Skip to content

Commit

Permalink
Handle more corner cases with pre-existing mappings
Browse files Browse the repository at this point in the history
  • Loading branch information
@bgyori
bgyori committed Jun 28, 2024
1 parent 30ed57d commit 10d681f
Show file tree
Hide file tree
Showing 3 changed files with 24 additions and 26 deletions.
7 changes: 0 additions & 7 deletions gilda/resources/mesh_ambig_mappings.tsv
View file
Original file line number Diff line number Diff line change
Expand Up @@ -937,8 +937,6 @@ MESH D000070816 Nogo Receptor 1 HGNC 18601 RTN4R
MESH D000071164 Trefoil Factor-2 HGNC 11756 TFF2
MESH D000071165 Trefoil Factor-3 HGNC 11757 TFF3
MESH D000071480 APOBEC-3G Deaminase HGNC 17357 APOBEC3G
MESH D000071698 Latent Autoimmune Diabetes in Adults MESH D000071698 Latent Autoimmune Diabetes in Adults
MESH D000071698 Latent Autoimmune Diabetes in Adults EFO 0009706 latent autoimmune diabetes in adults
MESH D000071837 Fibrillins GO GO:0001527 microfibril
MESH D000072503 Cytochrome P450 Family 46 HGNC 2641 CYP46A1
MESH D000072556 Cholesterol 24-Hydroxylase HGNC 2641 CYP46A1
Expand All @@ -954,8 +952,6 @@ MESH D000077214 Becaplermin HGNC 8800 PDGFB
MESH D000077214 Becaplermin FPLX PDGF_BB PDGF_BB
MESH D000077385 Silybin CHEBI CHEBI:9144 silibinin
MESH D000077740 Procalcitonin HGNC 1437 CALCA
MESH D000077765 Cone Dystrophy MESH D000077765 Cone Dystrophy
MESH D000077765 Cone Dystrophy HP HP:0008020 Cone dystrophy
MESH D000078224 Lenograstim HGNC 2438 CSF3
MESH D000078787 Neuroglobin HGNC 14077 NGB
MESH D000079302 Necroptosis GO GO:0070266 necroptotic process
Expand Down Expand Up @@ -1015,9 +1011,6 @@ MESH D000754 Anemia, Refractory, with Excess of Blasts DOID DOID:0050908 myelody
MESH D000799 Angioedema DOID DOID:0060002 C1 inhibitor deficiency
MESH D000804 Angiotensin II CHEBI CHEBI:2719 Ile(5)-angiotensin II
MESH D000809 Angiotensins CHEBI CHEBI:2719 Ile(5)-angiotensin II
MESH D000848 Anodontia HP HP:0000677 Oligodontia
MESH D000848 Anodontia HP HP:0001592 Selective tooth agenesis
MESH D000848 Anodontia HP HP:0009804 Tooth agenesis
MESH D000970 Antineoplastic Agents CHEBI CHEBI:35610 antineoplastic agent
MESH D000979 alpha-2-Antiplasmin HGNC 9075 SERPINF2
MESH D001081 Apyrase HGNC 3363 ENTPD1
Expand Down
14 changes: 3 additions & 11 deletions gilda/resources/mesh_mappings.tsv
View file
Original file line number Diff line number Diff line change
Expand Up @@ -24999,7 +24999,6 @@ MESH D000071248 Peroxisome Proliferator-Activated Receptor Gamma Coactivator 1-a
MESH D000071256 Uncoupling Protein 1 HGNC 12517 UCP1
MESH D000071257 Emergence Delirium EFO 0009954 post-operative delirium
MESH D000071316 Forkhead Box Protein O3 HGNC 3821 FOXO3
MESH D000071380 Fibromatosis, Plantar MESH D000071380 Fibromatosis, Plantar
MESH D000071396 Aldehyde Dehydrogenase, Mitochondrial HGNC 404 ALDH2
MESH D000071417 Twist-Related Protein 2 HGNC 20670 TWIST2
MESH D000071425 Src Homology 2 Domain-Containing, Transforming Protein 1 HGNC 10840 SHC1
Expand Down Expand Up @@ -25035,6 +25034,7 @@ MESH D000071656 Receptor, Notch3 HGNC 7883 NOTCH3
MESH D000071676 Zinc Finger Protein GLI1 HGNC 4317 GLI1
MESH D000071679 Glycogen Synthase Kinase 3 beta HGNC 4617 GSK3B
MESH D000071681 Tartrate-Resistant Acid Phosphatase HGNC 124 ACP5
MESH D000071698 Latent Autoimmune Diabetes in Adults EFO 0009706 latent autoimmune diabetes in adults
MESH D000071699 Bilateral Vestibulopathy HP HP:0008568 Vestibular areflexia
MESH D000071700 Cone-Rod Dystrophies DOID DOID:0050572 cone-rod dystrophy
MESH D000071716 Regulatory Factor X1 HGNC 9982 RFX1
Expand Down Expand Up @@ -25250,7 +25250,6 @@ MESH D000077157 Sorafenib CHEBI CHEBI:50924 sorafenib
MESH D000077185 Resveratrol CHEBI CHEBI:27881 resveratrol
