Minor edits

mavedb_mapping/blat_alignment.py

@@ -55,8 +55,8 @@ def extract_blat_output(dat: dict):
 def obtain_hit_starts(output, hit: int):
     # a hit is a portion of similarity between query seq and matched seq
     """
-    Helper function to obtain HSP
-    Returns the start of hit
+    Helper function to obtain HSP.
+    Returns the starts of hit sequence.
     """
     hit_starts = list()
     for n in range(len(output[hit])):
@@ -66,7 +66,7 @@ def obtain_hit_starts(output, hit: int):
 
 def obtain_hsp(output):
     """
-    Obtains high-scoring pairs (HSP) for query sequence
+    Obtains high-scoring pairs (HSP) for query sequence.
 
     Parameters
     ----------

mavedb_mapping/get_allele.py

@@ -8,6 +8,7 @@
 tr = Translator(data_proxy=dp, normalize=False)
 
 
+# TODO: docstrings
 def return_normalized_allele(allele, l):
     if allele.state.sequence == "N" and l != "p":
         allele.state.sequence = str(

mavedb_mapping/output.py

@@ -1,25 +1,36 @@
-import json
+# TODO: output for case where hgvs_nt column available
 
 
 def output(dat, mappings, vrsmaps, blat_dict):
     output_dict = {}
     if mappings:
-        output_dict["sequence"] = coding(dat, mappings, blat_dict)
+        output_dict["sequence"] = protein_coding(dat, mappings, blat_dict)
         output_dict["mapping"] = mapped_variants(vrsmaps[0])
         return output_dict
     else:
-        # TODO:for non coding
-        pass
+        output_dict["sequence"] = non_coding(dat, blat_dict)
+        output_dict["mapping"] = mapped_variants(vrsmaps[0])
 
 
-def coding(dat, mappings, blat_dict, relation="SO:is_homologous_to"):
+def non_coding(dat, blat_dict, relation="SO:is_homologous_to"):
+    seq_dict = {
+        "target": dat["target_sequence"],
+        "chrom": blat_dict["chrom"],
+        "target_type": dat["target_type"],
+        "relation": relation,
+    }
+    return seq_dict
+
+
+def protein_coding(dat, mappings, blat_dict, relation="SO:is_homologous_to"):
     seq_dict = {
         "target": dat["target_sequence"],
         "RefSeq_prot": mappings["RefSeq_prot"],
         "RefSeq_nuc": mappings["RefSeq_nuc"],
         "gsymb": mappings["gsymb"],
         "chrom": blat_dict["chrom"],
-        "relation": relation
+        "target_type": dat["target_type"],
+        "relation": relation,
     }
     return seq_dict
 
@@ -28,7 +39,7 @@ def mapped_variants(vrs):
     premapped = vrs["pre_mapping"]
     mapped = vrs["mapped"]
     mapp = list()
-    for i in range(3):
+    for i in range(len(premapped)):
         c = maps(premapped[i], mapped[i])
         mapp.append(c)
     return mapp
@@ -38,5 +49,5 @@ def maps(pre, post):
     d = {}
     d["pre_mapped"] = pre
     d["mapped"] = post
-    
+
     return d

mavedb_mapping/vrs_mapping.py

@@ -239,11 +239,7 @@ def vrs_mapping_for_protein_coding(
         scores_list.append(sn)
         accessions_list.append(accn)
 
-    vrs_mappings_dict = mappings_list
-    scores_dict_coding = scores_list
-    mavedb_ids_coding = accessions_list
-
-    return vrs_mappings_dict
+    return mappings_list
 
 
 def check_for_transcripts(mappings_dict):
@@ -305,14 +301,12 @@ def vrs_mapping_for_non_coding(dat, mave_blat_dict, ref, ranges, hits, variant_d
     scores_list.append(sn)
     accessions_list.append(accn)
 
-    vrs_mappings_dict = mappings_list
-    scores_dict_coding = scores_list
-    mavedb_ids_coding = accessions_list
-
-    return vrs_mappings_dict
+    return mappings_list
 
 
-def vrs_mapping(dat, mappings_dict, mave_blat_dict, variant_data):
+def vrs_mapping(
+    dat: dict, mappings_dict: dict, mave_blat_dict: dict, variant_data: dict
+) -> list:
     """
     Perform VRS mapping for protein coding scoresets.
 
@@ -327,7 +321,7 @@ def vrs_mapping(dat, mappings_dict, mave_blat_dict, variant_data):
         mave_blat_dict: dict
             Dicitionary containing data after doing BLAT Alignment
 
-        scores_csv: csv
+        variant_data: dict
             Scores from MaveDB.
 
     Returns