changeset 14:436da36c6114 draft

Uploaded
author ieguinoa
date Tue, 22 Sep 2020 20:36:41 +0000
parents 91a3a617d94b
children d85e35a36715
files ena_upload.xml extract_tables.py tool-data/geographic_location_1.loc.sample tool-data/host_health_state_1.loc.sample tool-data/host_sex_1.loc.sample
diffstat 5 files changed, 308 insertions(+), 10 deletions(-) [+]
line wrap: on
line diff
--- a/ena_upload.xml	Fri Sep 18 14:29:47 2020 +0000
+++ b/ena_upload.xml	Tue Sep 22 20:36:41 2020 +0000
@@ -1,6 +1,6 @@
 <tool id="ena_upload" name="ENA Upload tool" version="0.1.0" python_template_version="3.5">
   <macros>
-    <token name="@VERSION@">0.1.7</token>
+    <token name="@VERSION@">0.1.8</token>
   </macros>    
   <requirements>
     <requirement type="package" version="@VERSION@">ena-upload-cli</requirement>
@@ -69,6 +69,9 @@
     --study $action_options.input_format_conditional.studies_users_table
     --run $action_options.input_format_conditional.runs_users_table
     --sample $action_options.input_format_conditional.samples_users_table
+    #if $action_options.input_format_conditional.viral_submission == "true":
+        --vir
+    #end if
 #else:
     --experiment $experiments_table_path
     --study $studies_table_path
@@ -101,7 +104,7 @@
             #end for
             $runs.append($run_files) 
         #end for
-        $experiments.append({'title':str($experiment.experiment_title),'experiment_design':str($experiment.experiment_design),'library_strategy':str($experiment.library_strategy),'library_source':str($experiment.library_source),'library_selection':str($experiment.library_selection),'library_layout':str($experiment.library_layout),'insert_size':str($experiment.insert_size),'library_construction_protocol':str($experiment.library_construction_protocol),'platform':str($experiment.platform),'instrument_model':str($experiment.instrument_model),'runs':$runs})
+        $experiments.append({'title':str($experiment.experiment_title),'experiment_design':str($experiment.experiment_design),'library_strategy':str($experiment.library_strategy),'library_source':str($experiment.library_source),'library_selection':str($experiment.library_strategy),'library_layout':str($experiment.library_layout),'insert_size':str($experiment.insert_size),'library_construction_protocol':str($experiment.library_construction_protocol),'platform':str($experiment.platform),'instrument_model':str($experiment.instrument_model),'runs':$runs})
       #end for
       $samples.append({'title':str($sample.sample_title),'description':str($sample.sample_description),'tax_name':str($sample.scientific_name),'tax_id':str($sample.tax_id),'experiments':$experiments})
     #end for
@@ -125,6 +128,7 @@
                         <option value="build_tables" selected="False">Interactive generation of studies structure from dataset</option>
                     </param>    
                     <when value="user_generated_tables">
+                        <param name="viral_submission" type="boolean" label="Does your submission data belong to a viral sample?" help="If you select yes then your data will be submitted using the ENA virus pathogen reporting standard checklist (see: https://ena-browser-docs.readthedocs.io/en/latest/help_and_guides/sars-cov-2-submissions.html)" />
                         <param name="data" type="data" format="fastqsanger.gz,fastqsanger.bz2,fastq.gz,fastq.bz2" multiple="true" label="Select all datasets to upload" help="Compressed reads files listed in the runs table"/>
                         <param name="studies_users_table" type="data" format="tabular" multiple="false" label="Studies table" help="Studies metadata file"/>
                         <param name="samples_users_table" type="data" format="tabular" multiple="false" label="Samples table" help="Samples metadata file"/>
@@ -137,7 +141,7 @@
                             <param name="study_title" type="text" optional="False" label="Please provide a short descriptive title for the study"/>
                             <param name="study_abstract" type="text" optional="True" label="Please provide an abstract to describe the study in detail"/>
                             <param name="study_type" type="select" label="Please select the type of study">
-                                    <options from_data_table="study_type">
+                                    <options from_file="study_type.txt">
