From 711045acd4ab2cb2260350d2413a385f4a5d6bdf Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Fri, 1 Jul 2022 11:11:19 +0200
Subject: [PATCH 01/43] refactor: fgbio read clipping (#545)

* change primer file formatting

* change read clipping

* fmt

* fix primer clipping plot

* fix primer clipping plot

* fix

* fix

* typo

* test
---
 workflow/rules/read_clipping.smk              | 51 +++++++------------
 .../{bed-to-bedpe.py => bed-to-tsv.py}        |  5 +-
 workflow/scripts/plot-primer-clipping.py      |  8 +--
 3 files changed, 25 insertions(+), 39 deletions(-)
 rename workflow/scripts/{bed-to-bedpe.py => bed-to-tsv.py} (85%)

diff --git a/workflow/rules/read_clipping.smk b/workflow/rules/read_clipping.smk
index 8abdde7ed..4502dfcbb 100644
--- a/workflow/rules/read_clipping.smk
+++ b/workflow/rules/read_clipping.smk
@@ -21,63 +21,48 @@ rule samtools_sort:
         "0.74.0/bio/samtools/sort"
 
 
-rule bed_to_bedpe:
+rule bed_to_tsv:
     input:
         check_bed_for_URL(config["preprocessing"]["amplicon-primers"]),
     output:
-        "resources/primer.bedpe",
+        "resources/primer.tsv",
     log:
         "logs/bed-to-bedpe.log",
     conda:
         "../envs/python.yaml"
     script:
-        "../scripts/bed-to-bedpe.py"
+        "../scripts/bed-to-tsv.py"
 
 
-rule bamclipper:
+rule trim_primers_fgbio:
     input:
         bam="results/{date}/read-sorted/{read_type}~position/{sample}.initial.bam",
         bai="results/{date}/read-sorted/{read_type}~position/{sample}.initial.bam.bai",
-        bedpe="resources/primer.bedpe",
-    output:
-        temp(
-            "results/{date}/read-clipping/softclipped/{read_type}/{sample}/{sample}.initial.primerclipped.bam"
+        ref="resources/genomes/{reference}.fasta".format(
+            reference=config["preprocessing"]["amplicon-reference"]
         ),
-    params:
-        output_dir=get_output_dir,
-        cwd=lambda w: os.getcwd(),
-        bed_path=lambda w, input: os.path.join(os.getcwd(), input.bedpe),
-        bam=lambda w, input: os.path.basename(input.bam),
+        primers="resources/primer.tsv",
+    output:
+        "results/{date}/read-clipping/hardclipped/{read_type}/{sample}/{sample}.bam",
     log:
-        "logs/{date}/bamclipper/{read_type}/{sample}.log",
+        "logs/{date}/fgbio_primer_clipping/{read_type}/{sample}.log",
     conda:
-        "../envs/bamclipper.yaml"
-    threads: 6
+        "../envs/fgbio.yaml"
     shell:
-        "(cp {input.bam} {params.output_dir} &&"
-        " cp {input.bai} {params.output_dir} &&"
-        " cd {params.output_dir} &&"
-        " bamclipper.sh -b {params.bam} -p {params.bed_path} -n {threads} -u 5 -d 5) "
-        " > {params.cwd}/{log} 2>&1"
+        "fgbio TrimPrimers -i {input.bam} -p {input.primers} -o {output} -H true -r {input.ref} > {log} 2>&1"
 
 
-rule fgbio:
+rule filter_bam_fgbio:
     input:
-        bam="results/{date}/read-clipping/softclipped/{read_type}/{sample}/{sample}.initial.primerclipped.bam",
-        bai="results/{date}/read-clipping/softclipped/{read_type}/{sample}/{sample}.initial.primerclipped.bam.bai",
-        ref="resources/genomes/{reference}.fasta".format(
-            reference=config["preprocessing"]["amplicon-reference"]
-        ),
+        bam="results/{date}/read-clipping/hardclipped/{read_type}/{sample}/{sample}.bam",
     output:
-        temp(
-            "results/{date}/read-clipping/hardclipped/{read_type}/{sample}/{sample}.bam"
-        ),
+        "results/{date}/read-clipping/hc_filtered/{read_type}/{sample}/{sample}.bam",
     log:
-        "logs/{date}/fgbio/{read_type}/{sample}.log",
+        "logs/{date}/fgbio_filter_bam/{read_type}/{sample}.log",
     conda:
         "../envs/fgbio.yaml"
     shell:
-        "fgbio --sam-validation-stringency=LENIENT ClipBam -i {input.bam} -o {output} -H true -r {input.ref} > {log} 2>&1"
+        "fgbio FilterBam -i {input.bam} -o {output} --min-insert-size 100 --remove-single-end-mappings > {log} 2>&1"
 
