Skip to content
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

adding simple capability to handle fasta data #6

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

adding simple capability to handle fasta data #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
36 changes: 36 additions & 0 deletions q2_sourmash/_compute.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,13 +7,49 @@
# ----------------------------------------------------------------------------

from q2_types.per_sample_sequences import SingleLanePerSampleSingleEndFastqDirFmt, FastqGzFormat
from q2_types.feature_data import DNAIterator
import qiime2.util
import pandas as pd
from q2_sourmash._format import MinHashSigJsonDirFormat
import os
import subprocess
import glob
import sys
import tempfile
import shutil

def compute_fasta(sequence_file: DNAIterator,
ksizes: int,
scaled: int,
track_abundance: bool=True) -> MinHashSigJsonDirFormat:
output = MinHashSigJsonDirFormat()

# write files in tmp dir
#with tempfile.TemporaryDirectory() as temp_dir:
for seq in sequence_file:
tmp_fp = os.path.join(str(output), str(seq.metadata['id']) + '.fasta')
with open(tmp_fp, 'w') as indiv_fasta:
seq.write(indiv_fasta)

command = ['sourmash',
'compute',
str(output) + "/*",
'--ksizes',
str(ksizes),
'--scaled',
str(scaled)]

if track_abundance:
command.append('--track-abundance')

subprocess.run(' '.join(command), check=True, shell=True, cwd=str(output))

for seq_file in glob.glob(os.path.join(str(output), '*fasta')):
os.remove(seq_file)

sys.stdout.flush()

return output


def compute(sequence_file:SingleLanePerSampleSingleEndFastqDirFmt, ksizes: int, scaled: int, track_abundance: bool=True) -> MinHashSigJsonDirFormat:
Expand Down
14 changes: 13 additions & 1 deletion q2_sourmash/plugin_setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,10 +13,11 @@
from qiime2.plugin import Plugin, Metadata, Str, List, Citations, SemanticType, TextFileFormat, ValidationError
from qiime2.plugin import model
import qiime2.util
from q2_sourmash._compute import compute
from q2_sourmash._compute import compute, compute_fasta
from q2_sourmash._compare import compare
from q2_types.distance_matrix import DistanceMatrix
from q2_types.sample_data import SampleData
from q2_types.feature_data import FeatureData, Sequence
from q2_types.per_sample_sequences import SequencesWithQuality
from ._format import MinHashSigJsonDirFormat, MinHashSigJson
from ._types import MinHashSig
Expand All @@ -41,6 +42,17 @@
plugin.register_views(MinHashSigJson, MinHashSigJsonDirFormat)
plugin.register_semantic_types(MinHashSig)

plugin.methods.register_function(
function=compute_fasta,
inputs={'sequence_file': FeatureData[Sequence]},
parameters={'ksizes': qiime2.plugin.Int,
'scaled': qiime2.plugin.Int,
'track_abundance': qiime2.plugin.Bool},
outputs=[('min_hash_signature', MinHashSig)],
name = 'compute sourmash signature',
description = 'Computes a sourmash MinHash signature from genome fasta files.'
)

plugin.methods.register_function(
function=compute,
inputs={'sequence_file': SampleData[SequencesWithQuality]},
Expand Down