Plugin qiita-pet

qiita_db/support_files/populate_test_db.sql

@@ -488,7 +488,7 @@ INSERT INTO qiita.message_user (message_id, email) VALUES (1, 'test@foo.bar'),(1
 
 -- Create a loggin entry
 INSERT INTO qiita.logging (time, severity_id, msg, information)
-    VALUES ('Sun Nov 22 21:29:30 2015', 2, 'Error message', NULL);
+    VALUES ('Sun Nov 22 21:29:30 2015', 2, 'Error message', '{}');
 
 -- Create some processing jobs
 INSERT INTO qiita.processing_job

qiita_db/test/test_util.py

@@ -688,5 +688,11 @@ def test_infer_status(self):
         obs = qdb.util.infer_status([['sandbox'], ['sandbox']])
         self.assertEqual(obs, 'sandbox')
 
+    def test_get_pubmed_ids_from_dois(self):
+        exp = {'10.100/123456': '123456'}
+        obs = qdb.util.get_pubmed_ids_from_dois(['', '10.100/123456'])
+        self.assertEqual(obs, exp)
+
+
 if __name__ == '__main__':
     main()

qiita_db/util.py

@@ -30,6 +30,7 @@
     move_filepaths_to_upload_folder
     move_upload_files_to_trash
     add_message
+    get_pubmed_ids_from_dois
 """
 # -----------------------------------------------------------------------------
 # Copyright (c) 2014--, The Qiita Development Team.
@@ -1057,6 +1058,30 @@ def get_timeseries_types():
         return qdb.sql_connection.TRN.execute_fetchindex()
 
 
+def get_pubmed_ids_from_dois(doi_ids):
+    """Get the dict of pubmed ids from a list of doi ids
+
+    Parameters
+    ----------
+    doi_ids : list of str
+        The list of doi ids
+
+    Returns
+    -------
+    dict of {doi: pubmed_id}
+        Return dict of doi and pubmed ids
+
+    Notes
+    -----
+    If doi doesn't exist it will not return that {key: value} pair
+    """
+    with qdb.sql_connection.TRN:
+        sql = "SELECT doi, pubmed_id FROM qiita.publication WHERE doi IN %s"
+        qdb.sql_connection.TRN.add(sql, [tuple(doi_ids)])
+        return {row[0]: row [1]
+                for row in qdb.sql_connection.TRN.execute_fetchindex()}
+
+
 def check_access_to_analysis_result(user_id, requested_path):
     """Get filepath IDs for a particular requested_path, if user has access
 

qiita_pet/handlers/analysis_handlers.py

@@ -27,6 +27,7 @@
 from qiita_pet.exceptions import QiitaPetAuthorizationError
 from qiita_ware.dispatchable import run_analysis
 from qiita_db.analysis import Analysis
+from qiita_db.artifact import Artifact
 from qiita_db.job import Job, Command
 from qiita_db.util import (get_db_files_base_dir,
                            check_access_to_analysis_result,
@@ -163,7 +164,7 @@ def get(self, analysis_id):
         for proc_data_id, samples in viewitems(dropped_samples):
             if not samples:
                 continue
-            proc_data = ProcessedData(proc_data_id)
+            proc_data = Artifact(proc_data_id)
             data_type = proc_data.data_type()
             study = proc_data.study
             dropped[data_type].append((Study(study).title, len(samples),
@@ -214,8 +215,7 @@ def get(self):
         level = self.get_argument('level', '')
         user = self.current_user
 
-        analyses = [Analysis(a) for a in
-                    user.shared_analyses | user.private_analyses]
+        analyses = user.shared_analyses | user.private_analyses
 
