def main():
parser = argparse.ArgumentParser(
description=f"""
Version: {__version__}
Author: Gabriele Girelli
Docs: http://ggirelli.github.io/ifish-probe-design
Code: http://github.com/ggirelli/ifish-probe-design
An iFISH probe design pipeline, with web interface included.
""",
formatter_class=argparse.RawDescriptionHelpFormatter,
)
parser.set_defaults(parse=default_parser)
parser = ap.add_version_option(parser)
subparsers = parser.add_subparsers(
title="sub-commands",
help="Access the help page for a sub-command with: sub-command -h",
)
scripts.dbchk.init_parser(subparsers)
scripts.mkdb.init_parser(subparsers)
scripts.query.query.init_parser(subparsers)
scripts.serve.init_parser(subparsers)
args = parser.parse_args()
args = args.parse(args)
args.run(args)
def init_parser(subparsers: argparse._SubParsersAction) -> argparse.ArgumentParser:
parser = subparsers.add_parser(
__name__.split(".")[-1],
description="""
Checks integrity of a database. Specifically:
- a ".config" file must be present
* Overlapping status must match.
- At least one non-empty chromosome file
* Appropriate format (3 columns).
* Positions must be sorted.
* An ODN must end after it starts.
* No ODNs can start from the same position.
* No ODNs can be totally included in another one.
""",
formatter_class=argparse.RawDescriptionHelpFormatter,
help="Check integrity of a database.",
)
parser.add_argument(
"dbDirPath", type=str, default=".", help="""Path to database directory."""
)
parser = ap.add_version_option(parser)
parser.set_defaults(parse=parse_arguments, run=run)
return parser
def init_parser(
subparsers: argparse._SubParsersAction) -> argparse.ArgumentParser:
parser = subparsers.add_parser(
__name__.split(".")[-1],
description="""Possible ifpd db queries.""",
formatter_class=argparse.RawDescriptionHelpFormatter,
help="Possible ifpd db queries.",
)
parser.set_defaults(parse=default_parser)
parser = ap.add_version_option(parser)
sub_subparsers = parser.add_subparsers(
title="sub-commands",
help="Access the help page for a sub-command with: sub-command -h",
)
scripts.query.probe.init_parser(sub_subparsers)
scripts.query.set.init_parser(sub_subparsers)
return parser
def init_parser(subparsers: argparse._SubParsersAction) -> argparse.ArgumentParser:
parser = subparsers.add_parser(
__name__.split(".")[-1],
description="""
Builds a database of complementary oligodeoxyribonucleotides (ODNs) in a format
compatible with ifpd.
DISCLAIMER: this script does NOT generate a new database. It only re-formats an
existing database to a format compatible with ifpd.
The script takes a tabulation-separated values (tsv) file with four (4) columns:
chromosome (or feature), chromStart, chromEnd, sequence. The first three (3) column are
identical to the columns of a BED3 file.
NOTE: only non-arbitrary nucleotides in standard IUPAC format are allowed in the
ODNs sequence. https://www.bioinformatics.org/sms/iupac.html
After the database is created, we advise running the ifpd dbchk script to
test its integrity.
Details on the BED3 format are available on the UCSC website:
https://genome.ucsc.edu/FAQ/FAQformat.html#format1
""",
formatter_class=argparse.RawDescriptionHelpFormatter,
help="Builds a database of complementary ODNs compatible with FISH-ProDe.",
)
parser.add_argument(
"input",
metavar="input",
type=str,
help="""Path to input file. Four (4) tabulation-separated columns are expected:
chromosome, chromStart, chromEnd, and sequence.""",
)
parser.add_argument("dbName", metavar="dbName", type=str, help="Database name.")
parser.add_argument(
"--output",
metavar="dirPath",
type=str,
default=".",
help="""Path to directory where to build the database. Created if missing.
Defaults a subfolder of current directory with database name.""",
)
parser.add_argument(
"--refGenome",
metavar="refGen",
type=str,
default="",
help="Reference genome. Only stored in the config file.",
)
parser = ap.add_version_option(parser)
advanced = parser.add_argument_group("advanced arguments")
advanced.add_argument(
"--increment-chrom-end",
action="store_const",
dest="incrementChromEnd",
const=True,
default=False,
help="""Use this option if your input bed file is not in UCSC bed format,
and the last position (chromEnd) is actually included. This forces
a unit increase of that position to convert to UCSC bed format.""",
)
advanced.add_argument(
"--custom-config",
metavar="config",
type=str,
nargs="*",
help="""Space separated "key:value" pairs to store in the
database .config file. No quotes needed.""",
)
advanced.add_argument(
"-f",
action="store_const",
dest="forceRun",
const=True,
default=False,
help="""Force overwriting of the database if already run.