 
 rule samtools_fastq_pe:
@@ -132,7 +117,7 @@ rule plot_primer_clipping:
         ),
     params:
         samples=lambda wildcards: get_samples_for_date(wildcards.date),
-        bedpe="resources/primer.bedpe",
+        bedpe="resources/primer.tsv",
     log:
         "logs/{date}/plot-primer-clipping.log",
     conda:
diff --git a/workflow/scripts/bed-to-bedpe.py b/workflow/scripts/bed-to-tsv.py
similarity index 85%
rename from workflow/scripts/bed-to-bedpe.py
rename to workflow/scripts/bed-to-tsv.py
index 4a3b343df..098a18cb7 100644
--- a/workflow/scripts/bed-to-bedpe.py
+++ b/workflow/scripts/bed-to-tsv.py
@@ -23,10 +23,9 @@
     df_sense["chrom"],
     df_sense["start"],
     df_sense["end"],
-    df_antisense["chrom"],
     df_antisense["start"],
     df_antisense["end"],
 ]
-headers = ["chrom1", "start1", "end1", "chrom2", "start2", "end2"]
+headers = ["chrom", "left_start", "left_end", "right_start", "right_end"]
 df_bedpe = pd.concat(data, axis=1, keys=headers)
-df_bedpe.to_csv(snakemake.output[0], header=None, index=None, sep="\t", mode="a")
+df_bedpe.to_csv(snakemake.output[0], index=None, sep="\t", mode="a")
diff --git a/workflow/scripts/plot-primer-clipping.py b/workflow/scripts/plot-primer-clipping.py
index c6dabb8e3..a99b55a8f 100644
--- a/workflow/scripts/plot-primer-clipping.py
+++ b/workflow/scripts/plot-primer-clipping.py
@@ -13,8 +13,10 @@
 from intervaltree import IntervalTree
 
 # read primer bedpe to df
-PRIMER = pd.read_csv(snakemake.params.get("bedpe", ""), delimiter="\t", header=None)
-PRIMER.drop(PRIMER.columns[[0, 3]], axis=1, inplace=True)
+PRIMER = pd.read_csv(snakemake.params.get("bedpe", ""), delimiter="\t", header=0)
+print(PRIMER)
+PRIMER.drop(PRIMER.columns[[0]], axis=1, inplace=True)
+print(PRIMER)
 PRIMER.columns = ["p1_start", "p1_end", "p2_start", "p2_end"]
 
 # convert df to interval trees
@@ -116,7 +118,7 @@ def count_intervals(file):
                     "uncut primer within",
                     "cut primer exact",
                     "cut primer within",
-                    "no mathing win",
+                    "no matching win",
                 ],
             }
         )

From 08b19cf6377cd7af9f47c4f0557f614e8d591bd9 Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Mon, 4 Jul 2022 11:17:47 +0200
Subject: [PATCH 02/43] Update pangolin to 4.1 (#546)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: thomasbtf <thomasbtf@users.noreply.github.com>
Co-authored-by: Ann-Kathrin Brüggemann <90249112+AKBrueggemann@users.noreply.github.com>
---
 workflow/envs/pangolin.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflow/envs/pangolin.yaml b/workflow/envs/pangolin.yaml
index a36746fcb..2af1a4e7b 100644
--- a/workflow/envs/pangolin.yaml
+++ b/workflow/envs/pangolin.yaml
@@ -2,4 +2,4 @@ channels:
   - bioconda
   - conda-forge
 dependencies:
-  - pangolin =4.0.6
+  - pangolin =4.1

From 57e868e877976324164973234496e99c215eb26f Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Fri, 15 Jul 2022 08:56:58 +0200
Subject: [PATCH 03/43] Update pangolin to 4.1.1 (#547)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: thomasbtf <thomasbtf@users.noreply.github.com>
Co-authored-by: Ann-Kathrin Brüggemann <90249112+AKBrueggemann@users.noreply.github.com>
---
 workflow/envs/pangolin.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflow/envs/pangolin.yaml b/workflow/envs/pangolin.yaml
index 2af1a4e7b..6c35b9d1f 100644
--- a/workflow/envs/pangolin.yaml
+++ b/workflow/envs/pangolin.yaml
@@ -2,4 +2,4 @@ channels:
   - bioconda
   - conda-forge
 dependencies:
-  - pangolin =4.1
+  - pangolin =4.1.1

From 56e46ef7e1663b4de3447068df7cb8b9d1d7b67f Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Tue, 2 Aug 2022 09:09:56 +0200
Subject: [PATCH 04/43] fix: disable ont actions (#555)

