annotate ideas.xml @ 142:8cfcf32c4282 draft

Uploaded
author greg
date Wed, 20 Dec 2017 13:01:02 -0500
parents a976dd6fcd1b
children a80b76535243
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
d75cbb2db2c4 Uploaded
greg
parents: 0
diff changeset
1 <tool id="ideas" name="IDEAS" version="1.2.0">
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
2 <description>accounts for position dependent epigenetic events and detects local cell type relationships</description>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
3 <requirements>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
4 <requirement type="package" version="2.26.0">bedtools</requirement>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
5 <requirement type="package" version="332">ucsc-bedgraphtobigwig</requirement>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
6 <requirement type="package" version="332">ucsc-bedsort</requirement>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
7 <requirement type="package" version="332">ucsc-bigwigaverageoverbed</requirement>
100
86445eab5f51 Uploaded
greg
parents: 99
diff changeset
8 <requirement type="package" version="1.20">ideas</requirement>
106
a0e38f759ad5 Uploaded
greg
parents: 104
diff changeset
9 <requirement type="package" version="1.4.4">r-optparse</requirement>
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
10 </requirements>
30
1d854705de39 Uploaded
greg
parents: 29
diff changeset
11 <command detect_errors="exit_code"><![CDATA[
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
12 #set output_pdf_dir = "output_pdf_dir"
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
13 #set output_txt_dir = "output_txt_dir"
66
dc5d5a08c370 Uploaded
greg
parents: 65
diff changeset
14 #set tmp_dir = "tmp"
72
6dece3e06a10 Uploaded
greg
parents: 71
diff changeset
15 #set prep_input_config = "prep_input_config.txt"
119
1d99221369b1 Uploaded
greg
parents: 117
diff changeset
16 #set prep_output_config = "prep_output_config.txt"
3
9874800487e6 Uploaded
greg
parents: 1
diff changeset
17 ##############################################
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
18 ## Create the config file and prepare the data
3
9874800487e6 Uploaded
greg
parents: 1
diff changeset
19 ##############################################
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
20 #set specify_genomic_window = $specify_genomic_window_cond.specify_genomic_window
132
8ce93420010c Uploaded
greg
parents: 131
diff changeset
21 #if str($output_heatmaps) == "yes":
8ce93420010c Uploaded
greg
parents: 131
diff changeset
22 mkdir '$output_pdf_dir' &&
8ce93420010c Uploaded
greg
parents: 131
diff changeset
23 #end if
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
24 mkdir '$output_txt_dir' &&
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
25 cp '$gen_prep_input_config' $prep_input_config &&
138
8a10282ce217 Uploaded
greg
parents: 134
diff changeset
26 sort $prep_input_config -o $prep_input_config &&
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
27 prepMat
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
28 $prep_input_config
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
29 #if str($specify_genomic_window) == "yes":
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
30 -bed '$specify_genomic_window_cond.bed_input'
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
31 #else:
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
32 -gsz '$chromInfo'
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
33 -wsz $specify_genomic_window_cond.window_size
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
34 #set restrict_chromosomes = $specify_genomic_window_cond.restrict_chromosomes_cond.restrict_chromosomes
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
35 #if str($restrict_chromosomes) == "yes":
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
36 #set chroms = []
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
37 #set chrom_repeat = $specify_genomic_window_cond.restrict_chromosomes_cond.chrom_repeat
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
38 #for $i in $chrom_repeat.chrom
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
39 $chroms.append($i)
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
40 #end for
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
41 -chr ",".join(chroms)
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
42 #end if
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
43 #end if
45
25f82826cfa1 Uploaded
greg
parents: 44
diff changeset
44 $bychr
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
45 -c $reads_per_bp
78
949de45a7269 Uploaded
greg
parents: 77
diff changeset
46 #if str($blacklist_input) not in ["None", ""]:
34
8d8f796a3bda Uploaded
greg
parents: 33
diff changeset
47 -exclude '$blacklist_input'
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
48 #end if
45
25f82826cfa1 Uploaded
greg
parents: 44
diff changeset
49 $norm
139
84c909b549a9 Uploaded
greg
parents: 138
diff changeset
50 &>prepmat_log.txt;
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
51 if [[ $? -ne 0 ]]; then
139
84c909b549a9 Uploaded
greg
parents: 138
diff changeset
52 cp prepmat_log.txt '$output_txt_dir';
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
53 exit 1;
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
54 fi
3
9874800487e6 Uploaded
greg
parents: 1
diff changeset
55 ##############################################
29
06522a4aae6d Uploaded
greg
parents: 28
diff changeset
56 ## Coerce the prepMat config output to the
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
57 ## format expected by IDEAS.
