Update and prepare ReporTree for L. pneumophila wgMLST analysis

Dockerfile

@@ -4,6 +4,6 @@ WORKDIR /app
 
 RUN conda install -c etetoolkit -c anaconda -c bioconda -c conda-forge -c defaults biopython=1.77 cgmlst-dists=0.4.0 ete3 grapetree=2.1 numba=0.55.1 numpy=1.19.2 numpy-base=1.19.2 pandas=1.1.3 python=3.8 scikit-learn snp-sites=2.5.1 treecluster=1.0.3 zip pytest git --yes
 
-RUN git clone -b v2.6.0 https://github.com/insapathogenomics/ReporTree && chmod 755 ReporTree/reportree.py && chmod 755 ReporTree/scripts/partitioning_grapetree.py && chmod 755 ReporTree/scripts/partitioning_HC.py && chmod 755 ReporTree/scripts/partitioning_treecluster.py && chmod 755 ReporTree/scripts/alignment_processing.py && chmod 755 ReporTree/scripts/metadata_report.py && cd ReporTree/scripts/ && git clone https://github.com/insapathogenomics/ComparingPartitions.git && git clone https://github.com/insapathogenomics/GrapeTree.git && git clone https://github.com/insapathogenomics/vcf2mst.git && cd ComparingPartitions && chmod 755 comparing_partitions_v2.py
+RUN git clone -b v2.6.1 https://github.com/insapathogenomics/ReporTree && chmod 755 ReporTree/reportree.py && chmod 755 ReporTree/scripts/partitioning_grapetree.py && chmod 755 ReporTree/scripts/partitioning_HC.py && chmod 755 ReporTree/scripts/partitioning_treecluster.py && chmod 755 ReporTree/scripts/alignment_processing.py && chmod 755 ReporTree/scripts/metadata_report.py && cd ReporTree/scripts/ && git clone https://github.com/insapathogenomics/ComparingPartitions.git && git clone https://github.com/insapathogenomics/GrapeTree.git && git clone https://github.com/insapathogenomics/vcf2mst.git && cd ComparingPartitions && chmod 755 comparing_partitions_v2.py
 
 ENV PATH="/app/ReporTree:/app/ReporTree/scripts:/app/ReporTree/scripts/ComparingPartitions:${PATH}"

README.md

@@ -24,6 +24,9 @@ In summary, ReporTree facilitates and accelerates the production of surveillance
 _Note: this tool relies on the usage of programs/modules of other developers. DO NOT FORGET TO ALSO [CITE](https://github.com/insapathogenomics/ReporTree/edit/main/README.md#citation) THEM!_
 
 ## News!
+#### 2025.11.27 - ReporTree v2.6.1
+Fixes a bug when updating cluster names in metadata table.
+
 #### 2025.10.22 - ReporTree v2.6.0
 We release a new version of ReporTree that besides fixing some small issues, also brings important new features:
 1. ReporTree is much more efficient in filtering allele matrices based on "--loci-called, "--site-inclusion" or "--loci" arguments.
@@ -209,14 +212,14 @@ python reportree.py -h
 docker pull insapathogenomics/reportree:latest
 ```
 
-- Or install a specific version by specifying the release you want (e.g. for v2.5.4):
+- Or install a specific version by specifying the release you want (e.g. for v2.6.1):
 ```bash
-docker pull insapathogenomics/reportree:v2.6.0
+docker pull insapathogenomics/reportree:v2.6.1
 ```
 
 Run ReporTree:
 ```bash
-docker run insapathogenomics/reportree:v2.6.0 reportree.py -h
+docker run insapathogenomics/reportree:v2.6.1 reportree.py -h
 ```
 
 ## Usage

reportree.py

@@ -18,8 +18,8 @@
 import numpy
 from collections import defaultdict
 
-version = "2.6.0"
-last_updated = "2025-10-22"
+version = "2.6.1"
+last_updated = "2025-11-27"
 
 reportree_script = os.path.realpath(__file__)
 reportree_path = reportree_script.rsplit("/", 1)[0]

scripts/metadata_report.py

@@ -15,8 +15,8 @@
 from pandas.api.types import is_datetime64_any_dtype as is_datetime
 import datetime
 
-version = "1.4.0"
-last_updated = "2025-10-22"
+version = "1.5.0"
+last_updated = "2025-11-27"
 
 # functions	----------
 
@@ -128,9 +128,10 @@ def partitions2metadata(partitions_name, partitions, mx_metadata, partitions2rep
 			else:
 				required_partitions = partitions2report.split(",")
 				for column_name in required_partitions:
-					if column_name in b.columns and column_name not in shared_columns:
-						valid_rows = b.index.intersection(c.index)
-						c = pandas.concat([c, b.loc[valid_rows, [column_name]].reindex(c.index)], axis=1)
+					if column_name in b.columns:
+						if column_name not in shared_columns:
+							valid_rows = b.index.intersection(c.index)
+							c = pandas.concat([c, b.loc[valid_rows, [column_name]].reindex(c.index)], axis=1)
 					else:
 						print("\t\t" + column_name + " will not be reported because it was not found in the partitions table!!")
 						print("\t\t" + column_name + " will not be reported because it was not found in the partitions table!!", file=log)