Merge pull request #98 from apriha/develop

v2.0.1
apriha · Sep 25, 2020 · 2baeb62 · 2baeb62
2 parents 5acb035 + 826ce27
commit 2baeb62
Show file tree

Hide file tree

Showing 3 changed files with 38 additions and 19 deletions.
diff --git a/src/snps/io/reader.py b/src/snps/io/reader.py
@@ -167,8 +167,8 @@ def __call__(self):
             d = self.read_myheritage(file, compression)
         elif "Living DNA" in first_line:
             d = self.read_livingdna(file, compression)
-        elif "SNP Name	rsID	Sample.ID	Allele1...Top" in first_line:
-            d = self.read_mapmygenome(file, compression)
+        elif "SNP Name\trsID" in first_line or "SNP.Name\tSample.ID" in first_line:
+            d = self.read_mapmygenome(file, compression, first_line)
         elif "lineage" in first_line or "snps" in first_line:
             d = self.read_snps_csv(file, comments, compression)
         elif "Chromosome" in first_line:
@@ -705,7 +705,7 @@ def parser():
 
         return self.read_helper("LivingDNA", parser)
 
-    def read_mapmygenome(self, file, compression):
+    def read_mapmygenome(self, file, compression, header):
         """ Read and parse Mapmygenome file.
 
         https://mapmygenome.in
@@ -722,22 +722,28 @@ def read_mapmygenome(self, file, compression):
         """
 
         def parser():
-            df = pd.read_csv(
-                file,
-                comment="#",
-                sep="\t",
-                na_values="--",
-                header=0,
-                index_col=1,
-                dtype={
-                    "rsID": object,
-                    "Chr": object,
-                    "Position": np.uint32,
-                    "Allele1...Top": object,
-                    "Allele2...Top": object,
-                },
-                compression=compression,
-            )
+            def parse(rsid_col_name, rsid_col_idx):
+                return pd.read_csv(
+                    file,
+                    comment="#",
+                    sep="\t",
+                    na_values="--",
+                    header=0,
+                    index_col=rsid_col_idx,
+                    dtype={
+                        rsid_col_name: object,
+                        "Chr": object,
+                        "Position": np.uint32,
+                        "Allele1...Top": object,
+                        "Allele2...Top": object,
+                    },
+                    compression=compression,
+                )
+
+            if "rsID" in header:
+                df = parse("rsID", 1)
+            else:
+                df = parse("SNP.Name", 0)
 
             df["genotype"] = df["Allele1...Top"] + df["Allele2...Top"]
             df.rename(columns={"Chr": "chrom", "Position": "pos"}, inplace=True)

diff --git a/tests/input/mapmygenome_alt_header.txt b/tests/input/mapmygenome_alt_header.txt
@@ -0,0 +1,9 @@
+SNP.Name	Sample.ID	Allele1...Top	Allele2...Top	GC.Score	Sample.Name	Sample.Group	Sample.Index	SNP.Index	SNP.Aux	Allele1...Forward	Allele2...Forward	Allele1...Design	Allele2...Design	Allele1...AB	Allele2...AB	Allele1...Plus	Allele2...Plus	Chr	Position	GT.Score	Cluster.Sep	SNP	ILMN.Strand	Customer.Strand	Top.Genomic.Sequence	Plus.Minus.Strand	Theta	R	X	Y	X.Raw	Y.Raw	B.Allele.Freq	Log.R.Ratio	CNV.Value	CNV.Confidence
+rs1	0	A	A	0	NA	NA	0	0	0	A	A	A	A	A	A	A	A	1	101	0	1	[A/A]	TOP	TOP	NA	+	0	0	0	0	0	0	0	0	NA	NA
+rs2	0	C	C	0	NA	NA	0	0	0	A	A	A	A	A	A	A	A	1	102	0	1	[A/A]	TOP	TOP	NA	+	0	0	0	0	0	0	0	0	NA	NA
+rs3	0	G	G	0	NA	NA	0	0	0	A	A	A	A	A	A	A	A	1	103	0	1	[A/A]	TOP	TOP	NA	+	0	0	0	0	0	0	0	0	NA	NA
+rs4	0	T	T	0	NA	NA	0	0	0	A	A	A	A	A	A	A	A	1	104	0	1	[A/A]	TOP	TOP	NA	+	0	0	0	0	0	0	0	0	NA	NA
+rs5	0	--	--	0	NA	NA	0	0	0	A	A	A	A	A	A	A	A	1	105	0	1	[A/A]	TOP	TOP	NA	+	0	0	0	0	0	0	0	0	NA	NA
+rs6	0	G	C	0	NA	NA	0	0	0	A	A	A	A	A	A	A	A	1	106	0	1	[A/A]	TOP	TOP	NA	+	0	0	0	0	0	0	0	0	NA	NA
+rs7	0	T	C	0	NA	NA	0	0	0	A	A	A	A	A	A	A	A	1	107	0	1	[A/A]	TOP	TOP	NA	+	0	0	0	0	0	0	0	0	NA	NA
+rs8	0	A	T	0	NA	NA	0	0	0	A	A	A	A	A	A	A	A	1	108	0	1	[A/A]	TOP	TOP	NA	+	0	0	0	0	0	0	0	0	NA	NA
diff --git a/tests/io/test_reader.py b/tests/io/test_reader.py
@@ -302,6 +302,10 @@ def test_read_mapmygenome(self):
         # https://mapmygenome.in
         self.run_parsing_tests("tests/input/mapmygenome.txt", "Mapmygenome")
 
+    def test_read_mapmygenome_alt_header(self):
+        # https://mapmygenome.in
+        self.run_parsing_tests("tests/input/mapmygenome_alt_header.txt", "Mapmygenome")
+
     def test_read_myheritage(self):
         # https://www.myheritage.com
         self.run_parsing_tests("tests/input/myheritage.csv", "MyHeritage")