Update README and config

Author: gregdenay

README.md

@@ -21,10 +21,9 @@ cd path/to/repo/
 git clone --recurse-submodules https://github.com/CVUA-RRW/BAnalyzer.git
 ```
 
-Set up a conda environment containing snakemake, python and the pandas library and activate it:
-
+Set up a conda environment containing snakemake (version 6 not supported), python and the pandas library and activate it:
 ```bash
-conda create --name snakemake -c bioconda -c anaconda snakemake pandas
+conda create --name snakemake -c bioconda -c anaconda "snakemake>=5.10,<6.0" pandas
 conda activate snakemake
 ```
 
@@ -37,9 +36,11 @@ to know how to format it.
 If you want to extract barcodes from a database of reference genomes you can check out 
 our [RRW-PrimerBLAST](https://github.com/CVUA-RRW/RRW-PrimerBLAST) pipeline.
 
-You will also need to provide the [taxdb](https://ftp.ncbi.nlm.nih.gov/blast/db/taxdb.tar.gz) 
+You will also need to provide the [taxdb](https://ftp.ncbi.nlm.nih.gov/blast/db/taxdb.tar.gz) and 
+[taxdump](https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz)
 files available from the NCBI server.
 
+
 ### Running BAnalyzer
 
 BAnalyzer should be run using the snakemake command-line application.
@@ -63,6 +64,8 @@ The configuration file contains the following parameters:
 workdir:                # Path to output directory
 blast_db:               # Path to BLAST-formated database
 taxdb:                  # Path to the folder containing the taxdb files
+rankedlineage_dmp:      # Path to rankedlineage.dmp
+nodes_dmp:              # Path to nodes.dmp
 
 # Modify the parameters below:
 trim_primers: False     # True to trim primers from sequences

Snakefile

@@ -318,8 +318,8 @@ rule get_consensus_level:
     message:
         "Determining consensus ranks"
     params:
-        lineage = config["taxonomy"]["rankedlineage_dmp"],
-        nodes = config["taxonomy"]["nodes_dmp"],
+        lineage = config["rankedlineage_dmp"],
+        nodes = config["nodes_dmp"],
     script:
         "../scripts/consensus_levels.py"
 
@@ -332,8 +332,8 @@ rule write_report:
         derep = "reports/dereplication.tsv",
         nderep = "reports/derep_number.txt",
         nNfilt = "reports/high_N.txt",
-        clusterSize = "reports/cluster_size.tsv"
-        consensus = "reports/consensus.tsv"
+        clusterSize = "reports/cluster_size.tsv",
+        consensus = "reports/consensus.tsv",
     output:
         "reports/report.html"
     params:

config.yaml

@@ -2,6 +2,8 @@
 workdir:                # Path to output directory
 blast_db:               # Path to BLAST-formated database
 taxdb:                  # Path to the folder containing the taxdb files
+rankedlineage_dmp:      # Path to rankedlineage.dmp
+nodes_dmp:              # Path to nodes.dmp
 
 # Modify the parameters below:
 trim_primers: False     # True to trim primers from sequences