tabtk 1.0.1__tar.gz → 1.0.3__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: 1.0.1
3
+ Version: 1.0.3
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__ = "1.0.1"
3
+ __version__ = "1.0.3"
4
4
 
@@ -57,7 +57,7 @@ def pairwiseSimilarity(firstRecord,secondRecord):
57
57
  return(similarityData)
58
58
 
59
59
 
60
- def alignmentSimilarity(ij):
60
+ def alignmentSimilarity(i,j):
61
61
  seqMatch=0
62
62
  seqMisMatch=0
63
63
 
@@ -89,6 +89,11 @@ def mashSimilarity(cmdValues):
89
89
  else:
90
90
  pass
91
91
 
92
+ if int(cmdValues["length"])>=16:
93
+ print("Note: use shorter k-mers ≤16 when working diverse sequences")
94
+ else:
95
+ pass
96
+
92
97
  tmpOut = f"mash.{str(datetime.datetime.now()).replace(" ","").replace("-",".").replace(":",".")}"
93
98
  tmpOutR = f"mash.{str(datetime.datetime.now()).replace(" ","").replace("-",".").replace(":",".")}"
94
99
 
@@ -168,7 +173,7 @@ def blastSimilarity(cmdValues):
168
173
  tmpOut2 = f"blast.{str(datetime.datetime.now()).replace(" ","").replace("-",".").replace(":",".")}"
169
174
 
170
175
  blastCmd1 = f"echo \'qseqid sseqid length pident qcovs\' | tr \' \' \'\\t\' > {tmpOut2}"
171
- blastCmd2 = f"blastn -db {tmpOut} -query {tmpOut} -num_threads {cmdValues["threads"]} -outfmt \'6 qseqid sseqid length pident qcovs\' -evalue 0.001 >> {tmpOut2}"
176
+ 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}"
172
177
 
173
178
  subprocess.call(blastCmd1,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
174
179
  subprocess.call(blastCmd2,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
@@ -177,7 +182,7 @@ def blastSimilarity(cmdValues):
177
182
  blastData["tmp"] = blastData.apply(lambda x: (x["qcovs"] * x["pident"])/100,axis=1)
178
183
 
179
184
  blastData["qseqidR"] = blastData.apply(lambda x: x["qseqid"] if x["qseqid"] > x["sseqid"] else x["sseqid"],axis=1)
180
- blastData["sseqidR"] = blastData.apply(lambda x: x["qseqid"] if x["qseqid"] < x["sseqid"] else x["sseqid"],axis=1)
185
+ blastData["sseqidR"] = blastData.apply(lambda x: x["sseqid"] if x["qseqid"] > x["sseqid"] else x["qseqid"],axis=1)
181
186
 
182
187
  blastData["qseqid"] = blastData["qseqidR"]
183
188
  blastData["sseqid"] = blastData["sseqidR"]
@@ -225,23 +230,35 @@ def fastaniSimilarity(cmdValues):
225
230
  else:
226
231
  pass
227
232
 
233
+ if int(cmdValues["length"])>=16:
234
+ print("Note: use shorter k-mers ≤16 when working diverse sequences")
235
+ else:
236
+ pass
237
+
228
238
  tmpOut = f"mash.{str(datetime.datetime.now()).replace(" ","").replace("-",".").replace(":",".")}"
229
239
 
230
- fastaniCmd = f"fastANI --rl {cmdValues["data"]} --ql {cmdValues["data"]} -k {cmdValues["length"]} --matrix --fragLen {cmdValues["fragment"]} --minFraction {cmdValues["fraction"]} --output {tmpOut} -t {cmdValues["threads"]}"
240
+ fastaniCmd = f"fastANI --rl {cmdValues["data"]} --ql {cmdValues["data"]} --kmer {cmdValues["length"]} --matrix --fragLen {cmdValues["fragment"]} --minFraction {cmdValues["fraction"]} --output {tmpOut} --threads {cmdValues["threads"]}"
231
241
 
232
242
  print("Calculating percent similarity... may take longer... be patient...")
233
243
 
234
244
  subprocess.call(fastaniCmd,shell=True,stdout=subprocess.DEVNULL,stderr=subprocess.STDOUT)
235
245
 
