Merge branch 'network_relabelling' of https://github.com/bacpop/PopPUNK…

… into network_relabelling

PopPUNK/__init__.py

@@ -3,7 +3,7 @@
 
 '''PopPUNK (POPulation Partitioning Using Nucleotide Kmers)'''
 
-__version__ = '2.7.2'
+__version__ = '2.7.3'
 
 # Minimum sketchlib version
 SKETCHLIB_MAJOR = 2

PopPUNK/plot.py

@@ -836,7 +836,7 @@ def outputsForMicroreact(combined_list, clustering, nj_tree, mst_tree, accMat, p
 
     return outfiles
 
-def createMicroreact(prefix, microreact_files, api_key=None):
+def createMicroreact(prefix, microreact_files, api_key=None, info_csv=None):
     """Creates a .microreact file, and instance via the API
 
     Args:
@@ -846,6 +846,8 @@ def createMicroreact(prefix, microreact_files, api_key=None):
             List of Microreact files [clusters, dot, tree, mst_tree]
         api_key (str)
             API key for your account
+        info_csv (str)
+            CSV file containing additional information for Microreact
     """
     import pkg_resources
     import pickle
@@ -859,7 +861,10 @@ def createMicroreact(prefix, microreact_files, api_key=None):
     with pkg_resources.resource_stream(__name__, 'data/microreact_example.pkl') as example_pickle:
         json_pickle = pickle.load(example_pickle)
     json_pickle["meta"]["name"] = description_string
-
+
+    # Update maps and timelines
+    update_maps_timelines(json_pickle, info_csv)
+
     # Read data in
     with open(microreact_files[0]) as cluster_file:
         csv_string = cluster_file.read()
@@ -898,6 +903,27 @@ def createMicroreact(prefix, microreact_files, api_key=None):
 
     return url
 
+def update_maps_timelines(micoreact_sample_json, info_csv=None):
+    """
+    Update the maps and timelines in the Microreact JSON file.
+    Removes maps and timelines if the required columns are not present in the info CSV.
+    
+    Args:
+        micoreact_sample_json (dict)
+            Microreact JSON file
+        info_csv (str)
+            CSV file containing additional information for Microreact
+    """
+    if info_csv is None:
+        micoreact_sample_json["maps"] = {}
+        micoreact_sample_json["timelines"] = {}
+    else:
+        info_df = pd.read_csv(info_csv)
+        if 'latitude' not in info_df.columns or 'longitude' not in info_df.columns:
+            micoreact_sample_json["maps"] = {}
+        if 'year' not in info_df.columns:
+            micoreact_sample_json["timelines"] = {}
+
 def outputsForPhandango(combined_list, clustering, nj_tree, mst_tree, outPrefix, epiCsv,
                         queryList = None, overwrite = False):
     """Generate files for Phandango

PopPUNK/visualise.py

@@ -691,7 +691,7 @@ def generate_visualisations(query_db,
                                                 n_threads=threads,
                                                 use_gpu=gpu_graph,
                                                 device_id=deviceid)
-        url = createMicroreact(output, microreact_files, api_key)
+        url = createMicroreact(output, microreact_files, api_key, info_csv)
         if url != None:
             sys.stderr.write("Microreact: " + url + "\n")
         else:

docs/troubleshooting.rst

@@ -174,5 +174,18 @@ used to assign new queries.
 If you want to change cluster names or assign queries to your own cluster definitions
 you can use the ``--external-clustering`` argument instead.
 
+"No non-zero Jaccard distances" Error
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+When running ``--create-db`` or ``poppunk_assign`` as::
+
+    No non-zero Jaccard distances
+    Fitting k-mer gradient failed, for:SampleAvs.SampleB
+
+Means that ``SampleA`` and ``SampleB`` are not the same species or are highly contaminated,
+and so share no k-mers with eachother. This may cause PopPUNK to hang, crash, or finish but not generate
+output files.
+
+To fix this error, check that genomes for ``SampleA`` and ``SampleB``
+are the correct species (e.g. using `BLAST <https://blast.ncbi.nlm.nih.gov/Blast.cgi>`_ or `Kraken2 <https://github.com/DerrickWood/kraken2>`_); if not, remove them from your input file and re-run your analysis.