diff --git a/scripts/generate_vo_mesh_mappings.py b/scripts/generate_vo_mesh_mappings.py index 650eb8ee..fedc79e5 100644 --- a/scripts/generate_vo_mesh_mappings.py +++ b/scripts/generate_vo_mesh_mappings.py @@ -5,6 +5,8 @@ import bioontologies import gilda import pyobo +import pyobo.gilda_utils +from bioontologies.obograph import Node from tqdm import tqdm from biomappings import PredictionTuple @@ -14,39 +16,38 @@ def main(): """Generate mappings from between VO and MeSH.""" + mesh_grounder = pyobo.gilda_utils.get_grounder("mesh") provenance = get_script_url(__file__) - graph = ( - bioontologies.get_obograph_by_prefix( - "vo", check=False, json_path="/Users/cthoyt/Desktop/vo.json" - ) - .guess("vo") - .standardize() - ) + graph = bioontologies.get_obograph_by_prefix("vo", check=False).guess("vo").standardize() rows = [] extracted_mesh = 0 for node in tqdm(graph.nodes, unit="node", unit_scale=True): - if not node.lbl or node.prefix != "vo": + if not node.name or node.prefix != "vo": continue if node.meta: found_mesh = False - for p in node.meta.basicPropertyValues or []: - if p.pred_prefix == "rdfs" and p.pred_identifier == "seeAlso": - values = [value.strip().replace(" ", "") for value in p.val.strip().split(";")] + for p in node.meta.properties or []: + if not p.predicate: + continue + if p.predicate.curie == "rdfs:seeAlso": + values = [ + value.strip().replace(" ", "") for value in p.value_raw.strip().split(";") + ] # print(node.luid, values) for value in values: - # TODO this is place to extract oher mapping types + # TODO this is place to extract other mapping types if not value.lower().startswith("mesh:"): continue mesh_id = value.split(":", 1)[1].strip() mesh_name = pyobo.get_name("mesh", mesh_id) if not mesh_name: - tqdm.write(f"No mesh name for vo:{node.luid} mapped to mesh:{mesh_id}") + tqdm.write(f"No mesh name for vo:{node.name} mapped to mesh:{mesh_id}") continue rows.append( PredictionTuple( - "vo", - node.luid, - node.lbl, + node.prefix, + node.identifier, + node.name, "skos:exactMatch", "mesh", mesh_id, @@ -61,41 +62,39 @@ def main(): if found_mesh: continue - _ground(node, rows, provenance) + _ground(mesh_grounder, node, rows, provenance) append_prediction_tuples(rows) - print(f"extracted {extracted_mesh} mesh mappings. should be abount 65") + print(f"extracted {extracted_mesh} mesh mappings. should be about 65") -def _ground(node, rows, provenance): - texts = [node.lbl] +def _ground(grounder: gilda.Grounder, node: Node, rows, provenance): + texts = [node.name] # VO doesn't store its synonyms using standard predicates, # so look in IAO_0000118 (alternate label) or IAO_0000116 (editor note) # with "synonym: " as the string prefix if node.meta: - for p in node.meta.basicPropertyValues or []: - if p.pred_prefix == "iao" and p.pred_identifier == "0000118": - texts.append(p.val) - if ( - p.pred_prefix == "iao" - and p.pred_identifier == "0000116" - and p.val.startswith("synonym:") - ): - texts.append(p.val.removeprefix("synonym:").strip()) + for p in node.meta.properties or []: + if not p.predicate: + continue + if p.predicate.curie == "iao:0000118": + texts.append(p.value_raw) + elif p.predicate.curie == "iao:0000116" and p.value_raw.startswith("synonym:"): + texts.append(p.value_raw.removeprefix("synonym:").strip()) - for text in [node.lbl, *(s.val for s in node.synonyms)]: - for scored_match in gilda.ground(text, namespaces=["MESH"]): + for text in [node.name, *(s.value for s in node.synonyms)]: + for scored_match in grounder.ground(text): rows.append( PredictionTuple( - "vo", - node.luid, - node.lbl, + node.prefix, + node.identifier, + node.name, "skos:exactMatch", scored_match.term.db.lower(), scored_match.term.id, scored_match.term.entry_name, "semapv:LexicalMatching", - scored_match.score, + round(scored_match.score, 2), provenance, ) ) diff --git a/src/biomappings/resources/incorrect.tsv b/src/biomappings/resources/incorrect.tsv index 300ab736..593fd316 100644 --- a/src/biomappings/resources/incorrect.tsv +++ b/src/biomappings/resources/incorrect.tsv @@ -1406,6 +1406,7 @@ uberon UBERON:0012245 silk skos:exactMatch bto BTO:0002854 corn silk semapv:Manu uberon UBERON:0022469 primary