Merge f723f10 into bf4fca7

CHANGELOG.md

@@ -4,8 +4,22 @@
 * Fix documentation issues [ ]
     * Add subpackage docstrings [ ]
 * Create methods for Sample and Project
-    * .describe []
-    * .write_paths_to_file, .copy_files_to_dir(), .link_files_to_dir()
+    * .describe [ ]
+    * .write_paths_to_file, .copy_files_to_dir(), .link_files_to_dir() [ ]
+* Add logger calls when saving to JSON and uploading to ProvStore [ ]
+
+### v0.1.20
+* Debug graphical DOT output [x]
+* Add Muscle PresetProgram [x]
+* Add MAFFT PresetProgram [x]
+* Add Kallisto PresetProgram [x]
+* Add extra_flags attribute to PresetProgram [x]
+* Refactor EnvProv class as Environment [x]
+* Allow creation of users and envs to be optional [x]
+* Create environments only when there's an associated activity [x]
+* Create Sample dunder enter and dunder exit methods [x]
+* Fixing wasDerivedFrom bug when sample and file have same names [x]
+* Fix extra Environments bug [x]
 
 ### v0.1.19
 * Debug API endpoint (#23) [x]

CONTRIBUTING.md

@@ -126,4 +126,5 @@ Before you submit a pull request, if your pull request includes code changes che
 * If the pull request adds functionality:
     * Put your new functionality into a function or class with a docstring;
     * Make a new test for said functionality.
+* Add a one-line description of the contribution to the CHANGELOG.md file under the current development version.
 * Make sure your code changes were formatted with the Black styling tool.

README.md

@@ -1,7 +1,7 @@
 ### BioProv - W3C-PROV provenance documents for bioinformatics
 
 
-Package | [![License](https://img.shields.io/github/license/vinisalazar/bioprov)](https://img.shields.io/github/license/vinisalazar/bioprov) | [![PyPI Version](https://img.shields.io/pypi/v/bioprov)](https://pypi.org/project/bioprov/) | [![Requirements Status](https://requires.io/github/vinisalazar/BioProv/requirements.svg?branch=master)](https://requires.io/github/vinisalazar/BioProv/requirements/?branch=master)
+Package | [![License](https://img.shields.io/github/license/vinisalazar/bioprov)](https://github.com/vinisalazar/BioProv/blob/master/LICENSE) | [![PyPI Version](https://img.shields.io/pypi/v/bioprov)](https://pypi.org/project/bioprov/) | [![Requirements Status](https://requires.io/github/vinisalazar/BioProv/requirements.svg?branch=master)](https://requires.io/github/vinisalazar/BioProv/requirements/?branch=master)
 ---------------|--|--|--
 Tests | [![Build Status](https://travis-ci.org/vinisalazar/BioProv.svg?branch=master)](https://travis-ci.org/vinisalazar/BioProv) |  [![tests](https://github.com/vinisalazar/bioprov/workflows/tests/badge.svg?branch=master)](https://github.com/vinisalazar/bioprov/actions?query=workflow%3Atests) | [![Coverage Status](https://coveralls.io/repos/github/vinisalazar/BioProv/badge.svg?branch=master&service=github)](https://coveralls.io/github/vinisalazar/BioProv?branch=master&service=github)
 Code | [![Code style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black) | [![lint](https://github.com/vinisalazar/BioProv/workflows/lint/badge.svg?branch=master)](https://github.com/vinisalazar/BioProv/actions?query=workflow%3Alint)
@@ -95,7 +95,7 @@ You can import data into BioProv using Pandas objects.
 