---
 .github/workflows/main.yml | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 0be53d2b3..fbc4299df 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -67,7 +67,9 @@ jobs:
     strategy:
       matrix:
         rule: [all, all -npr]
-        technology: [all, illumina, ont, ion]
+        # disable ont actions
+        # technology: [all, illumina, ont, ion]
+        technology: [all, illumina, ion]
         seq_method: [shotgun, amplicon]
     steps:
       - uses: actions/checkout@v2
@@ -85,11 +87,9 @@ jobs:
           mkdir -p .tests/data
           curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/B.1.1.7.reads.1.fastq.gz > .tests/data/B117.1.fastq.gz
           curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/B.1.1.7.reads.1.fastq.gz > .tests/data/B117.2.fastq.gz
-          curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/ont_reads.fastq.gz > .tests/data/ont_reads.fastq.gz
           curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/ERR5745913.fastq.gz > .tests/data/ion_reads.fastq.gz
           echo sample_name,fq1,fq2,date,is_amplicon_data,technology > .tests/config/pep/samples.csv
           echo illumina-test,data/B117.1.fastq.gz,data/B117.2.fastq.gz,2022-01-01,$AMPLICON,illumina >> .tests/config/pep/samples.csv
-          echo ont-test,data/ont_reads.fastq.gz,,2022-01-01,$AMPLICON,ont >> .tests/config/pep/samples.csv
           echo ion-test,data/ion_reads.fastq.gz,,2022-01-01,$AMPLICON,ion >> .tests/config/pep/samples.csv
       - name: Prepare test data for Illumina
         if: steps.test-data.outputs.cache-hit != true && (startsWith(matrix.rule, 'all') && matrix.technology == 'illumina' || matrix.rule == 'compare_assemblers')
@@ -100,14 +100,14 @@ jobs:
           curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/B.1.1.7.reads.1.fastq.gz > .tests/data/B117.2.fastq.gz
           echo sample_name,fq1,fq2,date,is_amplicon_data,technology > .tests/config/pep/samples.csv
           echo illumina-test,data/B117.1.fastq.gz,data/B117.2.fastq.gz,2022-01-01,$AMPLICON,illumina >> .tests/config/pep/samples.csv
-      - name: Prepare test data for Oxford Nanopore
-        if: steps.test-data.outputs.cache-hit != true && (startsWith(matrix.rule, 'all') && matrix.technology == 'ont' || matrix.rule == 'compare_assemblers')
-        run: |
-          if [[ "${{ matrix.seq_method }}"  = "shotgun" ]] ; then export AMPLICON=0; else export AMPLICON=1; fi
-          mkdir -p .tests/data
-          curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/ont_reads.fastq.gz > .tests/data/ont_reads.fastq.gz
-          echo sample_name,fq1,date,is_amplicon_data,technology > .tests/config/pep/samples.csv
-          echo ont-test,data/ont_reads.fastq.gz,2022-01-01,$AMPLICON,ont >> .tests/config/pep/samples.csv
+      # - name: Prepare test data for Oxford Nanopore
+      #   if: steps.test-data.outputs.cache-hit != true && (startsWith(matrix.rule, 'all') && matrix.technology == 'ont' || matrix.rule == 'compare_assemblers')
+      #   run: |
+      #     if [[ "${{ matrix.seq_method }}"  = "shotgun" ]] ; then export AMPLICON=0; else export AMPLICON=1; fi
+      #     mkdir -p .tests/data
+      #     curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/ont_reads.fastq.gz > .tests/data/ont_reads.fastq.gz
+      #     echo sample_name,fq1,date,is_amplicon_data,technology > .tests/config/pep/samples.csv
+      #     echo ont-test,data/ont_reads.fastq.gz,2022-01-01,$AMPLICON,ont >> .tests/config/pep/samples.csv
       - name: Prepare test data for Ion Torrent
         if: steps.test-data.outputs.cache-hit != true && (startsWith(matrix.rule, 'all') && matrix.technology == 'ion' || matrix.rule == 'compare_assemblers')
         run: |
@@ -176,15 +176,14 @@ jobs:
       - Pre-Commit
     strategy:
       matrix:
-        rule:
-          [
+        rule: [
             benchmark_strain_calling,
             benchmark_assembly,
             benchmark_mixtures,
             benchmark_non_sars_cov_2,
             benchmark_reads,
             compare_assemblers,
-            generate_test_cases,
+            # generate_test_cases,
           ]
     steps:
       - uses: actions/checkout@v2

From 2c2bde32b0bdf00fccd9eba39a0e8d974f448ffd Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Tue, 2 Aug 2022 10:33:56 +0200
Subject: [PATCH 05/43] Revert "refactor: fgbio read clipping (#545)" (#551)

