annotate umi-tools_whitelist.xml @ 10:3adbf2fa0928 draft

"planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
author iuc
date Tue, 27 Aug 2019 17:11:52 -0400
parents 095c349b4343
children 262026eb36a5
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
10
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
1 <tool id="umi_tools_whitelist" name="UMI-tools whitelist" version="@VERSION@.0">
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
2 <description>Extract cell barcodes from FASTQ files</description>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
3 <macros>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
4 <import>macros.xml</import>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
5 </macros>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
6 <expand macro="requirements" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
7 <command detect_errors="exit_code"><![CDATA[
4
095c349b4343 planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 3
diff changeset
8 @COMMAND_LINK@
3
853f74e08009 planemo upload commit d8f6e961cc9f14c5b39762f87e11352c0aadefc9
iuc
parents: 2
diff changeset
9
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
10 umi_tools whitelist
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
11 --bc-pattern='$bc_pattern'
10
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
12 --extract-method='$extract_method'
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
13 --subset-reads='$subset_reads'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
14 #if $input_type.type == 'single':
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
15 #if $gz:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
16 --stdin=input_single.gz
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
17 #else
3
853f74e08009 planemo upload commit d8f6e961cc9f14c5b39762f87e11352c0aadefc9
iuc
parents: 2
diff changeset
18 --stdin=input_single.txt
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
19 #end if
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
20 #else: ## equally valid for both 'paired' and 'paired_collection'
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
21 #if $gz:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
22 --stdin=input_read1.gz
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
23 --read2-in=input_read2.gz
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
24 #else:
3
853f74e08009 planemo upload commit d8f6e961cc9f14c5b39762f87e11352c0aadefc9
iuc
parents: 2
diff changeset
25 --stdin=input_read1.txt
853f74e08009 planemo upload commit d8f6e961cc9f14c5b39762f87e11352c0aadefc9
iuc
parents: 2
diff changeset
26 --read2-in=input_read2.txt
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
27 #end if
4
095c349b4343 planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 3
diff changeset
28 #if $input_type.barcode.barcode_select == "both_reads":
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
29 --bc-pattern2='$input_type.barcode.bc_pattern2'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
30 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
31 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
32 #if $celloptions.use_cell_opts == "advanced":
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
33 #if $celloptions.set_cell_number != "0":
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
34 --set-cell-number=$celloptions.set_cell_number
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
35 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
36 #if $celloptions.expect_cells != "0":
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
37 --expect-cells=$celloptions.expect_cells
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
38 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
39 --error-correct-threshold=$celloptions.error_correct_thresh
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
40 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
41 --method=$method
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
42 --plot-prefix=OUT
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
43
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
44 $prime3
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
45
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
46 #if $log:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
47 --log='$out_log'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
48 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
49
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
50 --log2stderr
1
dac4e7dc837d planemo upload commit c69e558f5186d40896ee40a49bdb2275949faf9e
iuc
parents: 0
diff changeset
51
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
52 > '$out_whitelist' &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
53
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
54 mkdir '${ out_html_report.files_path }' &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
55 cp OUT_*.png '${ out_html_report.files_path }' &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
56
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
57 echo "<html>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
58 <head></head><body>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
59 <h1>Cell and Count Metrics</h1>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
60 <img src=\"OUT_cell_barcode_count_density.png\" ><br />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
61 <img src=\"OUT_cell_barcode_knee.png\" ><br />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
62 <img src=\"OUT_cell_barcode_counts.png\" ><br />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
63 </body></html>" > '$out_html_report'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
64 &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
65 mv OUT_cell_thresholds.tsv '$out_thresh'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
66 ]]></command>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
67 <inputs>
4
095c349b4343 planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 3
diff changeset
68 <expand macro="input_types" />
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
69 <param name="bc_pattern" argument="--bc-pattern" type="text" label="Barcode pattern for first read"
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
70 help="Use this option to specify the format of the UMI/barcode. Use Ns to
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
71 represent the random positions and Xs to indicate the bc positions.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
72 Bases with Ns will be extracted and added to the read name. Remaining
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
73 bases, marked with an X will be reattached to the read.">
10
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
74 <expand macro="barcode_sanitizer" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
75 </param>
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
76 <param name="extract_method" argument="--extract-method" type="select" label="Barcode Extraction Method"
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
77 help="If bracketed expressions are used in the above barcode pattern, then set this to 'regex'. Otherwise leave as 'string'" >
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
78 <option value="string" selected="true" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
79 <option value="regex" />
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
80 </param>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
81 <param name="method" argument="--method" type="select" label="Count reads or UMIs"
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
82 help="Many published protocols rank CBs by the number of reads the CBs appear in. However you could also use the number of unique UMIs a CB is associated with. Note that this is still and approximation to the number of transcripts captured because the same UMI could be associated with two different transcripts and be counted as independent." >
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
83 <option value="reads" selected="true" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
84 <option value="umis" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
85 </param>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
86 <param argument="--3prime" name="prime3" type="boolean" label="Is barcode on 3' end of the read?"