                                         <column name="value" index="0"/>
                                     </options>
                             </param>
@@ -151,22 +155,22 @@
                                     <param name="experiment_title" type="text" label="Specify an experiment title" />
                                     <param name="experiment_design" type="text" label="Describe the experiment design" />
                                     <param name="library_strategy" type="select" label="Library strategy" help="The library strategy specifies the sequencing technique intended for this library">
-                                        <options from_data_table="library_strategy">
+                                        <options from_file="library_strategy.txt">
                                             <column name="value" index="0"/>
                                         </options>
                                     </param>
                                     <param name="library_source" type="select" label="Select library source" help="The library source specifies the type of source material that is being sequenced">
-                                        <options from_data_table="library_source">
+                                        <options from_file="library_source.txt">
                                             <column name="value" index="0"/>
                                         </options>
                                     </param>
                                     <param name="library_selection" type="select" label="Library selection" help="The library selection specifies whether any method was used to select for or against, enrich, or screen the material being sequenced">
-                                        <options from_data_table="library_selection">
+                                        <options from_file="library_selection.txt">
                                             <column name="value" index="0"/>
                                         </options>
                                     </param>
                                     <param name="library_layout" type="select" label="Library layout">
-                                        <options from_data_table="library_layout">
+                                        <options from_file="library_layout.txt">
                                             <column name="value" index="0"/>
                                         </options>
                                     </param>
@@ -185,7 +189,7 @@
                                         <option value="CAPILLARY">Capillary sequencing</option>
                                     </param>
                                     <param name="instrument_model" type="select" label="Instrument model">
-                                        <options from_data_table="instrument_model">
+                                        <options from_file="instrument_model.txt">
                                             <column name="value" index="0"/>
                                         </options>
                                     </param>
--- a/extract_tables.py	Fri Sep 18 14:29:47 2020 +0000
+++ b/extract_tables.py	Tue Sep 22 20:36:41 2020 +0000
@@ -34,14 +34,14 @@
         for exp_index,exp in enumerate(sample['experiments']):
             exp_alias = 'experiment_'+str(exp_index)+'_'+str(sample_index)
             lib_alias = 'library_'+str(exp_index)+'_'+str(sample_index)
-            experiments_table.write('\t'.join([exp_alias,action,'accession_ena',exp['title'],study_alias,sample_alias,exp['experiment_design'],lib_alias,exp['library_strategy'],exp['library_source'],exp['library_selection'],exp['library_layout'].lower(),exp['insert_size'],exp['library_construction_protocol'],exp['platform'],exp['instrument_model'],'submission_date_ENA']) + '\n')
+            experiments_table.write('\t'.join([exp_alias,action,'accession_ena',exp['title'],study_alias,sample_alias,exp['experiment_design'],lib_alias,exp['library_strategy'],exp['library_source'],exp['library_selection'],exp['library_layout'],exp['insert_size'],exp['library_construction_protocol'],exp['platform'],exp['instrument_model'],'submission_date_ENA']) + '\n')
             run_index = 0
             # exp['runs'] is a list of lists
             for run in exp['runs']:
                 run_index += 1