---
 workflow/rules/read_clipping.smk              | 51 ++++++++++++-------
 .../{bed-to-tsv.py => bed-to-bedpe.py}        |  5 +-
 workflow/scripts/plot-primer-clipping.py      |  8 ++-
 3 files changed, 39 insertions(+), 25 deletions(-)
 rename workflow/scripts/{bed-to-tsv.py => bed-to-bedpe.py} (85%)

diff --git a/workflow/rules/read_clipping.smk b/workflow/rules/read_clipping.smk
index 4502dfcbb..8abdde7ed 100644
--- a/workflow/rules/read_clipping.smk
+++ b/workflow/rules/read_clipping.smk
@@ -21,48 +21,63 @@ rule samtools_sort:
         "0.74.0/bio/samtools/sort"
 
 
-rule bed_to_tsv:
+rule bed_to_bedpe:
     input:
         check_bed_for_URL(config["preprocessing"]["amplicon-primers"]),
     output:
-        "resources/primer.tsv",
+        "resources/primer.bedpe",
     log:
         "logs/bed-to-bedpe.log",
     conda:
         "../envs/python.yaml"
     script:
-        "../scripts/bed-to-tsv.py"
+        "../scripts/bed-to-bedpe.py"
 
 
-rule trim_primers_fgbio:
+rule bamclipper:
     input:
         bam="results/{date}/read-sorted/{read_type}~position/{sample}.initial.bam",
         bai="results/{date}/read-sorted/{read_type}~position/{sample}.initial.bam.bai",
-        ref="resources/genomes/{reference}.fasta".format(
-            reference=config["preprocessing"]["amplicon-reference"]
-        ),
-        primers="resources/primer.tsv",
+        bedpe="resources/primer.bedpe",
     output:
-        "results/{date}/read-clipping/hardclipped/{read_type}/{sample}/{sample}.bam",
+        temp(
+            "results/{date}/read-clipping/softclipped/{read_type}/{sample}/{sample}.initial.primerclipped.bam"
+        ),
+    params:
+        output_dir=get_output_dir,
+        cwd=lambda w: os.getcwd(),
+        bed_path=lambda w, input: os.path.join(os.getcwd(), input.bedpe),
+        bam=lambda w, input: os.path.basename(input.bam),
     log:
-        "logs/{date}/fgbio_primer_clipping/{read_type}/{sample}.log",
+        "logs/{date}/bamclipper/{read_type}/{sample}.log",
     conda:
-        "../envs/fgbio.yaml"
+        "../envs/bamclipper.yaml"
+    threads: 6
     shell:
-        "fgbio TrimPrimers -i {input.bam} -p {input.primers} -o {output} -H true -r {input.ref} > {log} 2>&1"
+        "(cp {input.bam} {params.output_dir} &&"
+        " cp {input.bai} {params.output_dir} &&"
+        " cd {params.output_dir} &&"
+        " bamclipper.sh -b {params.bam} -p {params.bed_path} -n {threads} -u 5 -d 5) "
+        " > {params.cwd}/{log} 2>&1"
 
 
-rule filter_bam_fgbio:
+rule fgbio:
     input:
-        bam="results/{date}/read-clipping/hardclipped/{read_type}/{sample}/{sample}.bam",
+        bam="results/{date}/read-clipping/softclipped/{read_type}/{sample}/{sample}.initial.primerclipped.bam",
+        bai="results/{date}/read-clipping/softclipped/{read_type}/{sample}/{sample}.initial.primerclipped.bam.bai",
+        ref="resources/genomes/{reference}.fasta".format(
+            reference=config["preprocessing"]["amplicon-reference"]
+        ),
     output:
-        "results/{date}/read-clipping/hc_filtered/{read_type}/{sample}/{sample}.bam",
+        temp(
+            "results/{date}/read-clipping/hardclipped/{read_type}/{sample}/{sample}.bam"
+        ),
     log:
-        "logs/{date}/fgbio_filter_bam/{read_type}/{sample}.log",
+        "logs/{date}/fgbio/{read_type}/{sample}.log",
     conda:
         "../envs/fgbio.yaml"
     shell:
-        "fgbio FilterBam -i {input.bam} -o {output} --min-insert-size 100 --remove-single-end-mappings > {log} 2>&1"
+        "fgbio --sam-validation-stringency=LENIENT ClipBam -i {input.bam} -o {output} -H true -r {input.ref} > {log} 2>&1"
 
 
 rule samtools_fastq_pe:
@@ -117,7 +132,7 @@ rule plot_primer_clipping:
         ),
     params:
         samples=lambda wildcards: get_samples_for_date(wildcards.date),
-        bedpe="resources/primer.tsv",
+        bedpe="resources/primer.bedpe",
     log:
         "logs/{date}/plot-primer-clipping.log",
     conda:
diff --git a/workflow/scripts/bed-to-tsv.py b/workflow/scripts/bed-to-bedpe.py
similarity index 85%
rename from workflow/scripts/bed-to-tsv.py
rename to workflow/scripts/bed-to-bedpe.py
index 098a18cb7..4a3b343df 100644
--- a/workflow/scripts/bed-to-tsv.py
+++ b/workflow/scripts/bed-to-bedpe.py
@@ -23,9 +23,10 @@
     df_sense["chrom"],
     df_sense["start"],
     df_sense["end"],
+    df_antisense["chrom"],
     df_antisense["start"],
     df_antisense["end"],
 ]
-headers = ["chrom", "left_start", "left_end", "right_start", "right_end"]
+headers = ["chrom1", "start1", "end1", "chrom2", "start2", "end2"]
 df_bedpe = pd.concat(data, axis=1, keys=headers)
-df_bedpe.to_csv(snakemake.output[0], index=None, sep="\t", mode="a")
+df_bedpe.to_csv(snakemake.output[0], header=None, index=None, sep="\t", mode="a")
diff --git a/workflow/scripts/plot-primer-clipping.py b/workflow/scripts/plot-primer-clipping.py
index a99b55a8f..c6dabb8e3 100644
--- a/workflow/scripts/plot-primer-clipping.py
+++ b/workflow/scripts/plot-primer-clipping.py
@@ -13,10 +13,8 @@
 from intervaltree import IntervalTree
 
 # read primer bedpe to df
-PRIMER = pd.read_csv(snakemake.params.get("bedpe", ""), delimiter="\t", header=0)
-print(PRIMER)
-PRIMER.drop(PRIMER.columns[[0]], axis=1, inplace=True)
-print(PRIMER)
+PRIMER = pd.read_csv(snakemake.params.get("bedpe", ""), delimiter="\t", header=None)
+PRIMER.drop(PRIMER.columns[[0, 3]], axis=1, inplace=True)
 PRIMER.columns = ["p1_start", "p1_end", "p2_start", "p2_end"]
 
 # convert df to interval trees
@@ -118,7 +116,7 @@ def count_intervals(file):
                     "uncut primer within",
                     "cut primer exact",
                     "cut primer within",
-                    "no matching win",
+                    "no mathing win",
                 ],
             }
         )

From d7539105fdd201e10ae5974ea7057af492f3f29a Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Tue, 2 Aug 2022 10:56:20 +0200
Subject: [PATCH 06/43] Update pangolin to 4.1.2 (#550)

---
 workflow/envs/pangolin.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflow/envs/pangolin.yaml b/workflow/envs/pangolin.yaml
index 6c35b9d1f..4cbee4451 100644
--- a/workflow/envs/pangolin.yaml
+++ b/workflow/envs/pangolin.yaml
@@ -2,4 +2,4 @@ channels:
   - bioconda
   - conda-forge
 dependencies:
-  - pangolin =4.1.1
+  - pangolin =4.1.2

From cf2e08e1696b0233104e51ddf09d500ee6d60fa5 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Tue, 2 Aug 2022 13:49:02 +0200
Subject: [PATCH 07/43] chore(deps): bump actions/setup-python from 3 to 4.1.0
 (#548)

---
 .github/workflows/documentation.yml | 2 +-
 .github/workflows/main.yml          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/documentation.yml b/.github/workflows/documentation.yml
index f2aa22e9d..226a47ce4 100644
--- a/.github/workflows/documentation.yml
+++ b/.github/workflows/documentation.yml
@@ -21,7 +21,7 @@ jobs:
       - uses: actions/checkout@v2
 
       - name: SetUp Python
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v4
         with:
           python-version: 3.x
 
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index fbc4299df..042365385 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -53,7 +53,7 @@ jobs:
     if: github.ref != 'refs/heads/master'
     steps:
       - uses: actions/checkout@v2
-      - uses: actions/setup-python@v3
+      - uses: actions/setup-python@v4
       - uses: pre-commit/action@v3.0.0
 
   Technology-Tests:

From bb00f7836500c28bf5eeb0e5f7c1d8e66a3318d8 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Tue, 2 Aug 2022 16:47:12 +0200
Subject: [PATCH 08/43] chore(deps): bump github/super-linter from 4.9.2 to
 4.9.4 (#540)

---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 042365385..160074f69 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -24,7 +24,7 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - name: Formatting
-        uses: github/super-linter@v4.9.2
+        uses: github/super-linter@v4.9.4
         env:
           VALIDATE_ALL_CODEBASE: false
           DEFAULT_BRANCH: master

