Merge branch 'master' into dependabot/github_actions/snakemake/snakem…

…ake-github-action-1.25.1

.github/workflows/copyright-preamble.yml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       # Checking out the repository which is to be actioned
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       # Implementing action on repository
       - uses: VinnyBabuManjaly/[email protected]
         with:
@@ -25,7 +25,7 @@ jobs:
 
       # Creates pull request with all changes in file
       - name: Create Pull Request
-        uses: peter-evans/create-pull-request@v4
+        uses: peter-evans/create-pull-request@v5
         with:
           commit-message: "chore: update copyright preamble"
           delete-branch: true

.github/workflows/documentation.yml

@@ -18,7 +18,7 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       - name: SetUp Python
         uses: actions/setup-python@v4

.github/workflows/main.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.ref != 'refs/heads/master'
     steps:
-      - uses: khan/[email protected].0
+      - uses: khan/[email protected].1
         with:
           workflows: "main.yml"
         env:
@@ -22,7 +22,7 @@ jobs:
   Formatting:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Formatting
         uses: github/[email protected]
         env:
@@ -39,7 +39,7 @@ jobs:
     env:
       GISAID_API_TOKEN: ${{ secrets.GISAID_API_TOKEN }}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Lint workflow
         uses: snakemake/[email protected]
         with:
@@ -55,7 +55,7 @@ jobs:
   #   runs-on: ubuntu-latest
   #   if: github.ref != 'refs/heads/master'
   #   steps:
-  #     - uses: actions/checkout@v2
+  #     - uses: actions/checkout@v4
   #     - uses: actions/setup-python@v4
   #     - uses: pre-commit/[email protected]
 
@@ -75,7 +75,7 @@ jobs:
         # technology: [all, illumina, ion]
         seq_method: [shotgun, amplicon]
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - uses: actions/setup-python@v4
         with:
           python-version: '3.11'
@@ -192,7 +192,7 @@ jobs:
           ]
     # generate_test_cases,
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       # - name: Cache conda dependencies
       #   uses: actions/cache@v2

.github/workflows/release-please.yml

@@ -68,14 +68,14 @@ jobs:
           remove-android: "true"
 
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Space
         run: |
           echo "Free space:"
           df -h
 
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       - name: Checkout release PR locally
         if: ${{ steps.pr_created.outputs.pr == 'true' && steps.release.outputs.release_created != 'true' }}
@@ -140,7 +140,7 @@ jobs:
 
       - name: Build and push
         if: ${{ steps.release.outputs.release_created == 'true' }}
-        uses: docker/build-push-action@v3
+        uses: docker/build-push-action@v5
         with:
           context: .
           push: true

.github/workflows/update-pangolin.yaml

@@ -9,7 +9,7 @@ jobs:
   Create-PR-for-new-Pangolin-release:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       - name: Install mamba
         uses: conda-incubator/setup-miniconda@v2
@@ -37,7 +37,7 @@ jobs:
       - name: Create Pull Request
         if: ${{ env.LATEST_PANGOLIN != env.CURRENT_PANGOLIN }}
         id: cpr
-        uses: peter-evans/create-pull-request@v4
+        uses: peter-evans/create-pull-request@v5
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
           committer: GitHub <[email protected]>

CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## [0.16.0](https://github.com/IKIM-Essen/uncovar/compare/v0.15.1...v0.16.0) (2023-11-16)
+
+
+### Features
+
+* Update README.md for dark/light theme ([#614](https://github.com/IKIM-Essen/uncovar/issues/614)) ([33ac5f7](https://github.com/IKIM-Essen/uncovar/commit/33ac5f7b4f7af8bbb500e9f531ccbdc45ac9427f))
+
+
+### Bug Fixes
+
+* changes in path requirements for snakedeploy ([#590](https://github.com/IKIM-Essen/uncovar/issues/590)) ([406d456](https://github.com/IKIM-Essen/uncovar/commit/406d456edd15715f7e14338b8195d2a09a807e49))
+* improved clonality event definition, usage of major subclone for assembly polishing; upgrade to varlociraptor 6.0 ([#585](https://github.com/IKIM-Essen/uncovar/issues/585)) ([aced95e](https://github.com/IKIM-Essen/uncovar/commit/aced95e798fd0483e99120550f49614e680f56dd))
+* QA genome generation ([#613](https://github.com/IKIM-Essen/uncovar/issues/613)) ([2bb74bf](https://github.com/IKIM-Essen/uncovar/commit/2bb74bfc26dee80af7d04089aafe636ea7c6d76a))
+* switch from jupyter notebook to script ([#598](https://github.com/IKIM-Essen/uncovar/issues/598)) ([d0f293d](https://github.com/IKIM-Essen/uncovar/commit/d0f293d2b8136fb0d8ef3753733ab1d30fb20d56))
+* update multiqc ([#607](https://github.com/IKIM-Essen/uncovar/issues/607)) ([0070d89](https://github.com/IKIM-Essen/uncovar/commit/0070d8927290dd01f418b876b60f3405158f1ab9))
+* use homopolymer-pair-HMM-mode of Varlociraptor in case of nanopore reads ([505a271](https://github.com/IKIM-Essen/uncovar/commit/505a2714ba0e5642312051f5e5154f7d454ff57f))
+* use homopolymer-pair-HMM-mode of Varlociraptor in case of nanopore reads ([#587](https://github.com/IKIM-Essen/uncovar/issues/587)) ([9bc814f](https://github.com/IKIM-Essen/uncovar/commit/9bc814f7cb9e9d9e53d557d463e782801070b46e))
+
+
+### Performance Improvements
+
+* update to varlociraptor 8.4 ([#596](https://github.com/IKIM-Essen/uncovar/issues/596)) ([34701af](https://github.com/IKIM-Essen/uncovar/commit/34701af485aa1ec199a418ec1487a97677f624ca))
+
 ## [0.15.1](https://github.com/IKIM-Essen/uncovar/compare/v0.15.0...v0.15.1) (2022-11-30)
 
