YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 07:50:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update Trim_Reads.py

Browse Source
This commit is contained in:
Adri K. Grow 2025-06-26 15:55:15 -04:00 committed by GitHub
parent ef6b633de7
commit d33ac6c2c3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 16 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
Utilities/For_Assemblies/Trim_Reads.py
View File

@ -37,27 +37,35 @@ else:
if not os.path.isdir('ToAssemble/'): if not os.path.isdir('ToAssemble/'):
os.system('mkdir ToAssemble') os.system('mkdir ToAssemble')
### takes your downloaded data and renames the file so that it has taxonomic information in the filename ### takes your raw read data and renames the files with your assigned new names and alters the end to either FwdPE or RevPE
def rename(code): def rename(code):
for filename in os.listdir(os.curdir): for filename in os.listdir(os.curdir):
if filename.endswith('.fastq.gz'): if filename.endswith('.fastq.gz'):
### check name code here for forward reads # Forward read patterns
if '_FwdPE' in filename or '_R1' in filename: forward_tags = ['_FwdPE', '_R1', '_FPE']
cur_name = filename.split('_FwdPE')[0] if '_FwdPE' in filename else filename.split('_R1')[0] if any(tag in filename for tag in forward_tags):
for tag in forward_tags:
if tag in filename:
cur_name = filename.split(tag)[0]
break
if cur_name in code: if cur_name in code:
new_name = code[cur_name] new_name = code[cur_name]
print(cur_name, new_name) print(cur_name, new_name)
os.system(f'mv {filename} {new_name}_FwdPE.fastq.gz') os.system(f'mv {filename} {new_name}_FwdPE.fastq.gz')
os.system(f'mkdir -p {new_name}') os.system(f'mkdir -p {new_name}')
### check name code here for reverse reads
elif '_RevPE' in filename or '_R2' in filename: # Reverse read patterns
cur_name = filename.split('_RevPE')[0] if '_RevPE' in filename else filename.split('_R2')[0] reverse_tags = ['_RevPE', '_R2', '_RPE']
if any(tag in filename for tag in reverse_tags):
for tag in reverse_tags:
if tag in filename:
cur_name = filename.split(tag)[0]
break
if cur_name in code: if cur_name in code:
new_name = code[cur_name] new_name = code[cur_name]
print(cur_name, new_name) print(cur_name, new_name)
os.system(f'mv {filename} {new_name}_RevPE.fastq.gz') os.system(f'mv {filename} {new_name}_RevPE.fastq.gz')
### Uses the adapters.fa file in the bbtools resources folder (and BBDuK) to remove adapter sequences -- update if necessary ### Uses the adapters.fa file in the bbtools resources folder (and BBDuK) to remove adapter sequences -- update if necessary
### Uses BBDuK to quality trim reads so the average is q24 and the min length is 100 -- adjust if needed ... flags will be added eventually ### Uses BBDuK to quality trim reads so the average is q24 and the min length is 100 -- adjust if needed ... flags will be added eventually
def QualityTrim(qtrim, minlen): def QualityTrim(qtrim, minlen):