermal dysplasia
      100.0
      1.000000
      ...
      1.000000
      0.028738
      0.028738
      0.925323
      0.017201
      True
      True
      False
      False
      4
    

    

      3900
      X-linked ichthyosis
      X-linked ichthyosis
      MONDO:0010622
      recessive X-linked ichthyosis
      label
      hasExactSynonym
      X-linked ichthyosis
      X-linked ichthyosis
      90.0
      1.000000
      ...
      1.000000
      0.029886
      0.029886
      0.916224
      0.024003
      True
      True
      False
      False
      7
    

    

      1968
      X-linked severe combined immunodeficiency
      X-linked severe combined immunodeficiency
      MONDO:0010315
      gamma chain deficiency
      label
      hasExactSynonym
      X-linked severe combined immunodeficiency
      X-Linked Severe Combined Immunodeficiency
      90.0
      1.000000
      ...
      1.000000
      0.029969
      0.029969
      0.918763
      0.021299
      True
      True
      False
      False
      8
    

    

      2543
      XFE progeroid syndrome
      XFE progeroid syndrome
      MONDO:0012590
      XFE progeroid syndrome
      label
      label
      XFE progeroid syndrome
      XFE progeroid syndrome
      100.0
      1.000000
      ...
      1.000000
      0.028891
      0.028891
      0.930268
      0.011949
      True
      True
      False
      False
      7
    

    

      3037
      XK aprosencephaly
      XK aprosencephaly
      MONDO:0008811
      XK aprosencephaly
      label
      label
      XK aprosencephaly
      XK aprosencephaly
      100.0
      1.000000
      ...
      1.000000
      0.028891
      0.028891
      0.930268
      0.011949
      True
      True
      False
      False
      8
    

    

      2070
      Xanthinuria type 1
      Xanthinuria type 1
      MONDO:0010209
      xanthinuria type I
      label
      label
      Xanthinuria type 1
      xanthinuria type I
      64.0
      1.000000
      ...
      1.000000
      0.205965
      0.205965
      0.392394
      0.195675
      True
      True
      False
      False
      5
    

    

      2414
      Xanthinuria type 2
      Xanthinuria type 2
      MONDO:0011346
      xanthinuria type II
      label
      label
      Xanthinuria type 2
      xanthinuria type II
      64.0
      1.000000
      ...
      1.000000
      0.205965
      0.205965
      0.392394
      0.195675
      True
      True
      False
      False
      6
    

    

      1509
      Xanthogranulomatous cholecystitis
      Xanthogranulomatous cholecystitis
      MONDO:0004875
      xanthogranulomatous cholecystitis
      label
      label
      Xanthogranulomatous cholecystitis
      xanthogranulomatous cholecystitis
      100.0
      1.000000
      ...
      1.000000
      0.028795
      0.028795
      0.927169
      0.015241
      True
      True
      False
      False
      8
    

    

      2867
      Xeroderma pigmentosum
      Xeroderma pigmentosum
      MONDO:0019600
      xeroderma pigmentosum
      label
      label
      Xeroderma pigmentosum
      xeroderma pigmentosum
      100.0
      1.000000
      ...
      1.000000
      0.028758
      0.028758
      0.925963
      0.016522
      True
      True
      False
      False
      8
    

    

      2077
      Xeroderma pigmentosum variant type
      Xeroderma pigmentosum variant type
      MONDO:0010214
      xeroderma pigmentosum variant type
      label
      label
      Xeroderma pigmentosum variant type
      xeroderma pigmentosum variant type
      100.0
      1.000000
      ...
      1.000000
      0.028758
      0.028758
      0.925963
      0.016522
      True
      True
      False
      False
      8
    

    

      3151
      Yaws
      Yaws
      MONDO:0006019
      yaws
      label
      label
      Yaws
      yaws
      100.0
      1.000000
      ...
      1.000000
      0.051830
      0.051830
      0.874531
      0.021809
      True
      True
      False
      False
      10
    

    

      3080
      Yellow fever
      Yellow fever
      MONDO:0020502
      yellow fever
      label
      label
      Yellow fever
      yellow fever
      100.0
      1.000000
      ...
      1.000000
      0.028891
      0.028891
      0.930268
      0.011949
      True
      True
      False
      False
      8
    

    

      4539
      Yellow nail syndrome
      Yellow nail syndrome
      MONDO:0007921
      yellow nail syndrome
      label
      label
      Yellow nail syndrome
      yellow nail syndrome
      100.0
      1.000000
      ...
      1.000000
      0.028891
      0.028891
      0.930268
      0.011949
      True
      True
      False
      False
      9
    