         is_local_request = is_localhost(self.request.headers['host'])
         gfi = partial(get_filepath_id, 'analysis')
@@ -307,13 +307,21 @@ def get(self):
         # Format sel_data to get study IDs for the processed data
         sel_data = defaultdict(dict)
         proc_data_info = {}
-        sel_samps = Analysis(self.current_user.default_analysis).samples
+        sel_samps = self.current_user.default_analysis.samples
         for pid, samps in viewitems(sel_samps):
-            proc_data = ProcessedData(pid)
+            proc_data = Artifact(pid)
             sel_data[proc_data.study][pid] = samps
             # Also get processed data info
-            proc_data_info[pid] = proc_data.processing_info
-            proc_data_info[pid]['data_type'] = proc_data.data_type()
+            # TODO plugin:
+            # proc_data_info[pid] = proc_data.processing_info
+            proc_data_info[pid] = {'processed_date': '10/10/1981',
+                                   'algorithm': 'My algorithm',
+                                   'reference_name': 'My reference name',
+                                   'reference_version': 'My reference version',
+                                   'sequence_filepath': 'My sequence filepath',
+                                   'taxonomy_filepath': 'My taxonomy filepath',
+                                   'tree_filepath': 'My taxonomy filepath'}
+            proc_data_info[pid]['data_type'] = proc_data.data_type
         self.render("analysis_selected.html", sel_data=sel_data,
                     proc_info=proc_data_info)
 
@@ -322,5 +330,5 @@ class AnalysisSummaryAJAX(BaseHandler):
     @authenticated
     @execute_as_transaction
     def get(self):
-        info = Analysis(self.current_user.default_analysis).summary_data()
+        info = self.current_user.default_analysis.summary_data()
         self.write(dumps(info))

qiita_pet/handlers/preprocessing_handlers.py

@@ -13,7 +13,7 @@ class PreprocessHandler(BaseHandler):
     def post(self):
         study_id = int(self.get_argument('study_id'))
         prep_template_id = int(self.get_argument('prep_template_id'))
-        raw_data = RawData(PrepTemplate(prep_template_id).raw_data)
+        raw_data = PrepTemplate(prep_template_id).artifacts
         param_id = int(self.get_argument('preprocessing_parameters_id'))
 
         # Get the preprocessing parameters

qiita_pet/handlers/study_handlers/listing_handlers.py

@@ -14,24 +14,25 @@
 from tornado.gen import coroutine, Task
 from pyparsing import ParseException
 
+from qiita_db.artifact import Artifact
 from qiita_db.user import User
 from qiita_db.study import Study, StudyPerson
 from qiita_db.search import QiitaStudySearch
 from qiita_db.metadata_template.sample_template import SampleTemplate
 from qiita_db.logger import LogEntry
 from qiita_db.exceptions import QiitaDBIncompatibleDatatypeError
-from qiita_db.util import get_table_cols
+from qiita_db.util import get_table_cols, get_pubmed_ids_from_dois
 from qiita_core.exceptions import IncompetentQiitaDeveloperError
 from qiita_core.util import execute_as_transaction
 from qiita_pet.handlers.base_handlers import BaseHandler
-from qiita_pet.handlers.util import study_person_linkifier, pubmed_linkifier
+from qiita_pet.handlers.util import (
+    study_person_linkifier, doi_linkifier, pubmed_linkifier)
 
 
 @execute_as_transaction
 def _get_shared_links_for_study(study):
     shared = []
     for person in study.shared_with:
-        person = User(person)
         name = person.info['name']
         email = person.email
         # Name is optional, so default to email if non existant
@@ -69,15 +70,23 @@ def _build_single_study_info(study, info, study_proc, proc_samples):
     """
     PI = StudyPerson(info['principal_investigator_id'])
     status = study.status
-    if info['pmid'] is not None:
-        info['pmid'] = ", ".join([pubmed_linkifier([p])
-                                  for p in info['pmid']])
+    if info['publication_doi'] is not None:
+        pmids = get_pubmed_ids_from_dois(info['publication_doi']).values()
+        info['pmid'] = ", ".join([pubmed_linkifier([p]) for p in pmids])
+        info['publication_doi'] = ", ".join([doi_linkifier([p])
+                                             for p in info['publication_doi']])
+
     else:
+        info['publication_doi'] = ""
         info['pmid'] = ""
     if info["number_samples_collected"] is None:
         info["number_samples_collected"] = 0
     info["shared"] = _get_shared_links_for_study(study)
-    info["num_raw_data"] = len(study.raw_data())
+    # raw data is any artifact that is not Demultiplexed or BIOM
+
+    info["num_raw_data"] = len([a for a in study.artifacts()
+                                if a.artifact_type not in ['Demultiplexed',
+                                                           'BIOM']])
     info["status"] = status
     info["study_id"] = study.id
     info["pi"] = study_person_linkifier((PI.email, PI.name))
@@ -112,11 +121,12 @@ def _build_single_proc_data_info(proc_data_id, data_type, samples):
     dict
         The information for the processed data, in the form {info: value, ...}
     """
-    proc_data = ProcessedData(proc_data_id)
-    proc_info = proc_data.processing_info
+    proc_data = Artifact(proc_data_id)
+    # TODO plugin:
+    # proc_info = proc_data.processing_info
+    proc_info = {'processed_date': '10/10/1981'}
     proc_info['pid'] = proc_data_id
     proc_info['data_type'] = data_type
-    proc_info['samples'] = sorted(samples)
     proc_info['processed_date'] = str(proc_info['processed_date'])
     return proc_info
 
