Merge pull request #42 from tanksha/new-atomtype

New atomtype
MOZI-AI · Aug 11, 2020 · bf77f80 · bf77f80
2 parents b443a3c + a0d662e
commit bf77f80
Show file tree

Hide file tree

Showing 6 changed files with 16 additions and 16 deletions.
diff --git a/atomwrappers.py b/atomwrappers.py
@@ -83,10 +83,10 @@ class CInheritanceLink(CLink):
     atom_type = 'InheritanceLink'
 
 class CRNANode(CNode):
-    atom_type = 'CodingRnaNode'
+    atom_type = 'EnstNode'
 
 class NcRNANode(CNode):
-    atom_type = 'NonCodingRnaNode'
+    atom_type = 'RefseqNode'
 
 class ChebiNode(CNode):
     atom_type = 'ChebiNode'

diff --git a/codingRNA.py b/codingRNA.py
@@ -33,7 +33,7 @@
 with open("dataset/codingRNA_{}.scm".format(str(date.today())), 'w') as f:
     for i in range(len(df)):
         rna = df.iloc[i]["transcript_stable_id"]
-        gene = df.iloc[i]['Approved symbol'].strip()
+        gene = df.iloc[i]['Approved symbol'].strip().upper()
         prot = df.iloc[i]["xref"]
         rnas.append(rna)
         genes.append(gene)

diff --git a/gene2proteinMapping.py b/gene2proteinMapping.py
@@ -39,13 +39,13 @@
                 genes.append(g)
                 prot.append(p)
                 expresion = CEvaluationLink(CPredicateNode("expresses"), CListLink(CGeneNode(g),ProteinNode(p)))
-                f.write(expresion.recursive_print())
+                f.write(expresion.recursive_print() + "\n")
             except:
                 continue
             if not math.isnan(data.iloc[i]['entrez']):
                 entrez_id = str(int(data.iloc[i]['entrez']))
                 has_entrez = CEvaluationLink(CPredicateNode("has_entrez_id"), CListLink(CGeneNode(g),CConceptNode("entrez:"+entrez_id)))
-                f.write(has_entrez.recursive_print())
+                f.write(has_entrez.recursive_print() + "\n")
 
         metadata.update_meta("gene2proteinMapping:latest", 
         "entrez2uniprot.csv",script,genes=len(set(genes)),prot=len(set(prot)))

diff --git a/noncodingRNA.py b/noncodingRNA.py
@@ -29,13 +29,13 @@
     for i in range(len(data)):
         rna = data.iloc[i]["product_accession"].split(".")[0]
         if rna.split("_")[0] in ["NR", "XR"]:
-            gene = data.iloc[i]["symbol"].strip()
+            gene = data.iloc[i]["symbol"].strip().upper()
             name = data.iloc[i]["name"]
             rnas.append(rna)
             genes.append(gene)
             transc = CEvaluationLink(CPredicateNode("transcribed_to"), CListLink(CGeneNode(gene),NcRNANode(rna)))
             transc_name = CEvaluationLink(CPredicateNode("has_name"), CListLink(NcRNANode(rna), CConceptNode("name")))
-            f.write(transc.recursive_print() + "\n" + transc_name.recursive_print())
+            f.write(transc.recursive_print() + "\n" + transc_name.recursive_print() + "\n")
 
 version = dataset.split(".")[1]
 script = "https://github.com/MOZI-AI/knowledge-import/noncodingRNA.py"

diff --git a/string_PPI.py b/string_PPI.py
@@ -83,9 +83,9 @@ def import_string():
                 gene2 = CGeneNode(prot2.split("|")[1].split("_")[0].upper())
                 stv = "(stv {} {})".format(1.0, score/1000)
 
-                f.write(str(CEvaluationLink(CPredicateNode(mode), CSetLink(protein1, protein2), stv=stv)) + "\n")
-                f.write(str(CEvaluationLink(CPredicateNode(mode), CSetLink(gene1, gene2), stv=stv)) + "\n")
-                symmetric[gene1 + gene2] = mode
+                f.write(CEvaluationLink(CPredicateNode(mode), CSetLink(protein1, protein2), stv=stv).recursive_print() + "\n")
+                f.write(CEvaluationLink(CPredicateNode(mode), CSetLink(gene1, gene2), stv=stv).recursive_print() + "\n")
+                symmetric[gene1.name + gene2.name] = mode
 
             except Exception as e:
                 print(e)
@@ -113,13 +113,13 @@ def import_string():
                 gene2 = CGeneNode(prot2.split("|")[1].split("_")[0].upper())
                 stv = "(stv {} {})".format(1.0, score/1000)
 
-                if not (gene1+gene2 in symmetric.keys() and symmetric[gene1+gene2] == mode):
+                if not (gene1.name + gene2.name in symmetric.keys() and symmetric[gene1.name + gene2.name] == mode):
                     if a_is_acting is "t": 
-                        f.write(str(CEvaluationLink(CPredicateNode(mode), CListLink(protein1, protein2), stv=stv)) + "\n")
-                        g.write(str(CEvaluationLink(CPredicateNode(mode), CListLink(gene1, gene2), stv=stv)) + "\n")
+                        f.write(CEvaluationLink(CPredicateNode(mode), CListLink(protein1, protein2), stv=stv).recursive_print() + "\n")
+                        g.write(CEvaluationLink(CPredicateNode(mode), CListLink(gene1, gene2), stv=stv).recursive_print() + "\n")
                     else:
-                        f.write(str(CEvaluationLink(CPredicateNode(mode), CListLink(protein2, protein1), stv=stv)) + "\n")
-                        g.write(str(CEvaluationLink(CPredicateNode(mode), CListLink(gene2, gene1), stv=stv)) + "\n")
+                        f.write(CEvaluationLink(CPredicateNode(mode), CListLink(protein2, protein1), stv=stv).recursive_print() + "\n")
+                        g.write(CEvaluationLink(CPredicateNode(mode), CListLink(gene2, gene1), stv=stv).recursive_print() + "\n")
 
             except Exception as e:
                 print(e)

diff --git a/uniprot2GO.py b/uniprot2GO.py
@@ -37,7 +37,7 @@
             go_namespace, go_term = find_gons.find_type(i.split('\t')[4], go_namespace)
             protein = ProteinNode(i.split('\t')[1])
             if go_term:
-                f.write(CInheritanceLink(protein,go_term).recursive_print() + "\n")
+                f.write(CMemberLink(protein,go_term).recursive_print() + "\n")
             prot.append(i.split('\t')[1])
             go.append(go_term)