26
53891e4e4c63 Uploaded
greg
parents: 25
diff changeset
58 ##############################################
65
e29e083ebef7 Uploaded
greg
parents: 64
diff changeset
59 && cut -d' ' $prep_input_config -f1,2 > file1.txt
29
06522a4aae6d Uploaded
greg
parents: 28
diff changeset
60 && ls tmp/*.bed.gz > file2.txt
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
61 && paste <(cat file1.txt) <(cat file2.txt) -d' ' > $prep_output_config
125
5e545c9030a0 Uploaded
greg
parents: 123
diff changeset
62 #if str($specify_genomic_window) == "yes":
132
8ce93420010c Uploaded
greg
parents: 131
diff changeset
63 ##############################################
8ce93420010c Uploaded
greg
parents: 131
diff changeset
64 ## Using a genomic window bed file, so categorize
8ce93420010c Uploaded
greg
parents: 131
diff changeset
65 ## the window positions by chromosome to enable
8ce93420010c Uploaded
greg
parents: 131
diff changeset
66 ## the IDEAS -inv option.
8ce93420010c Uploaded
greg
parents: 131
diff changeset
67 ##############################################
129
d064db60a06d Uploaded
greg
parents: 128
diff changeset
68 #import collections
d064db60a06d Uploaded
greg
parents: 128
diff changeset
69 #set window_positions_by_chroms = collections.OrderedDict()
d064db60a06d Uploaded
greg
parents: 128
diff changeset
70 #for count, line in enumerate(open($specify_genomic_window_cond.bed_input.file_name, 'r')):
d064db60a06d Uploaded
greg
parents: 128
diff changeset
71 #set $line = $line.strip()
d064db60a06d Uploaded
greg
parents: 128
diff changeset
72 #if not $line or $line.startswith('#'):
d064db60a06d Uploaded
greg
parents: 128
diff changeset
73 #continue
d064db60a06d Uploaded
greg
parents: 128
diff changeset
74 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
75 #set items = $line.split('\t')
d064db60a06d Uploaded
greg
parents: 128
diff changeset
76 #if $items[0] in $window_positions_by_chroms:
d064db60a06d Uploaded
greg
parents: 128
diff changeset
77 #set tup = $window_positions_by_chroms[$items[0]]
d064db60a06d Uploaded
greg
parents: 128
diff changeset
78 #set $tup[1] += 1
d064db60a06d Uploaded
greg
parents: 128
diff changeset
79 #set $window_positions_by_chroms[$items[0]] = $tup
d064db60a06d Uploaded
greg
parents: 128
diff changeset
80 #else:
d064db60a06d Uploaded
greg
parents: 128
diff changeset
81 #set $window_positions_by_chroms[$items[0]] = [$count, $count+1]
d064db60a06d Uploaded
greg
parents: 128
diff changeset
82 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
83 #end for
d064db60a06d Uploaded
greg
parents: 128
diff changeset
84 #for chrom, tup in $window_positions_by_chroms.items():
128
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
85 && ideas
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
86 '$prep_output_config'
129
d064db60a06d Uploaded
greg
parents: 128
diff changeset
87 '$specify_genomic_window_cond.bed_input'
d064db60a06d Uploaded
greg
parents: 128
diff changeset
88 $hp
d064db60a06d Uploaded
greg
parents: 128
diff changeset
89 -inv $tup[0] $tup[1]
d064db60a06d Uploaded
greg
parents: 128
diff changeset
90 #if str($log2) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
91 -log2 $log2
d064db60a06d Uploaded
greg
parents: 128
diff changeset
92 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
93 #if str($max_states) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
94 -G $max_states
d064db60a06d Uploaded
greg
parents: 128
diff changeset
95 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
96 #if str($initial_states) != "0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
97 -C $initial_states
d064db60a06d Uploaded
greg
parents: 128
diff changeset
98 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
99 #if str($max_position_classes) != "0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
100 -P $max_position_classes
d064db60a06d Uploaded
greg
parents: 128
diff changeset
101 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
102 #if str($max_cell_type_clusters) != "0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
103 -K $max_cell_type_clusters
d064db60a06d Uploaded
greg
parents: 128
diff changeset
104 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
105 #if str($prior_concentration) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
106 -A $prior_concentration
d064db60a06d Uploaded
greg
parents: 128
diff changeset
107 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
108 -sample $burnin_num $mcmc_num
d064db60a06d Uploaded
greg
parents: 128
diff changeset
109 #if str($minerr) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
110 -minerr $minerr
d064db60a06d Uploaded
greg
parents: 128
diff changeset
111 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
112 #if str($maxerr) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
113 -maxerr $maxerr
d064db60a06d Uploaded
greg
parents: 128
diff changeset
114 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
115 -rseed $rseed
d064db60a06d Uploaded
greg
parents: 128
diff changeset
116 -thread \${GALAXY_SLOTS:-4}
d064db60a06d Uploaded
greg
parents: 128
diff changeset
117 -o '$project_name.$chrom'
d064db60a06d Uploaded
greg
parents: 128
diff changeset
118 #if str($save_ideas_log) == "yes":
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
119 &>>'$output_log';
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
120 if [[ $? -ne 0 ]]; then
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
121 exit 1;
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
122 fi
129
d064db60a06d Uploaded
greg
parents: 128
diff changeset
123 #else:
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
124 &>>ideas_log.txt;
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
125 if [[ $? -ne 0 ]]; then
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
126 cp ideas_log.txt '$output_txt_dir'
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
127 exit 1;
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
128 fi
129
d064db60a06d Uploaded
greg
parents: 128
diff changeset
129 #end if
128
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
130 #end for
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
131 #else:
132
8ce93420010c Uploaded
greg
parents: 131
diff changeset
132 ##############################################
8ce93420010c Uploaded
greg
parents: 131
diff changeset
133 ## Not using a genomic window bed file.
8ce93420010c Uploaded
greg
parents: 131
diff changeset
134 ##############################################
128
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
135 && ideas
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
136 '$prep_output_config'
129
d064db60a06d Uploaded
greg
parents: 128
diff changeset
137 $tmp_dir/*.bed
d064db60a06d Uploaded
greg
parents: 128
diff changeset
138 $hp
d064db60a06d Uploaded
greg
parents: 128
diff changeset
139 #if str($log2) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
140 -log2 $log2
d064db60a06d Uploaded
greg
parents: 128
diff changeset
141 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
142 #if str($max_states) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
143 -G $max_states
d064db60a06d Uploaded
greg
parents: 128
diff changeset
144 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
145 #if str($initial_states) != "0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
146 -C $initial_states
d064db60a06d Uploaded
greg
parents: 128
diff changeset
147 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
148 #if str($max_position_classes) != "0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
149 -P $max_position_classes
d064db60a06d Uploaded
greg
parents: 128
diff changeset
150 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
151 #if str($max_cell_type_clusters) != "0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
152 -K $max_cell_type_clusters
d064db60a06d Uploaded
greg
parents: 128
diff changeset
153 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
154 #if str($prior_concentration) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
155 -A $prior_concentration
d064db60a06d Uploaded
greg
parents: 128
diff changeset
156 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
157 -sample $burnin_num $mcmc_num
d064db60a06d Uploaded
greg
parents: 128
diff changeset
158 #if str($minerr) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
159 -minerr $minerr
d064db60a06d Uploaded
greg
parents: 128
diff changeset
160 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
161 #if str($maxerr) != "0.0":
d064db60a06d Uploaded
greg
parents: 128
diff changeset
162 -maxerr $maxerr
d064db60a06d Uploaded
greg
parents: 128
diff changeset
163 #end if
d064db60a06d Uploaded
greg
parents: 128
diff changeset
164 -rseed $rseed
d064db60a06d Uploaded
greg
parents: 128
diff changeset
165 -thread \${GALAXY_SLOTS:-4}
128
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
166 -o '$project_name'
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
167 #if str($save_ideas_log) == "yes":
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
168 &>'$output_log';
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
169 if [[ $? -ne 0 ]]; then
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
170 exit 1;
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
171 fi
128
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
172 #else:
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
173 &>ideas_log.txt;
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
174 if [[ $? -ne 0 ]]; then
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
175 cp ideas_log.txt '$output_txt_dir'
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
176 exit 1;
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
177 fi
128
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
178 #end if
125
5e545c9030a0 Uploaded
greg
parents: 123
diff changeset
179 #end if
129
d064db60a06d Uploaded
greg
parents: 128
diff changeset
180 && mv ./*.cluster '$output_txt_dir'
d064db60a06d Uploaded
greg
parents: 128
diff changeset
181 && mv ./*.para '$output_txt_dir'
d064db60a06d Uploaded
greg
parents: 128
diff changeset
182 && mv ./*.profile '$output_txt_dir'
d064db60a06d Uploaded
greg
parents: 128
diff changeset
183 && mv ./*.state '$output_txt_dir'
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
184 #if str($output_heatmaps) == "yes":
141
a976dd6fcd1b Uploaded
greg
parents: 139
diff changeset
185 && Rscript '$__tool_directory__/create_heatmaps.R'
142
8cfcf32c4282 Uploaded
greg
parents: 141
diff changeset
186 --input_dir '$output_txt_dir'
8cfcf32c4282 Uploaded
greg
parents: 141
diff changeset
187 --output_dir '$output_pdf_dir'
8cfcf32c4282 Uploaded
greg
parents: 141
diff changeset
188 --script_dir '$__tool_directory__'
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
189 #end if
128
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
190 ]]></command>
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
191 <configfiles>
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
192 <configfile name="gen_prep_input_config"><![CDATA[#if str($cell_type_epigenetic_factor_cond.cell_type_epigenetic_factor) == "extract":
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
193 #set input_name_positions = $cell_type_epigenetic_factor_cond.input_name_positions
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
194 #for $i in $cell_type_epigenetic_factor_cond.input:
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
195 #set file_name_with_ext = $i.name
130
d088f25661d9 Uploaded
greg
parents: 129
diff changeset
196 #if str($file_name_with_ext).find("http") >= 0 or str($file_name_with_ext).find("ftp") >= 0:
d088f25661d9 Uploaded
greg
parents: 129
diff changeset
197 #set file_name_with_ext = $file_name_with_ext.split('/')[-1]
d088f25661d9 Uploaded
greg
parents: 129
diff changeset
198 #end if
128
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
199 #assert str($file_name_with_ext).find("-") >= 0, "The selected input '%s' is invalid because it does not include the '-' character which is required when setting cell type and epigenetic factor names by extracting them from the input file names." % $file_name_with_ext
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
200 #set file_name = $file_name_with_ext.split(".")[0]
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
201 #if str($input_name_positions) == "cell_first":
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
202 #set cell_type_name = $file_name.split("-")[0]
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
203 #set epigenetic_factor_name = $file_name.split("-")[1]
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
204 #else:
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
205 #set cell_type_name = $file_name.split("-")[1]
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
206 #set epigenetic_factor_name = $file_name.split("-")[0]
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
207 #end if
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
208 ${cell_type_name} ${epigenetic_factor_name} ${i}
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
209 #end for
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
210 #else:
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
211 #for $input_items in $cell_type_epigenetic_factor_cond.input_repeat:
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
212 ${input_items.cell_type_name} ${input_items.epigenetic_factor_name} ${input_items.input}
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
213 #end for
de93d8e8a096 Uploaded
greg
parents: 126
diff changeset
214 #end if]]></configfile>
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
215 </configfiles>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
216 <inputs>
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
217 <conditional name="cell_type_epigenetic_factor_cond">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
218 <param name="cell_type_epigenetic_factor" type="select" label="Set cell type and epigenetic factor names by">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
219 <option value="extract" selected="true">extracting them from the selected input file names</option>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
220 <option value="manual">manually setting them for each selected input</option>
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
221 </param>
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
222 <when value="extract">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
223 <param name="input" type="data" format="bigwig,bam" multiple="True" label="BAM or BigWig files">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
224 <validator type="empty_field"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
225 <validator type="unspecified_build"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
226 </param>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
227 <param name="input_name_positions" type="select" display="radio" label="Selected input file name pattern is" help="A '-' character must separate cell type and epigenetic factor names within the selected input file names">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
228 <option value="cell_first" selected="true">Cell type name - Epigenetic factor name</option>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
229 <option value="cell_last">Epigenetic factor name - Cell type name</option>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
230 </param>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
231 </when>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
232 <when value="manual">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
233 <repeat name="input_repeat" title="Cell type, Epigenetic factor and Input" min="1">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
234 <param name="cell_type_name" type="text" value="" label="Cell type name">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
235 <validator type="empty_field"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
236 </param>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
237 <param name="epigenetic_factor_name" type="text" value="" label="Epigenetic factor name">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
238 <validator type="empty_field"/>
32
58f5b2af9473 Uploaded
greg
parents: 31
diff changeset
239 </param>
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
240 <param name="input" type="data" format="bigwig,bam" label="BAM or BigWig file">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
241 <validator type="empty_field"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
242 <validator type="unspecified_build"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
243 </param>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
244 </repeat>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
245 </when>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
246 </conditional>
113
ba7238a53377 Uploaded
greg
parents: 112
diff changeset
247 <param name="project_name" type="text" value="myProject" label="Project name" help="Outputs will have this base name">
112
5753c1386737 Uploaded
greg
parents: 111
diff changeset
248 <validator type="empty_field"/>
5753c1386737 Uploaded
greg
parents: 111
diff changeset
249 </param>
99
585557b96a9a Uploaded
greg
parents: 98
diff changeset
250 <param argument="-rseed" type="integer" value="1234" min="0" max="1000000" label="Seed for IDEAS model initialization" help="Zero value generates a random seed, and this seed will be different for each job run."/>
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
251 <conditional name="specify_genomic_window_cond">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
252 <param name="specify_genomic_window" type="select" label="Select Bed file that defines genomic windows on which to process the data">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
253 <option value="no" selected="true">No</option>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
254 <option value="yes">Yes</option>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
255 </param>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
256 <when value="no">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
257 <param name="window_size" type="integer" value="200" label="Window size in base pairs"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
258 <conditional name="restrict_chromosomes_cond">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
259 <param name="restrict_chromosomes" type="select" label="Restrict processing to specified chromosomes">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
260 <option value="no" selected="true">No</option>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
261 <option value="yes">Yes</option>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
262 </param>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
263 <when value="no"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
264 <when value="yes">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
265 <repeat name="chrom_repeat" title="Chromosomes" min="1">
98
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
266 <param name="chrom" type="text" value="" label="Chromosome" help="One chromosome (e.g., chr1, chr2, chrX) per text field"/>
68
5fb237a06499 Uploaded
greg
parents: 67
diff changeset
267 </repeat>
5fb237a06499 Uploaded
greg
parents: 67
diff changeset
268 </when>
5fb237a06499 Uploaded
greg
parents: 67
diff changeset
269 </conditional>
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
270 </when>
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
271 <when value="yes">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
272 <param name="bed_input" type="data" format="bed" label="Bed file specifying the genomic windows"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
273 </when>
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
274 </conditional>
45
25f82826cfa1 Uploaded
greg
parents: 44
diff changeset
275 <param argument="-bychr" type="boolean" truevalue="-bychr" falsevalue="" checked="False" label="Output chromosomes in separate files"/>
98
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
276 <param name="reads_per_bp" type="select" display="radio" label="Calculate the signal in each genomic window using">
36
859687afe7bc Uploaded
greg
parents: 35
diff changeset
277 <option value="6" selected="true">mean</option>
859687afe7bc Uploaded
greg
parents: 35
diff changeset
278 <option value="8">max</option>
859687afe7bc Uploaded
greg
parents: 35
diff changeset
279 </param>
33
695053a23fe4 Uploaded
greg
parents: 32
diff changeset
280 <param name="blacklist_input" type="data" format="bed" optional="True" multiple="True" label="Select file(s) containing regions to exclude"/>
45
25f82826cfa1 Uploaded
greg
parents: 44
diff changeset
281 <param argument="-norm" type="boolean" truevalue="-norm" falsevalue="" checked="False" label="Standardize all datasets"/>
44
8e449b51b581 Uploaded
greg
parents: 43
diff changeset
282 <param argument="-hp" type="boolean" truevalue="-hp" falsevalue="" checked="False" label="Discourage state transition across chromosomes"/>
101
ad45c3ba16b2 Uploaded
greg
parents: 100
diff changeset
283 <param name="log2" type="float" value="0" min="0" label="Use log2(x+number) transformation" help="Zero means no log2 transformation"/>
ad45c3ba16b2 Uploaded
greg
parents: 100
diff changeset
284 <param name="max_states" type="float" value="0" min="0" label="Maximum number of states to be inferred" help="Zero sets the maximum to a large number"/>
ad45c3ba16b2 Uploaded
greg
parents: 100
diff changeset
285 <param name="initial_states" type="integer" value="20" min="0" label="Initial number of states" help="Positive integer"/>
ad45c3ba16b2 Uploaded
greg
parents: 100
diff changeset
286 <param name="max_position_classes" type="integer" value="0" min="0" label="Maximum number of position classes to be inferred" help="Zero sets the maximum to a large number"/>
ad45c3ba16b2 Uploaded
greg
parents: 100
diff changeset
287 <param name="max_cell_type_clusters" type="integer" value="0" min="0" label="Maximum number of cell type clusters allowed" help="Zero sets the maximum to a large number"/>
ad45c3ba16b2 Uploaded
greg
parents: 100
diff changeset
288 <param name="prior_concentration" type="float" value="1" min="0" label="Prior concentration" help="Zero value results in the default: sqrt(number of cell types)"/>
34
8d8f796a3bda Uploaded
greg
parents: 33
diff changeset
289 <param name="burnin_num" type="integer" value="20" min="1" label="Number of burnin steps"/>
8d8f796a3bda Uploaded
greg
parents: 33
diff changeset
290 <param name="mcmc_num" type="integer" value="20" min="1" label="Number of maximization steps"/>
101
ad45c3ba16b2 Uploaded
greg
parents: 100
diff changeset
291 <param name="minerr" type="float" value="0.5" min="0" label="Minimum standard deviation for the emission Gaussian distribution" help="Zero value results in the default: 0.5"/>
ad45c3ba16b2 Uploaded
greg
parents: 100
diff changeset
292 <param name="maxerr" type="float" value="1000000" min="0" label="Maximum standard deviation for the emission Gaussian distribution" help="Zero sets the maximum to a large number"/>
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
293 <param name="output_heatmaps" type="select" display="radio" label="Output heatmaps?">
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
294 <option value="no" selected="true">No</option>
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
295 <option value="yes">Yes</option>
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
296 </param>
89
d6ab97fb8aca Uploaded
greg
parents: 88
diff changeset
297 <param name="save_ideas_log" type="select" display="radio" label="Save IDEAS log in an additional history item">
d6ab97fb8aca Uploaded
greg
parents: 88
diff changeset
298 <option value="no" selected="true">No</option>
d6ab97fb8aca Uploaded
greg
parents: 88
diff changeset
299 <option value="yes">Yes</option>
d6ab97fb8aca Uploaded
greg
parents: 88
diff changeset
300 </param>
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
301 </inputs>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
302 <outputs>
102
dad89ec8846f Uploaded
greg
parents: 101
diff changeset
303 <data name="output_log" format="txt" label="${tool.name} (output log) on ${on_string}">
89
d6ab97fb8aca Uploaded
greg
parents: 88
diff changeset
304 <filter>save_ideas_log == 'yes'</filter>
d6ab97fb8aca Uploaded
greg
parents: 88
diff changeset
305 </data>
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
306 <collection name="output_pdf_collection" type="list" label="${tool.name} (heatmaps) on ${on_string}">
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
307 <discover_datasets pattern="__name__" directory="output_pdf_dir" format="pdf"/>
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
308 <filter>output_heatmaps == 'yes'</filter>
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
309 </collection>
112
5753c1386737 Uploaded
greg
parents: 111
diff changeset
310 <collection name="output_txt_collection" type="list">
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
311 <discover_datasets pattern="__name__" directory="output_txt_dir" format="txt"/>
102
dad89ec8846f Uploaded
greg
parents: 101
diff changeset
312 </collection>
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
313 </outputs>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
314 <tests>
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
315 <test>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
316 <param name="cell_type_epigenetic_factor" value="extract"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
317 <param name="input" value="e001-h3k4me3.bigwig" ftype="bigwig" dbkey="hg19"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
318 <param name="input_name_positions" value="cell_first"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
319 <param name="specify_genomic_window" value="yes"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
320 <param name="bed_input" value="genomic_windows.bed" ftype="bed" dbkey="hg19"/>
115
242ff1426fb4 Uploaded
greg
parents: 113
diff changeset
321 <param name="project_name" value="IDEAS_out"/>
112
5753c1386737 Uploaded
greg
parents: 111
diff changeset
322 <output_collection name="output_txt_collection" type="list">
5753c1386737 Uploaded
greg
parents: 111
diff changeset
323 <element name="IDEAS_out.cluster" file="IDEAS_out.cluster" ftype="txt"/>
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
324 <element name="IDEAS_out.para" file="IDEAS_out.para" ftype="txt"/>
112
5753c1386737 Uploaded
greg
parents: 111
diff changeset
325 <element name="IDEAS_out.profile" file="IDEAS_out.profile" ftype="txt"/>
5753c1386737 Uploaded
greg
parents: 111
diff changeset
326 <element name="IDEAS_out.state" file="IDEAS_out.state" ftype="txt"/>
102
dad89ec8846f Uploaded
greg
parents: 101
diff changeset
327 </output_collection>
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
328 <output_collection name="output_pdf_collection" type="list">
123
e2995f2f127f Uploaded
greg
parents: 120
diff changeset
329 <element name="IDEAS_out.pdf" file="IDEAS_out.pdf" compare="contains"/>
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
330 </output_collection>
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
331 </test>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
332 <test>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
333 <param name="cell_type_epigenetic_factor" value="manual"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
334 <repeat name="input_repeat">
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
335 <param name="cell_type_name" value="e001" />
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
336 <param name="epigenetic_factor_name" value="h3k4me3"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
337 <param name="input" value="e001-h3k4me3.bigwig" ftype="bigwig" dbkey="hg19"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
338 </repeat>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
339 <param name="specify_genomic_window" value="yes"/>
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
340 <param name="bed_input" value="genomic_windows.bed" ftype="bed" dbkey="hg19"/>
115
242ff1426fb4 Uploaded
greg
parents: 113
diff changeset
341 <param name="project_name" value="IDEAS_out"/>
112
5753c1386737 Uploaded
greg
parents: 111
diff changeset
342 <output_collection name="output_txt_collection" type="list">
5753c1386737 Uploaded
greg
parents: 111
diff changeset
343 <element name="IDEAS_out.cluster" file="IDEAS_out.cluster" ftype="txt"/>
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
344 <element name="IDEAS_out.para" file="IDEAS_out.para" ftype="txt"/>
112
5753c1386737 Uploaded
greg
parents: 111
diff changeset
345 <element name="IDEAS_out.profile" file="IDEAS_out.profile" ftype="txt"/>
5753c1386737 Uploaded
greg
parents: 111
diff changeset
346 <element name="IDEAS_out.state" file="IDEAS_out.state" ftype="txt"/>
5753c1386737 Uploaded
greg
parents: 111
diff changeset
347 </output_collection>
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
348 <output_collection name="output_pdf_collection" type="list">
123
e2995f2f127f Uploaded
greg
parents: 120
diff changeset
349 <element name="IDEAS_out.pdf" file="IDEAS_out.pdf" compare="contains"/>
120
cfa683d96cae Uploaded
greg
parents: 119
diff changeset
350 </output_collection>
90
029e18c3c17b Uploaded
greg
parents: 89
diff changeset
351 </test>
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
352 </tests>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
353 <help>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
354 **What it does**
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
355
95
ff4d84a01fa7 Uploaded
greg
parents: 94
diff changeset
356 IDEAS (an **I**\ ntegrative and **D**\ iscriminative **E**\ pigenome **A**\ nnotation **S**\ ystem) identifies
ff4d84a01fa7 Uploaded
greg
parents: 94
diff changeset
357 de novo regulatory functions from epigenetic data in multiple cell types jointly. It is a full probabilistic
ff4d84a01fa7 Uploaded
greg
parents: 94
diff changeset
358 model defined on all data, and it combines signals across both the genome and cell types to boost power. The
ff4d84a01fa7 Uploaded
greg
parents: 94
diff changeset
359 underlying assumption of IDEAS is that, because all cell types share the same underlying DNA sequences,
ff4d84a01fa7 Uploaded
greg
parents: 94
diff changeset
360 **functions of each DNA segment should be correlated**. Also, cell type specific regulation is locus-dependent,
ff4d84a01fa7 Uploaded
greg
parents: 94
diff changeset
361 and thus IDEAS uses local epigenetic landscape to **identify de novo and local cell type clusters** without
ff4d84a01fa7 Uploaded
greg
parents: 94
diff changeset
362 assuming or requiring a known global cell type relationship.
94
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
363
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
364 IDEAS takes as input a list of epigenetic data sets (histones, chromatin accessibility, CpG methylation, TFs, etc)
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
365 or any other whole-genome data sets (e.g., scores). Currently the supported data formats include BigWig and BAM.
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
366 All data sets will first be mapped by IDEAS to a common genomic coordinate in a selected assembly (200bp windows
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
367 by default, or user-provided). The user can specify regions to be considered or removed from the analysis. The
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
368 input data may come from one cell type/condition/individual/time point (although it does not fully utilize the
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
369 advantage of IDEAS), or from multiple cell types/conditions/individuals/time points. The same set of epigenetic
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
370 features may not be present in all cell types, for which IDEAS will do imputation of the missing tracks if
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
371 specified.
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
372
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
373 .. image:: $PATH_TO_IMAGES/ideas.png
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
374
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
375 IDEAS predicts regulatory functions, denoted by epigenetic states, at each position in each cell type by
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
376 **combining information simultaneously learned from other cell types** at the same positions in cell types with
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
377 similar local epigenetic landscapes. Size of genomic intervals for determining the similarity are also learned.
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
378 All of the inferences are done through parallel infinite-state hidden Markov models (iHMM), which is a Bayesian
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
379 non-parametric technique to automatically determine the number of local cell type clusters and the number of
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
380 epigenetic states.
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
381
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
382 In addition to its improved power, IDEAS has two unique advantages:
7d9af0d824ad Uploaded
greg
parents: 93
diff changeset
383
96
90144b60033c Uploaded
greg
parents: 95
diff changeset
384 1) applies **linear time inference** with respect to the number of cell types, which allows it to study hundreds or more cell types jointly
90144b60033c Uploaded
greg
parents: 95
diff changeset
385 2) uses mini-batch training to **improve reproducibility** of the predicted epigenetic states, which is important because genome segmentation is not convex and hence cannot guarantee a global optimal solution.
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
386
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
387 -----
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
388
88
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
389 **Options**
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
390
88
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
391 * **Set cell type and epigenetic factor names by** - cell type and epigenetic factor names can be set manually or by extracting them from the names of the selected input datasets. The latter case requires all selected datasets to have names that contain a "-" character.
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
392
93
0c2cf49dfb58 Uploaded
greg
parents: 91
diff changeset
393 * **BAM or BigWig files** - select one or more Bam or Bigwig files from your history, making sure that the name of every selected input include a "-" character (e.g., e001-h3k4me3.bigwig).
98
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
394 * **Cell type, Epigenetic factor and Input** - manually select any number of inputs, setting the cell type and epigenetic factor name for each. The combination of "cell type name" and "epigenetic factor name" must be unique for each input. For example, if you have replicate data you may want to specify the cell name as "rep1", "rep2", etc and the factor name as "rep1", "rep2", etc.
130
d088f25661d9 Uploaded
greg
parents: 129
diff changeset
395
88
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
396 * **Cell type name** - cell type name
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
397 * **Epigenetic factor name** - epigenetic factor name
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
398 * **BAM or BigWig file** - BAM or BigWig file
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
399
108
021d1f60b0d3 Uploaded
greg
parents: 107
diff changeset
400 * **Project name** - datasets produced by IDEAS will have this base name.
98
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
401 * **Seed for IDEAS model initialization** - enter an integer to be used as the seed for the IDEAS model initialization. A zero value causes IDEAS to automatically generate a random seed, and this seed will be different for each job run.
88
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
402 * **Select Bed file that defines genomic windows on which to process the data** - if "No" is selected, IDEAS will run whole genome segmentation. If "Yes" is selected, IDEAS will segment genomes in the unit of the windows defined by the bed file. This file can be in BED3, BED4 or BED5 format, but only the first three columns (chr posst posed) will be used.
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
403
88
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
404 * **Window size in base pairs** - Window size in base pairs (if "No" is selected)
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
405 * **Restrict processing to specified chromosomes** - If "Yes" is selected, processing will be restricted to specified chromosomes
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
406
88
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
407 * **Chromosomes** - processing will be restricted to specified chromosomes (if "Yes" is selected)
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
408
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
409 * **Bed file specifying the genomic windows** - bed file specifying the genomic windows (if "Yes" is selected)
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
410
44
8e449b51b581 Uploaded
greg
parents: 43
diff changeset
411 * **Output chromosomes in separate files** - select "Yes" to produce separate files for each chromosome, allowing you to run IDEAS on different chromosomes separately.
98
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
412 * **Calculate the signal in each genomic window using** - use the bigWigAverageOverBed utility from the UCSC genome browser to calculate the signal (i.e., the number of reads per bp) in each genomic window.
33
695053a23fe4 Uploaded
greg
parents: 32
diff changeset
413 * **Select file(s) containing regions to exclude** - select one or more bed files that contains regions you'd like excluded from your datasets.
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
414 * **Standardize all datasets** - select "Yes" to standardize all datasets (e.g., reads / total_reads * 20 million) so that the signals from different cell types become comparable - your datasets can be read counts, logp-values or fold change.
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
415
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
416 * **Discourage state transition across chromosomes** - select "Yes" to produce similar states in adjacent windows, making the annotation smoother, but at risk of reducing precision.
98
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
417 * **Use log2(x+number) transformation** - perform Log2-transformation of the input data by log2(x+number) (recommended for read count data to reduce skewness). You can enter a number that is representative of the noise level in your data (e.g., a number less than 1). If this number is at a similar scale or larger than the signal in your data, it will lose power. For example, if your input data is mean read count per window, using 0.1 may produce better results.
33
695053a23fe4 Uploaded
greg
parents: 32
diff changeset
418 * **Maximum number of states to be inferred** - restrict the maximum number of states to be generated by IDEAS; the final number of inferred states may be smaller than the number you specified
695053a23fe4 Uploaded
greg
parents: 32
diff changeset
419 * **Initial number of states** - while IDEAS may infer 30 states or more by starting from just 20 states, it may not do so if it is trapped in a local mode. We recommend setting the initial number of states slightly larger than the number of states you expect.
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
420 * **Maximum number of position classes to be inferred** - Set this value only if:
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
421
88
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
422 * you do not want position classes (e.g., for testing purposes), in this case set the value to 1
462ce06410c6 Uploaded
greg
parents: 87
diff changeset
423 * IDEAS runs slow because there are too many position classes, generally less than 100 position classes will run fine
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
424
98
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
425 * **Maximum number of cell type clusters allowed** - If you set the value to 1, then all cell types will be clustered in one group, which may be desirable if all cell types are homogeneous and you want IDEAS to use information in all cell types equally.
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
426 * **Prior concentration** - specify the prior concentration parameter; default is A=sqrt(number of cell types). A smaller concentration parameter (e.g., 1 or less) will emphasize more on position specificity and a larger concentration parameter (e.g., 10 * number of cell types) will emphasize more on global homogeneity.
98
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
427 * **Number of burnin steps** - specify the number of burnin steps; default is 20. Increasing the burnin and maximization steps will increase computing and only slightly increase accuracy, while decreasing them will reduce computing resources but may also reduce accuracy. We recommend to run IDEAS with at least 20 burnins and 20 maximizations. IDEAS will not stop even if it reaches a maximum mode.
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
428 * **Number of maximization steps** - specify the number of maximization steps; default is 20.
ed15c6ca3c51 Uploaded
greg
parents: 96
diff changeset
429 * **Minimum standard deviation for the emission Gaussian distribution** - This number multiplied by the overall standard deviation of your data will be used as a lower bound for the standard deviation for each factor in each epigenetic state (the default is 0.5). This number is useful for removing very subtle clusters in the data. Setting this value near 0 will allow IDEAS to discover many subtle states, while setting it greater than 1 will result in IDEAS losing the ability to detect meaningful states.
130
d088f25661d9 Uploaded
greg
parents: 129
diff changeset
430 * **Maximim standard deviation for the emission Gaussian distribution** - if you want to find fine-grained states you may use this option (if not used, IDEAS uses infinity), but it is rearely used unless you need more states to be inferred.
0
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
431
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
432 </help>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
433 <citations>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
434 <citation type="doi">10.1093/nar/gkw278</citation>
3b27bfc37b83 Uploaded
greg
parents:
diff changeset
435 </citations>
131
5150fcdcd0fa Uploaded
greg
parents: 130
diff changeset
436 </tool>