 

README.md

@@ -1,6 +1,12 @@
 # UnCoVar
 
-![UnCoVar2](https://user-images.githubusercontent.com/77535027/133610563-d190e25c-504e-4953-92dd-f84a5b4a1191.png)
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://github.com/IKIM-Essen/uncovar/assets/77535027/8e17c6fc-ff7a-4c25-afc9-7888036d693e">
+  <source media="(prefers-color-scheme: light)" srcset="https://github.com/IKIM-Essen/uncovar/assets/77535027/c99f5a94-749b-422e-b319-1e3700d40a8e">
+  <img alt="UnCoVar Logo dark/light">
+</picture>
+
 
 ## SARS-CoV-2 Variant Calling and Lineage Assignment
 

config/config.yaml

@@ -72,12 +72,12 @@ assembly:
     # assemblers used for shotgun sequencing with on Illumina technology
     shotgun: "megahit-std"
     # assemblers used for amplicon sequencing with on Illumina technology
-    amplicon: "metaspades"
+    amplicon: "megahit-std"
   oxford nanopore:
     # assemblers used for shotgun sequencing with on Oxford Nanopore technology
     shotgun: "megahit-std"
     # assemblers used for amplicon sequencing with on Oxford Nanopore technology
-    amplicon: "spades"
+    amplicon: "megahit-std"
     # Medaka models are named to indicate i) the pore type, ii) the sequencing device (MinION or PromethION), iii) the basecaller variant, and iv) the basecaller version
     # with the format: {pore}_{device}_{caller variant}_{caller version}
     # See https://github.com/nanoporetech/medaka#models for more information.
@@ -86,7 +86,7 @@ assembly:
     # assemblers used for shotgun sequencing with on Ion Torrent technology
     shotgun: "megahit-std"
     # assemblers used for amplicon sequencing with on Torrent technology
-    amplicon: "spades"
+    amplicon: "megahit-std"
   # minimum posterior probability for a clonal variant to be included in the generated pseudo-assembly
   min-variant-prob: 0.95
 

version.txt

@@ -1 +1 @@
-0.15.1
+0.16.0

workflow/Snakefile

@@ -21,7 +21,7 @@ report: "report/workflow.rst"
 container: "docker://condaforge/mambaforge"
 
 
-containerized: "quay.io/uncovar/uncovar#0.15.1"
+containerized: "quay.io/uncovar/uncovar#0.16.0"
 
 
 include: "rules/common.smk"

workflow/envs/pangolin.yaml

@@ -3,5 +3,4 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - pangolin =4.1.3
-  - tabulate <0.9 # TODO remove once pangolin 4.1.3 is available in bioconda
+  - pangolin =4.3

workflow/envs/varlociraptor.yaml

@@ -3,4 +3,4 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - varlociraptor =6.0
+  - varlociraptor =8.4

workflow/scripts/masking.py

@@ -48,7 +48,6 @@ def get_base_count(pileupcolumn):
     for pileupread in pileupcolumn.pileups:
         # TODO Check pileupread for missing bases
         if not pileupread.is_del and not pileupread.is_refskip:
-
             read_base = pileupread.alignment.query_sequence[pileupread.query_position]
 
             bases.append(read_base)
@@ -102,7 +101,6 @@ def mask_sequence(sequence, coverages, base_counts):
     covered_postions = coverages.keys()
 
     for position, base in enumerate(sequence):
-
         if position not in covered_postions:
             # TODO Check why there are postions that are not covered by any reads and are not Ns
             # sequence[position] = "N"
@@ -160,10 +158,8 @@ def mask_sequence(sequence, coverages, base_counts):
 
 
 def write_sequence(sequence):
-    with pysam.FastxFile(snakemake.input.sequence) as infile, open(
-        snakemake.output.masked_sequence, mode="w"
-    ) as outfile:
-        print(">%s" % next(infile).name.split(".")[0], file=outfile)
+    with open(snakemake.output.masked_sequence, mode="w") as outfile:
+        print(">%s" % snakemake.wildcards.sample, file=outfile)
         print(sequence, file=outfile)
 
 

workflow/scripts/quality-filter.py

@@ -31,13 +31,11 @@ def get_identity(quast_report_paths: List[str]) -> dict:
         sample = path.dirname(report_path).split("/")[-1]
 
         # load report
-        report_df = pd.read_csv(
-            report_path, delimiter="\t", index_col=0, squeeze=True, names=["value"]
-        )
-
+        report_df = pd.read_csv(report_path, delimiter="\t", names=["name", "value"])
+        report_df.set_index("name", inplace=True)
         # select genome fraction (%)
         try:
-            fraction = float(report_df.at["Genome fraction (%)"]) / 100
+            fraction = float(report_df.at["Genome fraction (%)", "value"]) / 100
         except:
             # no "Genome fraction (%)" in quast report. Case for not assemblable samples
             fraction = 0.0