From 65657f98a1da0c5c73627215f692e7bb1b4ea830 Mon Sep 17 00:00:00 2001
From: Adriano Rutz <adriano.rutz@hotmail.com>
Date: Mon, 13 May 2024 10:00:54 +0200
Subject: [PATCH] WIP #50

---
 update/config.py                  |  9 ++++++
 update/generate_database_index.py |  4 +--
 update/queries/urls_formatters.rq | 46 +++++++++++++++++++++++++++++++
 3 files changed, 57 insertions(+), 2 deletions(-)
 create mode 100644 update/queries/urls_formatters.rq

diff --git a/update/config.py b/update/config.py
index 97c918c..8404042 100644
--- a/update/config.py
+++ b/update/config.py
@@ -407,6 +407,15 @@
             "output_file": "triplets.csv",
         },
     ),
+    Task(
+        name="urls_formatters",
+        f=download_query_as_csv.run,
+        group=DownloadGroup,
+        params={
+            "query_file": "update/queries/urls_formatters.rq",
+            "output_file": "urls_formatters.csv",
+        },
+    ),
     Task(
         name="generate_database_chemo",
         f=generate_database_chemo.run,
diff --git a/update/generate_database_index.py b/update/generate_database_index.py
index f724b7b..16e41a3 100644
--- a/update/generate_database_index.py
+++ b/update/generate_database_index.py
@@ -111,7 +111,7 @@ def run(path: Path) -> None:
     #     structures.append({"id": struct, "smiles": smiles})
     logging.info(" Processed structures")
 
-    # TODO add all structure IDs (See #50)
+    # TODO add all IDs and formatters (See #50)
 
     descriptors_dict = {}
     with open(path / "descriptors_rdkit.csv", "r") as f:
@@ -158,7 +158,7 @@ def run(path: Path) -> None:
 
     # Eventually TODO add taxa_names_com
 
-    # TODO add all taxon IDs (See #50)
+    # TODO add all IDs and formatters (See #50)
 
     taxon_ranks_dict = {}
     with open(path / "ranks_names.csv", "r") as f:
diff --git a/update/queries/urls_formatters.rq b/update/queries/urls_formatters.rq
new file mode 100644
index 0000000..e86c016
--- /dev/null
+++ b/update/queries/urls_formatters.rq
@@ -0,0 +1,46 @@
+PREFIX wd: <http://www.wikidata.org/entity/>
+PREFIX wdt: <http://www.wikidata.org/prop/direct/>
+PREFIX hint: <http://www.bigdata.com/queryHints#>
+
+SELECT * WHERE { 
+  # All properties we use with a formatter URL
+  VALUES ?property {
+    wd:P231   # STRUCTURE CAS
+    wd:P233   # STRUCTURE SMILES (canonical)
+    wd:P234   # STRUCTURE InChI
+    wd:P235   # STRUCTURE InChIKey
+    wd:P356   # REFERENCE DOI
+    wd:P592   # STRUCTURE ChEMBL
+    wd:P638   # STRUCTURE PDB structure
+    wd:P661   # STRUCTURE ChemSpider
+    wd:P662   # STRUCTURE PubChem CID
+    wd:P683   # STRUCTURE ChEBI
+    wd:P665   # STRUCTURE KEGG
+    wd:P685   # TAXON     NCBI
+    wd:P815   # TAXON     ITIS
+    wd:P830   # TAXON     EOL
+    wd:P846   # TAXON     GBIF
+    wd:P850   # TAXON     WoRMS
+    wd:P960   # TAXON     TROPICOS
+    wd:P961   # TAXON     IPNI
+    wd:P2017  # STRUCTURE SMILES (isomeric)
+    wd:P2057  # STRUCTURE HMDB
+    wd:P2064  # STRUCTURE KNApSAcK
+    wd:P2084  # STRUCTURE ZINC
+    wd:P2877  # STRUCTURE SureChEMBL
+    wd:P3151  # TAXON     iNat
+    wd:P3636  # STRUCTURE PDB ligand
+    wd:P4964  # STRUCTURE SPLASH
+    wd:P5037  # TAXON     PoWO
+    wd:P5055  # TAXON     IRMNG
+    wd:P6689  # STRUCTURE MassBank
+    wd:P7715  # TAXON     WFO
+    wd:P7746  # STRUCTURE NPAtlas
+    wd:P8533  # STRUCTURE SMARTS
+    wd:P9157  # TAXON     OTL
+    wd:P9405  # STRUCTURE NMRShiftDB
+    wd:P10718 # STRUCTURE CXSMILES
+    wd:P11375 # STRUCTURE CSD
+  }
+  ?property wdt:P1630 ?formatter. hint:Prior hint:rangeSafe TRUE.
+}