Docstrings

mavedb_mapping/main.py

@@ -4,6 +4,7 @@
 from mavedb_mapping.vrs_mapping import vrs_mapping
 from mavedb_mapping import data_file_path
 from mavedb_mapping.output import output
+from mavedb_mapping.find_start_pos import if_start_not_first
 import json
 
 """Function to create a mapping given a scoreset and its scores"""
@@ -18,6 +19,10 @@ def main_map(scoreset, scores_csv):
     # Mapping process
     blat_dict = mave_to_blat(dat)
     transcripts = main(blat_dict, dat)
+    # for seq where start pos is not first
+    c = if_start_not_first(dat, scores)
+    if c:
+        transcripts["start"] = c
     vrs = vrs_mapping(dat, transcripts, blat_dict, scores)
     out = output(dat, transcripts, vrs, blat_dict)
     return out

mavedb_mapping/metadata_process.py

@@ -3,6 +3,7 @@
 
 """Function that specifies input format"""
 
+
 def metadata_obtain(scoreset_json, scores_csv) -> dict:
     """
     Extract data from MaveDB scoresets and convert them into an input format that imitates
@@ -13,14 +14,14 @@ def metadata_obtain(scoreset_json, scores_csv) -> dict:
     ----------
         scoreset_json: json object
             Scoreset JSON object
-        
+
         scores_csv
 
     Returns:
     ----------
         dat: dict
             Dictionary containing extracted metadata
-        
+
         variant_data: dict
             Dictionary containing variants
 
@@ -41,15 +42,18 @@ def metadata_obtain(scoreset_json, scores_csv) -> dict:
         "target_sequence_type": target_type,
         "target_type": target,
     }
-    
+
     vardat = pd.read_csv(scores_csv)
 
     varm = vardat["hgvs_pro"]
     ntlist = vardat["hgvs_nt"]
     scores = vardat["score"].to_list()
     accessions = vardat["accession"].to_list()
 
-    variant_data = {"hgvs_pro": varm, "hgvs_nt":ntlist, "scores":scores, "accessions":accessions}
+    variant_data = {
+        "hgvs_pro": varm,
+        "hgvs_nt": ntlist,
+        "scores": scores,
+        "accessions": accessions,
+    }
     return dat, variant_data
-
-#TODO: change other things according to these changes

mavedb_mapping/output.py

@@ -1,11 +1,31 @@
-# TODO: output for case where hgvs_nt column available
+"""Produces the output with all data from the mapping"""
 
 
-def output(dat, mappings, vrsmaps, blat_dict):
+def output(dat: dict, mappings: dict, vrsmaps: dict, blat_dict: dict) -> dict:
+    """
+    Produces final output in the form of a dictionary
+
+    Parameters
+    ----------
+        dat: dict
+            Dictionary containing data required for mapping.
+
+        mappings: dict
+            Dictionary after transcript selection.
+
+        vrsmaps: dict
+            Dictionary containing premapped and mapped variants
+
+        blat_dict: dict
+            Dicitionary containing data after doing BLAT Alignment
+    """
     output_dict = {}
     if mappings:
         output_dict["sequence"] = protein_coding(dat, mappings, blat_dict)
         output_dict["mapping"] = mapped_variants(vrsmaps[0])
+        if len(vrsmaps > 1):
+            output_dict["mapping"] = mapped_variants(vrsmaps[1])
+
         return output_dict
     else:
         output_dict["sequence"] = non_coding(dat, blat_dict)