Skip to content

add compressed fasta support #53

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: prokka_optional
Choose a base branch
from
Open

add compressed fasta support #53

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5c0793f
add compressed fasta support
KateSakharova Aug 1, 2025
44cca57
add compressed fasta support
KateSakharova Aug 1, 2025
fde12bc
fix links support
KateSakharova Aug 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions assets/schema_input.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
},
"assembly": {
"type": "string",
"pattern": "^\\S+\\.(fa|fna|fasta)$",
"pattern": "^.+\\.(fa|fasta|fna)(\\.gz)?$",
"errorMessage": "The assembly needs to be a fasta file"
},
"user_gff": {
Expand Down Expand Up @@ -44,7 +44,7 @@
"maxLength": 0
}
]
},
}
},
"required": ["sample", "assembly"]
}
Expand Down
30 changes: 17 additions & 13 deletions bin/assembly_filter_rename.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@

from Bio import SeqIO
import argparse
import fileinput
import os


def rename(input_file, prefix):
Expand All @@ -27,19 +29,21 @@ def rename(input_file, prefix):
with open(output_1kb, "w") as to_1kb, open(output_5kb, "w") as to_5kb, open(
output_map, "w"
) as to_map, open(output_100kb, "w") as to_100kb:
for counter, record in enumerate(SeqIO.parse(input_file, "fasta"), 1):
new_id = ">contig_" + str(counter)
my_chain = str(record.seq).upper()
to_map.write(new_id + "\t" + str(record.id) + "\n")
if len(my_chain) > 1000:
to_1kb.write(new_id + "\n")
to_1kb.write(my_chain + "\n")
if len(my_chain) > 5000:
to_5kb.write(new_id + "\n")
to_5kb.write(my_chain + "\n")
if len(my_chain) >= 100000:
to_100kb.write(new_id + "\n")
to_100kb.write(my_chain + "\n")
real_path = os.path.realpath(input_file)
with fileinput.hook_compressed(real_path, "rt") as file_in:
for counter, record in enumerate(SeqIO.parse(file_in, "fasta"), 1):
new_id = ">contig_" + str(counter)
my_chain = str(record.seq).upper()
to_map.write(new_id + "\t" + str(record.id) + "\n")
if len(my_chain) > 1000:
to_1kb.write(new_id + "\n")
to_1kb.write(my_chain + "\n")
if len(my_chain) > 5000:
to_5kb.write(new_id + "\n")
to_5kb.write(my_chain + "\n")
if len(my_chain) >= 100000:
to_100kb.write(new_id + "\n")
to_100kb.write(my_chain + "\n")


def main():
Expand Down
3 changes: 2 additions & 1 deletion workflows/mobilomeannotation.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,8 +77,9 @@ workflow MAIN {
}
}

assembly_files = ch_inputs.map { meta, fasta, _user_proteins_gff, _virify_gff -> [meta, fasta] }
// PREPROCESSING
RENAME( ch_inputs.map { meta, fasta, _user_proteins_gff, _virify_gff -> [meta, fasta] } )
RENAME( assembly_files )

// PROKKA annotation is optional and is skipped by default.
// When PROKKA annotation is activated, AMRfinder plus run as well
Expand Down