 ### Installation
 
-```
+```sh
 # Install from pip
 $ pip install bioprov
 

bioprov/__init__.py

@@ -2,7 +2,7 @@
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 
 """
@@ -11,7 +11,7 @@
 Inherits objects from the src/ package.
 """
 
-from .src.config import config, EnvProv, BioProvDB
+from .src.config import config, Environment, BioProvDB
 from .src.files import File, SeqFile, Directory
 from .src.main import (
     Program,

bioprov/bioprov

@@ -3,7 +3,7 @@ __author__ = "Vini Salazar"
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 """
 Executable that goes in $PATH. Code for the command-line is on the bioprov.py module.

bioprov/bioprov.py

@@ -2,7 +2,7 @@
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 """
 BioProv command-line application. This module holds the main executable.

bioprov/data/__init__.py

@@ -2,7 +2,7 @@
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 
 """

bioprov/programs/__init__.py

@@ -2,7 +2,18 @@
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 
-from .programs import prodigal, diamond, blastn, blastp, prokka, kaiju, kaiju2table
+from .programs import (
+    prodigal,
+    diamond,
+    blastn,
+    blastp,
+    muscle,
+    mafft,
+    prokka,
+    kallisto_quant,
+    kaiju,
+    kaiju2table,
+)

bioprov/programs/programs.py

@@ -2,7 +2,7 @@
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 
 """
@@ -42,20 +42,17 @@ def diamond(blast_type, sample, db, query_tag="query", outformat=6, extra_flags=
         sample=sample,
         input_files={"--query": query_tag},
         output_files={"--out": ("_dmnd_hits", "_dmnd_hits.tsv")},
+        extra_flags=extra_flags,
     )
 
-    if extra_flags is not None:
-        params = [Parameter(key=command) for command in extra_flags]
-        for param in params:
-            _diamond.add_parameter(param)
-
     return _diamond
 
 
-def prodigal(sample=None, input_tag="assembly"):
+def prodigal(sample=None, input_tag="assembly", extra_flags=None):
     """
     :param sample: Instance of BioProv.Sample.
     :param input_tag: Instance of BioProv.Sample.
+    :param list extra_flags: A list of extra parameters to pass to Prodigal.
     :return: Instance of PresetProgram containing Prodigal.
     """
     _prodigal = PresetProgram(
@@ -68,12 +65,13 @@ def prodigal(sample=None, input_tag="assembly"):
             "-s": ("scores", "_scores.cds"),
         },
         preffix_tag=input_tag,
+        extra_flags=extra_flags,
     )
 
     return _prodigal
 
 
-def _create_blast_preset(blast_type, sample, db, query_tag, outformat):
+def _create_blast_preset(blast_type, sample, db, query_tag, outformat, extra_flags):
     """
     :param str blast_type: What BLAST program to build (e.g. 'blastn');
     :return: Instance of PresetProgram for the chosen blast program type.
@@ -93,43 +91,126 @@ def _create_blast_preset(blast_type, sample, db, query_tag, outformat):
         sample=sample,
         input_files={"-query": query_tag},
         output_files={"-out": (f"{blast_type}_hits", f"_{blast_type}_hits.txt")},
+        extra_flags=extra_flags,
     )
 
     return _blast_program
 
 
-def blastn(sample=None, db=None, query_tag="query", outformat=6):
+def blastn(sample=None, db=None, query_tag="query", outformat=6, extra_flags=None):
     """
     :param Sample sample: Instance of BioProv.Sample.
     :param str db: A string pointing to the reference database directory and title.
     :param str query_tag: A tag for the query file.
     :param int outformat: The output format to gather from blastn.
+    :param list extra_flags: A list of extra parameters to pass to BLASTN.
     :return: Instance of PresetProgram for BLASTN.
     :rtype: BioProv.PresetProgram.
     :raises AssertionError: Path to the reference database does not exist.
     """
 
-    _blastn = _create_blast_preset("blastn", sample, db, query_tag, outformat)
+    _blastn = _create_blast_preset(
+        "blastn", sample, db, query_tag, outformat, extra_flags
+    )
 
     return _blastn
 
 
-def blastp(sample, db, query_tag="query", outformat=6):
+def blastp(sample, db, query_tag="query", outformat=6, extra_flags=None):
     """
     :param Sample sample: Instance of BioProv.Sample.
     :param str db: A string pointing to the reference database directory and title.
     :param str query_tag: A tag for the query file.
     :param int outformat: The output format to gather from blastp.
+    :param list extra_flags: A list of extra parameters to pass to BLASTP.
     :return: Instance of PresetProgram for BLASTP.
     :rtype: BioProv.PresetProgram.
     :raises AssertionError: Path to the reference database does not exist.
     """
 
