feat: add wrapper for coolpuppy (#554)

<!-- Ensure that the PR title follows conventional commit style (<type>:
<description>)-->
<!-- Possible types are here:
https://github.com/commitizen/conventional-commit-types/blob/master/index.json
-->

### Description

Created a wrapper for coolpup.py (https://github.com/open2c/coolpuppy)

### QC
<!-- Make sure that you can tick the boxes below. -->

* [x] I confirm that:

For all wrappers added by this PR, 

* there is a test case which covers any introduced changes,
* `input:` and `output:` file paths in the resulting rule can be changed
arbitrarily,
* either the wrapper can only use a single core, or the example rule
contains a `threads: x` statement with `x` being a reasonable default,
* rule names in the test case are in
[snake_case](https://en.wikipedia.org/wiki/Snake_case) and somehow tell
what the rule is about or match the tools purpose or name (e.g.,
`map_reads` for a step that maps reads),
* all `environment.yaml` specifications follow [the respective best
practices](https://stackoverflow.com/a/64594513/2352071),
* wherever possible, command line arguments are inferred and set
automatically (e.g. based on file extensions in `input:` or `output:`),
* all fields of the example rules in the `Snakefile`s and their entries
are explained via comments (`input:`/`output:`/`params:` etc.),
* `stderr` and/or `stdout` are logged correctly (`log:`), depending on
the wrapped tool,
* temporary files are either written to a unique hidden folder in the
working directory, or (better) stored where the Python function
`tempfile.gettempdir()` points to (see
[here](https://docs.python.org/3/library/tempfile.html#tempfile.gettempdir);
this also means that using any Python `tempfile` default behavior
works),
* the `meta.yaml` contains a link to the documentation of the respective
tool or command,
* `Snakefile`s pass the linting (`snakemake --lint`),
* `Snakefile`s are formatted with
[snakefmt](https://github.com/snakemake/snakefmt),
* Python wrapper scripts are formatted with
[black](https://black.readthedocs.io).
* Conda environments use a minimal amount of channels, in recommended
ordering. E.g. for bioconda, use (conda-forge, bioconda, nodefaults, as
conda-forge should have highest priority and defaults channels are
usually not needed because most packages are in conda-forge nowadays).

Co-authored-by: Filipe G. Vieira <fgarrettvieira@gmail.com>

bio/coolpuppy/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - coolpuppy

bio/coolpuppy/meta.yaml

@@ -0,0 +1,20 @@
+name: coolpup.py
+description: Pileup features for a resolution in an .mcool file
+url: https://github.com/open2c/coolpuppy
+authors:
+  - Ilya Flyamer
+input:
+  - a multiresolution cooler file (.mcool)
+  - a file with features to pileup
+  - (optional) file with expected
+  - (optional) view, a bed-style file with region coordinates and names to use for analysis
+output:
+  - >
+    A file (.clpy, HDF5-based format) with the pileup.
+    Can have a {resolution} wildcard that specifies the resolution for the analysis,
+    then it doesn't need to be specified as a parameter.
+params:
+  resolution: >
+    Optional, can be instead specified as a wildcard in the output
+  extra: Any additional arguments to pass
+notes:

bio/coolpuppy/test/CN.mm9.toy_expected.tsv

@@ -0,0 +1,101 @@
+region1	region2	dist	n_valid	count.sum	balanced.sum	balanced.avg
+foo	foo	0	50			
+foo	foo	1	49			
+foo	foo	2	48	448255.0	2.3205076553434987	0.04834390948632289
+foo	foo	3	47	271497.0	1.38339695992966	0.02943397787084383
+foo	foo	4	46	179491.0	0.900655795691491	0.01957947381938024
+foo	foo	5	45	135426.0	0.6826130105698165	0.015169178012662588
+foo	foo	6	44	96841.0	0.48167647260294866	0.010947192559157925
+foo	foo	7	43	74458.0	0.36747755422094075	0.008545989633045134
+foo	foo	8	42	56431.0	0.2767897183400133	0.0065902313890479364
+foo	foo	9	41	46579.0	0.23020444753273792	0.005614742622749705
+foo	foo	10	40	42800.0	0.21407619204942857	0.005351904801235714
+foo	foo	11	39	38893.0	0.1931769021342914	0.0049532539008792665
+foo	foo	12	38	35915.0	0.1760485882134026	0.004632857584563227
+foo	foo	13	37	31507.0	0.15432815796541483	0.0041710312963625625
+foo	foo	14	36	28275.0	0.13916825128679033	0.003865784757966398
+foo	foo	15	35	26582.0	0.13214461875460215	0.0037755605358457756
+foo	foo	16	34	24080.0	0.1200420079045525	0.0035306472913103674
+foo	foo	17	33	22554.0	0.1123809167677425	0.0034054823262952274
+foo	foo	18	32	21069.0	0.10519693902501005	0.003287404344531564
+foo	foo	19	31	19565.0	0.09730388315158268	0.003138834940373635
+foo	foo	20	30	18830.0	0.09344118037915836	0.003114706012638612
+foo	foo	21	29	18180.0	0.09181365603513099	0.003165988139142448
+foo	foo	22	28	16817.0	0.0857312761411997	0.003061831290757132
+foo	foo	23	27	15637.0	0.08088906104487427	0.0029958911498101583
+foo	foo	24	26	13554.0	0.0696931607808895	0.0026805061838803654
+foo	foo	25	25	12151.0	0.062133968853916574	0.002485358754156663
+foo	foo	26	24	10641.0	0.053908741063492124	0.002246197544312172
+foo	foo	27	23	9371.0	0.04780835937733471	0.002078624320753683
+foo	foo	28	22	8684.0	0.04565538936132342	0.0020752449709692464
+foo	foo	29	21	7883.0	0.04194264489363847	0.0019972688044589747
+foo	foo	30	20	7602.0	0.04117335917285604	0.002058667958642802
+foo	foo	31	19	6783.0	0.03642786791651601	0.0019172562061324217
+foo	foo	32	18	6220.0	0.033609930607101324	0.0018672183670611847
+foo	foo	33	17	5752.0	0.03126540105125592	0.0018391412383091717
+foo	foo	34	16	5236.0	0.02870993254323146	0.0017943707839519663
+foo	foo	35	15	4806.0	0.026732726358511393	0.0017821817572340928
+foo	foo	36	14	4562.0	0.025516336044875902	0.0018225954317768502
+foo	foo	37	13	4484.0	0.025173064987642168	0.001936389614434013
+foo	foo	38	12	4322.0	0.024324300745100825	0.0020270250620917354
+foo	foo	39	11	3797.0	0.02095540632794532	0.00190503693890412
+foo	foo	40	10	3403.0	0.018630663941423948	0.0018630663941423947
+foo	foo	41	9	3044.0	0.016810995031025552	0.001867888336780617
+foo	foo	42	8	2716.0	0.015316241229781234	0.0019145301537226542
+foo	foo	43	7	2461.0	0.014124488058201323	0.002017784008314475
+foo	foo	44	6	2060.0	0.011782977088540664	0.0019638295147567774
+foo	foo	45	5	1629.0	0.009356770724295723	0.0018713541448591446
+foo	foo	46	4	1325.0	0.007777107004193509	0.0019442767510483773
+foo	foo	47	3	950.0	0.005574745304582236	0.0018582484348607453
+foo	foo	48	2	629.0	0.003669007156579109	0.0018345035782895544
+foo	foo	49	1	326.0	0.0020415942196967394	0.0020415942196967394
+bar	bar	0	49			
+bar	bar	1	48			
+bar	bar	2	47	450107.0	2.1180050802546933	0.04506393787775943
+bar	bar	3	46	238644.0	1.1182026520831783	0.02430875330615605
+bar	bar	4	45	151877.0	0.7065426657897472	0.01570094812866105
+bar	bar	5	44	105862.0	0.4889639900117408	0.01111281795481229
+bar	bar	6	43	84565.0	0.3886687958491317	0.00903880920579376
+bar	bar	7	42	67656.0	0.305587801420597	0.007275900033823738
+bar	bar	8	41	56605.0	0.2536802573536893	0.006187323350089984
+bar	bar	9	40	49125.0	0.21940452543596367	0.005485113135899092
+bar	bar	10	39	43256.0	0.19302073776471373	0.004949249686274711
+bar	bar	11	38	38908.0	0.17213966992023477	0.0045299913136903885
+bar	bar	12	37	33613.0	0.1494114335367291	0.00403814685234403
+bar	bar	13	36	29008.0	0.1286862020151156	0.0035746167226421
+bar	bar	14	35	28208.0	0.1257340707416353	0.0035924020211895802
+bar	bar	15	34	26130.0	0.11682046178278417	0.0034358959347877698
+bar	bar	16	33	24355.0	0.10848220502658447	0.0032873395462601354
+bar	bar	17	32	21902.0	0.09720413992092795	0.0030376293725289986
+bar	bar	18	31	19754.0	0.08921457365055102	0.00287788947259842
+bar	bar	19	30	17506.0	0.0798108423392565	0.00266036141130855
+bar	bar	20	29	16951.0	0.07831020324831016	0.002700351836148626
+bar	bar	21	28	16124.0	0.07470713314986098	0.0026681118982093206
+bar	bar	22	27	16237.0	0.07516147832181286	0.002783758456363439
+bar	bar	23	26	15583.0	0.07144738725071081	0.0027479764327196466
+bar	bar	24	25	14864.0	0.06801519019393452	0.0027206076077573808
+bar	bar	25	24	14174.0	0.06516873511627985	0.002715363963178327
+bar	bar	26	23	14169.0	0.06554949528961256	0.002849978056070111
+bar	bar	27	22	13561.0	0.06221042530718225	0.0028277466048719207
+bar	bar	28	21	12073.0	0.055813578961226296	0.0026577894743441094
+bar	bar	29	20	11032.0	0.05118868034313225	0.0025594340171566127
+bar	bar	30	19	10723.0	0.050269590871060296	0.0026457679405821207
+bar	bar	31	18	10646.0	0.04998712073522266	0.0027770622630679254
+bar	bar	32	17	10320.0	0.04943531274185869	0.002907959573050511
+bar	bar	33	16	9664.0	0.04604888783607321	0.0028780554897545755
+bar	bar	34	15	9227.0	0.04425307710295975	0.0029502051401973164
+bar	bar	35	14	9111.0	0.04421548066666439	0.0031582486190474567
+bar	bar	36	13	9923.0	0.04945120961837048	0.003803939201413114
+bar	bar	37	12	9219.0	0.04674824569212995	0.0038956871410108294
+bar	bar	38	11	8027.0	0.04077733321358686	0.0037070302921442602
+bar	bar	39	10	6756.0	0.03230495094148628	0.0032304950941486276
+bar	bar	40	9	5996.0	0.027699878189309274	0.003077764243256586
+bar	bar	41	8	5280.0	0.023833680900535406	0.0029792101125669258
+bar	bar	42	7	4560.0	0.019837282406156377	0.002833897486593768
+bar	bar	43	6	3911.0	0.01627847374007839	0.0027130789566797314
+bar	bar	44	5	3155.0	0.012966661266117605	0.002593332253223521
+bar	bar	45	4	2335.0	0.008792759755829107	0.0021981899389572766
+bar	bar	46	3	1518.0	0.005519380548429014	0.0018397935161430046
+bar	bar	47	2	1142.0	0.003471630969823881	0.0017358154849119406
+bar	bar	48	1	756.0	0.0019403909506671992	0.0019403909506671992
+bar	bar	49	0	361.0	0.0	

bio/coolpuppy/test/CN.mm9.toy_features.bed

@@ -0,0 +1,2 @@
+chr1	100100000	100150000
+chr2	100200000	100250000

bio/coolpuppy/test/CN.mm9.toy_regions.bed

@@ -0,0 +1,2 @@
+chr1	100000000	150000000	foo
+chr2	100000000	150000000	bar

bio/coolpuppy/test/Snakefile

@@ -0,0 +1,17 @@
+rule coolpuppy:
+    input:
+        cooler="CN.mm9.1000kb.mcool",  ## Multiresolution cooler file
+        features="CN.mm9.toy_features.bed",  ## Feature file
+        expected="CN.mm9.toy_expected.tsv",  ## Expected file
+        view="CN.mm9.toy_regions.bed",  ## File with the region names and coordinates
+    output:
+        "CN_{resolution,[0-9]+}.clpy",
+    params:
+        ## Add optional parameters
+        features_format="bed",  ## Format of the features file
+        extra="--local",  ## Add extra parameters
+    threads: 2
+    log:
+        "logs/CN_{resolution}_coolpuppy.log",
+    wrapper:
+        "master/bio/coolpuppy"

bio/coolpuppy/wrapper.py

@@ -0,0 +1,33 @@
+__author__ = "Ilya Flyamer"
+__copyright__ = "Copyright 2022, Ilya Flyamer"
+__email__ = "flyamer@gmail.com"
+__license__ = "MIT"
+
+from snakemake.shell import shell
+
+## Extract arguments
+view = snakemake.input.get("view", "")
+if view:
+    view = f"--view {view}"
+expected = snakemake.input.get("expected", "")
+if expected:
+    expected = f"--expected {expected}"
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+resolution = snakemake.params.get("resolution", snakemake.wildcards.get("resolution"))
+if not resolution:
+    raise ValueError("Please specify resolution either as a wildcard or as a parameter")
+
+shell(
+    "(coolpup.py"
+    " {snakemake.input.cooler}::resolutions/{resolution}"
+    " {snakemake.input.features}"
+    " {expected}"
+    " --features-format {snakemake.params.features_format}"
+    " {view}"
+    " -p {snakemake.threads}"
+    " {extra}"
+    " -o {snakemake.output}) {log}"
+)

test.py

@@ -1817,6 +1817,14 @@ def test_clustalo():
     )
 
 
+@skip_if_not_modified
+def test_coolpuppy():
+    run(
+        "bio/coolpuppy",
+        ["snakemake", "--cores", "1", "CN_1000000.clpy", "--use-conda", "-F"],
+    )
+
+
 @skip_if_not_modified
 def test_cooltools_insulation():
     run(