    

      2555
      Yemenite deaf-blind hypopigmentation syndrome
      Yemenite deaf-blind hypopigmentation syndrome
      MONDO:0011133
      Deaf blind hypopigmentation syndrome, Yemenite...
      label
      hasExactSynonym
      Yemenite deaf-blind hypopigmentation syndrome
      Yemenite deaf-blind hypopigmentation syndrome
      90.0
      1.000000
      ...
      1.000000
      0.030109
      0.030109
      0.923042
      0.016740
      True
      True
      False
      False
      6
    

    

      4262
      Yolk sac tumor
      Yolk sac tumor
      MONDO:0005744
      yolk sac tumor
      label
      label
      Yolk sac tumor
      yolk sac tumor
      100.0
      1.000000
      ...
      1.000000
      0.028758
      0.028758
      0.925963
      0.016522
      True
      True
      False
      False
      7
    

    

      3775
      Yorifuji Okuno syndrome
      Yorifuji Okuno syndrome
      MONDO:0010802
      pancreatic hypoplasia-diabetes-congenital hear...
      label
      hasExactSynonym
      Yorifuji Okuno syndrome
      Yorifuji-Okuno syndrome
      58.0
      1.000000
      ...
      1.000000
      0.205965
      0.205965
      0.392394
      0.195675
      True
      True
      False
      False
      5
    

    

      4330
      Young Hughes syndrome
      Young Hughes syndrome
      MONDO:0017614
      X-linked intellectual disability-hypogonadism-...
      label
      hasExactSynonym
      Young Hughes syndrome
      Young-Hughes syndrome
      58.0
      1.000000
      ...
      1.000000
      0.200803
      0.200803
      0.382559
      0.215835
      True
      True
      False
      False
      4
    

    

      2384
      Young Simpson syndrome
      Young Simpson syndrome
      MONDO:0011365
      blepharophimosis-intellectual disability syndr...
      label
      hasRelatedSynonym
      Young Simpson syndrome
      Young-Simpson Syndrome
      32.0
      1.000000
      ...
      1.000000
      0.200803
      0.200803
      0.382559
      0.215835
      True
      True
      False
      False
      7
    

    

      2059
      Young syndrome
      Young syndrome
      MONDO:0010220
      young syndrome
      label
      label
      Young syndrome
      young syndrome
      100.0
      1.000000
      ...
      1.000000
      0.028891
      0.028891
      0.930268
      0.011949
      True
      True
      False
      False
      7
    

    

      2892
      Yunis Varon syndrome
      Yunis Varon syndrome
      MONDO:0008995
      Yunis-Varon syndrome
      label
      label
      Yunis Varon syndrome
      Yunis-Varon syndrome
      64.0
      1.000000
      ...
      1.000000
      0.062922
      0.062922
      0.817066
      0.057090
      True
      True
      False
      False
      7
    

    

      1473
      Zechi Ceide syndrome
      Zechi Ceide syndrome
      MONDO:0013036
      Zechi-Ceide syndrome
      label
      label
      Zechi Ceide syndrome
      Zechi-Ceide syndrome
      64.0
      1.000000
      ...
      1.000000
      0.205965
      0.205965
      0.392394
      0.195675
      True
      True
      False
      False
      6
    

    

      2866
      Zellweger syndrome
      Zellweger syndrome
      MONDO:0019609
      Zellweger syndrome
      label
      label
      Zellweger syndrome
      Zellweger syndrome
      100.0
      1.000000
      ...
      1.000000
      0.028758
      0.028758
      0.925963
      0.016522
      True
      True
      False
      False
      6
    

    

      657
      Zollinger-Ellison syndrome
      Zollinger-Ellison syndrome
      MONDO:0006020
      Zollinger-Ellison syndrome (disease)
      label
      hasExactSynonym
      Zollinger-Ellison syndrome
      Zollinger-Ellison Syndrome
      90.0
      1.000000
      ...
      0.473684
      0.075251
      0.062185
      0.839062
      0.023503
      True
      True
      False
      False
      11
    

    

      655
      Zollinger-Ellison syndrome
      Zollinger-Ellison syndrome
      HP:0002044
      Zollinger-Ellison syndrome
      label
      label
      Zollinger-Ellison syndrome
      Zollinger-Ellison syndrome
      100.0
      1.000000
      ...
      1.000000
      0.028891
      0.028891
      0.930268
      0.011949
      True
      True
      False
      False
      11
    

    

      656
      Zollinger-Ellison syndrome
      Zollinger-Ellison syndrome
      MONDO:0019610
      Zollinger-Ellison syndrome
      label
      label
      Zollinger-Ellison syndrome
      Zollinger-Ellison syndrome
      100.0
      1.000000
      ...
      0.526316
      0.055295
      0.045694
      0.882570
      0.016441
      True
      True
      False
      False
      11
    

    

      3377
      Zori Stalker Williams syndrome
      Zori Stalker Williams syndrome
      MONDO:0010883
      pectus excavatum-macrocephaly-dysplastic nails...
      label
      hasExactSynonym
      Zori Stalker Williams syndrome
      Zori-Stalker-Williams syndrome
      58.0
      1.000000
      ...
      1.000000
      0.205965
      0.205965
      0.392394
      0.195675
      True
      True
      False
      False
      5
    

    

      2061
      Zunich neuroectodermal syndrome
      Zunich neuroectodermal syndrome
      MONDO:0010221
      CHIME syndrome
      label
      hasRelatedSynonym
      Zunich neuroectodermal syndrome
      Zunich Neuroectodermal Syndrome
      50.0
      1.000000
      ...
      1.000000
      0.061951
      0.061951
      0.804454
      0.071645
      True
      True
      False
      False
      6
    

    

      3649
      Zygomycosis
      Zygomycosis
      MONDO:0019136
      zygomycosis
      label
      label
      Zygomycosis
      zygomycosis
      100.0
      1.000000
      ...
      1.000000
      0.051830
      0.051830
      0.874531
      0.021809
      True
      True
      False
      False
      9
    

  



4558 rows × 22 columns



















In [20]:



    


## write to file (not used here but can be examined separately)
df.to_csv('rare-matches.tsv', sep="\t", index=False)



    











In [21]:



    


udf = lexmap.unmapped_dataframe(g)



    











In [22]:



    


## unmapped (TODO this includes unmapped from MONDO/HP to R, which we don't care about so much)
udf.to_csv('rare-no-matches.tsv', sep="\t", index=False)
udf



    


















    
Out[22]:











  
    

      
      id
      label
      mapped_equivs
    

  
  
    

      18057
      16p11.2 deletion syndrome
      16p11.2 deletion syndrome
      
    

    

      105646
      2-Methylacetoacetyl CoA thiolase deficiency
      2-Methylacetoacetyl CoA thiolase deficiency
      
    

    

      41905
      2-hydroxyethyl methacrylate sensitization
      2-hydroxyethyl methacrylate sensitization
      
    

    

      29133
      22q11.2 duplication syndrome
      22q11.2 duplication syndrome
      
    

    

      100428
      22q13.3 deletion syndrome
      22q13.3 deletion syndrome
      
    

    

      96122
      2q37 deletion syndrome
      2q37 deletion syndrome
      
    

    

      88482
      3 Methylcrotonyl-CoA carboxylase 1 deficiency
      3 Methylcrotonyl-CoA carboxylase 1 deficiency
      
    

    

      34501
      3 alpha methylcrotonyl-CoA carboxylase 2 defic...
      3 alpha methylcrotonyl-CoA carboxylase 2 defic...
      
    

    

      85670
      3-alpha hydroxyacyl-CoA dehydrogenase deficiency
      3-alpha hydroxyacyl-CoA dehydrogenase deficiency
      
    

    

      77929
      3p deletion syndrome
      3p deletion syndrome
      
    

    

      95095
      46 XX Gonadal dysgenesis epibulbar dermoid
      46 XX Gonadal dysgenesis epibulbar dermoid
      
    

    

      90032
      5-Nucleotidase syndrome
      5-Nucleotidase syndrome
      
    

    

      74374
      6 alpha mercaptopurine sensitivity
      6 alpha mercaptopurine sensitivity
      
    

    

      51486
      ACTH-independent macronodular adrenal hyperplasia
      ACTH-independent macronodular adrenal hyperplasia
      
    

    

      26334
      AIDS Dementia Complex
      AIDS Dementia Complex
      
    

    

      12881
      AIDS dysmorphic syndrome
      AIDS dysmorphic syndrome
      
    

    

      77859
      ALK+ histiocytosis
      ALK+ histiocytosis
      
    

    

      26275
      ALS-like syndrome of encephalomyopathy
      ALS-like syndrome of encephalomyopathy
      
    

    

