diff --git a/aligned_sequences.xlsx b/aligned_sequences.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..ef2b101421df0f57d891e8cba4561fe44b63f055 Binary files /dev/null and b/aligned_sequences.xlsx differ diff --git a/test.py b/test.py index a4664a96885d6045fad7bfc3765217c87dcc75be..2374a8abb58e16148e1156ee23ae0bc9277f2019 100644 --- a/test.py +++ b/test.py @@ -27,7 +27,23 @@ for csv in ["Resultat.b.csv"]: #cldb_tmp.rename_proteins({"TssKHis6":"TssK","StrepTssF":"TssF","TssGFlag":"TssG","HATssE":"TssE"}) cldb_tmp.set_name(csv) cldb.append_database(cldb_tmp) - -cldb.align_sequence('pairwise_alignment_NeisseriaTo_3ja1n_0.08.txt') + +cldb.align_sequence('tools/pairwise_alignment_NeisseriaTo_3ja1n_0.08.txt') + +renamedict={} +for xl in cldb: + try: + protname=xl[cldb.protein1_key].split("|")[2] + renamedict[xl[cldb.protein1_key]]=protname + except: + pass + try: + protname=xl[cldb.protein2_key].split("|")[2] + renamedict[xl[cldb.protein2_key]]=protname + except: + pass + +cldb.rename_proteins(renamedict) + #print(cldb)