-    _blastp = _create_blast_preset("blastp", sample, db, query_tag, outformat)
+    _blastp = _create_blast_preset(
+        "blastp", sample, db, query_tag, outformat, extra_flags
+    )
 
     return _blastp
 
 
+def muscle(sample, input_tag="input", msf=False, extra_flags=None):
+    """
+    :param Sample sample: Instance of BioProv.Sample.
+    :param str input_tag: A tag for the input multi-fasta file.
+    :param bool msf: Whether or not to have the output in msf format.
+    :param list extra_flags: A list of extra parameters to pass to Muscle.
+    :return: Instance of PresetProgram for Muscle.
+    :rtype: BioProv.PresetProgram.
+    """
+
+    _muscle = PresetProgram(
+        name="muscle",
+        sample=sample,
+        input_files={"-in": input_tag},
+        output_files={"-out": ("_muscle_hits", "_muscle_hits.afa")},
+        extra_flags=extra_flags,
+    )
+
+    if msf:
+        _muscle.add_parameter(Parameter(key="-msf"))
+
+    return _muscle
+
+
+def mafft(sample, input_tag="input", extra_flags=None):
+    """
+    :param Sample sample: Instance of BioProv.Sample.
+    :param str input_tag:  A tag for the input fasta file.
+    :param list extra_flags: A list of extra parameters to pass to MAFFT.
+    :return: Instance of PresetProgram containing MAFFT.
+    :rtype: BioProv.PresetProgram.
+    """
+    _mafft = PresetProgram(
+        name="mafft",
+        sample=sample,
+        input_files={"": input_tag},
+        output_files={">": ("aligned", "_aligned.afa")},
+        preffix_tag=input_tag,
+        extra_flags=extra_flags,
+    )
+
+    return _mafft
+
+
+def kallisto_quant(sample, index, output_dir="./", extra_flags=None):
+    """
+    Run kallisto's alignment and quantification
+
+    :param Sample sample: Instance of BioProv.Sample.
+    :param str index: A path to a kallisto index file.
+    :param str output_dir: A path to kallisto's output directory.
+    :param list extra_flags: A list of extra parameters to pass to kallisto
+        (e.g. --single or --plaintext).
+    :return: Instance of PresetProgram containing kallisto.
+    :rtype: BioProv.PresetProgram.
+    """
+
+    _kallisto = PresetProgram(
+        name="kallisto",
+        params=(
+            Parameter(key="quant"),
+            Parameter(key="--index", value=index),
+            Parameter(key="--output-dir", value=output_dir),
+        ),
+        sample=sample,
+        extra_flags=extra_flags,
+    )
+
+    input_files = [Parameter(key=str(fastq.path)) for fastq in sample.files.values()]
+
+    for read in input_files:
+        _kallisto.add_parameter(read)
+
+    return _kallisto
+
+
 def prokka_():
     """
     :return: Instance of PresetProgram containing Prokka.

bioprov/src/__init__.py

@@ -2,7 +2,7 @@
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 
 """

bioprov/src/config.py

@@ -2,7 +2,7 @@
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 
 """
@@ -35,7 +35,7 @@ def __init__(self, db_path=None, threads=0):
         """
         # This duplication is to order the keys in the __dict__ attribute.
         self.user = None
-        self.env = EnvProv()
+        self.env = Environment()
         self.user = self.env.user
         if not threads:
             threads = int(os.cpu_count() / 2)
@@ -248,7 +248,7 @@ def _get_confirm():
             print("Canceled operation.")
 
 
-class EnvProv:
+class Environment:
     """
     Class containing provenance information about the current environment.
     """
@@ -265,7 +265,7 @@ def __init__(self):
         self.update()
 
     def __repr__(self):
-        return f"Environment_{self.env_hash}"
+        return self.env_hash
 
     def update(self):
         """

bioprov/src/files.py

@@ -2,7 +2,7 @@
 __license__ = "MIT"
 __maintainer__ = "Vini Salazar"
 __url__ = "https://github.com/vinisalazar/bioprov"
-__version__ = "0.1.19"
+__version__ = "0.1.20"
 
 
 """