236
246
  fastaniResults = []
237
-
247
+
238
248
  with open(tmpOut,"r") as fastaniFile:
239
249
  for itemPos,fastaniOutput in enumerate(fastaniFile):
240
- if itemPos == 0:
241
- pass
242
- else:
243
- item = fastaniOutput.strip().split("\t")
244
- fastaniResults.append(f"{Path(item[0]).stem}\t{Path(item[1]).stem}\t{float(item[2])}")
250
+ item = fastaniOutput.strip().split("\t")
251
+ fastaniResults.append([Path(item[0]).stem,Path(item[1]).stem,float(item[2])])
252
+
253
+ fastaniData = pd.DataFrame(fastaniResults, columns=["seq1R","seq2R","pidR"])
254
+ fastaniData['pidR'] = fastaniData['pidR'].astype(float)
255
+
256
+ fastaniData["seq1RR"] = fastaniData.apply(lambda x: x["seq1R"] if x["seq1R"] > x["seq2R"] else x["seq2R"],axis=1)
257
+ fastaniData["seq2RR"] = fastaniData.apply(lambda x: x["seq2R"] if x["seq1R"] > x["seq2R"] else x["seq1R"],axis=1)
258
+
259
+ fastaniData = fastaniData[["seq1RR","seq2RR","pidR"]].groupby(['seq1RR','seq2RR']).agg({'pidR':min})
260
+ fastaniDataR = fastaniData.reset_index()
261
+ fastaniDataFinal = fastaniDataR[["seq1RR","seq2RR","pidR"]].rename(columns={"seq1RR":"seq1","seq2RR":"seq2","pid":"pidR"}).values.tolist()
245
262
 
246
263
  if os.path.exists(tmpOut):
247
264
  os.remove(tmpOut)
@@ -253,7 +270,7 @@ def fastaniSimilarity(cmdValues):
253
270
  else:
254
271
  pass
255
272
 
256
- return(fastaniResults)
273
+ return(fastaniDataFinal)
257
274
 
258
275
 
259
276
  def similarity(cmdValues):
@@ -307,7 +324,7 @@ def similarity(cmdValues):
307
324
 
308
325
  bar = ChargingBar('Writing similarity values', max=len(similarityResults))
309
326
  for itemPair in similarityResults:
310
- simData.write(f"{itemPair}\n")
327
+ simData.write(f"{"\t".join([str(r) for r in itemPair])}\n")
311
328
 
312
329
  bar.next()
313
330
  bar.finish()
@@ -1210,7 +1227,7 @@ def table(cmdValues):
1210
1227
  args = [(seqFileNum,seqFileName,kmersFile,cmdValues) for seqFileNum,seqFileName in seqFileDF]
1211
1228
  kmerResults = pool.starmap(queryKmers, args)
1212
1229
 
1213
- with open(f"{Path(cmdValues["output"]).stem}.table.tsv","w") as kmerData:
1230
+ with open(f"{cmdValues["output"]}","w") as kmerData:
1214
1231
  kmerFiles = []
1215
1232
  kmerHeaderFiles = []
1216
1233
 
@@ -1557,8 +1574,8 @@ def tabtkMain():
1557
1574
  'output': options.output[0:][0] if isinstance(options.output,list) else options.output,
1558
1575
  'length': int(options.length[0:][0]) if isinstance(options.length,list) else int(options.length),
1559
1576
  'fragment': int(options.fragment[0:][0]) if isinstance(options.fragment,list) else int(options.fragment),
1560
- 'fraction': int(options.fraction[0:][0]) if isinstance(options.fraction,list) else int(options.fraction),
1561
- 'size': int(options.size[0:][0]) if isinstance(options.size,list) else int(options.size),
1577
+ 'fraction': float(options.fraction[0:][0]) if isinstance(options.fraction,list) else float(options.fraction),
1578
+ 'size': float(options.size[0:][0]) if isinstance(options.size,list) else float(options.size),
1562
1579
  'mash': options.mash,
1563
1580
  'fastani': options.fastani,
1564
1581
  'blast': options.blast,
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tabtk
3
- Version: 1.0.1
3
+ Version: 1.0.3
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