Merge pull request #17 from databio/dev

Release 0.1.0a4

bedboss/__init__.py

@@ -1,12 +1,18 @@
 """ Package-level data """
+import logmuse
+import coloredlogs
+
 from bedboss import *
-from bedboss.bedqc import bedqc
-from bedboss.bedmaker import bedmaker
-from bedboss.bedstat import bedstat
+
+# from bedboss.bedqc.bedqc import bedqc
+# from bedboss.bedmaker.bedmaker import BedMaker
+# from bedboss.bedstat.bedstat import bedstat
 from bedboss._version import __version__
-import logmuse
+from bedboss.bedboss import run_all, run_all_by_pep, bedqc, BedMaker, bedstat
+
 
 __package_name__ = "bedboss"
+
 __author__ = [
     "Oleksandr Khoroshevskyi",
     "Michal Stolarczyk",
@@ -20,9 +26,18 @@
     "__version__",
     "__package_name__",
     "__author__",
+    "bedboss",
     "bedqc",
     "bedmaker",
+    "BedMaker",
     "bedstat",
+    "run_all",
+    "run_all_by_pep",
 ]
 
-logmuse.init_logger(__version__)
+_LOGGER = logmuse.init_logger("bedboss")
+coloredlogs.install(
+    logger=_LOGGER,
+    datefmt="%H:%M:%S",
+    fmt="[%(levelname)s] [%(asctime)s] %(message)s",
+)

bedboss/_version.py

@@ -1 +1 @@
-__version__ = "0.1.0a3"
+__version__ = "0.1.0a4"

bedboss/bedboss.py

@@ -1,9 +1,12 @@
 import logging
 import os
 from typing import NoReturn, Union, Dict
+
+import peppy
 import pypiper
 from argparse import Namespace
 import logmuse
+import peppy
 
 from bedboss.bedstat.bedstat import bedstat
 from bedboss.bedmaker.bedmaker import BedMaker
@@ -25,7 +28,7 @@
     check_db_connection,
 )
 from bedboss.exceptions import OpenSignalMatrixException
-from bedboss import __version__
+from bedboss._version import __version__
 
 _LOGGER = logging.getLogger("bedboss")
 
@@ -54,7 +57,11 @@ def get_osm_path(genome: str) -> Union[str, None]:
     if not os.path.exists(osm_path):
         if not os.path.exists(OPEN_SIGNAL_FOLDER):
             os.makedirs(OPEN_SIGNAL_FOLDER)
-        download_file(url=f"{OPEN_SIGNAL_URL}{osm_name}", path=osm_path)
+        download_file(
+            url=f"{OPEN_SIGNAL_URL}{osm_name}",
+            path=osm_path,
+            no_fail=True,
+        )
     return osm_path
 
 
@@ -163,6 +170,43 @@ def run_all(
     )
 
 
+def run_all_by_pep(pep: Union[str, peppy.Project]) -> NoReturn:
+    """
+    Run bedboss pipeline by providing pep config file.
+
+    :param pep: path to the pep config file or peppy.Project object
+    """
+    if isinstance(pep, str):
+        pep = peppy.Project(pep)
+    elif isinstance(pep, peppy.Project):
+        pass
+    else:
+        raise Exception("Incorrect pep type. Exiting...")
+
+    for pep_sample in pep.samples:
+        _LOGGER.info(f"Running bedboss pipeline for {pep_sample.sample_name}")
+        run_all(
+            sample_name=pep_sample.sample_name,
+            input_file=pep_sample.input_file,
+            input_type=pep_sample.input_type,
+            outfolder=pep_sample.outfolder,
+            genome=pep_sample.genome,
+            bedbase_config=pep_sample.bedbase_config,
+            rfg_config=pep_sample.get("rfg_config"),
+            narrowpeak=pep_sample.get("narrowpeak"),
+            check_qc=pep_sample.get("check_qc"),
+            standard_chrom=pep_sample.get("standard_chrom"),
+            chrom_sizes=pep_sample.get("chrom_sizes"),
+            open_signal_matrix=pep_sample.get("open_signal_matrix"),
+            ensdb=pep_sample.get("ensdb"),
+            sample_yaml=pep_sample.get("sample_yaml"),
+            just_db_commit=pep_sample.get("just_db_commit"),
+            no_db_commit=pep_sample.get("no_db_commit"),
+            force_overwrite=pep_sample.get("force_overwrite"),
+            skip_qdrant=pep_sample.get("skip_qdrant"),
+        )
+
+
 def main(test_args: dict = None) -> NoReturn:
     """
     Run pipeline that was specified in as positional argument.
@@ -196,6 +240,8 @@ def main(test_args: dict = None) -> NoReturn:
         bedqc(pm=pm, **args_dict)
     elif args_dict["command"] == "stat":
         bedstat(pm=pm, **args_dict)
+    elif args_dict["command"] == "all-pep":
+        run_all_by_pep(args_dict["pep_config"])
     else:
         parser.print_help()
         # raise Exception("Incorrect pipeline name.")