MESH D000077191 Wortmannin CHEBI CHEBI:52289 wortmannin
MESH D000077192 Adenocarcinoma of Lung DOID DOID:3910 lung adenocarcinoma
MESH D000077195 Squamous Cell Carcinoma of Head and Neck MESH D000077195 Squamous Cell Carcinoma of Head and Neck
MESH D000077203 Sodium-Glucose Transporter 2 Inhibitors CHEBI CHEBI:73273 sodium-glucose transport protein subtype 2 inhibitor
MESH D000077204 Temozolomide CHEBI CHEBI:72564 temozolomide
MESH D000077205 Pioglitazone CHEBI CHEBI:8228 pioglitazone
Expand Down Expand Up @@ -25384,6 +25383,7 @@ MESH D000077734 Gatifloxacin CHEBI CHEBI:5280 gatifloxacin
MESH D000077735 Gemifloxacin CHEBI CHEBI:101853 gemifloxacin
MESH D000077743 Diterpene Alkaloids CHEBI CHEBI:23847 diterpene alkaloid
MESH D000077764 Dronedarone CHEBI CHEBI:50659 dronedarone
MESH D000077765 Cone Dystrophy HP HP:0008020 Cone dystrophy
MESH D000077767 Panobinostat CHEBI CHEBI:85990 panobinostat
MESH D000077768 Ciclopirox CHEBI CHEBI:453011 ciclopirox
MESH D000077769 Rilmenidine CHEBI CHEBI:8862 Rilmenidine
Expand Down Expand Up @@ -25439,7 +25439,6 @@ MESH D000080343 Meibomian Gland Dysfunction HP HP:0025610 Posterior blepharitis
MESH D000080344 Optic Nerve Hypoplasia HP HP:0000609 Optic nerve hypoplasia
MESH D000080345 Familial Exudative Vitreoretinopathies DOID DOID:0050535 exudative vitreoretinopathy
MESH D000080346 Retinal Arterial Macroaneurysm HP HP:0025355 Retinal arterial macroaneurysms
MESH D000080365 Birdshot Chorioretinopathy MESH D000080365 Birdshot Chorioretinopathy
MESH D000080424 Cytokine Release Syndrome HP HP:0033041 Cytokine storm
MESH D000080485 Sudden Unexpected Death in Epilepsy HP HP:0033258 Sudden unexpected death in epilepsy
MESH D000080506 Sialyl Lewis X Antigen CHEBI CHEBI:61711 alpha-Neup5Ac-(2->3)-beta-D-Galp-(1->4)-[alpha-L-Fucp-(1->3)]-D-GlcpNAc
Expand Down Expand Up @@ -25477,7 +25476,6 @@ MESH D000082182 Clonal Hematopoiesis EFO 0010819 clonal hematopoiesis
MESH D000082424 Internet Addiction Disorder EFO 0803368 internet addiction disorder
MESH D000082843 Ovarian Torsion HP HP:0034503 Ovarian torsion
MESH D000082862 Aortic Valve Disease DOID DOID:62 aortic valve disease
MESH D000082882 Bicuspid Aortic Valve Disease MESH D000082882 Bicuspid Aortic Valve Disease
MESH D000082902 Quadricuspid Aortic Valve HP HP:0031655 Quadricuspid aortic valve
MESH D000082903 Aortico-Ventricular Tunnel HP HP:0011627 Aorto-ventricular tunnel
MESH D000083242 Ischemic Stroke HP HP:0002140 Ischemic stroke
Expand Down Expand Up @@ -27044,7 +27042,6 @@ MESH D005182 Flavin-Adenine Dinucleotide CHEBI CHEBI:16238 FAD
MESH D005183 Failure to Thrive HP HP:0001508 Failure to thrive
MESH D005185 Fallopian Tube Neoplasms DOID DOID:1963 fallopian tube carcinoma
MESH D005195 Family Relations EFO 0004424 family relationship
MESH D005203 Farmer's Lung MESH D005203 Farmer's Lung
MESH D005204 Farnesol CHEBI CHEBI:28600 farnesol
MESH D005215 Fasting EFO 0002756 fasting
MESH D005222 Mental Fatigue HP HP:0033630 Brain fog
Expand Down Expand Up @@ -27502,7 +27499,6 @@ MESH D006987 Hypesthesia HP HP:0033748 Hypoesthesia
MESH D006993 Hypnotics and Sedatives CHEBI CHEBI:35717 sedative
MESH D006997 Hypochlorous Acid CHEBI CHEBI:24757 hypochlorous acid
MESH D007004 Hypoglycemic Agents CHEBI CHEBI:35526 hypoglycemic agent
MESH D007007 Hypohidrosis MESH D007007 Hypohidrosis
MESH D007008 Hypokalemia DOID DOID:4500 hypokalemia
MESH D007012 Hypopharyngeal Neoplasms EFO 0002938 hypopharyngeal carcinoma
MESH D007020 Hypoprothrombinemias DOID DOID:2235 prothrombin deficiency
Expand Down Expand Up @@ -27635,7 +27631,6 @@ MESH D007555 Isoxazoles CHEBI CHEBI:55373 isoxazoles
MESH D007559 Ivermectin CHEBI CHEBI:6078 ivermectin
MESH D007567 Jaundice, Neonatal DOID DOID:2383 neonatal jaundice
