minor change . readme

p2m2 · Oct 21, 2024 · 768a06f · 768a06f
1 parent 953f779
commit 768a06f
Show file tree

Hide file tree

Showing 7 changed files with 64 additions and 37 deletions.
diff --git a/README.md b/README.md
@@ -24,9 +24,7 @@ This approach aims to significantly enrich the metadata of scientific articles,
 ## Installation
 
 ```bash
-python -m venv env
-source env/bin/activate
-pip install git+https://github.com/p2m2/encoder-ontology-match-abstract
+exec.sh <json_config_file>
 ```
 
 ## Configuration
@@ -103,22 +101,8 @@ check exemple on [config](./config) directory
 </table>
 
 
-### Execution
+### Tests Execution
 
-```bash
-python -m llm_semantic_annotator config/test.json populate_owl_tag_embeddings
-```
-
-```bash
-python -m llm_semantic_annotator config/test.json populate_ncbi_abstract_embeddings
-```
-```bash
-python -m llm_semantic_annotator config/igepp.json populate_ncbi_abstract_embeddings
-```
-
-```bash
-python -m llm_semantic_annotator config/test.json compute_tag_chunk_similarities
-```
 
 ```bash
 python -m unittest discover

diff --git a/config/1-article.json b/config/1-article.json
@@ -77,10 +77,6 @@
             "json_files" : [
                 "data/abstracts/abstracts_1.json",
                 "data/abstracts/abstracts_2.json"
-            ],
-            "text_files" : [
-                "data/abstracts/abstracts_3.txt",
-                "data/abstracts/abstracts_4.txt"
             ]
         }
 

diff --git a/config/planteom-example.json b/config/planteom-example.json
@@ -0,0 +1,58 @@
+{
+    "encodeur" : "sentence-transformers/all-MiniLM-L6-v2",
+    "threshold_similarity_tag_chunk" : 0.60,
+    "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>"]
+                }
+            }
+        },
+        "debug_nb_terms_by_ontology" : -1
+    },
+    "populate_ncbi_taxon_tag_embeddings" : {
+        "regex" : "(assic.*)|(arab.*)" ,
+        "tags_per_file" : 2000
+    },
+    "populate_abstract_embeddings" : {
+        "abstracts_per_file" : 500,
+        "from_ncbi_api" : {
+            "ncbi_api_chunk_size" : 200,
+            "debug_nb_ncbi_request" : -1,
+            "retmax" : 2000,
+            "selected_term" : [
+                "Crops%2C+Agricultural%2Fmetabolism%5BMeSH%5D"
+            ]
+        }
+
+    }
+}
diff --git a/exec-1article.sh b/exec-1article.sh
diff --git a/exec.sh b/exec.sh
@@ -46,14 +46,14 @@ execute_command() {
 create_venv_if_not_exists
 
 echo "What would you like to execute?"
-echo "1. Full workflow"
+echo "1. Pseudo workflow [2,4,5,6,7]"
 echo "2. populate_owl_tag_embeddings"
 echo "3. populate_ncbi_taxon_tag_embeddings"
 echo "4. populate_abstract_embeddings"
 echo "5. compute similarities between tags and chunks abstracts"
 echo "6. display similarities information"
 echo "7. build turtle knowledge graph"
-echo "8. evaluate encoder with mesh descriptors"
+echo "8. evaluate encoder with mesh descriptors (experimental)"
 read -p "Enter your choice (1-8): " choice
 
 case $choice in
@@ -62,6 +62,7 @@ case $choice in
         #run_command python3 -m llm_semantic_annotator "$conffile" populate_ncbi_taxon_tag_embeddings
         run_command python3 -m llm_semantic_annotator "$conffile" populate_abstract_embeddings
         run_command python3 -m llm_semantic_annotator "$conffile" compute_tag_chunk_similarities
+        run_command python3 -m llm_semantic_annotator "$conffile" build_graph
         run_command python3 -m llm_semantic_annotator "$conffile" display_summary
         ;;
     2|3|4|5|6|7|8)

diff --git a/llm_semantic_annotator/abstract/abstract_manager.py b/llm_semantic_annotator/abstract/abstract_manager.py
@@ -73,7 +73,7 @@ def get_ncbi_abstracts_from_api(self):
                 chunk = id_list[i:i+self.ncbi_api_chunk_size]
                 ids = ",".join(chunk)
                 fetch_url = f"{base_url}efetch.fcgi?db=pubmed&id={ids}&rettype=abstract&retmode=xml"
-                print(fetch_url)
+
                 fetch_response = requests.post(fetch_url)
 
                 root = ET.fromstring(fetch_response.content)

diff --git a/llm_semantic_annotator/core.py b/llm_semantic_annotator/core.py
@@ -80,8 +80,6 @@ def main_compute_tag_chunk_similarities(config_all):
     if len(abstracts_pth_files) == 0:
         raise FileNotFoundError("No abstracts embeddings found")
 
-
-
     ### Loading tags embeddings
     ### -----------------------
     tag_embeddings_all = {}