YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 07:40:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
Auden Cote-L'Heureux 2024-10-17 16:45:55 -04:00 committed by GitHub
parent d57fdad826
commit d249add545
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 16 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
Utilities/for_fastas/CUB.py
View File

@ -1,4 +1,4 @@
#Author, date: Xyrus (last modified by him Sept 17 2020), most recently updated by Auden on July 19 2023 #Author, date: Xyrus (last modified by him Sept 17 2020), most recently updated by Auden on October 17 2024
#Motivation: Generate lots of codon usage statistics to aid in identifying useful characteristics for de novo ORF calling #Motivation: Generate lots of codon usage statistics to aid in identifying useful characteristics for de novo ORF calling
#Intent: Summarize nucleotide composition statistics for a fasta file or folder of fasta files #Intent: Summarize nucleotide composition statistics for a fasta file or folder of fasta files
#Dependencies: Python3, numpy, BioPython #Dependencies: Python3, numpy, BioPython
@ -356,6 +356,12 @@ class GCeval():
return round(GC(''.join([seq[n] for n in return round(GC(''.join([seq[n] for n in
range(2, len(seq)-len(seq[2:]) % 3, 3)])), 4) range(2, len(seq)-len(seq[2:]) % 3, 3)])), 4)
def gc3s(cdnTbl):
# This function return the GC content of the third position of a codon excluding Tryp and Met
syn = round(GC(''.join([k[-1]*v[-1] for k, v in cdnTbl.items() if v[0] != 'W' and v[0] != 'M'])), 4)
return syn
def gc3_4F(cdnTbl): def gc3_4F(cdnTbl):
# # This function return the GC content of the third position of four-fold # # This function return the GC content of the third position of four-fold
# # degenerate codons # # degenerate codons
@ -385,7 +391,7 @@ class SeqInfo(object):
def ENcStats(self): def ENcStats(self):
# Stores the various Effective Number of Codons calculations in the class # Stores the various Effective Number of Codons calculations in the class
self.expENc = CalcCUB.expWrightENc(self.gc3) self.expENc = CalcCUB.expWrightENc(self.gc3s)
self.obsENc_6F = CalcCUB.calcWrightENc(self.cdnCounts_6F) self.obsENc_6F = CalcCUB.calcWrightENc(self.cdnCounts_6F)
self.obsENc_No6F = CalcCUB.calcWrightENc(self.cdnCounts_No6F) self.obsENc_No6F = CalcCUB.calcWrightENc(self.cdnCounts_No6F)
self.SunENc_6F = CalcCUB.SunEq5(self.cdnCounts_6F) self.SunENc_6F = CalcCUB.SunEq5(self.cdnCounts_6F)
@ -396,6 +402,7 @@ class SeqInfo(object):
for k, v in self.gcFuncs.items(): for k, v in self.gcFuncs.items():
setattr(self,k,v(self.ntd)) setattr(self,k,v(self.ntd))
self.gc4F = GCeval.gc3_4F(self.cdnCounts_No6F) self.gc4F = GCeval.gc3_4F(self.cdnCounts_No6F)
self.gc3s = GCeval.gc3s(self.cdnCounts_No6F)
def RSCUstats(self): def RSCUstats(self):
@ -429,23 +436,23 @@ def CalcRefFasta(fasta, gCode):
def WriteWrightOut(seqData, outName, comp): def WriteWrightOut(seqData, outName, comp):
if comp == False: if comp == False:
with open(outName+'/SpreadSheets/'+outName.split('/')[-1]+'.ENc.Raw.tsv','w+') as w: with open(outName+'/SpreadSheets/'+outName.split('/')[-1]+'.ENc.Raw.tsv','w+') as w:
w.write('SequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\t' w.write('SequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\tGC3S\t'
'GC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\t' 'GC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\t'
'ObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n') 'ObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n')
for k, v in seqData.items(): for k, v in seqData.items():
name = [k] name = [k]
gcs = [str(v.gcOverall),str(v.gc1),str(v.gc2),str(v.gc3),str(v.gc4F)] gcs = [str(v.gcOverall),str(v.gc1),str(v.gc2),str(v.gc3),str(v.gc3s),str(v.gc4F)]
