Skip to content

Commit

Permalink
DEV: Replace argparse with click and fix #26
Browse files Browse the repository at this point in the history
  • Loading branch information
@Vini2
Vini2 committed May 15, 2023
1 parent 1d239da commit 09f36e8
Show file tree
Hide file tree
Showing 2 changed files with 233 additions and 335 deletions.
275 changes: 233 additions & 42 deletions metacoag
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
#!/usr/bin/env python3

import click
import concurrent.futures
import csv
import gc
Expand All @@ -15,9 +16,7 @@ from Bio import SeqIO
from igraph import *
from tqdm import tqdm

from metacoag_utils import (feature_utils, file_utils, graph_utils,
label_prop_utils, marker_gene_utils,
matching_utils)
from metacoag_utils import (feature_utils, graph_utils, label_prop_utils, marker_gene_utils, matching_utils)
from metacoag_utils.bidirectionalmap import BidirectionalMap

__author__ = "Vijini Mallawaarachchi and Yu Lin"
Expand All @@ -28,49 +27,185 @@ __maintainer__ = "Vijini Mallawaarachchi"
__email__ = "vijini.mallawaarachchi@anu.edu.au"
__status__ = "Stable Release"

# Set paramters

# Set global paramters
# ---------------------------------------------------

MAX_WEIGHT = sys.float_info.max
M_MARKER_GENES = 108


def main():
# Setup argument parser
# ---------------------------------------------------

args = file_utils.get_args(__version__)

# Validate arguments
validated_args = file_utils.validate(args)

# Parse arguments
assembler = validated_args["assembler"]
contigs_file = validated_args["contigs"]
assembly_graph_file = validated_args["graph"]
contig_paths_file = validated_args["paths"]
abundance_file = validated_args["abundance"]
output_path = validated_args["output"]
prefix = validated_args["prefix"]
min_length = validated_args["min_length"]
p_intra = validated_args["p_intra"]
p_inter = validated_args["p_inter"]
depth = validated_args["depth"]
mg_threshold = validated_args["mg_threshold"]
bin_mg_threshold = validated_args["bin_mg_threshold"]
min_bin_size = validated_args["min_bin_size"]
hmm = validated_args["hmm"]
d_limit = validated_args["d_limit"]
delimiter = validated_args["delimiter"]
nthreads = validated_args["nthreads"]
# Setup argument parser
# ---------------------------------------------------

@click.command()
@click.option(
"--assembler",
help="name of the assembler used. (Supports SPAdes, MEGAHIT and Flye)",
type=click.Choice(["spades", "megahit", "megahitc", "flye"], case_sensitive=False),
required=True,
)
@click.option(
"--graph",
help="path to the assembly graph file",
type=click.Path(exists=True),
required=True,
)
@click.option(
"--contigs",
help="path to the contigs file",
type=click.Path(exists=True),
required=True,
)
@click.option(
"--abundance",
help="path to the abundance file",
type=click.Path(exists=True),
required=True,
)
@click.option(
"--paths",
help="path to the contigs.paths (metaSPAdes) or assembly.info (metaFlye) file",
type=click.Path(exists=True),
required=False,
)
@click.option(
"--output",
help="path to the output folder",
type=click.Path(dir_okay=True, writable=True, readable=True),
required=True,
)
@click.option(
"--hmm",
help="path to marker.hmm file. [default: auxiliary/marker.hmm]",
type=click.Path(exists=True),
required=False,
)
@click.option(
"--prefix",
help="prefix for the output file",
type=str,
required=False,
)
@click.option(
"--min_length",
help="minimum length of contigs to consider for binning.",
type=int,
default=1000,
show_default=True,
required=False,
)
@click.option(
"--p_intra",
help="minimum probability of an edge matching to assign to the same bin.",
type=click.FloatRange(0, 1),
default=0.1,
show_default=True,
required=False,
)
@click.option(
"--p_inter",
help="maximum probability of an edge matching to create a new bin.",
type=click.FloatRange(0, 1),
default=0.01,
show_default=True,
required=False,
)
@click.option(
"--d_limit",
help="distance limit for contig matching.",
type=int,
default=20,
show_default=True,
required=False,
)
@click.option(
"--depth",
help="depth to consider for label propagation.",
type=int,
default=10,
show_default=True,
required=False,
)
@click.option(
"--mg_threshold",
help="length threshold to consider marker genes.",
type=click.FloatRange(0, 1, clamp=True),
default=0.5,
show_default=True,
required=False,
)
@click.option(
"--bin_mg_threshold",
help="minimum fraction of marker genes that should be present in a bin.",
type=click.FloatRange(0, 1, clamp=True),
default=0.33333,
show_default=True,
required=False,
)
@click.option(
"--min_bin_size",
help="minimum size of a bin to output in base pairs (bp).",
type=int,
default=200000,
show_default=True,
required=False,
)
@click.option(
"--delimiter",
help="delimiter for output results. Supports a comma (,), a semicolon (;), a tab ($'\\t'), a space (\" \") and a pipe (|) .",
type=click.Choice([",", ";", "$'\\t'", "\" \""], case_sensitive=False),
default=",",
show_default=True,
required=False,
)
@click.option(
"--nthreads",
help="number of threads to use.",
type=int,
default=8,
show_default=True,
required=False,
)
@click.version_option(__version__, "-v", "--version", is_flag=True)
def main(
assembler,
graph,
contigs,
abundance,
paths,
output,
hmm,
prefix,
min_length,
p_intra,
p_inter,
d_limit,
depth,
mg_threshold,
bin_mg_threshold,
min_bin_size,
delimiter,
nthreads
):

