annotate umi-tools_whitelist.xml @ 2:c1743022a8cd draft

planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
author iuc
date Thu, 29 Mar 2018 18:24:04 -0400
parents dac4e7dc837d
children 853f74e08009
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
1 <tool id="umi_tools_whitelist" name="UMI-tools whitelist" version="@VERSION@.1">
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>
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
5 <macro name="barcode2_conditional" >
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
6 <conditional name="barcode">
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
7 <param name="barcode_select" argument="--split-barcode" type="select" label="Barcode on both reads?">
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
8 <option value="first_read_only">Barcode on first read only</option>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
9 <option value="both_reads">Barcode on both reads</option>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
10 </param>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
11 <when value="first_read_only"/>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
12 <when value="both_reads">
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
13 <param name="bc_pattern2" argument="--bc-pattern2" type="text" value="" label="Barcode pattern for second read"
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
14 help="Use this option to specify the format of the UMI/barcode for
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
15 the second read pair if required.">
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
16 </param>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
17 </when>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
18 </conditional>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
19 </macro>
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
20 </macros>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
21 <expand macro="requirements" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
22 <command detect_errors="exit_code"><![CDATA[
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
23 #set $gz = False
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
24 #if $input_type.type == 'single':
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
25 #if $input_type.input_single.is_of_type("fastq.gz", "fastqsanger.gz"):
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
26 ln -s '$input_type.input_single' input_single.gz &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
27 #set $gz = True
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
28 #end if
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
29 #elif $input_type.type == 'paired':
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
30 #if $input_type.input_read1.is_of_type("fastq.gz", "fastqsanger.gz"):
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
31 ln -s '$input_type.input_read1' input_read1.gz &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
32 ln -s '$input_type.input_read2' input_read2.gz &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
33 #set $gz = True
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
34 #end if
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
35 #else ## paired_collection
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
36 #if $input_type.input_readpair.forward.is_of_type("fastq.gz", "fastqsanger.gz"):
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
37 ln -s '$input_type.input_readpair.forward' input_read1.gz &&
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
38 ln -s '$input_type.input_readpair.reverse' input_read2.gz &&
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
39 #set $gz = True
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
40 #end if
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
41 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
42 umi_tools whitelist
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
43 --bc-pattern='$bc_pattern'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
44 --subset-reads='$subset_reads'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
45 #if $input_type.type == 'single':
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
46 #if $gz:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
47 --stdin=input_single.gz
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
48 #else
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
49 --stdin='$input_type.input_single'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
50 #end if
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
51 #else: ## equally valid for both 'paired' and 'paired_collection'
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
52 #if $gz:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
53 --stdin=input_read1.gz
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
54 --read2-in=input_read2.gz
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
55 #else:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
56 --stdin='$input_type.input_read1'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
57 --read2-in='$input_type.input_read2'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
58 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
59 #if $input_type.barcode.barcode_select == "1":
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
60 --bc-pattern2='$input_type.barcode.bc_pattern2'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
61 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
62 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
63 #if $celloptions.use_cell_opts == "advanced":
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
64 #if $celloptions.set_cell_number != "0":
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
65 --set-cell-number=$celloptions.set_cell_number
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
66 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
67 #if $celloptions.expect_cells != "0":
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
68 --expect-cells=$celloptions.expect_cells
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
69 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
70 --error-correct-threshold=$celloptions.error_correct_thresh
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
71 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
72 --method=$method
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
73 --plot-prefix=OUT
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
74
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
75 $prime3
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
76
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
77 #if $log:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
78 --log='$out_log'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
79 #end if
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
80
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
81 --log2stderr
1
dac4e7dc837d planemo upload commit c69e558f5186d40896ee40a49bdb2275949faf9e
iuc
parents: 0
diff changeset
82
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
83 > '$out_whitelist' &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
84
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
85 mkdir '${ out_html_report.files_path }' &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
86 cp OUT_*.png '${ out_html_report.files_path }' &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
87
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
88 echo "<html>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
89 <head></head><body>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
90 <h1>Cell and Count Metrics</h1>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
91 <img src=\"OUT_cell_barcode_count_density.png\" ><br />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
92 <img src=\"OUT_cell_barcode_knee.png\" ><br />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
93 <img src=\"OUT_cell_barcode_counts.png\" ><br />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
94 </body></html>" > '$out_html_report'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
95 &&
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
96 mv OUT_cell_thresholds.tsv '$out_thresh'
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
97 ]]></command>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
98 <inputs>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
99 <conditional name="input_type">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
100 <param name="type" type="select" label="Library type">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
101 <option value="single">Single-end</option>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
102 <option value="paired">Paired-end</option>
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
103 <option value="paired_collection">Paired-end Dataset Collection</option>
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
104 </param>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
105 <when value="single">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
106 <param name="input_single" type="data" format="fastq,fastq.gz" label="Reads in FASTQ format" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
107 </when>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
108 <when value="paired">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
109 <param name="input_read1" type="data" format="fastq,fastq.gz" label="Reads in FASTQ format" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
110 <param name="input_read2" type="data" format="fastq,fastq.gz" label="Reads in FASTQ format" />