ENc = [str(v.expENc),str(v.obsENc_6F),str(v.obsENc_No6F), ENc = [str(v.expENc),str(v.obsENc_6F),str(v.obsENc_No6F),
str(v.SunENc_6F),str(v.SunENc_No6F)] str(v.SunENc_6F),str(v.SunENc_No6F)]
w.write('\t'.join(name+[str(v.amb_cdn)]+gcs+ENc)+'\n') w.write('\t'.join(name+[str(v.amb_cdn)]+gcs+ENc)+'\n')
else: else:
with open(outName+'/SpreadSheets/'+outName.split('/')[-1]+'.CompTrans.ENc.Raw.tsv','w+') as w: with open(outName+'/SpreadSheets/'+outName.split('/')[-1]+'.CompTrans.ENc.Raw.tsv','w+') as w:
w.write('SequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\t' w.write('SequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\tGC3S\t'
'GC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\t' 'GC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\t'
'ObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n') 'ObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n')
for k, v in seqData.items(): for k, v in seqData.items():
name = [k] name = [k]
gcs = [str(v.gcOverall),str(v.gc1),str(v.gc2),str(v.gc3),str(v.gc4F)] gcs = [str(v.gcOverall),str(v.gc1),str(v.gc2),str(v.gc3),str(v.gc3s),str(v.gc4F)]
ENc = [str(v.expENc),str(v.obsENc_6F),str(v.obsENc_No6F), ENc = [str(v.expENc),str(v.obsENc_6F),str(v.obsENc_No6F),
str(v.SunENc_6F),str(v.SunENc_No6F)] str(v.SunENc_6F),str(v.SunENc_No6F)]
w.write('\t'.join(name+[str(v.amb_cdn)]+gcs+ENc)+'\n') w.write('\t'.join(name+[str(v.amb_cdn)]+gcs+ENc)+'\n')
@ -473,7 +480,7 @@ def getCompFasta(fasta, gCode, require_start, require_stop):
def WriteNullENcOut(outName): def WriteNullENcOut(outName):
with open(outName+'/SpreadSheets/' + outName.split('/')[-1] + '.ENc.Null.tsv','w+') as w: with open(outName+'/SpreadSheets/' + outName.split('/')[-1] + '.ENc.Null.tsv','w+') as w:
w.write('GC3\tENc\n') w.write('GC3S\tENc\n')
w.write('\n'.join(CalcCUB.nullENcGC3())) w.write('\n'.join(CalcCUB.nullENcGC3()))
@ -558,14 +565,14 @@ if __name__ == "__main__":
o.write(folder.split('/')[-1] + '\t' + line) o.write(folder.split('/')[-1] + '\t' + line)
with open('CUBOutput/SpreadSheets/ENc.Raw.tsv', 'w') as o: with open('CUBOutput/SpreadSheets/ENc.Raw.tsv', 'w') as o:
o.write('File\tSequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\tGC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\tObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n') o.write('File\tSequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\tGC3S\tGC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\tObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n')
for folder in folders: for folder in folders:
for line in open(folder + '/SpreadSheets/' + folder.split('/')[-1] + '.ENc.Raw.tsv'): for line in open(folder + '/SpreadSheets/' + folder.split('/')[-1] + '.ENc.Raw.tsv'):
if 'SequenceID' not in line: if 'SequenceID' not in line:
o.write(folder.split('/')[-1] + '\t' + line) o.write(folder.split('/')[-1] + '\t' + line)
with open('CUBOutput/SpreadSheets/CompTrans.ENc.Raw.tsv', 'w') as o: with open('CUBOutput/SpreadSheets/CompTrans.ENc.Raw.tsv', 'w') as o:
o.write('File\tSequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\tGC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\tObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n') o.write('File\tSequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\tGC3S\tGC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\tObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n')
for folder in folders: for folder in folders:
for line in open(folder + '/SpreadSheets/' + folder.split('/')[-1] + '.CompTrans.ENc.Raw.tsv'): for line in open(folder + '/SpreadSheets/' + folder.split('/')[-1] + '.CompTrans.ENc.Raw.tsv'):
if 'SequenceID' not in line: if 'SequenceID' not in line: