YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 15:50:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update CUB.py

Browse Source 
Updates to notes only, including clarifying that we use GC3 and GC3S interchangeably .. though GC3S probably most correct
This commit is contained in:
Katzlab 2025-06-12 04:25:47 -04:00 committed by GitHub
parent d81926f179
commit 3fe4ee3ae5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
Utilities/for_fastas/CUB.py
View File

@ -3,9 +3,10 @@
#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
#Inputs: Fasta file or folder of fasta files #Inputs: Fasta file or folder of fasta files
#Outputs: A fasta file filtered for properly formatted sequences and several spreadsheets summarizing GC, ENc, RSCU, etc. #Outputs: A fasta file filtered for properly formatted sequences and several spreadsheets summarizing GC3S, ENc, RSCU, etc.
#Example: python3 CUB.py -i seqs.fasta #Example: python3 CUB.py -i seqs.fasta
#Note: Use "python3 CUB.py -i seqs.fasta --require_start --require_stop" when using the on R2G files. #Note: Use "python3 CUB.py -i seqs.fasta --require_start --require_stop" to see more conservative estimate
#Note: in this script we use GC3 and GC3S interchangeably, though the abbreviation GC3S is probably more correct
#Dependencies #Dependencies
import os import os
@ -19,11 +20,11 @@ import argparse
class CalcCUB: class CalcCUB:
""" """
Returns the Effective Number of Codons used (observed and expected) Returns the Effective Number of Codons (ENc) used (observed and expected)
following the equations originally from Wright 1990. following the equations originally from Wright 1990.
""" """
def expWrightENc(gc3): def expWrightENc(gc3):
# Calculates the expected ENc from a sequence's GC3 under Wright 1990 # Calculates the expected ENc from a sequence's GC3 (GC3S) under Wright 1990
if gc3 > 1: if gc3 > 1:
# If GC3 looks as though it is > 1 (e.g. 100%), converts to a float ≤ 1. # If GC3 looks as though it is > 1 (e.g. 100%), converts to a float ≤ 1.
# Calculations expect a value between 0 and 1 # Calculations expect a value between 0 and 1
@ -32,7 +33,7 @@ class CalcCUB:
return round(exp_enc, 4) return round(exp_enc, 4)
def nullENcGC3(): def nullENcGC3():
# Calculates the expected ENc from the null distribution of GC3 # Calculates the expected ENc from the null distribution of GC3S
# values (0, 100% GC) # values (0, 100% GC)
null = [CalcCUB.expWrightENc(n) for n in np.arange(0,.51,0.01)] null = [CalcCUB.expWrightENc(n) for n in np.arange(0,.51,0.01)]
null += null[:-1][::-1] null += null[:-1][::-1]