Skip to content

Commit

Permalink
add example .
Browse files Browse the repository at this point in the history
  • Loading branch information
@ofilangi
ofilangi committed Oct 11, 2024
1 parent 7e61b7a commit 523e3f3
Show file tree
Hide file tree
Showing 3 changed files with 160 additions and 0 deletions.
70 changes: 70 additions & 0 deletions config/sylvain.json
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
{
"encodeur" : "sentence-transformers/all-MiniLM-L6-v2",
"threshold_similarity_tag_chunk" : 0.49,
"threshold_similarity_tag" : 0.80,
"batch_size" : 32,

"populate_owl_tag_embeddings" : {
"ontologies": {
"planteome_link" : {
"peco": {
"url": "http://purl.obolibrary.org/obo/peco.owl",
"prefix": "http://purl.obolibrary.org/obo/PECO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
},
"po": {
"url": "http://purl.obolibrary.org/obo/po.owl",
"prefix": "http://purl.obolibrary.org/obo/PO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
},
"pso": {
"url": "http://purl.obolibrary.org/obo/pso.owl",
"prefix": "http://purl.obolibrary.org/obo/PSO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
},
"to": {
"url": "http://purl.obolibrary.org/obo/to.owl",
"prefix": "http://purl.obolibrary.org/obo/TO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
},
"pato": {
"url": "http://purl.obolibrary.org/obo/pato.owl",
"prefix": "http://purl.obolibrary.org/obo/PATO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
}
},
"mesh_link" : {
"mesh": {
"filepath" : "data/mesh/2024.ttl",
"prefix": "http://id.nlm.nih.gov/mesh/",
"format": "turtle",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://www.w3.org/2000/01/rdf-schema#comment>"]
}
}
},
"debug_nb_terms_by_ontology" : -1
},
"populate_ncbi_taxon_tag_embeddings" : {
"regex" : "(assic.*)|(ola)" ,
"tags_per_file" : 2000
},
"populate_abstract_embeddings" : {
"abstracts_per_file" : 50,
"from_file" : {
"json_files" : [
"data/abstracts/sylvain.json"
]
}
}
}
83 changes: 83 additions & 0 deletions config/test_lotus.json
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,83 @@
{
"encodeur" : "sentence-transformers/all-MiniLM-L6-v2",
"threshold_similarity_tag_chunk" : 0.49,
"threshold_similarity_tag" : 0.80,
"batch_size" : 32,

"populate_owl_tag_embeddings" : {
"ontologies": {
"planteome_link" : {
"peco": {
"url": "http://purl.obolibrary.org/obo/peco.owl",
"prefix": "http://purl.obolibrary.org/obo/PECO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
},
"po": {
"url": "http://purl.obolibrary.org/obo/po.owl",
"prefix": "http://purl.obolibrary.org/obo/PO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
},
"pso": {
"url": "http://purl.obolibrary.org/obo/pso.owl",
"prefix": "http://purl.obolibrary.org/obo/PSO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
},
"to": {
"url": "http://purl.obolibrary.org/obo/to.owl",
"prefix": "http://purl.obolibrary.org/obo/TO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
}
},
"technology_link" : {
"ms": {
"url": "http://purl.obolibrary.org/obo/ms.owl",
"prefix": "http://purl.obolibrary.org/obo/MS_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]
}
},
"mesh_link" : {
"mesh": {
"filepath" : "data/mesh/2024.ttl",
"prefix": "http://id.nlm.nih.gov/mesh/",
"format": "turtle",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://www.w3.org/2000/01/rdf-schema#comment>"]
}
},
"chemical_link" : {
"chmo" : {
"url": "http://purl.obolibrary.org/obo/chmo.owl",
"prefix": "http://purl.obolibrary.org/obo/CHMO_",
"format": "xml",
"label" : "<http://www.w3.org/2000/01/rdf-schema#label>",
"properties": ["<http://purl.obolibrary.org/obo/IAO_0000115>"]

}
}
},
"debug_nb_terms_by_ontology" : -1
},
"populate_ncbi_taxon_tag_embeddings" : {
"regex" : "(assic.*)|(ola)" ,
"tags_per_file" : 2000
},
"populate_abstract_embeddings" : {
"abstracts_per_file" : 50,
"from_file" : {
"json_files" : [
"data/abstracts/abstracts_Identification_and_Quantification_of_Glucosinolates.json"
]
}

}
}
7 changes: 7 additions & 0 deletions data/abstracts/sylvain.json
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
[
{
"title": "--",
"abstract": "Water loss data during leaf dehydratation to better understand species survival during drought events. 7 replicates per species.",
"doi": "--"
}
]

0 comments on commit 523e3f3

Please sign in to comment.