      60831
      Abderhalden Kaufmann Lignac syndrome
      Abderhalden Kaufmann Lignac syndrome
      
    

    

      10975
      Abdominal chemodectomas with cutaneous angioli...
      Abdominal chemodectomas with cutaneous angioli...
      
    

    

      108580
      Abdominal cystic lymphangioma
      Abdominal cystic lymphangioma
      
    

    

      94496
      Aberrant subclavian artery
      Aberrant subclavian artery
      
    

    

      93116
      Abidi X-linked mental retardation syndrome
      Abidi X-linked mental retardation syndrome
      
    

    

      40555
      Absence of fingerprints congenital milia
      Absence of fingerprints congenital milia
      
    

    

      7562
      Absence of gluteal muscle
      Absence of gluteal muscle
      
    

    

      6259
      Absence of tibia with polydactyly
      Absence of tibia with polydactyly
      
    

    

      75137
      Absent T lymphocytes
      Absent T lymphocytes
      
    

    

      49480
      Absent breasts and nipples
      Absent breasts and nipples
      
    

    

      56640
      Abuse dwarfism syndrome
      Abuse dwarfism syndrome
      
    

    

      8138
      Acanthamoeba infection
      Acanthamoeba infection
      
    

    

      ...
      ...
      ...
      ...
    

    

      25120
      http://www.orpha.net/ORDO/Orphanet_99948
      None
      [MONDO:0008961]
    

    

      21037
      http://www.orpha.net/ORDO/Orphanet_99949
      None
      [MONDO:0011113]
    

    

      17454
      http://www.orpha.net/ORDO/Orphanet_99950
      None
      [MONDO:0011085]
    

    

      20779
      http://www.orpha.net/ORDO/Orphanet_99951
      None
      [MONDO:0011527]
    

    

      70495
      http://www.orpha.net/ORDO/Orphanet_99952
      None
      []
    

    

      94070
      http://www.orpha.net/ORDO/Orphanet_99953
      None
      [MONDO:0011534]
    

    

      82089
      http://www.orpha.net/ORDO/Orphanet_99954
      None
      []
    

    

      106842
      http://www.orpha.net/ORDO/Orphanet_99955
      None
      [MONDO:0011066]
    

    

      99610
      http://www.orpha.net/ORDO/Orphanet_99956
      None
      [MONDO:0011475]
    

    

      10190
      http://www.orpha.net/ORDO/Orphanet_99960
      None
      []
    

    

      100192
      http://www.orpha.net/ORDO/Orphanet_99961
      None
      []
    

    

      30752
      http://www.orpha.net/ORDO/Orphanet_99965
      None
      []
    

    

      51288
      http://www.orpha.net/ORDO/Orphanet_99966
      None
      []
    

    

      24502
      http://www.orpha.net/ORDO/Orphanet_99967
      None
      []
    

    

      102919
      http://www.orpha.net/ORDO/Orphanet_99969
      None
      []
    

    

      79112
      http://www.orpha.net/ORDO/Orphanet_99970
      None
      []
    

    

      17426
      http://www.orpha.net/ORDO/Orphanet_99971
      None
      []
    

    

      15059
      http://www.orpha.net/ORDO/Orphanet_99976
      None
      []
    

    

      65846
      http://www.orpha.net/ORDO/Orphanet_99977
      None
      []
    

    

      6381
      http://www.orpha.net/ORDO/Orphanet_99978
      None
      [MONDO:0003345]
    

    

      3759
      http://www.orpha.net/ORDO/Orphanet_99981
      None
      []
    

    

      3847
      http://www.orpha.net/ORDO/Orphanet_99983
      None
      []
    

    

      85668
      http://www.orpha.net/ORDO/Orphanet_99989
      None
      []
    

    

      4382
      http://www.orpha.net/ORDO/Orphanet_99990
      None
      []
    

    

      45866
      http://www.orpha.net/ORDO/Orphanet_99991
      None
      []
    

    

      21041
      http://www.orpha.net/ORDO/Orphanet_99994
      None
      []
    

    

      65561
      http://www.orpha.net/ORDO/Orphanet_99995
      None
      []
    

    

      43256
      http://www.w3.org/2000/01/rdf-schema#seeAlso
      seeAlso
      
    

    

      21673
      http://www.w3.org/2002/07/owl#Thing
      None
      
    

    

      15400
      http://www.w3.org/2002/07/owl#topObjectProperty
      None
      
    

  



110240 rows × 3 columns



















In [ ]:

Content source: biolink/ontobio

Similar notebooks:

notebook.community | gallery | about