From a4951a60f16548e93cbc99d0544eef4837fb2a19 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Wed, 3 Aug 2022 11:06:33 +0200
Subject: [PATCH 09/43] chore(deps): bump github/super-linter from 4.9.4 to
 4.9.6 (#557)

Bumps [github/super-linter](https://github.com/github/super-linter) from 4.9.4 to 4.9.6.
- [Release notes](https://github.com/github/super-linter/releases)
- [Changelog](https://github.com/github/super-linter/blob/main/docs/release-process.md)
- [Commits](https://github.com/github/super-linter/compare/v4.9.4...v4.9.6)

---
updated-dependencies:
- dependency-name: github/super-linter
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 160074f69..c0e32dfed 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -24,7 +24,7 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - name: Formatting
-        uses: github/super-linter@v4.9.4
+        uses: github/super-linter@v4.9.6
         env:
           VALIDATE_ALL_CODEBASE: false
           DEFAULT_BRANCH: master

From a0b6fd0557b7e6cb3aeddd22e6a3350560c18415 Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Wed, 12 Oct 2022 16:07:19 +0200
Subject: [PATCH 10/43] fix: update channel priorities and snakemake wrappers
 (#562)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* change channel priorities in all environments

* fix

* change python version

* fix typo

* remove stage in

* revert python version pinning

* updated versions of wrappers in rules

* removed dependency of entrez-direct from entrez.yaml as a test because of error message

