Merge pull request #4 from MPUSP/dev

fix: various small fixes for linting and formatting errors

.github/workflows/main.yml

@@ -2,9 +2,9 @@ name: Tests
 
 on:
   push:
-    branches: [ main ]
+    branches: [ main, dev ]
   pull_request:
-    branches: [ main ]
+    branches: [ main, dev ]
 
 
 jobs:

.gitignore

@@ -1,6 +1,7 @@
 results/**
 data/**
 .test/results/**
+.test/data/**
 resources/**
 logs/**
 .snakemake

README.md

@@ -1,8 +1,10 @@
 # snakemake-ont-bacterial-variants
 
+![Platform](https://img.shields.io/badge/platform-all-green)
 [![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
-[![GitHub actions status](https://github.com/MPUSP/snakemake-ont-bacterial-variants/workflows/Tests/badge.svg?branch=main)](https://github.com/MPUSP/snakemake-ont-bacterial-variants/actions?query=branch%3Amain+workflow%3ATests)
+[![Tests](https://github.com/MPUSP/snakemake-ont-bacterial-variants/actions/workflows/main.yml/badge.svg)](https://github.com/MPUSP/snakemake-ont-bacterial-variants/actions/workflows/main.yml)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
+[![workflow catalog](https://img.shields.io/badge/Snakemake%20workflow%20catalog-darkgreen)](https://snakemake.github.io/snakemake-workflow-catalog)
 
 A Snakemake workflow for the identification of variants in bacterial genomes using nanopore long-read sequencing.
 

workflow/envs/basic.yml

@@ -1,7 +1,6 @@
 name: basic
 channels:
   - conda-forge
-  - defaults
 dependencies:
   - python=3.9
   - pandas=2.1.4

workflow/envs/bcftools.yml

@@ -1,6 +1,6 @@
 name: bcftools
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - bcftools=1.19

workflow/envs/clair3.yml

@@ -1,6 +1,6 @@
 name: clair3
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - clair3=1.0.5

workflow/envs/cutesv.yml

@@ -1,6 +1,6 @@
 name: cutesv
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - cutesv=2.1.0

workflow/envs/filtlong.yml

@@ -1,6 +1,6 @@
 name: filtlong
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - filtlong=0.2.1

workflow/envs/igv-reports.yml

@@ -1,6 +1,6 @@
 name: igv-reports
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - igv-reports=1.10.0

workflow/envs/medaka.yml

@@ -1,6 +1,6 @@
 name: medaka
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - medaka=1.11.3

workflow/envs/multiqc.yml

@@ -1,7 +1,7 @@
 name: multiqc
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - multiqc=1.19
   - rich-click=1.6.1

workflow/envs/nanoplot.yml

@@ -1,6 +1,6 @@
 name: nanoplot
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - nanoplot=1.42.0

workflow/envs/ngmlr.yml

@@ -1,7 +1,7 @@
 name: ngmlr
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - ngmlr=0.2.7
   - samtools=1.9

workflow/envs/sniffles2.yml

@@ -1,6 +1,6 @@
 name: sniffles2
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - sniffles=2.2

workflow/envs/vcftools.yml

@@ -1,6 +1,6 @@
 name: vcftools
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
   - vcftools=0.1.16

workflow/rules/common.smk

@@ -14,7 +14,8 @@ def list_reference_genomes():
     paths = SAMPLEINFO["reference"].unique()
     genomes = {}
     for path in paths:
-        ident = ".".join(path.split('/')[-1].split(".")[:-1])
+        ident = os.path.basename(path)
+        ident = os.path.splitext(ident)[0]
         if not ident in genomes.keys():
             genomes[ident] = path
     return genomes
@@ -51,10 +52,10 @@ def download_model_for_clair3(wildcards):
         "r1041_e82_400bps_sup_v4.2.0": "https://cdn.oxfordnanoportal.com/software/analysis/models/clair3/r1041_e82_400bps_sup_v420.tar.gz",
         "r1041_e82_400bps_sup_v4.3.0": "https://cdn.oxfordnanoportal.com/software/analysis/models/clair3/r1041_e82_400bps_sup_v430.tar.gz",
     }
-    return (
-        path2model[config["basecalling_model"]],
-        path2model[config["basecalling_model"]].split('/')[-1].split(".tar.gz")[0],
-    )
+    model = path2model[config["basecalling_model"]]
+    model_name = os.path.basename(model)
+    model_name = model_name.replace(".tar.gz", "")
+    return (model, model_name)
 
 
 def get_medaka_model(wildcards):