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
87 truevalue="--3prime" falsevalue=""
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
88 help="By default the barcode is assumed to be on the 5' end of the read, but
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
89 use this option to specify that it is on the 3' end instead." />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
90 <param name="subset_reads" argument="--subset-reads" type="integer" min="0" value="0" label="Use the first N reads to automatically identify the true cell barcodes." />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
91 <conditional name="celloptions" >
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
92 <param name="use_cell_opts" type="select" label="Cell parameters" >
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
93 <option value="defaults" selected="True">Use Defaults</option>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
94 <option value="advanced">Advanced Options</option>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
95 </param>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
96 <when value="defaults"/>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
97 <when value="advanced">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
98 <param name="set_cell_number" type="integer" min="0" value="0" label="Specify the number of cell barcodes to accept" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
99 <param name="expect_cells" type="integer" min="0" value="0" label="Prior expectation on the upper limit on the number of cells sequenced" />
10
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
100 <param name="error_correct_thresh" type="integer" min="0" value="0" label="Hamming distance for correction of barcodes to whitelist barcodes. Set to zero to generate no error correcting metrics." />
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
101 </when>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
102 </conditional>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
103 <param argument="--log" type="boolean" label="Output log?" truevalue="--log" falsevalue=""
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
104 help="Choose if you want to generate a text file containing logging information." />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
105 </inputs>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
106 <outputs>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
107 <data name="out_whitelist" format="tabular" label="${tool.name} on ${on_string}: Whitelist"/>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
108 <data name="out_log" format="txt" label="${tool.name} on ${on_string}: logfile" >
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
109 <filter>log</filter>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
110 </data>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
111 <data name="out_html_report" format="html" label="${tool.name} on ${on_string}: Webpage" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
112 <data name="out_thresh" format="tabular" label="${tool.name} on ${on_string}: TSV Cell Thresholds" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
113 </outputs>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
114 <tests>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
115 <test expect_num_outputs="3">
10
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
116 <conditional name="input_type" >
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
117 <param name="type" value="single" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
118 <param name="input_single" value="t_R2.fastq.gz" ftype="fastq.gz" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
119 </conditional>
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
120 <param name="bc_pattern" value="CCCCCCCCNNNNNNNN" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
121 <param name="method" value="reads" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
122 <param name="prime3" value="true" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
123 <output name="out_whitelist" file="out_wl_single.txt" lines_diff="40" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
124 <output name="out_thresh" file="out_wl_single.tresh.tab" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
125 <output name="out_html_report" file="out_wl_single.html" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
126 </test>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
127 <test expect_num_outputs="4">
10
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
128 <conditional name="input_type" >
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
129 <param name="type" value="paired" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
130 <param name="input_read1" value="t_R1.fastq.gz" ftype="fastq.gz" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
131 <param name="input_read2" value="t_R2.fastq.gz" ftype="fastq.gz" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
132 </conditional>
4
095c349b4343 planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 3
diff changeset
133 <param name="barcode_select" value="first_read_only" />
095c349b4343 planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 3
diff changeset
134 <param name="bc_pattern" value="CCCNNNNNNNNXXXXX" />
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
135 <param name="bc_pattern2" value="CCCCCCCCNNNNNNNN" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
136 <param name="method" value="reads" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
137 <param name="prime3" value="false" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
138 <param name="use_cell_opts" value="advanced" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
139 <param name="expect_cells" value="5" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
140 <param name="error_correct_thresh" value="3" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
141 <param name="log" value="true" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
142 <output name="out_whitelist" file="out_wl_paired.txt" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
143 <output name="out_log" file="out_wl_paired.log" lines_diff="40" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
144 <output name="out_html_report" file="out_wl_paired.html" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
145 <output name="out_thresh" file="out_wl_paired.tresh.tab" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
146 </test>
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
147 <test expect_num_outputs="4"> <!-- As previous, identical outputs but paired collection input -->
10
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
148 <conditional name="input_type" >
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
149 <param name="type" value="paired_collection" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
150 <param name="input_readpair" >
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
151 <collection type="paired">
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
152 <element name="forward" ftype="fastq.gz" value="t_R1.fastq.gz" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
153 <element name="reverse" ftype="fastq.gz" value="t_R2.fastq.gz" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
154 </collection>
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
155 </param>
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
156 </conditional>
4
095c349b4343 planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 3
diff changeset
157 <param name="barcode_select" value="first_read_only" />
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
158 <param name="bc_pattern" value="CCCNNNNNNNNXXXXX" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
159 <param name="bc_pattern2" value="CCCCCCCCNNNNNNNN" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
160 <param name="method" value="reads" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
161 <param name="prime3" value="false" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
162 <param name="use_cell_opts" value="advanced" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
163 <param name="expect_cells" value="5" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
164 <param name="error_correct_thresh" value="3" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
165 <param name="log" value="true" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
166 <output name="out_whitelist" file="out_wl_paired.txt" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
167 <output name="out_log" file="out_wl_paired.log" lines_diff="40" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
168 <output name="out_html_report" file="out_wl_paired.html" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
169 <output name="out_thresh" file="out_wl_paired.tresh.tab" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
170 </test>
10
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
171 <!-- Error report on not accepting regex and lt and gt symbols -->
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
172 <test expect_num_outputs="3">
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
173 <conditional name="input_type" >
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
174 <param name="type" value="single" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
175 <param name="input_single" value="testYYY.40k.fastq.gz" ftype="fastq.gz" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
176 </conditional>
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
177 <param name="bc_pattern" value="(?P&#60;cell_1&#62;.{8,10})(?P&#60;discard_1&#62;ACTGGCCTGCGA){s&#60;=3}(?P&#60;cell_2&#62;.{9})(?P&#60;discard_2&#62;GGTAGCGGTGACA){s&#60;=3}(?P&#60;cell_3&#62;.{9})(?P&#60;umi_1&#62;.{8})T{3}.*" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
178 <param name="extract_method" value="regex" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
179 <param name="method" value="umis" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
180 <param name="prime3" value="true" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
181 <output name="out_whitelist" file="out_wl_user.single.txt" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
182 <output name="out_thresh" file="out_wl_user.single.tresh.tab" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
183 <output name="out_html_report" file="out_wl_user.single.html" />
3adbf2fa0928 "planemo upload commit 28e58376e1d70e38276873a7d5e2ab44db88c2c0"
iuc
parents: 4
diff changeset
184 </test>
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
185 </tests>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
186 <help><![CDATA[
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
187
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
188
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
189 UMI-tools whitelist - Extract barcodes from fastq
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
190 ==================================================
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
191
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
192 Purpose
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
193 -------
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
194
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
195 Extract cell barcodes and identify the most likely true barcodes using
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
196 the 'knee' method.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
197
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
198 Options
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
199 -------
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
200
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
201 --bc-pattern
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
202 This should be used where the barcodes are always in the same
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
203 place in the read.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
204
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
205 - N = UMI position (required)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
206 - C = cell barcode position (optional)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
207 - X = sample position (optional)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
208
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
209 Bases with Ns and Cs will be extracted and added to the read
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
210 name. The corresponding sequence qualities will be removed from
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
211 the read. Bases with an X will be reattached to the read.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
212
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
213 E.g. If the pattern is NNNNCC,
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
214 Then the read:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
215 @HISEQ:87:00000000 read1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
216 AAGGTTGCTGATTGGATGGGCTAG
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
217 DA1AEBFGGCG01DFH00B1FF0B
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