bedboss/bedmaker/bedmaker.py

@@ -84,14 +84,14 @@ def __init__(
                                 If true, filter the input file to contain only
                                 the standard chromosomes, remove regions on
                                 ChrUn chromosomes
-        :param check_qc: run quality control during badmaking
+        :param check_qc: run quality control during bedmaking
         :param pm: pypiper object
         :return: noReturn
         """
 
         # Define file paths
         self.input_file = input_file
-        self.input_type = input_type
+        self.input_type = input_type.lower()
         self.output_bed = output_bed
         self.output_bigbed = output_bigbed
         self.file_name = os.path.basename(input_file)
@@ -186,7 +186,7 @@ def make_bed(self) -> NoReturn:
         on input file type and execute the command.
         """
 
-        _LOGGER.info(f"Converting {self.input_file} to BED format.")
+        _LOGGER.info(f"Converting {os.path.abspath(self.input_file)} to BED format.")
         temp_bed_path = os.path.splitext(self.output_bed)[0]
 
         # creat cmd to run that convert non bed file to bed file
@@ -195,14 +195,14 @@ def make_bed(self) -> NoReturn:
 
             # Use the gzip and shutil modules to produce temporary unzipped files
             if self.input_extension == ".gz":
-                input_file = os.path.join(
+                temp_input_file = os.path.join(
                     os.path.dirname(self.output_bed),
                     os.path.splitext(self.file_name)[0],
                 )
                 with gzip.open(self.input_file, "rb") as f_in:
-                    with open(input_file, "wb") as f_out:
+                    with open(temp_input_file, "wb") as f_out:
                         shutil.copyfileobj(f_in, f_out)
-                self.pm.clean_add(input_file)
+                self.pm.clean_add(temp_input_file)
 
             # creating cmd for bedGraph files
             if self.input_type == "bedGraph":
@@ -309,6 +309,7 @@ def make_bed(self) -> NoReturn:
                     ),
                 ]
         self.pm.run(cmd, target=self.output_bed)
+        self.pm._cleanup()
 
     def make_bigbed(self) -> NoReturn:
         """
@@ -337,7 +338,7 @@ def make_bigbed(self) -> NoReturn:
                     "https://genome.ucsc.edu/goldenpath/help/bigBed.html"
                 )
             if bedtype is not None:
-                cmd = "zcat " + self.output_bed + "  | sort -k1,1 -k2,2n > " + temp
+                cmd = f"zcat {self.output_bed} | sort -k1,1 -k2,2n > {temp}"
                 self.pm.run(cmd, temp)
 
                 cmd = f"{BED_TO_BIGBED_PROGRAM} -type={bedtype} {temp} {self.chrom_sizes} {big_narrow_peak}"
@@ -371,6 +372,7 @@ def make_bigbed(self) -> NoReturn:
                         f"unable to validate genome assembly with Refgenie. "
                         f"Error: {err}"
                     )
+            self.pm._cleanup()
 
     def get_rgc(self) -> str:
         """

bedboss/bedstat/bedstat.py

@@ -239,7 +239,7 @@ def bedstat(
             del plot["name"]
             data.update({plot_id: plot})
         bbc.bed.report(
-            sample_name=bed_digest,
+            record_identifier=bed_digest,
             values=data,
             force_overwrite=force_overwrite,
         )

bedboss/cli.py

@@ -2,7 +2,7 @@
 from argparse import ArgumentParser
 import logmuse
 
-from bedboss import __version__, __package_name__
+from bedboss._version import __version__
 
 
 def build_argparser() -> ArgumentParser:
@@ -11,7 +11,7 @@ def build_argparser() -> ArgumentParser:
     :retrun: Tuple[pipeline, arguments]
     """
     parser = VersionInHelpParser(
-        prog=__package_name__,
+        prog="bedboss",
         description="Warehouse of pipelines for BED-like files: "
         "bedmaker, bedstat, and bedqc.",
         epilog="",
@@ -22,6 +22,10 @@ def build_argparser() -> ArgumentParser:
     sub_all = subparser.add_parser(
         "all", help="Run all bedboss pipelines and insert data into bedbase"
     )
+    sub_all_pep = subparser.add_parser(
+        "all-pep",
+        help="Run all bedboss pipelines using one PEP and insert data into bedbase",
+    )
     sub_make = subparser.add_parser(
         "make",
         help="A pipeline to convert bed, bigbed, bigwig or bedgraph "
@@ -136,6 +140,21 @@ def build_argparser() -> ArgumentParser:
         help="just commit the JSON to the database",
     )
 
