tabtk 1.0.4__tar.gz → 1.0.6__tar.gz

{tabtk-1.0.4 → tabtk-1.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tabtk
-Version: 1.0.4
+Version: 1.0.6
 Summary: tabtk: A toolkit for sequence similarity analysis based on tabular data
 Author-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>
 Maintainer-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>

{tabtk-1.0.4 → tabtk-1.0.6}/tabtk/__init__.py

@@ -1,4 +1,4 @@
 """tabkit: A toolkit for sequence similarity analysis based on tabular data"""
 
-__version__ = "1.0.4"
+__version__ = "1.0.6"
 

{tabtk-1.0.4 → tabtk-1.0.6}/tabtk/tabtk.py

@@ -161,10 +161,16 @@ def blastSimilarity(cmdValues):
 
     tmpOut = f"blast.{str(datetime.datetime.now()).replace(" ","").replace("-",".").replace(":",".")}"
 
-    Cmd1 = f"cat {" ".join(tmpFileNames)} > {tmpOut}"
+    bar = ChargingBar("Creating database", max=len(tmpFileNames))
+    with open(tmpOut,"w") as tmpOutFile:
+        for fileName in tmpFileNames:
+            for seq in SeqIO.parse(fileName,"fasta"):
+                tmpOutFile.write(f">{seq.id}\n{seq.seq}\n")
+            bar.next()
+        bar.finish()
+
     Cmd2 = f"makeblastdb -in {tmpOut} -dbtype nucl"
 
-    subprocess.call(Cmd1,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
     subprocess.call(Cmd2,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
 
     print("Calculating percent similarity... may take longer... be patient...")
@@ -179,9 +185,11 @@ def blastSimilarity(cmdValues):
     subprocess.call(blastCmd2,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
 
     blastData = pd.read_csv(tmpOut2,delimiter="\t",dtype={'pident': float,'qcovs': float})
-    blastData["tmp"] = blastData.apply(lambda x: (x["qcovs"] * x["pident"])/100,axis=1)
+    blastData["tmp"] = blastData.apply(lambda x: (x["length"] * x["pident"]),axis=1)
+
+    blastDataR = blastData[["qseqid","sseqid","tmp","length","qcovs"]].groupby(['qseqid','sseqid']).agg({'tmp':'sum','length':'sum'})
+    blastData["tmp"] = blastData.apply(lambda x: (((x["tmp"] / x["length"]) * x["qcovs"]) / 100),axis=1)
 
-    blastDataR = blastData[["qseqid","sseqid","tmp"]].groupby(['qseqid','sseqid']).agg({'tmp':'mean'})
     blastDataR = blastDataR.reset_index()
 
     blastData["qseqidR"] = blastData.apply(lambda x: x["qseqid"] if x["qseqid"] > x["sseqid"] else x["sseqid"],axis=1)

{tabtk-1.0.4 → tabtk-1.0.6}/tabtk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tabtk
-Version: 1.0.4
+Version: 1.0.6
 Summary: tabtk: A toolkit for sequence similarity analysis based on tabular data
 Author-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>
 Maintainer-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>