* fix entrez env

* Update bcftools concat wrapper

* update bcftools concat wrapper

* bump to latest entrez

* fix output file names for bwa index wrappers

* adapt sort argument of bwa mem wrapper to latest version

* adapt mark duplicates to wrapper changes

* bump pangolin

* requre older tabulate version

* fmt

* try bumping notebook version

* fix: notebook versions

* fix wrapper name

* bump bcftools concat wrapper

* updated and checked all wrappers

* cleanup

* fix extra args

Co-authored-by: lenakinzel <l.kinzel@web.de>
Co-authored-by: Johannes Köster <johannes.koester@tu-dortmund.de>
Co-authored-by: Johannes Köster <johannes.koester@uni-due.de>
---
 .github/workflows/main.yml                    |  1 -
 workflow/envs/abyss.yaml                      |  3 ++-
 workflow/envs/bamclipper.yaml                 |  3 ++-
 workflow/envs/bcftools.yaml                   |  3 ++-
 workflow/envs/bedtools.yaml                   |  3 ++-
 workflow/envs/canu.yaml                       |  3 ++-
 workflow/envs/delly.yaml                      |  3 ++-
 workflow/envs/entrez.yaml                     |  5 ++--
 workflow/envs/fgbio.yaml                      |  3 ++-
 workflow/envs/genometools.yaml                |  3 ++-
 workflow/envs/gff3sort.yaml                   |  3 ++-
 workflow/envs/kraken.yaml                     |  3 ++-
 workflow/envs/longshot.yaml                   |  2 ++
 workflow/envs/mason.yaml                      |  3 ++-
 workflow/envs/medaka.yaml                     |  3 ++-
 workflow/envs/megahit.yaml                    |  3 ++-
 workflow/envs/minimap2.yaml                   |  3 ++-
 workflow/envs/multiqc.yaml                    |  3 ++-
 workflow/envs/nanofilt.yaml                   |  3 ++-
 workflow/envs/nanoqc.yaml                     |  2 ++
 workflow/envs/notramp.yaml                    |  3 ++-
 workflow/envs/pangolin.yaml                   |  4 ++-
 workflow/envs/pysam.yaml                      |  1 +
 workflow/envs/python.yaml                     |  1 +
 workflow/envs/quast.yaml                      |  3 ++-
 workflow/envs/ragoo.yaml                      |  3 ++-
 workflow/envs/rbt.yaml                        |  3 ++-
 workflow/envs/samtools.yaml                   |  3 ++-
 workflow/envs/seqtk.yaml                      |  3 ++-
 workflow/envs/snakemake.yaml                  |  3 ++-
 workflow/envs/sourmash.yaml                   |  3 ++-
 workflow/envs/spades.yaml                     |  3 ++-
 workflow/envs/svn.yaml                        |  1 +
 workflow/envs/tabix.yaml                      |  3 ++-
 workflow/envs/trinity.yaml                    |  4 +--
 workflow/envs/ucsc.yaml                       |  3 ++-
 workflow/envs/unix.yaml                       |  3 ++-
 workflow/envs/varlociraptor.yaml              |  3 ++-
 workflow/envs/velvet.yaml                     |  3 ++-
 .../assembly-benchmark-results.py.ipynb       |  2 +-
 workflow/notebooks/call-strains.py.ipynb      |  2 +-
 .../plot-all-strains-kallisto.py.ipynb        |  2 +-
 .../plot-all-strains-pangolin.py.ipynb        |  2 +-
 workflow/notebooks/plot-read-call.py.ipynb    |  2 +-
 .../notebooks/plot-strains-kallisto.py.ipynb  |  2 +-
 .../notebooks/test-benchmark-results.py.ipynb |  2 +-
 workflow/rules/common.smk                     |  4 ---
 workflow/rules/lineage_variant_calling.smk    |  9 +++++++
 workflow/rules/qc.smk                         | 12 ++++-----
 workflow/rules/read_clipping.smk              |  3 +--
 workflow/rules/read_mapping.smk               | 27 +++++++------------
 workflow/rules/read_trimming.smk              |  4 +--
 workflow/rules/strain_calling.smk             |  6 ++---
 workflow/rules/utils.smk                      |  6 ++---
 workflow/rules/variant_annotation.smk         |  4 +--
 workflow/rules/variant_calling.smk            | 14 +++++-----
 workflow/rules/variant_filtration.smk         | 10 +++----
 57 files changed, 129 insertions(+), 95 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index c0e32dfed..f2ff33e4d 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -133,7 +133,6 @@ jobs:
       - name: Test rule ${{ matrix.rule }} on ${{ matrix.technology }} ${{ matrix.seq_method }} data
         uses: snakemake/snakemake-github-action@v1.24.0
         with:
-          stagein: mamba env create -f workflow/envs/trinity.yaml -n trinity
           directory: .tests
           snakefile: workflow/Snakefile
           args: "-pr --use-conda --show-failed-logs --cores 2 --resources ncbi_api_requests=1 --conda-cleanup-pkgs cache --conda-frontend mamba ${{ matrix.rule }}"
diff --git a/workflow/envs/abyss.yaml b/workflow/envs/abyss.yaml
index d108c4bbe..d78e585d5 100644
--- a/workflow/envs/abyss.yaml
+++ b/workflow/envs/abyss.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - abyss =2.3.1
diff --git a/workflow/envs/bamclipper.yaml b/workflow/envs/bamclipper.yaml
index 403412f2b..bffea9bdf 100644
--- a/workflow/envs/bamclipper.yaml
+++ b/workflow/envs/bamclipper.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - bamclipper =1.0
   - samtools =1.14 # see https://github.com/merenlab/anvio/issues/1479
diff --git a/workflow/envs/bcftools.yaml b/workflow/envs/bcftools.yaml
index 22df755f9..af0652bb7 100644
--- a/workflow/envs/bcftools.yaml
+++ b/workflow/envs/bcftools.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - bcftools =1.10
diff --git a/workflow/envs/bedtools.yaml b/workflow/envs/bedtools.yaml
index 9a8a4f74c..3df68a030 100644
--- a/workflow/envs/bedtools.yaml
