From 58067bdf01d1cd64e10297ef654948a0133d3485 Mon Sep 17 00:00:00 2001
From: John Lees <lees.john6@gmail.com>
Date: Tue, 3 Feb 2026 15:36:39 +0000
Subject: [PATCH] Pass freq param to ska

Also improve instructions for dates

Closes #26
---
 README.md  | 19 +++++++++++++++----
 Snakefile  |  6 +++---
 config.yml |  4 ++--
 3 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index cbad0eb..c0b230d 100644
--- a/README.md
+++ b/README.md
@@ -51,7 +51,20 @@ In addition to the above, for each strain:
 - Use [bactdating](https://github.com/xavierdidelot/BactDating) to make timed trees.
 - Use [transphylo](https://github.com/xavierdidelot/TransPhylo) to infer transmission events on these timed trees.
 
-This requires a `transmission_metadata.csv` file containing sampling times, see the PopPIPE configuration section below for a description of its format.
+This requires a `transmission_metadata.csv` file containing sampling times, this file should look like this:
+```
+Name,Date
+001334,2001
+279388,2001
+5Z52R,2007
+```
+Where the sample names match the PopPUNK analysis, followed by a date.
+
+Please note that bactDating parses the dates using:
+```r
+tryFormats = c("%Y-%m-%d", "%Y/%m/%d", "%Y")
+```
+So your dates should be in a compatible format, usually at the same resolution (e.g. all just years)
 
 For an example of this analysis, please find data at [10.6084/m9.figshare.28495571](https://dx.doi.org/10.6084/m9.figshare.28495571).
 Input files and config file are in `input/` and the pipeline output after running `snakemake transmission --cores 4` is
@@ -122,9 +135,7 @@ in `config.yml` which lists the sampling dates. The run the transmission target:
 snakemake transmission
 ```
 
-## Usage example
-
-TODO
+Ensure dates are formatted consistently (see above).
 
 ## Config file
 
diff --git a/Snakefile b/Snakefile
index 3192f40..b958ab4 100644
--- a/Snakefile
+++ b/Snakefile
@@ -137,9 +137,10 @@ rule ska_align:
     log:
         "logs/ska_align_{strain}.log"
     params:
-        prefix="output/strains/{strain}/align"
+        prefix="output/strains/{strain}/align",
+        min_freq=config['ska']['freq_filter']
     shell:
-        "ska align -v --filter no-const --no-gap-only-sites {input.skf} > {output.alignment} 2> {log}"
+        "ska align -v --min-freq {params.min_freq} --filter no-const --no-gap-only-sites {input.skf} > {output.alignment} 2> {log}"
 
 # ska for mapping (needed for gubbins)
 rule ska_map:
@@ -174,7 +175,6 @@ rule iq_tree:
         mode=config['iqtree']['mode'],
         model=config['iqtree']['model'],
         prefix="output/strains/{strain}/besttree.unrooted"
-
     threads:
         4
     script:
diff --git a/config.yml b/config.yml
index 4b9a0c0..85efd1d 100644
--- a/config.yml
+++ b/config.yml
@@ -16,7 +16,7 @@ ska:
   fastq_cov: 4
   kmer: 31
   single_strand: false
-  freq_filter: 0.9
+  freq_filter: 0.9 # only used in ska align step
 
 # IQ-TREE options
 iqtree:
@@ -37,7 +37,7 @@ mandrake:
 
 # Microreact title, and your contact details
 microreact:
-  name: Listeria PopPIPE
+  name: PopPIPE run
   website: https://www.poppunk.net
   email: poppunk@poppunk.net
   api_token: a1b2c3d4  ## see https://docs.microreact.org/api/access-tokens