1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
|
%global _empty_manifest_terminate_build 0
Name: python-NanoComp
Version: 1.21.0
Release: 1
Summary: Comparing runs of Oxford Nanopore sequencing data and alignments
License: MIT
URL: https://github.com/wdecoster/NanoComp
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/df/5c/90c269e98d84fddd731ebb897a12ca6d2d793212fa76315e2f0406368996/NanoComp-1.21.0.tar.gz
BuildArch: noarch
%description
# NanoComp
Compare multiple runs of long read sequencing data and alignments. Creates violin plots or box plots of length, quality and percent identity and creates dynamic, overlaying read length histograms and a cumulative yield plot.
As of version 1.1.0 NanoComp will also create a static png image for dynamic html plots, as the latter can get quite big and slow to load for big datasets. This however requires that you install [orca](https://github.com/plotly/orca). Without orca the script still works, but no static copies of dynamic plots are created.
[](https://twitter.com/wouter_decoster)
### INSTALLATION
`pip install NanoComp`
This script is written for Python3.
### USAGE
```
NanoComp [-h] [-v] [-t THREADS] [-o OUTDIR] [-p PREFIX] [--verbose]
[--raw] [--readtype {1D,2D,1D2}] [--barcoded]
[--split_runs TSV_FILE]
[-f {eps,jpeg,jpg,pdf,pgf,png,ps,raw,rgba,svg,svgz,tif,tiff}]
[-n names [names ...]] [--plot {violin,box}] [--title TITLE]
(--fastq files [files ...] | --summary files [files ...] | --bam files [files ...])
General options:
-h, --help show the help and exit
-v, --version Print version and exit.
-t, --threads THREADS
Set the allowed number of threads to be used by the script
-o, --outdir OUTDIR Specify directory in which output has to be created.
-p, --prefix PREFIX Specify an optional prefix to be used for the output files.
--verbose Write log messages also to terminal.
--raw Store the extracted data in tab separated file.
Options for filtering or transforming input prior to plotting:
--readtype {1D,2D,1D2}
Which read type to extract information about from summary. Options are 1D, 2D,
1D2
--barcoded Barcoded experiment in summary format, splitting per barcode.
--split_runs TSV_FILE
File: Split the summary on run IDs and use names in tsv file. Mandatory header
fields are 'NAME' and 'RUN_ID'.
Options for customizing the plots created:
-f, --format {'png'(default),'jpg','jpeg','webp','svg','pdf','eps','json'}
Specify the output format of the plots. JSON output allows for customisation by the end-user after plotting the figures (https://plotly.com/python-api-reference/generated/plotly.io.read_json.html).
-n, --names names Specify the names to be used for the datasets.
-c, --colors colors Specify the colors to be used for the datasets.
--plot {violin,box,ridge,false}
Which plot type to use: 'box', 'violin' (default), 'ridge' (joyplot) or 'false' (no plots)
--title TITLE Add a title to all plots, requires quoting if using spaces
Input data sources, one of these is required.:
--fastq files [files ...]
Data is in (compressed) fastq format.
--fasta files [files ...]
Data is in (compressed) fasta format.
--summary files [files ...]
Data is in (compressed) summary files generated by albacore or guppy.
--bam files [files ...]
Data is in sorted bam files.
```
[Example file for --split_runs](https://github.com/wdecoster/nanocomp/blob/master/extra/split_file.tsv)
### EXAMPLES
```
NanoComp --bam alignment1.bam alignment2.bam alignment3.bam --outdir compare-runs
NanoComp --fastq reads1.fastq.gz reads2.fastq.gz reads3.fastq.gz reads4.fastq.gz --names run1 run2 run3 run4
```
### EXAMPLE OUTPUT
[See more examples](https://github.com/wdecoster/nanocomp/tree/master/examples)
I welcome all suggestions, bug reports, feature requests and contributions. Please leave an [issue](https://github.com/wdecoster/nanocomp/issues) or open a pull request. I will usually respond within a day, or rarely within a few days.