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
111 <expand macro="barcode2_conditional" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
112 </when>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
113 <when value="paired_collection">
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
114 <param name="input_readpair" type="data_collection" collection_type="paired" format="fastq,fastq.gz" label="Reads in FASTQ format" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
115 <expand macro="barcode2_conditional" />
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
116 </when>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
117 </conditional>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
118 <param name="bc_pattern" argument="--bc-pattern" type="text" label="Barcode pattern for first read"
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
119 help="Use this option to specify the format of the UMI/barcode. Use Ns to
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
120 represent the random positions and Xs to indicate the bc positions.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
121 Bases with Ns will be extracted and added to the read name. Remaining
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
122 bases, marked with an X will be reattached to the read.">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
123 </param>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
124 <param name="method" argument="--method" type="select" label="Count reads or UMIs"
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
125 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
126 <option value="reads" selected="true" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
127 <option value="umis" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
128 </param>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
129
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
130 <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
131 truevalue="--3prime" falsevalue=""
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
132 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
133 use this option to specify that it is on the 3' end instead." />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
134 <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
135 <conditional name="celloptions" >
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
136 <param name="use_cell_opts" type="select" label="Cell parameters" >
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
137 <option value="defaults" selected="True">Use Defaults</option>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
138 <option value="advanced">Advanced Options</option>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
139 </param>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
140 <when value="defaults"/>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
141 <when value="advanced">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
142 <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
143 <param name="expect_cells" type="integer" min="0" value="0" label="Prior expectation on the upper limit on the number of cells sequenced" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
144 <param name="error_correct_thresh" type="integer" min="0" value="0" label="Hamming distance for correction of barcodes to whilelist barcodes. Set to zero to generate no error correcting metrics." />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
145 </when>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
146 </conditional>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
147 <param argument="--log" type="boolean" label="Output log?" truevalue="--log" falsevalue=""
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
148 help="Choose if you want to generate a text file containing logging information." />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
149
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
150 </inputs>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
151 <outputs>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
152 <data name="out_whitelist" format="tabular" label="${tool.name} on ${on_string}: Whitelist"/>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
153 <data name="out_log" format="txt" label="${tool.name} on ${on_string}: logfile" >
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
154 <filter>log</filter>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
155 </data>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
156 <data name="out_html_report" format="html" label="${tool.name} on ${on_string}: Webpage" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
157 <data name="out_thresh" format="tabular" label="${tool.name} on ${on_string}: TSV Cell Thresholds" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
158 </outputs>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
159 <tests>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
160 <test expect_num_outputs="3">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
161 <param name="type" value="single" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
162 <param name="input_single" value="t_R2.fastq.gz" ftype="fastq" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
163 <param name="bc_pattern" value="CCCCCCCCNNNNNNNN" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
164 <param name="method" value="reads" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
165 <param name="prime3" value="true" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
166 <output name="out_whitelist" file="out_wl_single.txt" lines_diff="40" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
167 <output name="out_thresh" file="out_wl_single.tresh.tab" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
168 <output name="out_html_report" file="out_wl_single.html" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
169 </test>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
170 <test expect_num_outputs="4">
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
171 <param name="type" value="paired" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
172 <param name="input_read1" value="t_R1.fastq.gz" ftype="fastq" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
173 <param name="input_read2" value="t_R2.fastq.gz" ftype="fastq" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
174 <param name="barcode_select" value="both_reads" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
175 <param name="bc_pattern" value="CCCNNNNNNNNXXXXX" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
176 <param name="bc_pattern2" value="CCCCCCCCNNNNNNNN" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
177 <param name="method" value="reads" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
178 <param name="prime3" value="false" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
179 <param name="use_cell_opts" value="advanced" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
180 <param name="expect_cells" value="5" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
181 <param name="error_correct_thresh" value="3" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
182 <param name="log" value="true" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
183 <output name="out_whitelist" file="out_wl_paired.txt" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
184 <output name="out_log" file="out_wl_paired.log" lines_diff="40" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
185 <output name="out_html_report" file="out_wl_paired.html" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
186 <output name="out_thresh" file="out_wl_paired.tresh.tab" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
187 </test>
2
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
188 <test expect_num_outputs="4"> <!-- As previous, identical outputs but paired collection input -->
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
189 <param name="type" value="paired_collection" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
190 <param name="input_readpair" >
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
191 <collection type="paired">
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
192 <element name="forward" ftype="fastq.gz" value="t_R1.fastq.gz" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
193 <element name="reverse" ftype="fastq.gz" value="t_R2.fastq.gz" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
194 </collection>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
195 </param>
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
196 <param name="barcode_select" value="both_reads" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
197 <param name="bc_pattern" value="CCCNNNNNNNNXXXXX" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
198 <param name="bc_pattern2" value="CCCCCCCCNNNNNNNN" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
199 <param name="method" value="reads" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
200 <param name="prime3" value="false" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
201 <param name="use_cell_opts" value="advanced" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
202 <param name="expect_cells" value="5" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
203 <param name="error_correct_thresh" value="3" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
204 <param name="log" value="true" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
205 <output name="out_whitelist" file="out_wl_paired.txt" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
206 <output name="out_log" file="out_wl_paired.log" lines_diff="40" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