+    # all-pep
+    sub_all_pep.add_argument(
+        "--pep_config",
+        dest="pep_config",
+        required=True,
+        help="Path to the pep configuration file [Required]\n "
+        "Required fields in PEP are: "
+        "sample_name, input_file, input_type,outfolder, genome, bedbase_config.\n "
+        "Optional fields in PEP are: "
+        "rfg_config, narrowpeak, check_qc, standard_chrom, chrom_sizes, "
+        "open_signal_matrix, ensdb, sample_yaml, no_db_commit, just_db_commit, "
+        "no_db_commit, force_overwrite, skip_qdrant",
+        type=str,
+    )
+
     # bed_qc
     sub_qc.add_argument(
         "--bedfile",

bedboss/utils.py

@@ -1,6 +1,5 @@
 import os
 import logging
-import requests
 import urllib
 from bbconf import BedBaseConf
 from typing import NoReturn
@@ -43,22 +42,25 @@ def standardize_genome_name(input_genome: str) -> str:
         return input_genome
 
 
-def download_file(url: str, path: str) -> NoReturn:
+def download_file(url: str, path: str, no_fail: bool = False) -> NoReturn:
     """
     Download file from the url to specific location
 
     :param url: URL of the file
     :param path: Local path with filename
+    :param no_fail: If True, do not raise exception if download fails
     :return: NoReturn
     """
     _LOGGER.info(f"Downloading remote file: {url}")
-    _LOGGER.info(f"Local path: {path}")
+    _LOGGER.info(f"Local path: {os.path.abspath(path)}")
     try:
         urllib.request.urlretrieve(url, path)
         _LOGGER.info(f"File downloaded successfully!")
     except Exception as e:
         _LOGGER.error(f"File download failed.")
-        raise e
+        if not no_fail:
+            raise e
+        _LOGGER.error(f"File download failed. Continuing anyway...")
 
 
 def check_db_connection(bedbase_config: str) -> bool:

docs/how_run_script.md

@@ -0,0 +1,77 @@
+# How to run bedboss as a Python API
+
+## Install bedboss
+
+```bash
+pip install bedboss
+```
+
+## Run bedboss all
+
+```python
+from bedboss import run_all
+
+run_all(
+    sample_name="example_sample_name",
+    input_file="example/path/to/input_file",
+    input_type="bed",
+    outfolder="example/path/to/outfolder",
+    genome="hg38",
+    bedbase_config="example/path/to/bedbase_config.yaml",
+    # + another optional arguments
+)
+
+
+```
+
+
+## Run bedboss all-pep
+
+```python
+from bedboss import run_all_by_pep
+
+run_all_by_pep(
+    pep="example/path/to/pep.yaml"
+)
+```
+
+## Run bedboss make
+
+```python
+from bedboss import BedMaker
+
+BedMaker(
+    input_file="example/path/to/input_file",
+    input_type="bed",
+    output_bed="example/path/to/output_bed",
+    output_bigbed="example/path/to/output_bigbed",
+    sample_name="example_sample_name",
+    genome="hg38",
+)
+
+```
+
+## Run bedboss stat
+
+```python
+from bedboss import bedstat
+
+bedstat( 
+    bedfile="example/path/to/bedfile.bed",
+    bedbase_config="example/path/to/bedbase_config.yaml",
+    genome="hg38",
+    outfolder="example/path/to/outfolder",
+)
+
+```
+
+## Run bedboss qc
+
+```python
+from bedboss import bedqc
+
+bedqc(
+    bedfile="example/path/to/bedfile.bed",
+    outfolder="example/path/to/outfolder",
+)
+```

docs/templates/usage.template

@@ -0,0 +1,16 @@
+# Usage reference
+
+BEDboss is command-line tool-warehouse of 3 pipelines for genomic interval files
+
+BEDboss include: bedmaker, bedqc, bedstat. This pipelines can be run using next positional arguments:
+
+- `bedbase all`:  Runs all pipelines one in order: bedmaker -> bedqc -> bedstat
+
+- `bedbase make`:  Creates Bed and BigBed files from  other type of genomic interval files [bigwig|bedgraph|bed|bigbed|wig]
+
+- `bedbase qc`: Runs Quality control for bed file (Works only with bed files)
+
+- `bedbase stat`: Runs statistics for bed and bigbed files.
+
+Here you can see the command-line usage instructions for the main bedboss command and for each subcommand:
+