olfactory cortex skos:exactMatch mesh D066194 Olfactory Cortex semapv:ManualMappingCuration orcid:0000-0001-9439-5346 uberon UBERON:2001977 pad skos:exactMatch mesh D058729 Peripheral Arterial Disease semapv:ManualMappingCuration orcid:0000-0001-9439-5346 umls C0006142 Malignant neoplasm of breast skos:exactMatch mesh D001943 Breast Neoplasms semapv:ManualMappingCuration orcid:0000-0002-6601-2165 +vo 0000189 colony forming unit skos:exactMatch mesh D013234 Stem Cells semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.54 vo 0004075 PBT skos:exactMatch mesh D001803 Blood Transfusion semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 vo 0004075 PBT skos:exactMatch mesh D013601 T-Lymphocytes semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 vo 0004075 PBT skos:exactMatch mesh D061766 Proton Therapy semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 @@ -1433,7 +1434,9 @@ vo 0010927 ORF skos:exactMatch mesh D004474 Ecthyma, Contagious semapv:ManualMap vo 0010944 Eae skos:exactMatch mesh D004681 Encephalomyelitis, Autoimmune, Experimental semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5400948258091115 vo 0010971 SurA skos:exactMatch uberon UBERON:0003823 hindlimb zeugopod semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching mira 0.5209235209235209 vo 0010988 IroN skos:exactMatch chebi CHEBI:18248 iron atom semapv:ManualMappingCuration orcid:0000-0003-4423-4370 +vo 0010988 IroN skos:exactMatch mesh D007501 Iron semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.74 vo 0010997 IroN skos:exactMatch chebi CHEBI:18248 iron atom semapv:ManualMappingCuration orcid:0000-0003-4423-4370 +vo 0010997 IroN skos:exactMatch mesh D007501 Iron semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.74 vo 0011021 CP skos:exactMatch chebi CHEBI:3380 captopril semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0011021 CP skos:exactMatch hp HP:0100021 Cerebral palsy semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0011021 CP skos:exactMatch mesh D002547 Cerebral Palsy semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 diff --git a/src/biomappings/resources/mappings.tsv b/src/biomappings/resources/mappings.tsv index 4da27bdc..edf7f9ba 100644 --- a/src/biomappings/resources/mappings.tsv +++ b/src/biomappings/resources/mappings.tsv @@ -8051,7 +8051,7 @@ mesh D019346 Sodium Acetate skos:exactMatch ncit C47720 Sodium Acetate semapv:Ma mesh D019354 Sodium Lactate skos:exactMatch chebi CHEBI:75228 sodium lactate semapv:ManualMappingCuration orcid:0000-0003-4423-4370 mesh D019354 Sodium Lactate skos:exactMatch ncit C47726 Sodium Lactate semapv:ManualMappingCuration orcid:0000-0003-4423-4370 mesh D019379 Teriparatide skos:exactMatch chebi CHEBI:135983 teriparatide semapv:ManualMappingCuration orcid:0000-0003-4423-4370 -mesh D019386 Alendronate RO:0018033 chebi CHEBI:2567 alendronic acid semapv:ManualMappingCuration orcid:0000-0003-4423-4370 +mesh D019386 Alendronate RO:0018033 chebi CHEBI:2567 alendronic acid semapv:ManualMappingCuration orcid:0000-0003-4423-4370 mesh D019438 Ritonavir skos:exactMatch chebi CHEBI:45409 ritonavir semapv:ManualMappingCuration orcid:0000-0003-4423-4370 mesh D019457 Chromosome Breakage skos:exactMatch go GO:0031052 chromosome breakage semapv:ManualMappingCuration orcid:0000-0001-9439-5346 mesh D019522 Vaginal Discharge skos:exactMatch efo 0009365 vaginal discharge semapv:ManualMappingCuration orcid:0000-0001-9439-5346 @@ -9687,6 +9687,7 @@ vo 0000079 Fluzone High-dose skos:exactMatch mesh C000618615 Fluzone High-Dose s vo 0000082 Pediarix skos:exactMatch mesh C472675 PEDIARIX semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7623170480313337 vo 0000084 Pentacel skos:exactMatch mesh C512971 pentacel semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7623170480313337 vo 0000087 Plasmodium falciparum vaccine skos:exactMatch idomal 0000115 plasmodium falciparum vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 +vo 0000096 Adenovirus Type 4 and Type 7 Vaccine, Live, Oral skos:broadMatch mesh D062705 Adenovirus Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.56 vo 0000097 RotaTeq skos:exactMatch mesh C492535 RotaTeq semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7777777777777778 vo 0000113 Twinrix skos:exactMatch mesh C433226 twinrix semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7623170480313337 vo 0000123 Yellow fever virus vaccine skos:exactMatch mesh D022341 Yellow Fever Vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 @@ -9694,6 +9695,7 @@ vo 0000156 viral gene skos:exactMatch mesh D005814 Genes, Viral semapv:ManualMap vo 0000165 bacterial vaccine skos:exactMatch mesh D001428 Bacterial Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 vo 0000170 protozoan gene skos:exactMatch mesh D017125 Genes, Protozoan semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5400948258091115 vo 0000177 cancer vaccine skos:exactMatch mesh D019496 Cancer Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 +vo 0000186 RNA vaccine skos:narrowMatch mesh C000711953 mRNA Vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.55 vo 0000195 conjugate vaccine skos:exactMatch mesh D018074 Vaccines, Conjugate semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5400948258091115 vo 0000247 vaccine efficacy skos:exactMatch mesh D000087507 Vaccine Efficacy semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7623170480313337 vo 0000266 fungal disease skos:exactMatch mesh D009181 Mycoses semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5400948258091115 @@ -9713,6 +9715,7 @@ vo 0000534 subunit vaccine skos:exactMatch mesh D022223 Vaccines, Subunit semapv vo 0000560 toxin skos:exactMatch chebi CHEBI:27026 toxin semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0000560 toxin skos:exactMatch ido 0000549 toxin semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0000560 toxin skos:exactMatch idomal 0000043 toxin semapv:ManualMappingCuration orcid:0000-0003-4423-4370 +vo 0000577 peptide vaccine skos:broadMatch mesh D022223 Vaccines, Subunit semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.54 vo 0000580 vaccine adjuvant skos:exactMatch mesh D000089582 Adjuvants, Vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5400948258091115 vo 0000609 viral vaccine skos:exactMatch mesh D014765 Viral Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 vo 0000641 combination vaccine skos:exactMatch mesh D017778 Vaccines, Combined semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 @@ -9728,6 +9731,7 @@ vo 0000658 Rotavirus vaccine skos:exactMatch mesh D022243 Rotavirus Vaccines sem vo 0000661 Haemophilus vaccine skos:exactMatch mesh D018073 Haemophilus Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 vo 0000664 Poliovirus vaccine skos:exactMatch mesh D023321 Poliovirus Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 vo 0000665 Japanese encephalitis virus vaccine skos:exactMatch mesh D022321 Japanese Encephalitis Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 +vo 0000667 human papillomavirus vaccine skos:broadMatch mesh D053918 Papillomavirus Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.54 vo 0000724 cytomegalovirus vaccine skos:exactMatch mesh D022482 Cytomegalovirus Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5400948258091115 vo 0000725 Dengue virus vaccine skos:exactMatch mesh D053059 Dengue Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 vo 0000726 Ebola virus vaccine skos:exactMatch mesh D046129 Ebola Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 @@ -9763,6 +9767,7 @@ vo 0000771 BCG vaccine skos:exactMatch mesh D001500 BCG Vaccine semapv:ManualMap vo 0000772 Streptococcal vaccine skos:exactMatch mesh D022541 Streptococcal Vaccines semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 vo 0000809 vaccination coverage skos:exactMatch mesh D000073887 Vaccination Coverage semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7623170480313337 vo 0000843 Feline leukemia virus vaccine skos:exactMatch mesh C045569 feline leukemia virus vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7715934858792002 +vo 0000860 vaccine effectiveness skos:exactMatch mesh D000087507 Vaccine Efficacy semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.54 vo 0000862 Canada skos:exactMatch idocovid19 0001302 Canada semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0000862 