Fix downloads (#233)

* fix loaders * fix download workflow * finishing touches' * revert version * improve ensembl release listing --------- Co-authored-by: Anthony Cesnik <[email protected]>
smith-chem-wisc · Aug 12, 2023 · 1c5f44f · 1c5f44f
1 parent 63c3c3e
commit 1c5f44f
Show file tree

Hide file tree

Showing 6 changed files with 29 additions and 37 deletions.
diff --git a/Spritz/SpritzBackend/EnsemblRelease.cs b/Spritz/SpritzBackend/EnsemblRelease.cs
@@ -22,7 +22,7 @@ public static ObservableCollection<EnsemblRelease> GetReleases()
             foreach (string release in releases)
             {
                 // read txt file into obsv collection
-                var species = genomeDB.Select(g => g.Split(',')[1]).Distinct().ToList();
+                var species = genomeDB.Where(g => g.Contains(release)).Select(g => g.Split(',')[1]).Distinct().ToList();
                 Dictionary<string, string> genomes = new();
                 Dictionary<string, string> organisms = new();
 

diff --git a/Spritz/SpritzBackend/RunnerEngine.cs b/Spritz/SpritzBackend/RunnerEngine.cs
@@ -20,7 +20,7 @@ public class RunnerEngine
         public string SnakemakeCommand { get; private set; }
         public string SpritzCMDCommand { get; set; }
 
-        public static readonly string CurrentVersion = "0.3.8"; // should be the same here, in config.yaml, and in common.smk
+        public static readonly string CurrentVersion = "0.3.8";
         public static readonly bool PrebuiltSpritzMods = true; // always using prebuilt library now
         public RunnerEngine(Tuple<string, SpritzOptions> task, string outputFolder)
         {

diff --git a/Spritz/SpritzModifications/SpritzModifications.csproj b/Spritz/SpritzModifications/SpritzModifications.csproj
@@ -10,7 +10,8 @@
     <PackageReference Include="FluentCommandLineParser" Version="1.4.3">
       <NoWarn>$(NoWarn);NU1701</NoWarn>
     </PackageReference>
-    <PackageReference Include="mzLib" Version="1.0.532" />
+    <PackageReference Include="mzLib" Version="1.0.540" />
+    <PackageReference Include="TopDownProteomics" Version="0.0.295" />
   </ItemGroup>
 
   <ItemGroup>

diff --git a/Spritz/SpritzTest/SpritzTest.csproj b/Spritz/SpritzTest/SpritzTest.csproj
@@ -9,10 +9,13 @@
   </PropertyGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.3.1" />
+    <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.7.0" />
     <PackageReference Include="NUnit" Version="3.13.3" />
-    <PackageReference Include="NUnit3TestAdapter" Version="4.2.1" />
-    <PackageReference Include="coverlet.collector" Version="3.0.2" />
+    <PackageReference Include="NUnit3TestAdapter" Version="4.5.0" />
+    <PackageReference Include="coverlet.collector" Version="6.0.0">
+      <PrivateAssets>all</PrivateAssets>
+      <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
+    </PackageReference>
   </ItemGroup>
 
   <ItemGroup>

diff --git a/Spritz/workflow/scripts/download_uniprot.py b/Spritz/workflow/scripts/download_uniprot.py
@@ -1,28 +1,20 @@
-# see https://www.ebi.ac.uk/training/online/sites/ebi.ac.uk.training.online/files/UniProt_programmatically_py3.pdf
-
 import get_proteome
 import requests
 import sys
 
 format = sys.argv[1]
 
 proteome = get_proteome.proteome
-BASE = 'http://legacy.uniprot.org'
-KB_ENDPOINT = '/uniprot/'
-TOOL_ENDPOINT = '/uploadlists/'
-
-# query = 'name:"polymerase alpha" AND proteome:UP000005640 AND reviewed:yes'
-# query = 'proteome:UP000005640 AND reviewed:yes'
-query = 'proteome:' + proteome
+BASE_URL = 'https://rest.uniprot.org'
+ENDPOINT = '/uniprot/search'
 
 payload = {
-    'query': query,
+    'query': proteome,
     'format': format,
-    'include': 'yes', # include isoforms in fasta
-    # 'columns': 'id,entry_name,reviewed,protein_names,organism,ec,keywords',
+    'includeIsoforms': 'yes', # include isoforms in fasta
     }
 
-result = requests.get(BASE + KB_ENDPOINT, params=payload, stream=True)
+result = requests.get(BASE_URL + ENDPOINT, params=payload, stream=True)
 result.raise_for_status() # throw an error for bad status code
 for block in result.iter_content(1024):
     sys.stdout.buffer.write(block)
diff --git a/Spritz/workflow/scripts/get_proteome.py b/Spritz/workflow/scripts/get_proteome.py
@@ -5,33 +5,29 @@
 import yaml
 
 # find proteome
-BASE = 'http://legacy.uniprot.org'
-KB_ENDPOINT = '/proteomes/'
-TOOL_ENDPOINT = '/uploadlists/'
+BASE_URL = 'https://rest.uniprot.org'
+ENDPOINT = '/proteomes/search'
+
+params = {
+    'query': '*',
+    'format': 'tsv',
+}
 
 with open("config/config.yaml", 'r') as stream:
    data = yaml.safe_load(stream)
-
-query = data["species"] # read config
 organism = data["organism"].lower()
 
-# special case
-if query == 'canis_familiaris':
-    query = 'canis_lupus_familiaris'
-
-payload = {
-    'query': query,
-    'sort': 'score',
-    'format': 'tab',
-    }
-
-proteome_res = requests.get(BASE + KB_ENDPOINT, params=payload, stream=True)
+proteome_res = requests.get(BASE_URL + ENDPOINT, params=params, stream=True)
 proteome_res.raise_for_status() # throw an error for bad status code
 
 results = proteome_res.text.split('\n')[1:]
-
+proteome = None
 for r in results:
     splt = r.split('\t')
-    if organism in splt[1].lower():
+    if organism.replace('_', ' ') in splt[1].lower():
         proteome = splt[0]
         break
+
+if proteome is None:
+    print(f"Proteome for organism {organism} not found.")
+    sys.exit(1)