tabtk 1.0.6__tar.gz → 1.0.7__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: 1.0.6
3
+ Version: 1.0.7
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__ = "1.0.6"
3
+ __version__ = "1.0.7"
4
4
 
@@ -172,25 +172,24 @@ def blastSimilarity(cmdValues):
172
172
  Cmd2 = f"makeblastdb -in {tmpOut} -dbtype nucl"
173
173
 
174
174
  subprocess.call(Cmd2,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
175
-
175
+
176
176
  print("Calculating percent similarity... may take longer... be patient...")
177
177
 
178
178
  tmpOut1 = f"blast.{str(datetime.datetime.now()).replace(" ","").replace("-",".").replace(":",".")}"
179
179
  tmpOut2 = f"blast.{str(datetime.datetime.now()).replace(" ","").replace("-",".").replace(":",".")}"
180
180
 
181
181
  blastCmd1 = f"echo \'qseqid sseqid length pident qcovs\' | tr \' \' \'\\t\' > {tmpOut2}"
182
- blastCmd2 = f"blastn -db {tmpOut} -query {tmpOut} -word_size {cmdValues["length"]} -num_threads {cmdValues["threads"]} -outfmt \'6 qseqid sseqid length pident qcovs\' -evalue 0.001 >> {tmpOut2}"
182
+ blastCmd2 = f"blastn -db {tmpOut} -query {tmpOut} -word_size {cmdValues["length"]} -num_threads {cmdValues["threads"]} -outfmt \'6 qseqid sseqid length pident qcovs\' -evalue {cmdValues["evalue"]} >> {tmpOut2}"
183
183
 
184
184
  subprocess.call(blastCmd1,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
185
185
  subprocess.call(blastCmd2,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
186
186
 
187
- blastData = pd.read_csv(tmpOut2,delimiter="\t",dtype={'pident': float,'qcovs': float})
187
+ blastData = pd.read_csv(tmpOut2,delimiter="\t",dtype={'pident': float,'qcovs': float, 'length': int})
188
188
  blastData["tmp"] = blastData.apply(lambda x: (x["length"] * x["pident"]),axis=1)
189
189
 
190
- blastDataR = blastData[["qseqid","sseqid","tmp","length","qcovs"]].groupby(['qseqid','sseqid']).agg({'tmp':'sum','length':'sum'})
191
- blastData["tmp"] = blastData.apply(lambda x: (((x["tmp"] / x["length"]) * x["qcovs"]) / 100),axis=1)
190
+ blastData = blastData[["qseqid","sseqid","tmp","length","qcovs"]].groupby(['qseqid','sseqid']).agg({'tmp':'sum','length':'sum','qcovs':'mean'}).reset_index()
192
191
 
193
- blastDataR = blastDataR.reset_index()
192
+ blastData["tmp1"] = blastData.apply(lambda x: (((x["tmp"] / x["length"]) * x["qcovs"]) / 100),axis=1)
194
193
 
195
194
  blastData["qseqidR"] = blastData.apply(lambda x: x["qseqid"] if x["qseqid"] > x["sseqid"] else x["sseqid"],axis=1)
196
195
  blastData["sseqidR"] = blastData.apply(lambda x: x["sseqid"] if x["qseqid"] > x["sseqid"] else x["qseqid"],axis=1)
@@ -198,10 +197,9 @@ def blastSimilarity(cmdValues):
198
197
  blastData["qseqid"] = blastData["qseqidR"]
199
198
  blastData["sseqid"] = blastData["sseqidR"]
200
199
 
201
- blastDataR = blastData[["qseqid","sseqid","tmp"]].groupby(['qseqid','sseqid']).agg({'tmp':'min'})
202
- blastDataR = blastDataR.reset_index()
200
+ blastDataR = blastData[["qseqid","sseqid","tmp1"]].groupby(['qseqid','sseqid']).agg({'tmp1':'min'}).reset_index()
203
201
 
204
- blastDataFinal = blastDataR[["sseqid","qseqid","tmp"]].rename(columns={"sseqid":"seq1","qseqid":"seq2","tmp":"pid"}).values.tolist()
202
+ blastDataFinal = blastDataR[["sseqid","qseqid","tmp1"]].rename(columns={"sseqid":"seq1","qseqid":"seq2","tmp1":"pid"}).values.tolist()
205
203
 
206
204
  bar = ChargingBar("Cleaning temporary files", max=len(fileNames))
207
205
  for fileName in tmpFileNames:
@@ -334,7 +332,7 @@ def similarity(cmdValues):
334
332
 
335
333
  bar = ChargingBar('Writing similarity values', max=len(similarityResults))
336
334
  for itemPair in similarityResults:
337
- simData.write(f"{"\t".join([str(r) for r in itemPair])}\n")
335
+ simData.write(f"{"\t".join([str(r).strip() for r in itemPair])}\n")
338
336
 
339
337
  bar.next()
340
338
  bar.finish()
@@ -1365,6 +1363,9 @@ def tabtkMain():
1365
1363
  similarityOptions.add_argument('--fragment','-r',action='store',required=False,nargs=1,
1366
1364
  metavar='fragment',dest='fragment',default=500,type=int,
1367
1365
  help='Fragment length for calculating ANI; use with --fastani (default: 500)')
1366
+ similarityOptions.add_argument('--evalue','-e',action='store',required=False,nargs=1,
1367
+ metavar='evalue',dest='evalue',default=0.001,type=float,
1368
+ help='Minimum evalue for hits; use with --blast (default: 0.001)')
1368
1369
  similarityOptions.add_argument('--threads','-t',action='store',required=False,nargs=1,
1369
1370
  metavar='threads',dest='threads',default=5,type=int,
1370
1371
  help='Number of threads (default: 5)')
@@ -1590,6 +1591,7 @@ def tabtkMain():
1590
1591
  'fastani': options.fastani,
1591
1592
  'blast': options.blast,
1592
1593
  'aln': options.aln,
1594
+ 'evalue': float(options.evalue[0:][0]) if isinstance(options.evalue,list) else float(options.evalue),
1593
1595
  'threads': int(options.threads[0:][0]) if isinstance(options.threads,list) else int(options.threads)
1594
1596
  }
1595
1597
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tabtk
3
- Version: 1.0.6
3
+ Version: 1.0.7
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