Canada skos:exactMatch mesh D002170 Canada semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7777777777777778 vo 0000867 Influvac skos:exactMatch mesh C568705 influvac semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7623170480313337 @@ -9772,6 +9777,7 @@ vo 0000971 Novartis skos:exactMatch ncit C126403 Novartis semapv:ManualMappingCu vo 0000972 LHRH skos:exactMatch mesh D007987 Gonadotropin-Releasing Hormone semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 vo 0000978 Flublok skos:exactMatch mesh C528512 FluBlok semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.743764172335601 vo 0001010 Promega skos:exactMatch mesh C060580 Promega semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7777777777777778 +vo 0001080 Androstenedione skos:exactMatch mesh D000735 Androstenedione semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.78 vo 0001092 USDA skos:exactMatch mesh D016885 United States Department of Agriculture semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 vo 0001092 USDA skos:exactMatch ncit C68708 United States Department of Agriculture semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0001094 pregnant women skos:exactMatch mesh D037841 Pregnant Women semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7623170480313337 @@ -9779,6 +9785,7 @@ vo 0001215 Vaxstrate skos:exactMatch mesh C066608 Vaxstrate semapv:ManualMapping vo 0001252 toxoid skos:exactMatch mesh D014121 Toxoids semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5400948258091115 vo 0003028 human serum albumin skos:exactMatch mesh D000075462 Serum Albumin, Human semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5400948258091115 vo 0003030 gelatin skos:exactMatch chebi CHEBI:5291 gelatin semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7777777777777778 +vo 0003030 gelatin skos:exactMatch mesh D005780 Gelatin semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.76 vo 0003082 Vaxchora skos:exactMatch mesh C000613802 Vaxchora semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7777777777777778 vo 0003108 Genhevac B skos:exactMatch mesh C075656 GenHevac B Pasteur semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.530818387961245 vo 0003112 Rudivax skos:exactMatch mesh C112264 Rudivax semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7777777777777778 @@ -9827,6 +9834,13 @@ vo 0005409 mRNA-1073 skos:exactMatch mesh C000722748 mRNA-1073 COVID-19 and infl vo 0005410 SYS6006 skos:exactMatch mesh C000722716 SYS6006 COVID-19 vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 vo 0005414 LVRNA009 skos:exactMatch mesh C000722715 LVRNA009 COVID-19 vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 vo 0005415 mRNA-1273.214 skos:exactMatch mesh C000722752 mRNA-1273.214 COVID-19 vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.5555555555555556 +vo 0005445 immune globulin, intravenous skos:exactMatch mesh D016756 Immunoglobulins, Intravenous semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.5 +vo 0006001 botulinum antitoxin skos:exactMatch mesh D001904 Botulinum Antitoxin semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.76 +vo 0006005 diphtheria antitoxin skos:exactMatch mesh D004166 Diphtheria Antitoxin semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.76 +vo 0007193 Abagovomab skos:exactMatch mesh C518318 abagovomab semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.76 +vo 0007240 ALVAC Vaccine skos:exactMatch mesh C078788 ALVAC vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.77 +vo 0007244 ALVAC-CEA Vaccine skos:exactMatch mesh C404395 ALVAC-CEA vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.77 +vo 0007420 MUC-2-KLH Vaccine skos:exactMatch mesh C502357 MUC-2-KLH vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.77 vo 0010632 country skos:exactMatch commoncoreontology Country country semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0010637 Rubella virus vaccine skos:exactMatch mesh D012411 Rubella Vaccine semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:StructuralMatching vo 0.99 vo 0010710 Dukoral skos:exactMatch mesh C586175 Dukoral semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.7777777777777778 @@ -9837,6 +9851,8 @@ vo 0010737 Recombivax HB skos:exactMatch mesh C075655 Recombivax HB semapv:Manua vo 0010754 virus protein skos:exactMatch pr PR:000036197 viral protein semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0010950 SecA2 skos:exactMatch ogg 3000885594 secA2 semapv:ManualMappingCuration orcid:0000-0003-4423-4370 vo 0011093 Hepatitis B surface antigen skos:exactMatch mesh D006514 Hepatitis B Surface Antigens semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/4b2628/scripts/generate_vo_mesh_mappings.py 0.549371263656978 +vo 0011155 Beta-tubulin skos:broadMatch mesh D014404 Tubulin semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.54 +vo 0011231 Glycoprotein skos:exactMatch mesh D006023 Glycoproteins semapv:ManualMappingCuration orcid:0000-0003-4423-4370 semapv:LexicalMatching https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py 0.56 vo 0011241 Hsp90 skos:exactMatch pr PR:000025350 HSPC protein semapv:ManualMappingCuration orcid:0000-0003-4423-4370 wikipathways WP100 Glutathione metabolism debio:0000003 go GO:0006749 glutathione metabolic process semapv:ManualMappingCuration orcid:0000-0003-4423-4370 wikipathways WP100 Glutathione metabolism skos:exactMatch reactome R-HSA-174403 Glutathione synthesis and recycling semapv:ManualMappingCuration orcid:0000-0002-2046-6145 diff --git a/src/biomappings/resources/predictions.tsv b/src/biomappings/resources/predictions.tsv index 3fc56124..7f2ad12d 100644 --- a/src/biomappings/resources/predictions.tsv +++ b/src/biomappings/resources/predictions.tsv @@ -38872,6 +38872,65 @@ uberon UBERON:2000188 corpus cerebelli skos:exactMatch mesh D002531 Cerebellum s uberon UBERON:3011045 gasserian ganglion skos:exactMatch mesh D012668 Trigeminal Ganglion semapv:LexicalMatching 0.9 generate_uberon_mesh_mappings.py uberon UBERON:3011048 genital system skos:exactMatch mesh D005835 Genitalia semapv:LexicalMatching 0.9 generate_uberon_mesh_mappings.py vido 0001123 viral disease skos:exactMatch doid DOID:934 viral infectious disease semapv:LexicalMatching 0.549371263656978 mira +vo 0000004 ActHIB skos:exactMatch mesh C055753 Haemophilus influenza type b polysaccharide vaccine-tetanus toxin conjugate semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000031 MenHibrix skos:exactMatch mesh C527605 Hib-MenCY-TT vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000049 Gardasil skos:exactMatch mesh D000068857 Human Papillomavirus Recombinant Vaccine Quadrivalent, Types 6, 11, 16, 18 semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000052 Havrix skos:exactMatch mesh D022362 Hepatitis A Vaccines semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000064 Infanrix skos:exactMatch mesh D022681 Diphtheria-Tetanus-acellular Pertussis Vaccines semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000071 Menactra skos:exactMatch mesh D022401 Meningococcal Vaccines semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000083 PedvaxHIB skos:exactMatch mesh C061964 Haemophilus influenzae-type b polysaccharide-Neisseria meningitidis outer membrane protein conjugate vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000088 Pneumovax 23 skos:exactMatch mesh C414006 23-valent pneumococcal capsular polysaccharide vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000090 Prevnar skos:exactMatch mesh D000069443 Heptavalent Pneumococcal Conjugate Vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000091 ProQuad skos:exactMatch mesh C050102 measles, mumps, rubella, varicella vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000104 TYPHIM VI skos:exactMatch mesh C057664 Vi polysaccharide vaccine, typhoid semapv:LexicalMatching 0.54 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000112 Tripedia skos:exactMatch mesh D022681 Diphtheria-Tetanus-acellular Pertussis Vaccines semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000119 Varivax skos:exactMatch mesh D019433 Chickenpox Vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000124 Zostavax skos:exactMatch mesh D053061 Herpes Zoster Vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0000556 multivalent vaccine skos:exactMatch mesh D017778 Vaccines, Combined semapv:LexicalMatching 0.54 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0001110 Fecundin skos:exactMatch mesh C042013 polyandroalbumin semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0001244 Prevnar 13 skos:exactMatch mesh C538862 13-valent pneumococcal vaccine semapv:LexicalMatching 0.55 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0001245 Synflorix skos:exactMatch mesh C547294 PHiD-CV vaccine semapv:LexicalMatching 0.54 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0001246 Menveo skos:exactMatch mesh D022401 Meningococcal Vaccines semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003066 Bexsero skos:exactMatch mesh C570015 4CMenB vaccine semapv:LexicalMatching 0.54 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003075 Gardasil 9 skos:exactMatch mesh C000634046 Human Papillomavirus Recombinant Vaccine nonavalent semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003094 Pnu-Imune vaccine skos:exactMatch mesh D022242 Pneumococcal Vaccines semapv:LexicalMatching 0.55 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003105 Lymerix skos:exactMatch mesh C072045 OspA protein semapv:LexicalMatching 0.52 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003114 Trihibit skos:exactMatch mesh C080881 diphtheria-tetanus-pertussis-haemophilus b conjugate vaccine semapv:LexicalMatching 0.52 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003117 Virivac skos:exactMatch mesh D022542 Measles-Mumps-Rubella Vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003121 OmniHIB skos:exactMatch mesh C055753 Haemophilus influenza type b polysaccharide vaccine-tetanus toxin conjugate semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003152 HEPLISAV-B skos:exactMatch mesh C000726347 Heplisav-B semapv:LexicalMatching 0.77 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0003442 Acel-Imune skos:exactMatch mesh D022681 Diphtheria-Tetanus-acellular Pertussis Vaccines semapv:LexicalMatching 0.54 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0004097 MVA-BN skos:exactMatch mesh C527606 smallpox and monkeypox vaccine modified vaccinia ankara-bavarian nordic semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0004987 Comirnaty skos:exactMatch mesh D000090982 BNT162 Vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0004991 COVAXIN skos:exactMatch mesh C000722386 BBV152 COVID-19 vaccine semapv:LexicalMatching 0.54 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005081 Corbevax skos:exactMatch mesh C000723409 Corbevax COVID-19 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005090 IIBR-100 skos:exactMatch mesh C000722810 rVSV-deltaG-spike COVID-19 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005141 CoronaVac skos:exactMatch mesh C000722216 sinovac COVID-19 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005143 LNP-nCoVsaRNA skos:exactMatch mesh C000723217 COVAC1 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005160 WIBP-CorV skos:exactMatch mesh C000722771 WIBP COVID-19 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005166 BBIBP-CorV skos:exactMatch mesh C000722768 BIBP COVID-19 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005172 INO-4800 skos:exactMatch mesh C000706171 reluscovtogene ralaplasmid semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005193 COVAX-19 skos:exactMatch mesh C000718690 SARS-CoV-2 recombinant spike protein with delta inulin and CpG-ODN adjuvant vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005227 BBV154 skos:exactMatch mesh C000722386 BBV152 COVID-19 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005256 HDT-301 skos:exactMatch mesh C000720467 repRNA-CoV2S vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005277 mRNA-1273.211 skos:exactMatch mesh D000090983 2019-nCoV Vaccine mRNA-1273 semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005315 SCB-2020S skos:exactMatch mesh C000721887 SCB-2019 COVID-19 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005340 VB10.2129 skos:exactMatch mesh C000720500 VB10.COV-2 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0005341 VB10.2210 skos:exactMatch mesh C000720500 VB10.COV-2 