207 <output name="out_html_report" file="out_wl_paired.html" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
208 <output name="out_thresh" file="out_wl_paired.tresh.tab" />
c1743022a8cd planemo upload commit e274ffd67bede657f4f5a2c6524023ff57f0db87
iuc
parents: 1
diff changeset
209 </test>
0
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
210 </tests>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
211 <help><![CDATA[
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
212
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
213
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
214 UMI-tools whitelist - Extract barcodes from fastq
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
215 ==================================================
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
216
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
217 Purpose
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
218 -------
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
219
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
220 Extract cell barcodes and identify the most likely true barcodes using
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
221 the 'knee' method.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
222
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
223 Options
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
224 -------
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
225
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
226 --bc-pattern
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
227 This should be used where the barcodes are always in the same
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
228 place in the read.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
229
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
230 - N = UMI position (required)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
231 - C = cell barcode position (optional)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
232 - X = sample position (optional)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
233
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
234 Bases with Ns and Cs will be extracted and added to the read
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
235 name. The corresponding sequence qualities will be removed from
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
236 the read. Bases with an X will be reattached to the read.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
237
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
238 E.g. If the pattern is NNNNCC,
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
239 Then the read:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
240 @HISEQ:87:00000000 read1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
241 AAGGTTGCTGATTGGATGGGCTAG
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
242 DA1AEBFGGCG01DFH00B1FF0B
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
243 +
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
244 will become:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
245 @HISEQ:87:00000000_TT_AAGG read1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
246 GCTGATTGGATGGGCTAG
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
247 1AFGGCG01DFH00B1FF0B
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
248 +
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
249
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
250 where 'TT' is the cell barcode and 'AAGG' is the UMI.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
251
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
252
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
253 --set-cell-number
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
254 Use this option to explicity set the number of cell barcodes
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
255 which should be accepted. Note that the exact number of cell
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
256 barcodes in the outputted whitelist may be slightly less than
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
257 this if there are multiple cells observed with the same
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
258 frequency at the threshold between accepted and rejected cell
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
259 barcodes.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
260
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
261 --expect-cells=[EXPECTED_CELLS]
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
262 An upper limit estimate for the number of inputted cells. The knee
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
263 method will now select the first threshold (order ascendingly)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
264 which results in the number of cell barcodes accepted being <=
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
265 EXPECTED_CELLS and > EXPECTED_CELLS * 0.1.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
266
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
267
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
268 --bc-pattern2
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
269 Use this option to specify the format of the UMI/barcode for
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
270 the second read pair if required. If --bc-pattern2 is not
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
271 supplied, this defaults to the same pattern as --bc-pattern
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
272
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
273 --3prime
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
274 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
275 use this option to sepecify that it is on the 3' end instead
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
276
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
277 Usage:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
278 ------
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
279
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
280 For single ended reads:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
281 umi_tools whitelist --bc-pattern=[PATTERN] -L extract.log
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
282 [OPTIONS]
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
283
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
284 reads from stdin and outputs to stdout.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
285
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
286 For paired end reads where the cell barcodes is split across the read pairs:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
287 umi_tools whitelist --bc-pattern=[PATTERN]
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
288 --bc-pattern2=[PATTERN] --read2-in=[FASTQIN] -L extract.log
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
289 [OPTIONS]
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
290
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
291 reads end one from stdin and end two from FASTQIN and outputs to stdin
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
292
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
293
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
294 Output:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
295 -------
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
296
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
297 The whitelist is outputted as 4 tab-separated columns:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
298
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
299 1. whitelisted cell barcode
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
300 2. Other cell barcode(s) (comma-separated) to correct to the
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
301 whitelisted barcode
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
302 3. Count for whitelisted cell barcodes
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
303 4. Count(s) for the other cell barcode(s) (comma-separated)
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
304
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
305 example output:
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
306
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
307 AAAAAA AGAAAA 146 1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
308 AAAATC 22
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
309 AAACAT 21
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
310 AAACTA AAACTN,GAACTA 27 1,1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
311 AAATAC 72
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
312 AAATCA GAATCA 37 3
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
313 AAATGT AAAGGT,CAATGT 41 1,1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
314 AAATTG CAATTG 36 1
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
315 AACAAT 18
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
316 AACATA 24
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
317
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
318 If --error-correct-threshold is set to 0, columns 2 and 4 will be empty.
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
319
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
320
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
321 ]]></help>
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
322 <expand macro="citations" />
b911124762a8 planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
iuc
parents:
diff changeset
323 </tool>