query ncbi

tree_similarity/query_ncbi_accn2fasta.py

+import sys
+import requests
+
+db = 'protein'
+
+# ICI faire lire une liste en format csv (comma-separated values) avec les accession numbers des PROTEINES (pas des gènes)
+acc_list = 'NP_060022,NP_001349278,XP_025004865'
+
+acc_array = acc_list.split(',')
+
+#append [accn] field to each accession
+new_acc_array = []
+for acc in acc_array:
+    new_acc_array.append(acc+"[accn]")
+acc_array = new_acc_array
+
+#join the accessions with OR
+query = "+OR+".join(acc_array)
+
+#assemble the esearch URL
+base = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/'
+url = base + f'esearch.fcgi?db={db}&term={query}&usehistory=y'
+
+#post the esearch URL
+print("URL", url)
+output = requests.get(url)
+
+#parse WebEnv and QueryKey
+web, key = "", ""
+for line in output.text.split("\n"):
+    fields = line.split(">")
+    we = False
+    qk = False
+    for f in fields:
+        print(f)
+        if "<WebEnv" in f:
+            we = True
+            continue
+        if we:
+            web = f.split("<")[0]
+            we = False
+            continue
+        if "<QueryKey" in f:
+            qk = True
+            continue
+        if qk:
+            key = f.split("<")[0]
+            qk = False
+            continue
+if not (web and key):
+    exit(1)
+
+#assemble the efetch URL
+url = base + f'efetch.fcgi?db={db}&query_key={key}&WebEnv={web}'
+url += '&rettype=fasta&retmode=text'
+
+fasta = requests.get(url)
+#print(fasta.text)
+
+# ICI mettre le bon format