2578686232

Build Type

github

Committed by GitHub

Commit Message

<a href="https://github.com/sequana/sequana/commit/<a class=hub.com/sequana/sequana/commit/<a class="double-link" href="https://git"><a class=hub.com/sequana/sequana/commit/<a class="double-link" href="https://git"><a class=hub.com/sequana/sequana/commit/e0ab4d95c99d3b30aee0b7030f22fdaa4c9d57df">e0ab4d95c<a href="https://github.com/sequana/sequana/commit/e0ab4d95c99d3b30aee0b7030f22fdaa4c9d57df">&quot;&gt;&amp;lt;a href=&amp;quot;https://github.com/sequana/sequana/commit/&lt;/a&gt;&lt;a class=&quot;double-link&quot; href=&quot;https://github.com/sequana/sequana/commit/&amp;lt;a class=&amp;quot;double-link&amp;quot; href=&amp;quot;https://git&quot;&gt;&amp;lt;a class=&lt;/a&gt;hub.com/sequana/sequana/commit/e0ab4d95c99d3b30aee0b7030f22fdaa4c9d57df&quot;&gt;e0ab4d95c&lt;/a&gt;&lt;a href=&quot;https://github.com/sequana/sequana/commit/e0ab4d95c99d3b30aee0b7030f22fdaa4c9d57df&quot;&gt;&amp;lt;a href=&amp;quot;https://github.com/sequana/sequana/commit/e0ab4d95c99d3b30aee0b7030f22fdaa&lt;/a&gt;4c9d57df">&quot;&gt;Merge &lt;/a&gt;&lt;a class=&quot;double-link&quot; href=&quot;https://github.com/sequana/sequana/commit/&lt;a class=&quot;double-link&quot; href=&quot;https://github.com/sequana/sequana/commit/<a class="double-link" href="https://github.com/sequana/sequana/commit/578e512c805e36de6cd733b4011043d31c2158f1">578e512c8</a><a href="https://github.com/sequana/sequana/commit/e0ab4d95c99d3b30aee0b7030f22fdaa4c9d57df">&amp;quot;&amp;gt;578e512c8&amp;lt;/a&amp;gt;&amp;quot;&amp;gt;578e512c8&amp;lt;/a&amp;gt;&amp;lt;a href=&amp;quot;https://github.com/sequana/sequana/commit/e0ab4d95c99d3b30aee0b7030f22fdaa4c9d5&lt;/a&gt;7df&quot;&gt; into &lt;/a&gt;&lt;a class=&quot;double-link&quot; href=&quot;https://github.com/sequana/sequana/commit/<a class="double-link" href="https://github.com/sequana/sequana/commit/01b52271f">01b52271f">01b52271f</a>

Pull Request Pull Request #754: Fix incomplete annotation for kegg enrichment

Run Details

44 of 44 new or added lines in 8 files covered. (100.0%)

11936 of 17082 relevant lines covered (69.87%)

2.1 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

0.0

/sequana/scripts/main/enrichment_panther.py

#  This file is part of Sequana software
#
#  Copyright (c) 2016-2020 - Sequana Development Team
#
#  Distributed under the terms of the 3-clause BSD license.
#  The full license is in the LICENSE file, distributed with this software.
#
#  website: https://github.com/sequana/sequana
#  documentation: http://sequana.readthedocs.io
#
##############################################################################
import os
import sys

import click
import colorlog

from sequana.modules_report import ModulePantherEnrichment
from sequana.rnadiff import RNADiffResults
from sequana.utils import config

from .utils import CONTEXT_SETTINGS, common_logger, OptionEatAll


logger = colorlog.getLogger(__name__)


