Merge pull request #28 from antgonza/mv-update_job_step

mv qclient.update_job_step

qp_woltka/__init__.py

@@ -8,7 +8,8 @@
 
 from qiita_client import QiitaPlugin, QiitaCommand
 
-from .woltka import woltka, woltka_syndna, calculate_cell_counts
+from .woltka import (woltka, woltka_syndna, calculate_cell_counts,
+                     calculate_rna_copy_counts)
 from qp_woltka.util import generate_woltka_dflt_params, get_dbs, plugin_details
 from os import environ
 
@@ -61,9 +62,9 @@
     req_params, opt_params, outputs, dflt_param_set)
 plugin.register_command(syndna_cmd)
 
-# Cell counts
+# WGS cell counts
 req_params = {
-    'synDNA hits': ('artifact', ['BIOM']),
+    'SynDNA hits': ('artifact', ['BIOM']),
     'Woltka per-genome': ('artifact', ['BIOM'])
 }
 opt_params = {
@@ -85,3 +86,18 @@
     'Calculate Cell Counts', "Calculate cell counts per-genome",
     calculate_cell_counts, req_params, opt_params, outputs, dflt_param_set)
 plugin.register_command(calculate_cell_counts_cmd)
+
+
+# MTX calculate RNA copy counts
+req_params = {
+    'Woltka per-gene': ('artifact', ['BIOM'])
+}
+opt_params = {}
+outputs = {
+    'RNA copy counts': 'BIOM'
+}
+dflt_param_set = {'default': {}}
+calculate_rna_copy_counts_cmd = QiitaCommand(
+    'Calculate RNA Copy Counts', "Calculate RNA copy counts per-gene",
+    calculate_rna_copy_counts, req_params, opt_params, outputs, dflt_param_set)
+plugin.register_command(calculate_rna_copy_counts_cmd)

qp_woltka/tests/test_woltka.py

@@ -18,7 +18,7 @@
 from qp_woltka import plugin
 from qp_woltka.woltka import (
     woltka_to_array, woltka, woltka_syndna_to_array, woltka_syndna,
-    calculate_cell_counts)
+    calculate_cell_counts, calculate_rna_copy_counts)
 
 
 class WoltkaTests(PluginTestCase):
@@ -557,7 +557,7 @@ def test_woltka_syndna_to_array(self):
         self.assertCountEqual(ainfo, exp)
 
     def test_calculate_cell_counts(self):
-        params = {'synDNA hits': 5, 'Woltka per-genome': 6,
+        params = {'SynDNA hits': 5, 'Woltka per-genome': 6,
                   'min_coverage': 1, 'read_length': 150,
                   'min_rsquared': 0.8}
         job_id = 'my-job-id'
@@ -569,7 +569,7 @@ def test_calculate_cell_counts(self):
             self.qclient, job_id, params, out_dir)
         self.assertFalse(success)
         self.assertEqual(msg, "No logs found, are you sure you selected the "
-                         "correct artifact for 'synDNA hits'?")
+                         "correct artifact for 'SynDNA hits'?")
 
         # this should fail too because but now we are getting deeper into
         # the validation
@@ -603,7 +603,7 @@ def test_calculate_cell_counts(self):
             'type': "BIOM",
             'name': "SynDNA Hits - Test",
             'prep': pid}
-        params['synDNA hits'] = self.qclient.post(
+        params['SynDNA hits'] = self.qclient.post(
             '/apitest/artifact/', data=data)['artifact']
 
         success, ainfo, msg = calculate_cell_counts(
@@ -615,6 +615,22 @@ def test_calculate_cell_counts(self):
 
         # Finally, adding a full test is close to impossible - too many steps.
 
+    def test_calculate_rna_copy_counts(self):
+        params = {'Woltka per-gene': 6}
+        job_id = 'my-job-id'
+        out_dir = mkdtemp()
+        self._clean_up_files.append(out_dir)
+
+        # this should fail cause we don't have valid data
+        success, ainfo, msg = calculate_rna_copy_counts(
+            self.qclient, job_id, params, out_dir)
+        self.assertFalse(success)
+        self.assertEqual(msg, "The selected 'Woltka per-gene' artifact "
+                         "doesn't look like one, did you select the "
+                         "correct file?")
+
+        # Finally, adding a full test is close to impossible - too many steps.
+
 
 if __name__ == '__main__':
     main()

qp_woltka/woltka.py

@@ -16,6 +16,7 @@
 import pandas as pd
 from pysyndna import fit_linear_regression_models_for_qiita
 from pysyndna import calc_ogu_cell_counts_per_g_of_sample_for_qiita
+from pysyndna import calc_copies_of_ogu_orf_ssrna_per_g_sample_for_qiita
 
 from qp_woltka.util import search_by_filename
 
@@ -570,18 +571,18 @@ def calculate_cell_counts(qclient, job_id, parameters, out_dir):
     """
     error = ''
     # let's get the syndna_id and prep in a single go
-    syndna_id = parameters['synDNA hits']
+    syndna_id = parameters['SynDNA hits']
     syndna_files, prep = qclient.artifact_and_preparation_files(syndna_id)
     if 'log' not in syndna_files.keys():
         error = ("No logs found, are you sure you selected the correct "
-                 "artifact for 'synDNA hits'?")
+                 "artifact for 'SynDNA hits'?")
     else:
 
         lin_regress_by_sample_id_fp = [f for f in syndna_files['log']
                                        if 'lin_regress_by_sample_id' in f]
         if not lin_regress_by_sample_id_fp:
             error = ("No 'lin_regress_by_sample_id' log found, are you sure "
-                     " you selected the correct artifact for 'synDNA hits'?")
+                     " you selected the correct artifact for 'SynDNA hits'?")
         else:
             lin_regress_by_sample_id_fp = lin_regress_by_sample_id_fp[0]
 
@@ -615,8 +616,8 @@ def calculate_cell_counts(qclient, job_id, parameters, out_dir):
         output = calc_ogu_cell_counts_per_g_of_sample_for_qiita(
             sample_info, prep, lin_regress_by_sample_id_fp,
             ogu_counts_per_sample, ogu_lengths_fp,
-            parameters['read_length'], parameters['min_rsquared'],
-            parameters['min_rsquared'])
+            int(parameters['read_length']), float(parameters['min_coverage']),
+            float(parameters['min_rsquared']))
     except Exception as e:
         return False, None, str(e)
 
@@ -631,3 +632,65 @@ def calculate_cell_counts(qclient, job_id, parameters, out_dir):
             'Cell counts', 'BIOM', [(biom_fp, 'biom'), (log_fp, 'log')])]
 
     return True, ainfo, ""
+
+
+def calculate_rna_copy_counts(qclient, job_id, parameters, out_dir):
+    """Run calc_copies_of_ogu_orf_ssrna_per_g_sample_for_qiita
+
+    Parameters
+    ----------
+    qclient : tgp.qiita_client.QiitaClient
+        The Qiita server client
+    job_id : str
+        The job id
+    parameters : dict
+        The parameter values to wolka syndna
+    out_dir : str
+        The path to the job's output directory
+
+    Returns
+    -------
+    bool, list, str
+        The results of the job
+    """
+
+    per_gene_id = parameters['Woltka per-gene']
+    ainfo = qclient.get("/qiita_db/artifacts/%s/" % per_gene_id)
+    aparams = ainfo['processing_parameters']
+    pg_fp = ainfo['files']['biom'][0]['filepath']
+
+    if 'Database' not in aparams or not pg_fp.endswith('per-gene.biom'):
+        error = ("The selected 'Woltka per-gene' artifact doesn't "
+                 "look like one, did you select the correct file?")
+        return False, None, error
+
+    pergene = load_table(pg_fp)
+    db_files = _process_database_files(aparams['Database'])
+    ogu_orf_coords_fp = db_files["gene_coordinates"]
+
+    _, prep_info = qclient.artifact_and_preparation_files(per_gene_id)
+
+    sample_info = qclient.get(
+        '/qiita_db/prep_template/%s/data/?sample_information=true'
+        % ainfo['prep_information'][0])
+    sample_info = pd.DataFrame.from_dict(
+        sample_info['data'], orient='index')
+    sample_info.reset_index(names='sample_name', inplace=True)
+
+    try:
+        output, log_msgs = calc_copies_of_ogu_orf_ssrna_per_g_sample_for_qiita(
+            sample_info, prep_info, pergene, ogu_orf_coords_fp)
+    except Exception as e:
+        return False, None, str(e)
+
+    log_fp = f'{out_dir}/rna_copy_counts.log'
+    with open(log_fp, 'w') as f:
+        f.write(''.join(log_msgs))
+    biom_fp = f'{out_dir}/rna_copy_counts.biom'
+    with biom_open(biom_fp, 'w') as f:
+        output.to_hdf5(f, f"RNA copy counts - {job_id}")
+    ainfo = [
+        ArtifactInfo(
+            'RNA copy counts', 'BIOM', [(biom_fp, 'biom'), (log_fp, 'log')])]
+
+    return True, ainfo, ""

scripts/start_woltka

@@ -32,22 +32,23 @@ def execute(url, job_id, out_dir):
         command = job_info['command']
         parameters = job_info['parameters']
 
-        qclient.update_job_step(
-            job_id, "Step 1 of 4: Collecting info and generating submission")
-
         # these were defined in qp_woltka/__init.py__ while defining the
         # available commands for this plugin
         valid_commands = [
-            'Woltka v0.1.4', 'SynDNA Woltka', 'Calculate Cell Counts']
+            'Woltka v0.1.4', 'SynDNA Woltka', 'Calculate Cell Counts',
+            'Calculate RNA Copy Counts']
 
         # this if/elif is the current solution for
         # https://github.com/qiita-spots/qiita/issues/3340
         if command not in valid_commands:
             raise ValueError(f'Not a valid command: "{command}"')
-        elif command == 'Calculate Cell Counts':
+        elif command in {'Calculate Cell Counts', 'Calculate RNA Copy Counts'}:
             plugin(url, job_id, out_dir)
             exit(0)
 
+        qclient.update_job_step(
+            job_id, "Step 1 of 4: Collecting info and generating submission")
+
         artifact_id = parameters['input']
         del parameters['input']
         files, prep = qclient.artifact_and_preparation_files(artifact_id)