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0006033 meningococcal C conjugate vaccine skos:exactMatch mesh C410218 serogroup C meningococcal conjugate vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0007054 VCL-CB01 Vaccine skos:exactMatch mesh C547023 VCL-CB01 vaccine semapv:LexicalMatching 0.77 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0010719 Infanrix-hexa skos:exactMatch mesh C541235 diphtheria-tetanus-acellular pertussis-inactivated poliovirus-Haemophilus influenzae b conjugate-hepatitis B vaccine semapv:LexicalMatching 0.54 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0010730 Pediacel skos:exactMatch mesh C541234 diphtheria-tetanus-five component acellular pertussis-inactivated poliomyelitis -Haemophilus influenzae type b conjugate vaccine semapv:LexicalMatching 0.54 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0010734 Priorix skos:exactMatch mesh D022542 Measles-Mumps-Rubella Vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0010738 Rotarix skos:exactMatch mesh C492457 RIX4414 vaccine semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0010745 Vaqta skos:exactMatch mesh D022362 Hepatitis A Vaccines semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0011147 NS1 skos:exactMatch mesh C058271 4-(2-(4-isopropylbenzamido)ethoxy)benzoic acid semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0011148 NS3 skos:exactMatch mesh C031926 montirelin semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0011149 NS5 skos:exactMatch mesh C031785 8-dehydroxythienamycin semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0011154 F1-ATPase skos:exactMatch mesh D006180 Proton-Translocating ATPases semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0011312 NS1 skos:exactMatch mesh C058271 4-(2-(4-isopropylbenzamido)ethoxy)benzoic acid semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0011339 Catalase skos:exactMatch mesh D002374 Catalase semapv:LexicalMatching 0.78 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py +vo 0011559 Cervarix skos:exactMatch mesh C510352 human papillomavirus vaccine, L1 type 16, 18 semapv:LexicalMatching 0.56 https://github.com/biomappings/biomappings/blob/28ac41/scripts/generate_vo_mesh_mappings.py wikipathways WP1 Statin pathway RO:HOM0000017 wikipathways WP1041 Statin pathway semapv:LexicalMatching 0.95 https://github.com/biomappings/biomappings/blob/cf4bea/scripts/generate_wikipathways_orthologs.py wikipathways WP1 Statin pathway RO:HOM0000017 wikipathways WP1157 Statin pathway semapv:LexicalMatching 0.95 https://github.com/biomappings/biomappings/blob/cf4bea/scripts/generate_wikipathways_orthologs.py wikipathways WP1 Statin pathway RO:HOM0000017 wikipathways WP145 Statin pathway semapv:LexicalMatching 0.95 https://github.com/biomappings/biomappings/blob/cf4bea/scripts/generate_wikipathways_orthologs.py diff --git a/src/biomappings/templates/home.html b/src/biomappings/templates/home.html index cbbab2c8..75412fbc 100644 --- a/src/biomappings/templates/home.html +++ b/src/biomappings/templates/home.html @@ -66,7 +66,9 @@
{% endif %} Target Target Name - Confidence + Conf. + + @@ -111,6 +113,20 @@
+ + + -B- + + + + + -N- + + None: """ if line not in self._marked: self.total_curated += 1 - if value not in {"correct", "incorrect", "unsure"}: + if value not in {"correct", "incorrect", "unsure", "broad", "narrow"}: raise ValueError self._marked[line] = value @@ -459,6 +459,15 @@ def persist(self): prediction["prediction_confidence"] = prediction.pop("confidence") prediction["source"] = _manual_source() prediction["type"] = "semapv:ManualMappingCuration" + + # note these go backwards because of the way they are read + if value == "broad": + value = "correct" + prediction["relation"] = "skos:narrowMatch" + elif value == "narrow": + value = "correct" + prediction["relation"] = "skos:broadMatch" + entries[value].append(prediction) append_true_mappings(entries["correct"], path=self.positives_path) @@ -581,6 +590,10 @@ def _normalize_mark(value: str) -> str: return "incorrect" elif value in UNSURE: return "unsure" + elif value in {"broader", "broad"}: + return "broad" + elif value in {"narrow", "narrower"}: + return "narrow" else: raise ValueError