Trinity_CTAT_galaxy/ctat_lncrna.xml at master · NCIP/Trinity_CTAT_galaxy · GitHub

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
<tool id="ctat_lncrna" name="ctat_lncrna" version="1.0.0" profile="17.05">

    <description>Filters a high-quality set of lncRNA from reconstructed RNA-seq data</description>
    <requirements>
    <requirement type="package" version="1.0.1">ctat-lncrna</requirement>
    </requirements>
    <command detect_errors="default">
      <![CDATA[
     #if str($bedfile) != "":
     lncrna --bedfile $bedfile
     --config "${assembly.fields.path}"
     #end if

     #if str($assembly) != "":
         --assembly "${assembly.fields.value}"
     #end if

     #if $min_overlap != "":
         --min_overlap "$min_overlap"
     #end if

     #if str($min_cluster) != "":
         --min_cluster "$min_cluster"
     #end if

     #if str($min_coding) != "":
         --min_coding "$min_coding"
     #end if

    #if str($minMatch) != "":
        --minMatch "$minMatch"
    #end if

    #if str($pad) != "":
        --pad "$pad"
    #end if

    #if str($gap_open) != "":
        --gap_open "$gap_open"
    #end if

    #if str($gap_extend) != "":
        --gap_extend "$gap_extend"
    #end if
    --web
    && cp -r slncky.EvolutionBrowser $html_file.files_path
]]>
    </command>

    <inputs>
      <param name="bedfile" format="interval" type="data" value="bedfile" label="Bed File:" help="Reconstructed transcripts (ex. from StringTie or Trinity)"/>
      <param name="min_overlap" type="float" value="0.0" label="Min overlap" help="Remove any transcript that overlap annotated coding gene greater than min_overlap" />
      <param name="min_cluster" type="integer" value="2" label="Min cluster" help="Minimum size of duplication clusters to remove" />
      <param name="min_coding" type="float" value="0.1" label="Min exonic identity to filter out transcript that aligns to orthologous coding gene" help="default is set by learning coding alignment distribution from data"/>
      <param name="minMatch" type="float" value="0.1" label="Min match" help="Minimum match parameter for liftover" />
      <param name="pad" type="integer" value="0" label="Pad" help="No. of basepairs to search up- and down-stream when lifting over lnc to ortholog" />
      <param name="gap_open" type="integer" value="200" label="Gap open penalty to pass to lastz" help="Decreasing this parameter will increase sensitivity of orthology search"/>
      <param name="gap_extend" type="integer" value="40" label="Gap extend penalty to pass to lastz" help="Decreasing this parameter will increase sensitivity of orthology search."/>
      <param name="assembly" type="select" label="Choose annotation:" help="Select annotation">
            <options from_data_table="ctat_lncrna_annotations" />
      </param>
    </inputs>

    <outputs>
           <data format="html" name="html_file" label="web_report" from_work_dir="slncky.EvolutionBrowser/browse.html"/>
           <data format="tabular" name="canonical_to_lncs" label="canonical_to_lncs" from_work_dir="slncky.canonical_to_lncs.txt"/>
           <data format="tabular" name="cluster_info" label="cluster_info" from_work_dir="slncky.cluster_info.txt"/>
           <data format="tabular" name="filtered_info" label="filtered_info" from_work_dir="slncky.filtered_info.txt"/>
           <data format="bed" name="lncs" label="lncs" from_work_dir="slncky.lncs.bed"/>
           <data format="tabular" name="lncs_info" label="lncs.info" from_work_dir="slncky.lncs.info.txt"/>
           <data format="tabular" name="orfs" label="orfs" from_work_dir="slncky.orfs.txt"/>
           <data format="tabular" name="orthologs_top" label="orthologs.top" from_work_dir="slncky.orthologs.top.txt"/>
           <data format="tabular" name="orthologs" label="orthologs" from_work_dir="slncky.orthologs.txt"/>
    </outputs>

    <stdio>
          <exit_code range="1:" level="fatal" description="Error in SLNCky" />
    </stdio>

    <tests>
        <test>
            <param name="bedfile" value="reads.simPE.StringTie.transcripts.bed" />
            <param name="assembly" value="hg19" />
            <param name="min_overlap" value="0.0" />
            <param name="min_cluster" value="2" />
            <param name="min_coding" value="0.1" />
            <param name="minMatch" value="0.1" />
            <param name="pad" value="0" />
            <param name="gap_open" value="200" />
            <param name="gap_extend" value="40" />

            <!-- <data format="html" name="html_file" label="web_report" from_work_dir="slncky.EvolutionBrowser/browse.html"/> -->
            <output name="html_file" file="slncky/reads.simPE.browse.html" />

            <!-- <data format="txt" name="canonical_to_lncs" label="canonical_to_lncs" from_work_dir="slncky.canonical_to_lncs.txt"/> -->
            <output name="canonical_to_lncs" file="slncky/reads.simPE.canonical_to_lncs.txt" />

            <!-- <data format="txt" name="cluster_info" label="cluster_info" from_work_dir="slncky.cluster_info.txt"/> -->
            <output name="cluster_info" file="slncky/reads.simPE.cluster_info.txt" />

            <!-- <data format="txt" name="filtered_info" label="filtered_info" from_work_dir="slncky.filtered_info.txt"/> -->
            <output name="filtered_info" file="slncky/reads.simPE.filtered_info.txt" />

            <!-- <data format="bed" name="lncs" label="lncs" from_work_dir="slncky.lncs.bed"/> -->
            <output name="lncs" file="slncky/reads.simPE.lncs.bed" />

            <!-- <data format="txt" name="lncs_info" label="lncs.info" from_work_dir="slncky.lncs.info.txt"/> -->
            <output name="lncs_info" file="slncky/reads.simPE.lncs.info.txt" />

            <!-- <data format="txt" name="orfs" label="orfs" from_work_dir="slncky.orfs.txt"/> -->
            <output name="orfs" file="slncky/reads.simPE.orfs.txt" />

            <!-- <data format="txt" name="orthologs_top" label="orthologs.top" from_work_dir="slncky.orthologs.top.txt"/> -->
            <output name="orthologs_top" file="slncky/reads.simPE.orthologs.top.txt" />

            <!-- <data format="txt" name="orthologs" label="orthologs" from_work_dir="slncky.orthologs.txt"/> -->
            <output name="orthologs" file="slncky/reads.simPE.orthologs.txt" />

        </test>
        <test>
            <param name="bedfile" value="mir-17-92.StringTie.transcripts.bed" />
            <param name="assembly" value="hg19" />
            <param name="min_overlap" value="0.0" />
            <param name="min_cluster" value="2" />
            <param name="min_coding" value="0.1" />
            <param name="minMatch" value="0.1" />
            <param name="pad" value="0" />
            <param name="gap_open" value="200" />
            <param name="gap_extend" value="40" />

            <!-- <data format="html" name="html_file" label="web_report" from_work_dir="slncky.EvolutionBrowser/browse.html"/> -->
            <output name="html_file" file="slncky/mir-17-92.browse.html" />

            <!-- <data format="txt" name="canonical_to_lncs" label="canonical_to_lncs" from_work_dir="slncky.canonical_to_lncs.txt"/> -->
            <output name="canonical_to_lncs" file="slncky/mir-17-92.canonical_to_lncs.txt.sorted" sort="true" />

            <!-- <data format="txt" name="cluster_info" label="cluster_info" from_work_dir="slncky.cluster_info.txt"/> -->
            <!-- This file isn't being created for some reason...
            <output name="cluster_info" >
                <assert_contents>
                    <has_line_matching expression=".+" />
                </assert_contents>
            </output>
            -->

            <!-- <data format="txt" name="filtered_info" label="filtered_info" from_work_dir="slncky.filtered_info.txt"/> -->
            <output name="filtered_info" file="slncky/mir-17-92.filtered_info.txt.sorted" sort="true" />

            <!-- <data format="bed" name="lncs" label="lncs" from_work_dir="slncky.lncs.bed"/> -->
            <output name="lncs" file="slncky/mir-17-92.lncs.bed" />

            <!-- <data format="txt" name="lncs_info" label="lncs.info" from_work_dir="slncky.lncs.info.txt"/> -->
            <output name="lncs_info" file="slncky/mir-17-92.lncs.info.txt" />

            <!-- <data format="txt" name="orfs" label="orfs" from_work_dir="slncky.orfs.txt"/> -->
            <output name="orfs" file="slncky/mir-17-92.orfs.txt" />

            <!-- <data format="txt" name="orthologs_top" label="orthologs.top" from_work_dir="slncky.orthologs.top.txt"/> -->
            <output name="orthologs_top" file="slncky/mir-17-92.orthologs.top.txt" />

            <!-- <data format="txt" name="orthologs" label="orthologs" from_work_dir="slncky.orthologs.txt"/> -->
            <output name="orthologs" file="slncky/mir-17-92.orthologs.txt" />
        </test>
    </tests>

    <help>
.. class:: infomark

slncky is a tool for lncRNA discovery from RNA-Seq data. slncky filters a high-quality set of noncoding transcripts, discovers lncRNA orthologs, and characterizes conserved lncRNA evolution.

To learn more about slncky visit their website_ .

.. _website: https://github.com/slncky/slncky

</help>

<citations>
        <citation type="doi">10.1186/s13059-016-0880-9</citation>
</citations>

</tool>