MESH D007571 Jaw Diseases EFO 0009468 jaw disease
MESH D007572 Jaw Fractures MESH D007572 Jaw Fractures
MESH D007580 Jejunal Neoplasms DOID DOID:13499 jejunal cancer
MESH D007593 Joint Instability HP HP:0001382 Joint hypermobility
MESH D007605 Juvenile Hormones CHEBI CHEBI:24943 juvenile hormone
Expand Down Expand Up @@ -28302,7 +28297,6 @@ MESH D010368 Pectins CHEBI CHEBI:17309 pectin
MESH D010383 Pellagra EFO 0008570 Vitamin B3 deficiency
MESH D010389 Pemoline CHEBI CHEBI:7953 pemoline
MESH D010391 Pemphigoid, Bullous DOID DOID:0080841 pemphigoid
MESH D010392 Pemphigus MESH D010392 Pemphigus
MESH D010394 Penbutolol CHEBI CHEBI:7954 penbutolol
MESH D010396 Penicillamine CHEBI CHEBI:7959 D-penicillamine
MESH D010397 Penicillanic Acid CHEBI CHEBI:37806 penicillanic acid
Expand Down Expand Up @@ -28976,7 +28970,6 @@ MESH D013014 SOS Response, Genetics GO GO:0009432 SOS response
MESH D013015 Sotalol CHEBI CHEBI:63622 sotalol
MESH D013024 Soybean Oil CHEBI CHEBI:166975 soybean oil
MESH D013034 Sparteine CHEBI CHEBI:28827 sparteine
MESH D013036 Spasms, Infantile MESH D013036 Spasms, Infantile
MESH D013049 Spectrin GO GO:0008091 spectrin
MESH D013067 Speech Perception EFO 0004336 speech perception
MESH D013075 Sperm Capacitation GO GO:0048240 sperm capacitation
Expand Down Expand Up @@ -29230,7 +29223,6 @@ MESH D013940 Thymidylate Synthase HGNC 12441 TYMS
MESH D013941 Thymine CHEBI CHEBI:17821 thymine
MESH D013942 Thymine Nucleotides CHEBI CHEBI:27001 thymidine phosphate
MESH D013943 Thymol CHEBI CHEBI:27607 thymol
MESH D013945 Thymoma DOID DOID:4554 type C thymoma
MESH D013952 Thymus Hyperplasia EFO 1001860 thymus hyperplasia
MESH D013953 Thymus Neoplasms EFO 0002626 thymus neoplasm
MESH D013954 Thyroglobulin HGNC 11764 TG
Expand Down Expand Up @@ -29610,6 +29602,7 @@ MESH D015436 Panniculitis, Peritoneal EFO 1001384 Panniculitis, Peritoneal
MESH D015451 Leukemia, Lymphocytic, Chronic, B-Cell DOID DOID:1036 chronic leukemia
MESH D015459 Leukemia-Lymphoma, Adult T-Cell DOID DOID:5602 T-cell adult acute lymphocytic leukemia
MESH D015461 Leukemia, Prolymphocytic, T-Cell DOID DOID:0081042 T-cell prolymphocytic leukemia
MESH D015463 Leukemia, Prolymphocytic GO GO:0048915 posterior lateral line system development
MESH D015464 Leukemia, Myelogenous, Chronic, BCR-ABL Positive DOID DOID:8552 chronic myeloid leukemia
MESH D015467 Leukemia, Neutrophilic, Chronic DOID DOID:0080187 chronic neutrophilic leukemia
MESH D015470 Leukemia, Myeloid, Acute DOID DOID:0070323 childhood acute myeloid leukemia
Expand Down Expand Up @@ -32034,7 +32027,6 @@ MESH D065290 Acute-On-Chronic Liver Failure EFO 0007949 acute-on-chronic liver f
MESH D065427 Factor Xa Inhibitors CHEBI CHEBI:68581 EC 3.4.21.6 (coagulation factor Xa) inhibitor
MESH D065607 Cytochrome P-450 Enzyme Inhibitors CHEBI CHEBI:50183 P450 inhibitor
MESH D065608 Renal Reabsorption GO GO:0070293 renal absorption
MESH D065626 Non-alcoholic Fatty Liver Disease MESH D065626 Non-alcoholic Fatty Liver Disease
MESH D065632 Chikungunya Fever DOID DOID:0050012 chikungunya
MESH D065636 Myotonin-Protein Kinase HGNC 2933 DMPK
MESH D065646 Thyroid Carcinoma, Anaplastic DOID DOID:0080522 thyroid gland anaplastic carcinoma
Expand Down
29 changes: 21 additions & 8 deletions scripts/generate_mesh_mappings.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,12 @@ def get_nonambiguous(maps):
# We see if there are any name-level matches
name_matches = [(me, te) for me, te in maps
if (me.entry_name.lower() if me.entry_name else '')
== (te.entry_name.lower() if te.entry_name else '')]
== (te.entry_name.lower() if te.entry_name else '')
# Corner case where we have multiple MeSH-based terms
# due to an orignal term from e.g., DOID having been
# mapped to MeSH
and me.db != te.db]

