some fixes (#3341)

* some fixes

* flake8

* 2023.12

* addressing @charles-cowart comments

Author: antgonza

CHANGELOG.md

@@ -1,5 +1,19 @@
 # Qiita changelog
 
+Version 2023.12
+---------------
+
+* The sample and preparation information pages will display the timestamp of their last update.
+* Added a ProcessingJob.complete_processing_job method to retrieve the job that is completing the current job.
+* Added a ProcessingJob.trace method to trace all the jobs of a processing_job.
+* Analyses now accept SLURM reservation's via the GUI; this will be [helpful for workshops or classes](https://qiita.ucsd.edu/static/doc/html/faq.html#are-you-planning-a-workshop-or-class).
+* Admins can now add per-user-level SLURM submission parameters via the DB; this is helpful to prioritize wet-lab and admin jobs.
+* Workflow definitions can now use sample or preparation information columns/values to differentiate between them.
+* Updated the Adapter and host filtering plugin (qp-fastp-minimap2) to v2023.12 addressing a bug in adapter filtering; [more information](https://qiita.ucsd.edu/static/doc/html/processingdata/qp-fastp-minimap2.html).
+* Other fixes: [3334](https://github.com/qiita-spots/qiita/pull/3334), [3338](https://github.com/qiita-spots/qiita/pull/3338). Thank you @sjanssen2.
+* The internal Sequence Processing Pipeline is now using the human pan-genome reference, together with the GRCh38 genome + PhiX and CHM13 genome for human host filtering.
+
+
 Version 2023.10
 ---------------
 

qiita_core/__init__.py

@@ -6,4 +6,4 @@
 # The full license is in the file LICENSE, distributed with this software.
 # -----------------------------------------------------------------------------
 
-__version__ = "2023.10"
+__version__ = "2023.12"

qiita_db/__init__.py

@@ -27,7 +27,7 @@
 from . import user
 from . import processing_job
 
-__version__ = "2023.10"
+__version__ = "2023.12"
 
 __all__ = ["analysis", "artifact",  "archive", "base", "commands",
            "environment_manager", "exceptions", "investigation", "logger",

qiita_db/metadata_template/prep_template.py

@@ -851,10 +851,18 @@ def _get_predecessors(workflow, node):
             starting_job = None
             pt_artifact = self.artifact.artifact_type
 
-        workflows = []
+        all_workflows = [wk for wk in qdb.software.DefaultWorkflow.iter()]
+        # are there any workflows with parameters?
+        check_requirements = False
+        default_parameters = {'prep': {}, 'sample': {}}
+        if [wk for wk in all_workflows if wk.parameters != default_parameters]:
+            check_requirements = True
         ST = qdb.metadata_template.sample_template.SampleTemplate
-        for wk in qdb.software.DefaultWorkflow.iter():
+        workflows = []
+        for wk in all_workflows:
             if wk.artifact_type == pt_artifact and pt_dt in wk.data_type:
+                if check_requirements and wk.parameters == default_parameters:
+                    continue
                 wk_params = wk.parameters
                 reqs_satisfied = True
 

qiita_db/processing_job.py

@@ -999,7 +999,9 @@ def submit(self, parent_job_id=None, dependent_jobs_list=None):
             qdb.sql_connection.TRN.commit()
 
         job_dir = join(qdb.util.get_work_base_dir(), self.id)
-        software = self.command.software
+        command = self.command
+        software = command.software
+        cname = command.name
         plugin_start_script = software.start_script
         plugin_env_script = software.environment_script
 
@@ -1011,7 +1013,15 @@ def submit(self, parent_job_id=None, dependent_jobs_list=None):
         # case where we are going to execute some command and then wait for the
         # plugin to return their own id (first implemented for
         # fast-bowtie2+woltka)
-        if 'ENVIRONMENT' in plugin_env_script:
+        #
+        # This is the hardcoded lines described in issue:
+        # https://github.com/qiita-spots/qiita/issues/3340
+        # the idea is that in the future we shouldn't check specific command
+        # names to know if it should be executed differently and the
+        # plugin should let Qiita know that a specific command should be ran
+        # as job array or not
+        cnames_to_skip = {'Calculate Cell Counts'}
+        if 'ENVIRONMENT' in plugin_env_script and cname not in cnames_to_skip:
             # the job has to be in running state so the plugin can change its`
             # status
             with qdb.sql_connection.TRN:

qiita_pet/__init__.py

@@ -6,4 +6,4 @@
 # The full license is in the file LICENSE, distributed with this software.
 # -----------------------------------------------------------------------------
 
-__version__ = "2023.10"
+__version__ = "2023.12"

qiita_pet/handlers/api_proxy/__init__.py

@@ -38,7 +38,7 @@
 from .user import (user_jobs_get_req)
 from .util import check_access, check_fp
 
-__version__ = "2023.10"
+__version__ = "2023.12"
 
 __all__ = ['prep_template_summary_get_req', 'data_types_get_req',
            'study_get_req', 'sample_template_filepaths_get_req',

qiita_pet/support_files/doc/source/processingdata/processing-recommendations.rst

@@ -45,7 +45,7 @@ Shotgun sequencing
 ------------------
 
 Qiita currently has one active shotgun metagenomics data analysis pipeline: a per sample
-bowtie2 alignment step with Woltka classification using either the WoLr1, WoLr2 (default) or RS210 databases.
+bowtie2 alignment step with Woltka classification using either the WoLr2 (default) or RS210 databases.
 Below you will find more information about each of these options.
 
 .. note::
@@ -87,7 +87,7 @@ Note that the command produces up to 6 output artifacts based on the aligner and
 
 - Alignment Profile: contains the raw alignment file and the no rank classification BIOM table
 - Per genome Predictions: contains the per genome level predictions BIOM table
-- Per gene Predictions: Only WoLr1 & WoLr2, contains the per gene level predictions BIOM table
+- Per gene Predictions: Only WoLr2, contains the per gene level predictions BIOM table
 - KEGG Pathways: Only WoLr2, contains the functional profile
 - KEGG Ontology (KO): Only WoLr2, contains the functional profile
 - KEGG Enzyme (EZ): Only WoLr2, contains the functional profile

qiita_pet/templates/workflows.html

@@ -73,9 +73,9 @@ <h3>Recommended Default Workflows</h3>
         default Earth Microbiome Project protocol and so assumes the uploaded data are multiplexed sequences with the reversed barcodes in your mapping file and index sequence
         file (<a href="https://earthmicrobiome.org/protocols-and-standards/" target="_blank">see here</a> for more details). Thus, if the protocol does not apply to your data
         you can still use the Default Workflow, however, you should first manually process your data using the appropriate steps until you have a defined step; in our example,
-        demultiplexed your reads. After demultiplexing the Default Workflow is safe to use with any protocol.
+        demultiplex your reads. After demultiplexing, the Default Workflow is safe to use with any protocol.
         <br/><br/>
-        If you have already manually performed one of the processing steps in the Defaul Workflow pipeline, the "Add Default Workflow" button will not re-select those steps but
+        If you have already manually performed one of the processing steps in the Default Workflow pipeline, the "Add Default Workflow" button will not re-select those steps but
         instead will only select any remaining steps that have not been completed. You can also add additional workflows on top of the recommended Default Workflow at any time.
         <br/><br/>
         Note that this is not a full inclusive list of data types accepted by Qiita but only those that have a defined workflow.

qiita_ware/__init__.py

@@ -6,4 +6,4 @@
 # The full license is in the file LICENSE, distributed with this software.
 # -----------------------------------------------------------------------------
 
-__version__ = "2023.10"
+__version__ = "2023.12"

setup.py

@@ -10,7 +10,7 @@
 from setuptools import setup
 from glob import glob
 
-__version__ = "2023.10"
+__version__ = "2023.12"
 
 
 classes = """