From a38242d512114614adc4fcbfff9ef3f6d9fe686b Mon Sep 17 00:00:00 2001
From: GuillaumeG <guipagui@gmail.com>
Date: Tue, 12 Dec 2023 17:11:03 +0100
Subject: [PATCH] Tool `get_sbml_model` (#162)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* feat(tools): get_sbml_model, load file from history

* chore(wrapper): change option + taxonid version

* chore(python): use get_taxonid from taxonid pkg

* chore(wrapper): rm shell cmd

* chore(wrapper): upgrade version

* chore: global modifications

* fix: put back get_taxon_id for BiGG models

---------

Co-authored-by: Joan Hérisson <joan.herisson@univ-evry.fr>
---
 tools/get_sbml_model/get_infos.py       | 51 ++++++++++++++++++++++++-
 tools/get_sbml_model/get_sbml_model.xml |  4 +-
 2 files changed, 51 insertions(+), 4 deletions(-)

diff --git a/tools/get_sbml_model/get_infos.py b/tools/get_sbml_model/get_infos.py
index b764ed04..5ebdf7e4 100644
--- a/tools/get_sbml_model/get_infos.py
+++ b/tools/get_sbml_model/get_infos.py
@@ -81,6 +81,55 @@ def args():
     return params
 
 
+def get_taxon_id(hostid: str, bigg: bool):
+    '''
+    Returns the taxonomy ID of the host organism
+    
+    Parameters
+    ----------
+    hostid: str
+        Extended name of the host organism or host ID if from BiGG
+    bigg: bool
+        True if the model is from BiGG
+        
+    Returns
+    -------
+    taxid: str
+        Taxonomy ID of the host organism
+    '''
+    if not bigg:
+        return get_taxonid(hostid)
+
+    hostname = ''
+    # Extended Name
+    server = 'http://bigg.ucsd.edu/api/v2/models/'
+    ext = hostid
+    r = r_get(server+ext, headers={ "Content-Type" : "application/json"})
+    if not r.ok:
+        print(f"Warning: unable to retrieve host name for id {hostid}")
+    else:
+        try:
+            hostname = r.json()["organism"]
+        except KeyError:
+            print(f"Warning: unable to retrieve host name for id {hostid}")
+    if not hostname:
+        taxid = ''
+    else:
+        # TAXON ID
+        server = 'https://rest.ensembl.org'
+        ext = f'/taxonomy/id/{hostname}?'
+        r = r_get(server+ext, headers={ "Content-Type" : "application/json"})
+        if not r.ok:
+            print(f"Warning: unable to retrieve taxonomy ID for host organism {hostname}")
+        else:
+            try:
+                taxid = r.json()["id"]
+            except KeyError:
+                print(f"Warning: unable to retrieve taxonomy ID for host organism {hostname}")
+                taxid = ''
+    return taxid
+
+
 def entry_point():
 
     params = args()
@@ -116,7 +165,7 @@ def entry_point():
     else:
         print(f'Biomass reaction ID: {biomass_id}')
 
-    taxid = get_taxonid(params.hostname)
+    taxid = get_taxon_id(params.hostname, params.bigg)
 
     if params.taxid:
         with open(params.taxid, 'w') as f:
diff --git a/tools/get_sbml_model/get_sbml_model.xml b/tools/get_sbml_model/get_sbml_model.xml
index 808f8934..bbe6e363 100644
--- a/tools/get_sbml_model/get_sbml_model.xml
+++ b/tools/get_sbml_model/get_sbml_model.xml
@@ -11,16 +11,14 @@
         #if str($cond_src.from_src) == 'from_bigg'
             curl -o - 'http://bigg.ucsd.edu/static/models/${cond_src.hostid}.xml.gz' | gunzip > '$model' &&
         #end if
-        echo "listdir:";
-        ls;
         python '$__tool_directory__/'get_infos.py
             #if str($cond_src.from_src) == 'from_bigg'
                 '$model'
                 --bigg
             #else
                 '${cond_src.input_file}'
-                --hostname '${cond_src.hostid}'
             #end if
+            --hostname '${cond_src.hostid}'
             --taxid '$taxid'
             --comp '$compartments'
             --biomass '$biomass'