@@ -166,30 +176,29 @@ def _build_study_info(user, study_proc=None, proc_samples=None):
         # No studies left so no need to continue
         return []
 
-    # get info for the studies
     cols = ['study_id', 'email', 'principal_investigator_id',
-            'pmid', 'study_title', 'metadata_complete',
+            'publication_doi', 'study_title', 'metadata_complete',
             'number_samples_collected', 'study_abstract']
-    study_info = Study.get_info(study_set, cols)
 
+    # get info for the studies
     infolist = []
-    for info in study_info:
-        # Convert DictCursor to proper dict
-        info = dict(info)
-        study = Study(info['study_id'])
+    for study in study_set:
         # Build the processed data info for the study if none passed
         if build_samples:
-            proc_data_list = study.processed_data()
+            proc_data_list = [ar for ar in study.artifacts()
+                              if ar.artifact_type == 'BIOM']
             proc_samples = {}
             study_proc = {study.id: defaultdict(list)}
-            for pid in proc_data_list:
-                proc_data = ProcessedData(pid)
-                study_proc[study.id][proc_data.data_type()].append(pid)
-                proc_samples[pid] = proc_data.samples
+            for proc_data in proc_data_list:
+                study_proc[study.id][proc_data.data_type].append(proc_data.id)
+                # there is only one prep template for each processed data
+                proc_samples[proc_data.id] = proc_data.prep_templates[0].keys()
 
+        info = dict(study.get_info(info_cols=cols)[0])
         study_info = _build_single_study_info(study, info, study_proc,
                                               proc_samples)
         infolist.append(study_info)
+
     return infolist
 
 

qiita_pet/handlers/util.py

@@ -61,3 +61,6 @@ def download_link_or_path(is_local_request, filepath, fp_id, label):
 pubmed_linkifier = partial(
     linkify, "<a target=\"_blank\" href=\"http://www.ncbi.nlm.nih.gov/"
     "pubmed/{0}\">{0}</a>")
+
+doi_linkifier = partial(
+    linkify, "<a target=\"_blank\" href=\"http://dx.doi.org/{0}\">{0}</a>")

qiita_pet/handlers/websocket_handlers.py

@@ -12,6 +12,7 @@
 from moi import r_client
 from qiita_pet.handlers.base_handlers import BaseHandler
 from qiita_db.analysis import Analysis
+from qiita_db.artifact import Artifact
 from qiita_core.util import execute_as_transaction
 
 
@@ -85,17 +86,19 @@ def on_message(self, msg):
         # When the websocket receives a message from the javascript client,
         # parse into JSON
         msginfo = loads(msg)
-        default = Analysis(self.current_user.default_analysis)
+        default = self.current_user.default_analysis
 
         if 'remove_sample' in msginfo:
             data = msginfo['remove_sample']
-            default.remove_samples([data['proc_data']], data['samples'])
+            artifacts = [Artifact(_id) for _id in data['proc_data']]
+            default.remove_samples(artifacts, data['samples'])
         elif 'remove_pd' in msginfo:
             data = msginfo['remove_pd']
-            default.remove_samples([data['proc_data']])
+            default.remove_samples([Artifact(data['proc_data'])])
         elif 'clear' in msginfo:
             data = msginfo['clear']
-            default.remove_samples(data['pids'])
+            artifacts = [Artifact(_id) for _id in data['pids']]
+            default.remove_samples(artifacts)
         self.write_message(msg)
 
 
@@ -113,7 +116,7 @@ def on_message(self, msg):
             {proc_data_id': [s1, s2, ...], ...]}
         """
         msginfo = loads(msg)
-        default = Analysis(self.current_user.default_analysis)
+        default = self.current_user.default_analysis
         default.add_samples(msginfo['sel'])
         # Count total number of unique samples selected and return
         self.write_message(dumps({

qiita_pet/templates/analysis_selected.html

@@ -69,7 +69,6 @@
 {% end %}
 
 {% block content %}
-{% from qiita_db.study import Study %}
 {% set static_info = {'data_type', 'processed_date', 'algorithm', 'reference_name', 'reference_version', 'sequence_filepath', 'taxonomy_filepath', 'tree_filepath'}%}
 &nbsp;<br/>
 <h1>Selected Samples</h1>
@@ -91,13 +90,12 @@ <h3><a href="/study/list/">Please select at least one sample to continue</a><h3>
 </div>
 {% end %}
 
-{% for sid, proc_datas in viewitems(sel_data) %}
-  {% set study = Study(sid) %}
-<div class="row" id="study{{sid}}">
+{% for study, proc_datas in viewitems(sel_data) %}
+<div class="row" id="study{{study.id}}">
   <div class="col-md-12" style="border:2px solid #a1a1a1; border-radius: 15px;">
-    <h2><a href="/study/description/{{sid}}">{{study.title}}</a></h2>
+    <h2><a href="/study/description/{{study.id}}">{{study.title}}</a></h2>
     <h4>Processed Data</h4>
-    <table class='table table-striped' id='study{{sid}}-table'>
+    <table class='table table-striped' id='study{{study.id}}-table'>
     <tr>
       <th class="col-sm-1">id</th><th class="col-sm-1">Datatype</th><th class="col-sm-2">Processed Date</th><th class="col-sm-2">Algorithm</th><th class="col-sm-2">Reference</th><th class="col-sm-1">Samples</th><th></th><th></th>
     </tr>
@@ -110,12 +108,12 @@ <h4>Processed Data</h4>
       <td>{{proc_info[pid]["reference_name"]}} {{proc_info[pid]["reference_version"]}}</td>
       <td><span id="proc{{pid}}-sample-count">{% raw len(samples) %}</span></td>
       <td><a href="#" onclick="$('#proc{{pid}}-samples').toggle(); return false;">Show/Hide samples</a></td>
-      <td><a href="#" onclick = 'remove_proc_data({{pid}}, {{sid}})'>Remove</a></td>
+      <td><a href="#" onclick = 'remove_proc_data({{pid}}, {{study.id}})'>Remove</a></td>
      </tr>
      <tr id="proc{{pid}}-samples" hidden><td colspan=7>
      <table class="table table-striped sample-table" id="proc{{pid}}-samples-table" style="width:50%">
     {% for samp in samples %}
-      <tr id="{{pid}}@{{samp}}"><td>{{samp}}</td><td><a href="#" onclick="remove_sample('{{sid}}', '{{pid}}', '{{samp}}')">Remove</a></td></tr>
+      <tr id="{{pid}}@{{samp}}"><td>{{samp}}</td><td><a href="#" onclick="remove_sample('{{study.id}}', '{{pid}}', '{{samp}}')">Remove</a></td></tr>
     {% end %}
     </table>
     </td></tr>
@@ -182,4 +180,4 @@ <h4 class="modal-title" id="myModalLabel">Create new analysis</h4>
         </div>
       </div>
     </div>
-{% end %}
+{% end %}

qiita_pet/templates/error_log.html

@@ -1,6 +1,5 @@
 {% extends sitebase.html %}
 {% block head %}
-{% from qiita_db.study import StudyPerson %}
 {% from future.utils import viewitems %}
 
 <link rel="stylesheet" href="/static/vendor/css/jquery.dataTables.css" type="text/css">

qiita_pet/templates/study_description.html

@@ -311,7 +311,7 @@
 }
 
 function delete_sample_template() {
-  sample_template_id = {{study.sample_template}};
+  sample_template_id = {{study.sample_template.id}};
   if (confirm('Are you sure you want to delete sample template ID: ' + sample_template_id + '?')) {
     var form = $("<form>")
     .attr("action", window.location.href)