## CITATION
If you use this tool, please consider citing our [publication](https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/bty149/4934939).
%package -n python3-NanoComp
Summary: Comparing runs of Oxford Nanopore sequencing data and alignments
Provides: python-NanoComp
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-NanoComp
# NanoComp
Compare multiple runs of long read sequencing data and alignments. Creates violin plots or box plots of length, quality and percent identity and creates dynamic, overlaying read length histograms and a cumulative yield plot.
As of version 1.1.0 NanoComp will also create a static png image for dynamic html plots, as the latter can get quite big and slow to load for big datasets. This however requires that you install [orca](https://github.com/plotly/orca). Without orca the script still works, but no static copies of dynamic plots are created.
[](https://twitter.com/wouter_decoster)
### INSTALLATION
`pip install NanoComp`
This script is written for Python3.
### USAGE
```
NanoComp [-h] [-v] [-t THREADS] [-o OUTDIR] [-p PREFIX] [--verbose]
[--raw] [--readtype {1D,2D,1D2}] [--barcoded]
[--split_runs TSV_FILE]
[-f {eps,jpeg,jpg,pdf,pgf,png,ps,raw,rgba,svg,svgz,tif,tiff}]
[-n names [names ...]] [--plot {violin,box}] [--title TITLE]
(--fastq files [files ...] | --summary files [files ...] | --bam files [files ...])
General options:
-h, --help show the help and exit
-v, --version Print version and exit.
-t, --threads THREADS
Set the allowed number of threads to be used by the script
-o, --outdir OUTDIR Specify directory in which output has to be created.
-p, --prefix PREFIX Specify an optional prefix to be used for the output files.
--verbose Write log messages also to terminal.
--raw Store the extracted data in tab separated file.
Options for filtering or transforming input prior to plotting:
--readtype {1D,2D,1D2}
Which read type to extract information about from summary. Options are 1D, 2D,
1D2
--barcoded Barcoded experiment in summary format, splitting per barcode.
--split_runs TSV_FILE
File: Split the summary on run IDs and use names in tsv file. Mandatory header
fields are 'NAME' and 'RUN_ID'.
Options for customizing the plots created:
-f, --format {'png'(default),'jpg','jpeg','webp','svg','pdf','eps','json'}
Specify the output format of the plots. JSON output allows for customisation by the end-user after plotting the figures (https://plotly.com/python-api-reference/generated/plotly.io.read_json.html).
-n, --names names Specify the names to be used for the datasets.
-c, --colors colors Specify the colors to be used for the datasets.
--plot {violin,box,ridge,false}
Which plot type to use: 'box', 'violin' (default), 'ridge' (joyplot) or 'false' (no plots)
--title TITLE Add a title to all plots, requires quoting if using spaces
Input data sources, one of these is required.:
--fastq files [files ...]
Data is in (compressed) fastq format.
--fasta files [files ...]
Data is in (compressed) fasta format.
--summary files [files ...]
Data is in (compressed) summary files generated by albacore or guppy.
--bam files [files ...]
Data is in sorted bam files.
```
[Example file for --split_runs](https://github.com/wdecoster/nanocomp/blob/master/extra/split_file.tsv)
### EXAMPLES
```
NanoComp --bam alignment1.bam alignment2.bam alignment3.bam --outdir compare-runs
NanoComp --fastq reads1.fastq.gz reads2.fastq.gz reads3.fastq.gz reads4.fastq.gz --names run1 run2 run3 run4
```
### EXAMPLE OUTPUT
[See more examples](https://github.com/wdecoster/nanocomp/tree/master/examples)
I welcome all suggestions, bug reports, feature requests and contributions. Please leave an [issue](https://github.com/wdecoster/nanocomp/issues) or open a pull request. I will usually respond within a day, or rarely within a few days.
## CITATION
If you use this tool, please consider citing our [publication](https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/bty149/4934939).