# Parse arguments for paths
# ------------------------------------------------------------------------

contigs_file = contigs
assembly_graph_file = graph
contig_paths_file = paths
abundance_file = abundance
output_path = output

bin_threshold = -math.log(p_intra, 10)
break_threshold = -math.log(p_inter, 10)

n_bins = 0


# Setup logger
# -----------------------
# ------------------------------------------------------------------------

logger = logging.getLogger("MetaCoaAG 1.1.2")
logger.setLevel(logging.DEBUG)
Expand All @@ -82,11 +217,66 @@ def main():
logger.addHandler(consoleHeader)

# Setup output path for log file
fileHandler = logging.FileHandler(output_path + "/" + prefix + "metacoag.log")
fileHandler = logging.FileHandler(f"{output_path}/{prefix}metacoag.log")
fileHandler.setLevel(logging.DEBUG)
fileHandler.setFormatter(formatter)
logger.addHandler(fileHandler)


# Validate files
# ------------------------------------------------------------------------

# Check if paths file is provided when the assembler type is SPAdes
if assembler.lower() == "spades" and contig_paths_file is None:
logger.error("Please make sure to provide the path to the contigs.paths file.")
logger.error("Exiting MetaCoAG... Bye...!")
sys.exit(1)

# Check if paths file is provided when the assembler type is Flye
if assembler.lower() == "flye" and contig_paths_file is None:
logger.error("Please make sure to provide the path to the assembly_info.txt file.")
logger.error("Exiting MetaCoAG... Bye...!")
sys.exit(1)

# Skip paths file when the assembler type is MEGAHIT
if assembler.lower() == "megahit":
contig_paths_file = "None"

# Validate prefix
if prefix != None:
if not prefix.endswith("_"):
prefix = prefix + "_"
else:
prefix = ""

# Validate min_bin_size
if min_bin_size <= 0:
logger.error("Please enter a valid number for min_bin_size")
logger.error("Exiting MetaCoAG... Bye...!")
sys.exit(1)

# Validate depth
if depth <= 0:
logger.error("Please enter a valid number for depth")
logger.error("Exiting MetaCoAG... Bye...!")
sys.exit(1)

# Validate d_limit
if d_limit <= 0:
logger.error("Please enter a valid number for d_limit")
logger.error("Exiting MetaCoAG... Bye...!")
sys.exit(1)

# Validate number of threads
if nthreads <= 0:
logger.error("Please enter a valid number for the number of threads")
logger.error("Exiting MetaCoAG... Bye...!")
sys.exit(1)


# Start MetaCoAG
# ------------------------------------------------------------------------

logger.info(
"Welcome to MetaCoAG: Binning Metagenomic Contigs via Composition, Coverage and Assembly Graphs."
)
Expand All @@ -109,10 +299,11 @@ def main():
logger.info(f"min_bin_size: {min_bin_size} base pairs")
logger.info(f"d_limit: {d_limit}")
logger.info(f"Number of threads: {nthreads}")

logger.info("MetaCoAG started")

start_time = time.time()


# Get links of the assembly graph
# ------------------------------------------------------------------------

Expand Down Expand Up @@ -961,8 +1152,8 @@ def main():
# ----------------------------------------------------------

# Get output path
output_bins_path = output_path + prefix + "bins/"
lq_output_bins_path = output_path + prefix + "low_quality_bins/"
output_bins_path = f"{output_path}/{prefix}bins"
lq_output_bins_path = f"{output_path}/{prefix}low_quality_bins"

# Create output directory for bin files
if not os.path.isdir(output_bins_path):
Expand All @@ -975,7 +1166,7 @@ def main():

final_bin_count = 0

with open(output_path + prefix + "contig_to_bin.tsv", mode="w") as out_file:
with open(f"{output_path}/{prefix}contig_to_bin.tsv", mode="w") as out_file:
output_writer = csv.writer(
out_file, delimiter=delimiter, quotechar='"', quoting=csv.QUOTE_MINIMAL
)
Expand Down Expand Up @@ -1020,12 +1211,12 @@ def main():

for bin_name in set(final_bins.values()):
bin_files[bin_name] = open(
output_bins_path + prefix + "bin_" + bin_name + ".fasta", "w+"
f"{output_bins_path}/{prefix}bin_{bin_name}.fasta", "w+"
)

for bin_name in set(lowq_bins.values()):
bin_files[bin_name] = open(
lq_output_bins_path + prefix + "bin_" + bin_name + "_seqs.fasta", "w+"
f"{lq_output_bins_path}/{prefix}bin_{bin_name}_seqs.fasta", "w+"
)

for n, record in tqdm(
Expand Down Expand Up @@ -1054,8 +1245,8 @@ def main():
for c in set(lowq_bins.values()):
bin_files[c].close()

logger.info("Producing " + str(final_bin_count) + " bins...")
logger.info("Final binning results can be found in " + str(output_bins_path))
logger.info(f"Producing {final_bin_count} bins...")
logger.info(f"Final binning results can be found in {output_bins_path}")

# Exit program
# -----------------------------------
Expand Down
Loading

0 comments on commit 09f36e8

Please sign in to comment.