# This will be a complex command to provide HTML summary page for
# input files (e.g. bam), or results from pipelines. For each module,
# we should have corresponding option that starts with the module's name
# This can also takes as input various types of data (e.g. FastA)
@click.command(context_settings=CONTEXT_SETTINGS)
@click.argument("name", type=click.Path(exists=True), nargs=1)
@click.option(
    "--annotation-attribute",
    type=click.STRING,
    # required=True,
    default="index",
    show_default=True,
    help="a valid taxon identifiers",
)
@click.option(
    "--panther-taxon",
    type=click.INT,
    required=True,
    help="a valid taxon identifiers",
)
@click.option(
    "--log2-foldchange-cutoff",
    type=click.FLOAT,
    default=1,
    show_default=True,
    help="remove events with absolute log2 fold change below this value",
)
@click.option(
    "--padj-cutoff",
    type=click.FLOAT,
    default=0.05,
    show_default=True,
    help="remove events with pvalue abobe this value default (0.05).",
)
@click.option(
    "--plot-linearx",
    type=click.BOOL,
    default=False,
    is_flag=True,
    show_default=True,
    help="""Default is log2 fold enrichment in the plots. use this to use linear scale""",
)
@click.option(
    "--compute-levels/--no-compute-levels",
    default=True,
    help="""Compute the levels of each go term, set --no-compute-levels to skip this step""",
)
@click.option(
    "--max-genes",
    type=click.INT,
    default=2500,
    show_default=True,
    help="""Maximum number of genes (up or down) to use in PantherDB.""",
)
@click.option(
    "--ontologies",
    default=("MF", "BP", "CC"),
    help="""Provide the ontologies to be included in the analysis and HTML report.
Valid choices are: from MF, BP, CC, SLIM_MF, SLIM_BP, SLIM_CC, PROTEIN,
PANTHER_PATHWAY, REACTOME_PATHWAY""",
    cls=OptionEatAll,
    show_default=True,
)
@click.option(
    "--max-enriched-go-terms",
    type=click.INT,
    default=40,
    show_default=True,
    help="""Max number of enriched go terms to show in the plots (most
enriched). All enriched GO terms are stored in tables""",
)
@click.option("--output-directory", show_default=True, default="enrichment_panther")
@common_logger
def enrichment_panther(**kwargs):
    """Create a HTML report for various sequana out

    \b
    * enrichment: the output of RNADiff pipeline

    Example for the enrichment module:

        sequana enrichment-panther rnadiff.csv --panther-taxon 10090
            --log2-foldchange-cutoff 2 

        sequana enrichment rnadiff/rnadiff.csv
            --panther-taxon 189518 \
            --log2-foldchange-cutoff 2 
            --ontologies MF SLIM_MF

    \b
    Valid ontologies are: MF, BP, CC, SLIM_MF, SLIM_BP, SLIM_CC, 
    PROTEIN, "PANTHER_PATHWAY", "REACTOME_PATHWAY"


    """
    valid = [
        "MF",
        "BP",
        "CC",
        "SLIM_MF",
        "SLIM_BP",
        "SLIM_CC",
        "PROTEIN",
        "PANTHER_PATHWAY",
        "REACTOME_PATHWAY",
    ]

    ontologies = eval(kwargs["ontologies"])
    for ontology in ontologies:
        if ontology not in valid:
            logger.error(f"Provided incorrect ontology ({ontology}). Must be in {valid}")
            sys.exit(1)

    logger.setLevel(kwargs["logger"])

    taxon = kwargs["panther_taxon"]
    if taxon == 0:
        logger.error("You must provide a taxon with --panther-taxon")
        sys.exit(1)

    params = {
        "padj": kwargs["padj_cutoff"],
        "log2_fc": kwargs["log2_foldchange_cutoff"],
        "max_entries": kwargs["max_genes"],
        "nmax": kwargs["max_enriched_go_terms"],
        "plot_logx": not kwargs["plot_linearx"],
        "plot_compute_levels": kwargs["compute_levels"],
    }

    logger.info(f"Reading RNAdiff results from {kwargs['name']}")
    dirpath = os.path.dirname(os.path.abspath(kwargs["name"]))
    rnadiff = RNADiffResults(dirpath, index_col=0, header=[0, 1])

    # now that we have loaded all results from a rnadiff analysis, let us
    # perform the enrichment for each comparison found in the file
    annot_col = kwargs.get("annotation_attribute", "index")

    logger.info(f"Using the annotation column '{annot_col}'")

    # setting these attributes set the gene list with log2fc and padj filter
    rnadiff._log2_fc = params["log2_fc"]
    rnadiff._alpha = params["padj"]
    gene_lists = rnadiff.get_gene_lists(annot_col=annot_col, Nmax=kwargs.get("max_genes", None), dropna=True)

    output_directory = kwargs["output_directory"]
    for compa, gene_dict in gene_lists.items():
        config.output_dir = f"{output_directory}/{compa}"
        os.makedirs(f"{output_directory}", exist_ok=True)

        # for now, let us keep the 'all' category
        # del gene_dict["all"]

        ModulePantherEnrichment(
            gene_dict,
            taxon,
            enrichment_params=params,
            command=" ".join(["sequana"] + sys.argv[1:]),
            ontologies=ontologies,
        )

1	# This file is part of Sequana software
2	#
3	# Copyright (c) 2016-2020 - Sequana Development Team
4	#
5	# Distributed under the terms of the 3-clause BSD license.
6	# The full license is in the LICENSE file, distributed with this software.
7	#
8	# website: https://github.com/sequana/sequana
9	# documentation: http://sequana.readthedocs.io
10	#
11	##############################################################################
12	import os	×
13	import sys	×
14
15	import click	×
16	import colorlog	×
17
18	from sequana.modules_report import ModulePantherEnrichment	×
19	from sequana.rnadiff import RNADiffResults	×
20	from sequana.utils import config	×
21
22	from .utils import CONTEXT_SETTINGS, common_logger, OptionEatAll	×
23
24
25	logger = colorlog.getLogger(__name__)	×
26
27
28	# This will be a complex command to provide HTML summary page for
29	# input files (e.g. bam), or results from pipelines. For each module,
30	# we should have corresponding option that starts with the module's name
31	# This can also takes as input various types of data (e.g. FastA)
32	@click.command(context_settings=CONTEXT_SETTINGS)	×
33	@click.argument("name", type=click.Path(exists=True), nargs=1)	×
34	@click.option(	×
35	"--annotation-attribute",
36	type=click.STRING,
37	# required=True,
38	default="index",
39	show_default=True,
40	help="a valid taxon identifiers",
41	)
42	@click.option(	×
43	"--panther-taxon",
44	type=click.INT,
45	required=True,
46	help="a valid taxon identifiers",
47	)
48	@click.option(	×
49	"--log2-foldchange-cutoff",
50	type=click.FLOAT,
51	default=1,
52	show_default=True,
53	help="remove events with absolute log2 fold change below this value",
54	)
55	@click.option(	×
56	"--padj-cutoff",
57	type=click.FLOAT,
58	default=0.05,
59	show_default=True,
60	help="remove events with pvalue abobe this value default (0.05).",
61	)
62	@click.option(	×
63	"--plot-linearx",
64	type=click.BOOL,
65	default=False,
66	is_flag=True,
67	show_default=True,
68	help="""Default is log2 fold enrichment in the plots. use this to use linear scale""",
69	)
70	@click.option(	×
71	"--compute-levels/--no-compute-levels",
72	default=True,
73	help="""Compute the levels of each go term, set --no-compute-levels to skip this step""",
74	)
75	@click.option(	×
76	"--max-genes",
77	type=click.INT,
78	default=2500,
79	show_default=True,
80	help="""Maximum number of genes (up or down) to use in PantherDB.""",