%package help
Summary: Development documents and examples for NanoComp
Provides: python3-NanoComp-doc
%description help
# NanoComp
Compare multiple runs of long read sequencing data and alignments. Creates violin plots or box plots of length, quality and percent identity and creates dynamic, overlaying read length histograms and a cumulative yield plot.
As of version 1.1.0 NanoComp will also create a static png image for dynamic html plots, as the latter can get quite big and slow to load for big datasets. This however requires that you install [orca](https://github.com/plotly/orca). Without orca the script still works, but no static copies of dynamic plots are created.
[](https://twitter.com/wouter_decoster)
### INSTALLATION
`pip install NanoComp`
This script is written for Python3.
### USAGE
```
NanoComp [-h] [-v] [-t THREADS] [-o OUTDIR] [-p PREFIX] [--verbose]
[--raw] [--readtype {1D,2D,1D2}] [--barcoded]
[--split_runs TSV_FILE]
[-f {eps,jpeg,jpg,pdf,pgf,png,ps,raw,rgba,svg,svgz,tif,tiff}]
[-n names [names ...]] [--plot {violin,box}] [--title TITLE]
(--fastq files [files ...] | --summary files [files ...] | --bam files [files ...])
General options:
-h, --help show the help and exit
-v, --version Print version and exit.
-t, --threads THREADS
Set the allowed number of threads to be used by the script
-o, --outdir OUTDIR Specify directory in which output has to be created.
-p, --prefix PREFIX Specify an optional prefix to be used for the output files.
--verbose Write log messages also to terminal.
--raw Store the extracted data in tab separated file.
Options for filtering or transforming input prior to plotting:
--readtype {1D,2D,1D2}
Which read type to extract information about from summary. Options are 1D, 2D,
1D2
--barcoded Barcoded experiment in summary format, splitting per barcode.
--split_runs TSV_FILE
File: Split the summary on run IDs and use names in tsv file. Mandatory header
fields are 'NAME' and 'RUN_ID'.
Options for customizing the plots created:
-f, --format {'png'(default),'jpg','jpeg','webp','svg','pdf','eps','json'}
Specify the output format of the plots. JSON output allows for customisation by the end-user after plotting the figures (https://plotly.com/python-api-reference/generated/plotly.io.read_json.html).
-n, --names names Specify the names to be used for the datasets.
-c, --colors colors Specify the colors to be used for the datasets.
--plot {violin,box,ridge,false}
Which plot type to use: 'box', 'violin' (default), 'ridge' (joyplot) or 'false' (no plots)
--title TITLE Add a title to all plots, requires quoting if using spaces
Input data sources, one of these is required.:
--fastq files [files ...]
Data is in (compressed) fastq format.
--fasta files [files ...]
Data is in (compressed) fasta format.
--summary files [files ...]
Data is in (compressed) summary files generated by albacore or guppy.
--bam files [files ...]
Data is in sorted bam files.
```
[Example file for --split_runs](https://github.com/wdecoster/nanocomp/blob/master/extra/split_file.tsv)
### EXAMPLES
```
NanoComp --bam alignment1.bam alignment2.bam alignment3.bam --outdir compare-runs
NanoComp --fastq reads1.fastq.gz reads2.fastq.gz reads3.fastq.gz reads4.fastq.gz --names run1 run2 run3 run4
```
### EXAMPLE OUTPUT
[See more examples](https://github.com/wdecoster/nanocomp/tree/master/examples)
I welcome all suggestions, bug reports, feature requests and contributions. Please leave an [issue](https://github.com/wdecoster/nanocomp/issues) or open a pull request. I will usually respond within a day, or rarely within a few days.
## CITATION
If you use this tool, please consider citing our [publication](https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/bty149/4934939).
%prep
%autosetup -n NanoComp-1.21.0
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-NanoComp -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Wed May 10 2023 Python_Bot <Python_Bot@openeuler.org> - 1.21.0-1
- Package Spec generated
|