# If we still have ambiguity, we print to the user
if not name_matches or len(name_matches) > 1:
return None, maps
Expand Down Expand Up @@ -110,7 +115,11 @@ def resolve_duplicates(mappings):
def dump_mappings(mappings, fname):
with open(fname, 'w') as fh:
for mesh_term, other_term in sorted(mappings, key=lambda x: x[0].id):
fh.write(render_row(mesh_term, other_term) + '\n')
# Corner case where we have multiple MeSH-based terms
# due to an orignal term from e.g., DOID having been
# mapped to MeSH
if other_term.db != 'MESH':
fh.write(render_row(mesh_term, other_term) + '\n')


def get_ambigs_by_db(ambigs):
Expand All @@ -124,9 +133,9 @@ def get_mesh_mappings(ambigs):
mappings_by_mesh_id = defaultdict(dict)
for text, ambig_terms in ambigs.items():
ambigs_by_db = get_ambigs_by_db(ambig_terms)
print('Considering %s' % text)
for term in ambig_terms:
print('%s:%s %s' % (term.db, term.id, term.entry_name))
#print('Considering %s' % text)
#for term in ambig_terms:
# print('%s:%s %s' % (term.db, term.id, term.entry_name))
order = [('FPLX', is_protein),
('HGNC', is_protein),
('CHEBI', is_chemical),
Expand All @@ -140,9 +149,9 @@ def get_mesh_mappings(ambigs):
mappings_by_mesh_id[me.id][(ambigs_by_db[ns][0].db,
ambigs_by_db[ns][0].id)] = \
[me, ambigs_by_db[ns][0]]
print('Adding mapping for %s' % ns)
#print('Adding mapping for %s' % ns)
break
print('--------------')
#print('--------------')
return dict(mappings_by_mesh_id)


Expand Down Expand Up @@ -261,8 +270,12 @@ def manual_go_mappings(terms_by_id_tuple):
mesh_term = terms_by_id_tuple[('MESH', mesh_id)]
other_term = terms_by_id_tuple[other_id]
new_mappings[other_id] = [mesh_term, other_term]
# This is a corner case where something is in Biomappings
# but not in the set of Gilda terms. This can happen
# if a term has been deprecated/replaced in an ontology.
# We ignore these mappings and just keep what we have.
else:
raise ValueError('%s missing' % other_id)
print('%s missing from set of terms' % str(other_id))
new_mappings = mappings[mesh_id]
mappings[mesh_id] = new_mappings
# If we have a negative curation for this MeSH ID, we make sure
Expand Down

0 comments on commit 10d681f

Please sign in to comment.