tabtk 1.0.3__tar.gz → 1.0.5__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tabtk
3
- Version: 1.0.3
3
+ Version: 1.0.5
4
4
  Summary: tabtk: A toolkit for sequence similarity analysis based on tabular data
5
5
  Author-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>
6
6
  Maintainer-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>
@@ -1,4 +1,4 @@
1
1
  """tabkit: A toolkit for sequence similarity analysis based on tabular data"""
2
2
 
3
- __version__ = "1.0.3"
3
+ __version__ = "1.0.5"
4
4
 
@@ -161,10 +161,16 @@ def blastSimilarity(cmdValues):
161
161
 
162
162
  tmpOut = f"blast.{str(datetime.datetime.now()).replace(" ","").replace("-",".").replace(":",".")}"
163
163
 
164
- Cmd1 = f"cat {" ".join(tmpFileNames)} > {tmpOut}"
164
+ bar = ChargingBar("Creating database", max=len(tmpFileNames))
165
+ with open(tmpOut,"w") as tmpOutFile:
166
+ for fileName in tmpFileNames:
167
+ for seq in SeqIO.parse(fileName,"fasta"):
168
+ tmpOutFile.write(f">{seq.id}\n{seq.seq}\n")
169
+ bar.next()
170
+ bar.finish()
171
+
165
172
  Cmd2 = f"makeblastdb -in {tmpOut} -dbtype nucl"
166
173
 
167
- subprocess.call(Cmd1,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
168
174
  subprocess.call(Cmd2,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
169
175
 
170
176
  print("Calculating percent similarity... may take longer... be patient...")
@@ -181,17 +187,19 @@ def blastSimilarity(cmdValues):
181
187
  blastData = pd.read_csv(tmpOut2,delimiter="\t",dtype={'pident': float,'qcovs': float})
182
188
  blastData["tmp"] = blastData.apply(lambda x: (x["qcovs"] * x["pident"])/100,axis=1)
183
189
 
190
+ blastDataR = blastData[["qseqid","sseqid","tmp"]].groupby(['qseqid','sseqid']).agg({'tmp':'mean'})
191
+ blastDataR = blastDataR.reset_index()
192
+
184
193
  blastData["qseqidR"] = blastData.apply(lambda x: x["qseqid"] if x["qseqid"] > x["sseqid"] else x["sseqid"],axis=1)
185
194
  blastData["sseqidR"] = blastData.apply(lambda x: x["sseqid"] if x["qseqid"] > x["sseqid"] else x["qseqid"],axis=1)
186
195
 
187
196
  blastData["qseqid"] = blastData["qseqidR"]
188
197
  blastData["sseqid"] = blastData["sseqidR"]
189
198
 
190
- blastData["cov"] = blastData[["qseqid","sseqid","tmp"]].groupby(["qseqid","sseqid"])["tmp"].transform(lambda x: statistics.mean(x))
191
- blastDataR = blastData.groupby(["qseqid","sseqid"]).first().reset_index()
199
+ blastDataR = blastData[["qseqid","sseqid","tmp"]].groupby(['qseqid','sseqid']).agg({'tmp':'min'})
200
+ blastDataR = blastDataR.reset_index()
192
201
 
193
- blastData = blastDataR.drop(columns=["tmp","length","pident","qseqidR","sseqidR"])
194
- blastDataFinal = blastData[["sseqid","qseqid","cov"]].rename(columns={"sseqid":"seq1","qseqid":"seq2","cov":"pid"}).values.tolist()
202
+ blastDataFinal = blastDataR[["sseqid","qseqid","tmp"]].rename(columns={"sseqid":"seq1","qseqid":"seq2","tmp":"pid"}).values.tolist()
195
203
 
196
204
  bar = ChargingBar("Cleaning temporary files", max=len(fileNames))
197
205
  for fileName in tmpFileNames:
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tabtk
3
- Version: 1.0.3
3
+ Version: 1.0.5
4
4
  Summary: tabtk: A toolkit for sequence similarity analysis based on tabular data
5
5
  Author-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>
6
6
  Maintainer-email: Chrispin Chaguza <chrispin.chaguza@gmail.com>
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes