rbbt 1.1.0 → 1.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/README.rdoc +6 -6
- data/bin/rbbt_config +11 -11
- metadata +1 -1
data/README.rdoc
CHANGED
@@ -79,8 +79,8 @@ Install the gem normally <tt>gem install rbbt</tt>. The gem includes a configura
|
|
79
79
|
|
80
80
|
=== Using rbbt to translate identifiers
|
81
81
|
|
82
|
-
1. Do <tt>rbbt_config
|
83
|
-
3. Now you may do <tt>rbbt_config
|
82
|
+
1. Do <tt>rbbt_config prepare identifiers</tt> to do deploy the configuration files and download entrez data, this needs to be done just once.
|
83
|
+
3. Now you may do <tt>rbbt_config install organisms</tt> toprocess all the organisms, or <tt>rbbt_config install organisms -o sgd</tt> to process only yeast (sgd).
|
84
84
|
4. You may now use a script like this to translate gene identifiers from yeast feed from the standard input
|
85
85
|
require 'rbbt/sources/organism'
|
86
86
|
|
@@ -92,12 +92,12 @@ Install the gem normally <tt>gem install rbbt</tt>. The gem includes a configura
|
|
92
92
|
|
93
93
|
First prepare the organisms as you did in the previous section. Next, if you want to use the default NER module:
|
94
94
|
|
95
|
-
1. Install the Biocreative data used to train the model and compile the CRF++ plugin, <tt>rbbt_config
|
96
|
-
2. Build the module for a particular organism <tt>rbbt_config
|
95
|
+
1. Install the Biocreative data used to train the model and compile the CRF++ plugin, <tt>rbbt_config prepare rner</tt>. You may need at this point to install ParseTree and ruby2ruby
|
96
|
+
2. Build the module for a particular organism <tt>rbbt_config install ner -o sgd</tt>. You need to have the gems ParseTree and ruby2ruby for this to work. This process can take a long time.
|
97
97
|
|
98
98
|
Or, if you wan to use Abner or Banner:
|
99
99
|
|
100
|
-
1. Download and install the packages <tt>rbbt_config
|
100
|
+
1. Download and install the packages <tt>rbbt_config prepare java_ner</tt>
|
101
101
|
|
102
102
|
You may now, for example, find mentions to genes in articles from a PubMed query using this script
|
103
103
|
|
@@ -123,7 +123,7 @@ You may now, for example, find mentions to genes in articles from a PubMed query
|
|
123
123
|
|
124
124
|
This is the complete list of gem requirements: <tt>ParseTree ruby2ruby simpleconsole rjb rsruby stemmer rand rake progress-monitor</tt>. Some of these gems to not work with ruby 1.9 at the time, or may be a bit more complicated to install, for that reason *they are not reported as dependencies and are only required when they are about to be used*. Note that some of these gems are in the gemcutter repository, you may need to install the <tt>gemcutter</tt> gem and do <tt>gem tumble</tt>
|
125
125
|
|
126
|
-
Some of the API requires to have some data processed using rbbt_config. This command is used to install third party software, download data from the internet, or build models. The command <tt>rbbt_config
|
126
|
+
Some of the API requires to have some data processed using rbbt_config. This command is used to install third party software, download data from the internet, or build models. The command <tt>rbbt_config prepare all</tt> will install and process everything, this will take a long time, specially building the NER models. So you might want to start with the basic install and include more things as they are needed.
|
127
127
|
|
128
128
|
|
129
129
|
= Note on Patches/Pull Requests
|
data/bin/rbbt_config
CHANGED
@@ -15,13 +15,13 @@ end
|
|
15
15
|
TASKS= %w(organisms ner norm classifier biocreative entrez go wordlists polysearch abner banner crf++)
|
16
16
|
|
17
17
|
$USAGE =<<EOT
|
18
|
-
#{__FILE__} <action> [<subaction>] [--
|
18
|
+
#{__FILE__} <action> [<subaction>] [--update] [--organism <org>]
|
19
19
|
|
20
20
|
actions:
|
21
21
|
|
22
22
|
* configure: Set paths for data, cache, and tmp directories
|
23
23
|
|
24
|
-
*
|
24
|
+
* prepare:
|
25
25
|
|
26
26
|
Basic subactions:
|
27
27
|
|
@@ -50,12 +50,12 @@ $USAGE =<<EOT
|
|
50
50
|
* classifier: organisms, wordlists, classifier, go
|
51
51
|
* all: #{TASKS.join(", ")}
|
52
52
|
|
53
|
-
*
|
53
|
+
* install:
|
54
54
|
* organisms: Gather organisms data
|
55
55
|
* ner: Build Named Entity Recognition Models. Mention Normalization needs no training.
|
56
56
|
* classification: Build Function/Process Classifiers
|
57
57
|
|
58
|
-
--
|
58
|
+
--update: Rebuild models or reprocess organism data even if present. You may want to purge the cache
|
59
59
|
to be up to date with the data in the internet.
|
60
60
|
|
61
61
|
--organism: Gather data only for that particular organism. The organism must be specified by the
|
@@ -74,7 +74,7 @@ EOT
|
|
74
74
|
|
75
75
|
class Controller < SimpleConsole::Controller
|
76
76
|
|
77
|
-
params :bool => {:
|
77
|
+
params :bool => {:u => :update},
|
78
78
|
:string => {:o => :organism}
|
79
79
|
|
80
80
|
def organisms
|
@@ -89,7 +89,7 @@ class Controller < SimpleConsole::Controller
|
|
89
89
|
render :action => :usage
|
90
90
|
end
|
91
91
|
|
92
|
-
def
|
92
|
+
def install
|
93
93
|
raise "Run #{__FILE__} configure first to configure rbbt" if $noconfig
|
94
94
|
|
95
95
|
case params[:id]
|
@@ -103,12 +103,12 @@ class Controller < SimpleConsole::Controller
|
|
103
103
|
redirect_to :action => :help, :id => :update
|
104
104
|
end
|
105
105
|
|
106
|
-
$force = true if params[:
|
106
|
+
$force = true if params[:update]
|
107
107
|
$org = params[:organism] if params[:organism]
|
108
108
|
|
109
109
|
end
|
110
110
|
|
111
|
-
def
|
111
|
+
def prepare
|
112
112
|
raise "Run #{__FILE__} configure first to configure rbbt" if $noconfig
|
113
113
|
case params[:id]
|
114
114
|
when "identifiers"
|
@@ -146,7 +146,7 @@ class Controller < SimpleConsole::Controller
|
|
146
146
|
@tasks = [params[:id]]
|
147
147
|
end
|
148
148
|
|
149
|
-
$force = true if params[:
|
149
|
+
$force = true if params[:update]
|
150
150
|
$org = params[:organism] if params[:organism]
|
151
151
|
|
152
152
|
end
|
@@ -175,7 +175,7 @@ class View < SimpleConsole::View
|
|
175
175
|
end
|
176
176
|
|
177
177
|
|
178
|
-
def
|
178
|
+
def prepare
|
179
179
|
load File.join(Rbbt.rootdir, 'tasks/install.rake')
|
180
180
|
|
181
181
|
@tasks.each{|t|
|
@@ -184,7 +184,7 @@ class View < SimpleConsole::View
|
|
184
184
|
}
|
185
185
|
end
|
186
186
|
|
187
|
-
def
|
187
|
+
def install
|
188
188
|
|
189
189
|
puts "Changing directory to #{@location}"
|
190
190
|
chdir @location
|