81	)
82	@click.option(	×
83	"--ontologies",
84	default=("MF", "BP", "CC"),
85	help="""Provide the ontologies to be included in the analysis and HTML report.
86	Valid choices are: from MF, BP, CC, SLIM_MF, SLIM_BP, SLIM_CC, PROTEIN,
87	PANTHER_PATHWAY, REACTOME_PATHWAY""",
88	cls=OptionEatAll,
89	show_default=True,
90	)
91	@click.option(	×
92	"--max-enriched-go-terms",
93	type=click.INT,
94	default=40,
95	show_default=True,
96	help="""Max number of enriched go terms to show in the plots (most
97	enriched). All enriched GO terms are stored in tables""",
98	)
99	@click.option("--output-directory", show_default=True, default="enrichment_panther")	×
100	@common_logger	×
101	def enrichment_panther(**kwargs):
102	"""Create a HTML report for various sequana out
103
104	\b
105	* enrichment: the output of RNADiff pipeline
106
107	Example for the enrichment module:
108
109	sequana enrichment-panther rnadiff.csv --panther-taxon 10090
110	--log2-foldchange-cutoff 2
111
112	sequana enrichment rnadiff/rnadiff.csv
113	--panther-taxon 189518 \
114	--log2-foldchange-cutoff 2
115	--ontologies MF SLIM_MF
116
117	\b
118	Valid ontologies are: MF, BP, CC, SLIM_MF, SLIM_BP, SLIM_CC,
119	PROTEIN, "PANTHER_PATHWAY", "REACTOME_PATHWAY"
120
121
122	"""
123	valid = [	×
124	"MF",
125	"BP",
126	"CC",
127	"SLIM_MF",
128	"SLIM_BP",
129	"SLIM_CC",
130	"PROTEIN",
131	"PANTHER_PATHWAY",
132	"REACTOME_PATHWAY",
133	]
134
135	ontologies = eval(kwargs["ontologies"])	×
136	for ontology in ontologies:	×
137	if ontology not in valid:	×
138	logger.error(f"Provided incorrect ontology ({ontology}). Must be in {valid}")	×
139	sys.exit(1)	×
140
141	logger.setLevel(kwargs["logger"])	×
142
143	taxon = kwargs["panther_taxon"]	×
144	if taxon == 0:	×
145	logger.error("You must provide a taxon with --panther-taxon")	×
146	sys.exit(1)	×
147
148	params = {	×
149	"padj": kwargs["padj_cutoff"],
150	"log2_fc": kwargs["log2_foldchange_cutoff"],
151	"max_entries": kwargs["max_genes"],
152	"nmax": kwargs["max_enriched_go_terms"],
153	"plot_logx": not kwargs["plot_linearx"],
154	"plot_compute_levels": kwargs["compute_levels"],
155	}
156
157	logger.info(f"Reading RNAdiff results from {kwargs['name']}")	×
158	dirpath = os.path.dirname(os.path.abspath(kwargs["name"]))	×
159	rnadiff = RNADiffResults(dirpath, index_col=0, header=[0, 1])	×
160
161	# now that we have loaded all results from a rnadiff analysis, let us
162	# perform the enrichment for each comparison found in the file
163	annot_col = kwargs.get("annotation_attribute", "index")	×
164
165	logger.info(f"Using the annotation column '{annot_col}'")	×
166
167	# setting these attributes set the gene list with log2fc and padj filter
168	rnadiff._log2_fc = params["log2_fc"]	×
169	rnadiff._alpha = params["padj"]	×
170	gene_lists = rnadiff.get_gene_lists(annot_col=annot_col, Nmax=kwargs.get("max_genes", None), dropna=True)	×
171
172	output_directory = kwargs["output_directory"]	×
173	for compa, gene_dict in gene_lists.items():	×
174	config.output_dir = f"{output_directory}/{compa}"	×
175	os.makedirs(f"{output_directory}", exist_ok=True)	×
176
177	# for now, let us keep the 'all' category
178	# del gene_dict["all"]
179
180	ModulePantherEnrichment(	×
181	gene_dict,
182	taxon,
183	enrichment_params=params,
184	command=" ".join(["sequana"] + sys.argv[1:]),
185	ontologies=ontologies,
186	)

sequana / sequana / 2578686232

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous