feat: update all!

.github/workflows/cache.yml

@@ -10,15 +10,15 @@ jobs:
   weekly-cache:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4.1.4
       - name: Set up cache
-        uses: actions/cache@v2
+        uses: actions/cache@v4.0.2
         with:
           path: .snakemake/conda
           key: snakemake-conda
         id: cache
       - name: Download environments
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         with:
           directory: .
           snakefile: workflow/Snakefile

.github/workflows/conventional-prs.yml

@@ -13,7 +13,7 @@ jobs:
   title-format:
     runs-on: ubuntu-latest
     steps:
-      - uses: amannn/action-semantic-pull-request@v5.2.0
+      - uses: amannn/action-semantic-pull-request@v5.5.2
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:

.github/workflows/main.yml

@@ -4,20 +4,20 @@ name: Tests
 
 on:  # yamllint disable-line rule:truthy
   push:
-    branches: [main, devel]
+    branches: [master, devel]
   pull_request:
-    branches: [main, devel]
+    branches: [master, devel]
 
 jobs:
 
   Pre-Commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4.1.4
         with:
           lfs: 'true'
       - name: Run pre-commit on all files
-        uses: pre-commit/[email protected].0
+        uses: pre-commit/[email protected].1
         with:
           extra_args: --all-files
 
@@ -26,18 +26,18 @@ jobs:
     needs:
       - Pre-Commit
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4.1.4
         with:
           lfs: 'true'
 
       - name: Cache
-        uses: actions/cache@v3
+        uses: actions/cache@v4.0.2
         with:
           path: .snakemake/conda
           key: snakemake-conda
 
       - name: Download environments
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         with:
           directory: .
           snakefile: workflow/Snakefile
@@ -48,7 +48,7 @@ jobs:
             --cores 1
 
       - name: Test workflow
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         with:
           directory: .
           snakefile: workflow/Snakefile
@@ -57,4 +57,3 @@ jobs:
             --show-failed-logs
             --cores 3
             --conda-cleanup-pkgs cache
-            --all-temp

.github/workflows/release-please.yml

@@ -2,8 +2,7 @@
 ---
 on:  # yamllint disable-line rule:truthy
   push:
-    branches:
-      - main
+    branches: [main, devel, master]
 
 name: release-please
 
@@ -12,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
 
-      - uses: google-github-actions/release-please-action@v3
+      - uses: google-github-actions/release-please-action@v4.1.0
         id: release
         with:
           release-type: go

README.md

@@ -1,6 +1,6 @@
 # smsk_popoolation: A Snakemake pipeline for population genomics
 
-[![Build Status](https://travis-ci.org/jlanga/smsk_popoolation.svg?branch=master)](https://travis-ci.org/jlanga/smsk_popoolation)
+![Build Status](https://github.com/jlanga/smsk_popoolation/actions/workflows/main.yml/badge.svg)
 [![DOI](https://zenodo.org/badge/76841262.svg)](https://zenodo.org/badge/latestdoi/76841262)
 
 ## 1. Description
@@ -17,8 +17,6 @@ This is a repo that contains installers and snakemake scripts to execute the pip
 
 ## 2. First steps
 
-Follow the contents of the `.travis.yml` file:
-
 1. Install ([ana](https://www.continuum.io/downloads)|[mini](http://conda.pydata.org/miniconda.html))conda
 
 2. Clone and install the software

config/params.yml

@@ -19,7 +19,7 @@ popoolation:
         min_covered_fraction: 0.5
         analyses: [pi, theta, D]
         window_step:  # window: 5000, step: 1000 -> [1, 5000], [1000, 6000], [2000, 7000], ...
-            - [1, 1]
+            - [1K, 500]
             - [5K, 1K]
 
 popoolation2:
@@ -36,5 +36,5 @@ popoolation2:
         min_coverage: 4
         min_covered_fraction: 1.0
         window_step:  # window: 5000, step: 1000 -> [1, 5000], [1000, 6000], [2000, 7000], ...
-            - [1, 1]
+            - [1K, 500]
             - [5K, 1K]

workflow/Snakefile

@@ -18,9 +18,12 @@ samples = pd.read_table("config/samples.tsv", comment="#", dtype="str")
 
 # Other variables
 POPULATION_LIBRARY = (
-    samples[["population", "library"]].drop_duplicates().values.tolist()
+    samples[["population", "library"]]
+    .sort_values(by=["population", "library"])
+    .drop_duplicates()
+    .values.tolist()
 )
-POPULATIONS = list(set(population for population, library in POPULATION_LIBRARY))
+POPULATIONS = samples["population"].sort_values().drop_duplicates().values.tolist()
 
 PAIRS = ["pe_pe", "pe_se"]
 CHROMOSOMES = features["chromosomes"].split(" ")

workflow/rules/popoolation/__main__.smk

@@ -7,7 +7,5 @@ include: "hp.smk"
 
 rule popoolation:
     input:
-        rules.popoolation__mpileup.input,
-        rules.popoolation__variance_sliding.input,
         rules.popoolation__plot.input,
         rules.popoolation__hp.input,

workflow/rules/popoolation/variance_sliding.smk

@@ -47,7 +47,7 @@ rule popoolation__variance_sliding__:
             --snp-output {params.snps} \
         2> {log} 1>&2
 
-        gzip --keep {params.snps} {params.vs} 2>> {log} 1>&2
+        gzip {params.snps} {params.vs} 2>> {log} 1>&2
         """
 
 

workflow/rules/popoolation2/__main__.smk

@@ -7,6 +7,4 @@ include: "plot.smk"
 
 rule popoolation2:
     input:
-        rules.popoolation2__sync.input,
-        rules.popoolation2__fst_sliding.input,
         rules.popoolation2__plot.input,

workflow/rules/preprocess/__environment__.yml

@@ -8,3 +8,5 @@ dependencies:
   - pigz =2.8
   - python =3.12.3
   - samtools =1.20
+  - r-tidyverse =2.0.0
+  - r-tidyquant =1.0.7

workflow/rules/preprocess/coverage.smk

@@ -23,6 +23,23 @@ rule preprocess__coverage__compute_hist__:
         """
 
 
-rule preprocess__coverage:
+rule preprocess_coverage__plot__:
     input:
         [PRE_COV / f"{population}.hist" for population in POPULATIONS],
+    output:
+        pdf=PRE_COV / "coverage.pdf",
+        coverage=PRE_COV / "coverage.tsv",
+    log:
+        PRE_COV / "coverage.log",
+    conda:
+        "__environment__.yml"
+    shell:
+        """
+        Rscript workflow/scripts/plot_coverage.R 2> {log} 1>&2
+        """
+
+
+rule preprocess__coverage:
+    input:
+        hist=PRE_COV / "coverage.pdf",
+        coverage=PRE_COV / "coverage.tsv",

workflow/rules/preprocess/index.smk

@@ -3,20 +3,24 @@ rule preprocess__index:
     input:
         fa=REFERENCE / f"{REFERENCE_NAME}.fa.gz",
     output:
-        mock=touch(PRE_INDEX / f"{REFERENCE_NAME}"),
-        buckets=[
-            PRE_INDEX / f"{reference_name}.{suffix}"
-            for reference_name in [REFERENCE_NAME]
-            for suffix in "0123 amb ann bwt.2bit.64 pac".split()
-        ],
+        buckets=multiext(
+            str(PRE_INDEX / f"{REFERENCE_NAME}."),
+            "0123",
+            "amb",
+            "ann",
+            "bwt.2bit.64",
+            "pac",
+        ),
     log:
         PRE_INDEX / f"{REFERENCE_NAME}.log",
     conda:
         "__environment__.yml"
+    params:
+        prefix=PRE_INDEX / f"{REFERENCE_NAME}",
     shell:
         """
         bwa-mem2 index \
-            -p {output.mock} \
+            -p {params.prefix} \
             {input.fa} \
         > {log} 2>&1
         """

workflow/rules/preprocess/map.smk

@@ -3,24 +3,32 @@ rule preprocess__map__bwamem2__:
     input:
         forward_=READS / "{population}.{library}_1.fq.gz",
         reverse_=READS / "{population}.{library}_2.fq.gz",
-        index=PRE_INDEX / f"{REFERENCE_NAME}",
+        buckets=multiext(
+            str(PRE_INDEX / f"{REFERENCE_NAME}."),
+            "0123",
+            "amb",
+            "ann",
+            "bwt.2bit.64",
+            "pac",
+        ),
         reference=REFERENCE / f"{REFERENCE_NAME}.fa.gz",
     output:
         cram=PRE_MAP / "{population}.{library}.cram",
-    params:
-        rg_tag=compose_rg_tag,
     threads: 24
     log:
         PRE_MAP / "{population}.{library}.bwa_mem.log",
     conda:
         "__environment__.yml"
+    params:
+        rg_tag=compose_rg_tag,
+        prefix=PRE_INDEX / f"{REFERENCE_NAME}",
     shell:
         """
         ( bwa-mem2 mem \
             -M \
             -R '{params.rg_tag}' \
             -t {threads} \
-            {input.index} \
+            {params.prefix} \
             {input.forward_} \
             {input.reverse_} \
         | samtools sort \

workflow/scripts/plot_coverage.R

@@ -0,0 +1,47 @@
+#!/usr/bin/env Rscript
+library(tidyverse)
+library(tidyquant)
+
+
+frequencies <-
+  list.files(
+    path = "results/preprocess/coverage",
+    pattern = ".hist$",
+    full.names = TRUE
+  ) %>%
+  map(
+    function(x) {
+      read_tsv(
+        file = x,
+        col_names = c("population", "coverage", "frequency"),
+        col_types = "cii"
+      )
+    }
+  ) %>%
+  bind_rows()
+
+
+coverages <- frequencies %>%
+  filter(coverage > 0) %>%
+  ggplot(aes(x = coverage, y = frequency)) +
+  geom_ma(ma_fun = SMA, linetype = "solid", color = "black") +
+  scale_y_log10() +
+  facet_wrap(~population)
+
+ggsave(
+  filename = "results/preprocess/coverage/coverage.pdf",
+  plot = coverages,
+  width = 297, height = 210, units = "mm"
+)
+
+
+
+frequencies %>%
+  filter(coverage > 10) %>%
+  group_by(population) %>%
+  filter(frequency == max(frequency)) %>%
+  mutate(
+    max_coverage = 1.5 * coverage,
+    min_coverage = 0.5 * coverage
+  ) %>%
+  write_tsv("results/preprocess/coverage/coverage.tsv")