218 +
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
219 will become:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
220 @HISEQ:87:00000000_TT_AAGG read1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
221 GCTGATTGGATGGGCTAG
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
222 1AFGGCG01DFH00B1FF0B
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
223 +
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
224
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
225 where 'TT' is the cell barcode and 'AAGG' is the UMI.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
226
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
227
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
228 --set-cell-number
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
229 Use this option to explicity set the number of cell barcodes
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
230 which should be accepted. Note that the exact number of cell
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
231 barcodes in the outputted whitelist may be slightly less than
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
232 this if there are multiple cells observed with the same
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
233 frequency at the threshold between accepted and rejected cell
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
234 barcodes.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
235
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
236 --expect-cells=[EXPECTED_CELLS]
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
237 An upper limit estimate for the number of inputted cells. The knee
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
238 method will now select the first threshold (order ascendingly)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
239 which results in the number of cell barcodes accepted being <=
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
240 EXPECTED_CELLS and > EXPECTED_CELLS * 0.1.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
241
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
242
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
243 --bc-pattern2
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
244 Use this option to specify the format of the UMI/barcode for
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
245 the second read pair if required. If --bc-pattern2 is not
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
246 supplied, this defaults to the same pattern as --bc-pattern
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
247
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
248 --3prime
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
249 By default the barcode is assumed to be on the 5' end of the read, but
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
250 use this option to sepecify that it is on the 3' end instead
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
251
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
252 Usage:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
253 ------
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
254
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
255 For single ended reads:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
256 umi_tools whitelist --bc-pattern=[PATTERN] -L extract.log
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
257 [OPTIONS]
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
258
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
259 reads from stdin and outputs to stdout.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
260
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
261 For paired end reads where the cell barcodes is split across the read pairs:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
262 umi_tools whitelist --bc-pattern=[PATTERN]
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
263 --bc-pattern2=[PATTERN] --read2-in=[FASTQIN] -L extract.log
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
264 [OPTIONS]
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
265
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
266 reads end one from stdin and end two from FASTQIN and outputs to stdin
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
267
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
268
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
269 Output:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
270 -------
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
271
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
272 The whitelist is outputted as 4 tab-separated columns:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
273
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
274 1. whitelisted cell barcode
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
275 2. Other cell barcode(s) (comma-separated) to correct to the
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
276 whitelisted barcode
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
277 3. Count for whitelisted cell barcodes
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
278 4. Count(s) for the other cell barcode(s) (comma-separated)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
279
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
280 example output:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
281
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
282 AAAAAA AGAAAA 146 1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
283 AAAATC 22
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
284 AAACAT 21
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
285 AAACTA AAACTN,GAACTA 27 1,1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
286 AAATAC 72
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
287 AAATCA GAATCA 37 3
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
288 AAATGT AAAGGT,CAATGT 41 1,1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
289 AAATTG CAATTG 36 1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
290 AACAAT 18
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
291 AACATA 24
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
292
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
293 If --error-correct-threshold is set to 0, columns 2 and 4 will be empty.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
294
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
295
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
296 ]]></help>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
297 <expand macro="citations" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
298 </tool>