!!!This is potentially dangerous!!!""",
)
parser.set_defaults(parse=parse_arguments, run=run)
return parser
def init_parser(subparsers: argparse._SubParsersAction) -> argparse.ArgumentParser:
parser = subparsers.add_parser(
__name__.split(".")[-1],
description="""
Design a FISH probe set in a genomic region, with the aim of having the probes
as homogeneously spaced as possible. Concisely, the script does the following:
- Identify all probe candidates
- Calculate centrality, size, and homogeneity for each candidate
- Build a set of consecutive (nProbes+1) windows of the same size
+ Shift the windows set to build additional windows sets. Each windows set
will produce one probe set candidate.
- For each window set:
+ Find the best probe in each window.
+ Aggregate each window's best probe into a candidate probe set.
- Rank candidate probe sets based on probe homogeneity.
- Return the top N candidates (maxSets), with plots, tables, fasta and bed.
""",
formatter_class=argparse.RawDescriptionHelpFormatter,
help="Design a FISH probe set in a genomic region.",
)
parser.add_argument(
"database", metavar="database", type=str, help="Path to database folder."
)
parser.add_argument(
"chrom",
type=str,
help="Database feature to query for a probe set.",
)
parser.add_argument(
"outdir",
metavar="outDir",
type=str,
help="Path to query output directory. Stops if it exists already.",
)
parser.add_argument(
"nProbes", metavar="nProbes", type=int, help="Number of probes to design."
)
parser.add_argument(
"--region",
type=int,
nargs=2,
default=(0, np.inf),
help="""Start and end locations (space-separated) of the region of interest.
When a region is not provided (or start/end coincide),
the whole feature is queried.""",
)
parser.add_argument(
"--n-oligo",
metavar="nOligo",
type=int,
default=48,
help="Number of oligos per probe. Default: 48",
)
parser.add_argument(
"--max-sets",
metavar="maxProbes",
type=int,
default=-1,
help="""Maximum number of probe set candidates to output.
Set to -1 to retrieve all candidates. Default: -1""",
)
parser = ap.add_version_option(parser)
advanced = parser.add_argument_group("advanced arguments")
advanced.add_argument(
"--order",
metavar="feature",
type=str,
default=const.featureList,
nargs="+",
help="""Space-separated features, used as explained in script description.
The available features are: 'centrality', 'size', and 'homogeneity'. At least 2
features must be listed. Default: "size homogeneity centrality".""",
)
advanced.add_argument(
"--filter-thr",
metavar="filterThr",
type=float,
default=0.1,
help="""Threshold of first feature filter, used to identify
a range around the best value (percentage range around it). Accepts values
from 0 to 1. Default: 0.1""",
)
advanced.add_argument(
"--min-d",
metavar="minD",
type=int,
default=0,
help="*DEPRECATED* Minimum distance between consecutive oligos. Default: 1",
)
advanced.add_argument(
"--exact-n-oligo",
action="store_const",
dest="exact_n_oligo",
const=True,
default=False,
help="""Stop if not enough oligos are found,
instead of designing the largest probe.""",
)
advanced.add_argument(
"--window-shift",
metavar="winShift",
type=float,
default=0.1,
help="""Window fraction for windows shifting.""",
)
advanced.add_argument(
"-t",
"--threads",
metavar="nthreads",
type=int,
help="""Number of threads for parallelization. Default: 1""",
default=1,
)
advanced.add_argument(
"-f",
action="store_const",
dest="forceRun",
const=True,
default=False,
help="""Force overwriting of the query if already run.
This is potentially dangerous.""",
)
parser.set_defaults(parse=parse_arguments, run=run)
return parser
def init_parser(
subparsers: argparse._SubParsersAction) -> argparse.ArgumentParser:
parser = subparsers.add_parser(
__name__.split(".")[-1],
description="""
Design a FISH probe in a genomic region of interest using a database of
oligonucleotides. Concisely, the script does the following:
- Identify all probe candidates
- Calculate centrality, size, and homogeneity for each candidate
- Identify the candidate with the best first feature (featOrder), i.e.,
max(centrality), min(size), or max(homogeneity).
- Build a range around the best first feature value (filterThr) and filter out
all the candidates that do not fall in it.
- Rank the remaining candidates based on the second feature (featOrder), i.e.,
decreasing for centrality, increasing for size or homogeneity.
- Return the top N candidates (maxProbes), with plots, tables, fasta and bed.
""",
formatter_class=argparse.RawDescriptionHelpFormatter,
help="Design a FISH probe in a genomic region of interest.",
)
parser.add_argument("database",
metavar="database",
type=str,
help="Path to database folder.")
parser.add_argument(
"chrom",
type=str,
help="Database feature to query for a probe.",
)
parser.add_argument(
"outdir",
metavar="outDir",
type=str,
help="Path to query output directory. Stops if it exists already.",
)
parser.add_argument(
"--region",
metavar=("chromStart", "chromEnd"),
type=int,
nargs=2,
default=(0, np.inf),
help=
"""Start and end locations (space-separated) of the region of interest.
When a region is not provided (or start/end coincide),
the whole feature is queried.""",
)
parser.add_argument(
"--n-oligo",
metavar="nOligo",
type=int,
default=48,
help=
"""Number of oligos per probe. If not enough oligos are found, the largest
probe (with greater number of oligos) is designed by default. Default: 48""",
)
parser.add_argument(
"--max-probes",
metavar="nProbes",
type=int,
default=-1,
help="""Maximum number of probe candidates to output.
Set to -1 to retrieve all candidates. Default: -1""",
)
parser = ap.add_version_option(parser)
advanced = parser.add_argument_group("advanced arguments")
advanced.add_argument(
"--order",
metavar="feature",
type=str,
default=const.featureList,
nargs="+",
help=
"""Space-separated features, used as explained in script description.
The available features are: 'centrality', 'size', and 'homogeneity'. At least 2
features must be listed. Default: "size homogeneity centrality".""",
)
advanced.add_argument(
"--filter-thr",
metavar="filterThr",
type=float,
default=0.1,
help="""Threshold of first feature filter, used to identify
a range around the best value (percentage range around it). Accepts values
from 0 to 1. Default: 0.1""",
)
advanced.add_argument(
"--min-d",
metavar="minD",
type=int,
default=10,
help=
"*DEPRECATED* Minimum distance between consecutive oligos. Default: 10",
)
advanced.add_argument(
"--exact-n-oligo",
action="store_const",
dest="exact_n_oligo",
const=True,
default=False,
help="""Stop if not enough oligos are found,
instead of designing the largest probe.""",
)
advanced.add_argument(
"-f",
action="store_const",
dest="forceRun",
const=True,
default=False,
help="""Force overwriting of the query if already run.
!!!This is potentially dangerous!!!""",
)
parser.set_defaults(parse=parse_arguments, run=run)
return parser
def init_parser(
subparsers: argparse._SubParsersAction) -> argparse.ArgumentParser:
parser = subparsers.add_parser(
__name__.split(".")[-1],
description="Run WebServer.",
formatter_class=argparse.RawDescriptionHelpFormatter,
help="Run WebServer.",
)
parser.add_argument(
"static",
metavar="folder",
type=str,
help="Path to static folder (created if not found).",
)
parser.add_argument(
"-u",
"--url",
metavar="url",
type=str,
default="0.0.0.0",
help="URL hosting the web server. Default: 0.0.0.0",
)
parser.add_argument(
"-p",
"--port",
metavar="port",
type=int,
default=8080,
help="Web server port. Default: 8080",
)
parser.add_argument(
"-m",
"--mail",
metavar="email",
type=str,
default="*****@*****.**",
help="Email address of server admin.",
)
parser = ap.add_version_option(parser)
advanced = parser.add_argument_group("advanced arguments")
advanced.add_argument(
"--hide-breadcrumbs",
action="store_const",
dest="show_breadcrumbs",
const=False,
default=True,
help="""Hide navigation breadcrumbs.""",
)
advanced.add_argument(
"-R",
"--custom-routes",
metavar="routesFile",
type=str,
help="Path to custom routes Python file.",
)
parser.add_argument(
"-T",
"--custom-templates",
metavar="templateFolder",
type=str,
help="Path to folder with custom templates.",
)
parser.add_argument(
"-H",
"--homepage",
metavar="homepageTemplate",
type=str,
help="""Name of homepage template. Homepage is off by default.
Use "-H home_default" to turn default homepage template on.
When using a custom homepage template, -T must be specified.""",
)
parser.set_defaults(parse=parse_arguments, run=run)
return parser