                 run_alias = '_'.join(['run',str(exp_index),str(sample_index),str(run_index)])
                 for file_entry in run:
-                    file_format = 'fastq'
+                    file_format = 'fastq.gz' if os.path.splitext(file_entry)[-1] == '.gz' else 'fastq.bz2'
                     runs_table.write('\t'.join([run_alias,action,'ena_run_accession',exp_alias,file_entry,file_format,'file_checksum','submission_date_ENA']) + '\n')
 
 studies_table.close()
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/geographic_location_1.loc.sample	Tue Sep 22 20:36:41 2020 +0000
@@ -0,0 +1,279 @@
+not applicable
+not collected
+not provided
+restricted access
+Afghanistan
+Albania
+Algeria
+American Samoa
+Andorra
+Angola
+Anguilla
+Antarctica
+Antigua and Barbuda
+Arctic Ocean
+Argentina
+Armenia
+Aruba
+Ashmore and Cartier Islands
+Atlantic Ocean
+Australia
+Austria
+Azerbaijan
+Bahamas
+Bahrain
+Baker Island
+Baltic Sea
+Bangladesh
+Barbados
+Bassas da India
+Belarus
+Belgium
+Belize
+Benin
+Bermuda
+Bhutan
+Bolivia
+Borneo
+Bosnia and Herzegovina
+Botswana
+Bouvet Island
+Brazil
+British Virgin Islands
+Brunei
+Bulgaria
+Burkina Faso
+Burundi
+Cambodia
+Cameroon
+Canada
+Cape Verde
+Cayman Islands
+Central African Republic
+Chad
+Chile
+China
+Christmas Island
+Clipperton Island
+Cocos Islands
+Colombia
+Comoros
+Cook Islands
+Coral Sea Islands
+Costa Rica
+Cote d'Ivoire
+Croatia
+Cuba
+Curacao
+Cyprus
+Czech Republic
+Democratic Republic of the Congo
+Denmark
+Djibouti
+Dominica
+Dominican Republic
+East Timor
+Ecuador
+Egypt
+El Salvador
+Equatorial Guinea
+Eritrea
+Estonia
+Ethiopia
+Europa Island
+Falkland Islands (Islas Malvinas)
+Faroe Islands
+Fiji
+Finland
+France
+French Guiana
+French Polynesia
+French Southern and Antarctic Lands
+Gabon
+Gambia
+Gaza Strip
+Georgia
+Germany
+Ghana
+Gibraltar
+Glorioso Islands
+Greece
+Greenland
+Grenada
+Guadeloupe
+Guam
+Guatemala
+Guernsey
+Guinea
+Guinea-Bissau
+Guyana
+Haiti
+Heard Island and McDonald Islands
+Honduras
+Hong Kong
+Howland Island
+Hungary
+Iceland
+India
+Indian Ocean
+Indonesia
+Iran
+Iraq
+Ireland
+Isle of Man
+Israel
+Italy
+Jamaica
+Jan Mayen
+Japan
+Jarvis Island
+Jersey
+Johnston Atoll
+Jordan
+Juan de Nova Island
+Kazakhstan
+Kenya
+Kerguelen Archipelago
+Kingman Reef
+Kiribati
+Kosovo
+Kuwait
+Kyrgyzstan
+Laos
+Latvia
+Lebanon
+Lesotho
+Liberia
+Libya
+Liechtenstein
+Lithuania
+Luxembourg
+Macau
+Macedonia
+Madagascar
+Malawi
+Malaysia
+Maldives
+Mali
+Malta
+Marshall Islands
+Martinique
+Mauritania
+Mauritius
+Mayotte
+Mediterranean Sea
+Mexico
+Micronesia
+Midway Islands
+Moldova
+Monaco
+Mongolia
+Montenegro
+Montserrat
+Morocco
+Mozambique
+Myanmar
+Namibia
+Nauru
+Navassa Island
+Nepal
+Netherlands
+New Caledonia
+New Zealand
+Nicaragua
+Niger
+Nigeria
+Niue
+Norfolk Island
+North Korea
+North Sea
+Northern Mariana Islands
+Norway
+Oman
+Pacific Ocean
+Pakistan
+Palau
+Palmyra Atoll
+Panama
+Papua New Guinea
+Paracel Islands
+Paraguay
+Peru
+Philippines
+Pitcairn Islands
+Poland
+Portugal
+Puerto Rico
+Qatar
+Republic of the Congo
+Reunion
+Romania
+Ross Sea
+Russia
+Rwanda
+Saint Helena
+Saint Kitts and Nevis
+Saint Lucia
+Saint Pierre and Miquelon
+Saint Vincent and the Grenadines
+Samoa
+San Marino
+Sao Tome and Principe
+Saudi Arabia
+Senegal
+Serbia
+Seychelles
+Sierra Leone
+Singapore
+Sint Maarten
+Slovakia
+Slovenia
+Solomon Islands
+Somalia
+South Africa
+South Georgia and the South Sandwich Islands
+South Korea
+Southern Ocean
+Spain
+Spratly Islands
+Sri Lanka
+Sudan
+Suriname
+Svalbard
+Swaziland
+Sweden
+Switzerland
+Syria
+Taiwan
+Tajikistan
+Tanzania
+Tasman Sea
+Thailand
+Togo
+Tokelau
+Tonga
+Trinidad and Tobago
+Tromelin Island
+Tunisia
+Turkey
+Turkmenistan
+Turks and Caicos Islands
+Tuvalu
+USA
+Uganda
+Ukraine
+United Arab Emirates
+United Kingdom
+Uruguay
+Uzbekistan
+Vanuatu
+Venezuela
+Viet Nam
+Virgin Islands
+Wake Island
+Wallis and Futuna
+West Bank
+Western Sahara
+Yemen
+Zambia
+Zimbabwe
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/host_health_state_1.loc.sample	Tue Sep 22 20:36:41 2020 +0000
@@ -0,0 +1,6 @@
+not applicable
+diseased
+healthy
+not provided
+not collected
+restricted access
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/host_sex_1.loc.sample	Tue Sep 22 20:36:41 2020 +0000
@@ -0,0 +1,9 @@
+other
+not applicable
+not provided
+neuter
+not collected
+female
+restricted access
+male
+hermaphrodite