+++ b/workflow/envs/bedtools.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - bedtools =2.30.0
diff --git a/workflow/envs/canu.yaml b/workflow/envs/canu.yaml
index a8fec4951..c181758e3 100644
--- a/workflow/envs/canu.yaml
+++ b/workflow/envs/canu.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   # do not use canu 2.2 !
   - canu =2.1.1
diff --git a/workflow/envs/delly.yaml b/workflow/envs/delly.yaml
index 5e84c3e7e..0915d03b6 100644
--- a/workflow/envs/delly.yaml
+++ b/workflow/envs/delly.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - delly =0.8.7
   - pysam =0.16
diff --git a/workflow/envs/entrez.yaml b/workflow/envs/entrez.yaml
index 3387557de..8378303d8 100644
--- a/workflow/envs/entrez.yaml
+++ b/workflow/envs/entrez.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
-  - entrez-direct =13.9
+  - entrez-direct =16.2
diff --git a/workflow/envs/fgbio.yaml b/workflow/envs/fgbio.yaml
index 14ee90356..51f5e3524 100644
--- a/workflow/envs/fgbio.yaml
+++ b/workflow/envs/fgbio.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - fgbio =1.3
diff --git a/workflow/envs/genometools.yaml b/workflow/envs/genometools.yaml
index 8b295f90f..975fd5b6c 100644
--- a/workflow/envs/genometools.yaml
+++ b/workflow/envs/genometools.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - genometools-genometools =1.6.2
diff --git a/workflow/envs/gff3sort.yaml b/workflow/envs/gff3sort.yaml
index c3a285ae4..d554c69ff 100644
--- a/workflow/envs/gff3sort.yaml
+++ b/workflow/envs/gff3sort.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - gff3sort = 0.1
diff --git a/workflow/envs/kraken.yaml b/workflow/envs/kraken.yaml
index 1e279c562..979d75cff 100644
--- a/workflow/envs/kraken.yaml
+++ b/workflow/envs/kraken.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - kraken2 =2.1.1
   - krona =2.7.1
diff --git a/workflow/envs/longshot.yaml b/workflow/envs/longshot.yaml
index e9874cc14..244a10869 100644
--- a/workflow/envs/longshot.yaml
+++ b/workflow/envs/longshot.yaml
@@ -1,4 +1,6 @@
 channels:
+  - conda-forge
   - bioconda
+  - nodefaults
 dependencies:
   - longshot =0.4
diff --git a/workflow/envs/mason.yaml b/workflow/envs/mason.yaml
index cd253e39e..5025c1576 100644
--- a/workflow/envs/mason.yaml
+++ b/workflow/envs/mason.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - mason =2.0
diff --git a/workflow/envs/medaka.yaml b/workflow/envs/medaka.yaml
index 591aae2cb..dc5efb316 100644
--- a/workflow/envs/medaka.yaml
+++ b/workflow/envs/medaka.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - medaka =1.0
   - tensorflow =1.14
diff --git a/workflow/envs/megahit.yaml b/workflow/envs/megahit.yaml
index 19b84287a..278221b32 100644
--- a/workflow/envs/megahit.yaml
+++ b/workflow/envs/megahit.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - megahit =1.2
diff --git a/workflow/envs/minimap2.yaml b/workflow/envs/minimap2.yaml
index a44e24867..b8696b0df 100644
--- a/workflow/envs/minimap2.yaml
+++ b/workflow/envs/minimap2.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - minimap2 =2.22
diff --git a/workflow/envs/multiqc.yaml b/workflow/envs/multiqc.yaml
index e01cee038..990cfe07c 100644
--- a/workflow/envs/multiqc.yaml
+++ b/workflow/envs/multiqc.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - multiqc =1.11
diff --git a/workflow/envs/nanofilt.yaml b/workflow/envs/nanofilt.yaml
index e845b6fba..5c556e2c4 100644
--- a/workflow/envs/nanofilt.yaml
+++ b/workflow/envs/nanofilt.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - nanofilt =2.8
   - gzip =1.11
diff --git a/workflow/envs/nanoqc.yaml b/workflow/envs/nanoqc.yaml
index 24ef61680..a772998c8 100644
--- a/workflow/envs/nanoqc.yaml
+++ b/workflow/envs/nanoqc.yaml
@@ -1,4 +1,6 @@
 channels:
+  - conda-forge
   - bioconda
+  - nodefaults
 dependencies:
   - nanoqc =0.9
diff --git a/workflow/envs/notramp.yaml b/workflow/envs/notramp.yaml
index 2a57c7ba6..4f35530d1 100644
--- a/workflow/envs/notramp.yaml
+++ b/workflow/envs/notramp.yaml
@@ -1,7 +1,8 @@
 channels:
   - simakro
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - notramp =1.0.5
   - minimap2 =2.22
diff --git a/workflow/envs/pangolin.yaml b/workflow/envs/pangolin.yaml
index 4cbee4451..52f9310fd 100644
--- a/workflow/envs/pangolin.yaml
+++ b/workflow/envs/pangolin.yaml
@@ -1,5 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - pangolin =4.1.2
+  - tabulate <0.9 # TODO remove once pangolin 4.1.3 is available in bioconda
diff --git a/workflow/envs/pysam.yaml b/workflow/envs/pysam.yaml
index 125149cd4..2b748a104 100644
--- a/workflow/envs/pysam.yaml
+++ b/workflow/envs/pysam.yaml
@@ -1,6 +1,7 @@
 channels:
   - conda-forge
   - bioconda
+  - nodefaults
 dependencies:
   - jupyter =1.0
   - pysam =0.16
diff --git a/workflow/envs/python.yaml b/workflow/envs/python.yaml
index 15b460ad8..d918d4686 100644
--- a/workflow/envs/python.yaml
+++ b/workflow/envs/python.yaml
@@ -2,6 +2,7 @@ channels:
   - conda-forge
   - bioconda
   - anaconda
+  - nodefaults
 dependencies:
   - pandas =1.2
   - jupyter =1.0
diff --git a/workflow/envs/quast.yaml b/workflow/envs/quast.yaml
index fd77ea287..3f361e8a3 100644
--- a/workflow/envs/quast.yaml
+++ b/workflow/envs/quast.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - quast =5.0
diff --git a/workflow/envs/ragoo.yaml b/workflow/envs/ragoo.yaml
index 19ba3af9b..3e3edfcd9 100644
--- a/workflow/envs/ragoo.yaml
+++ b/workflow/envs/ragoo.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
   - imperial-college-research-computing
+  - nodefaults
 dependencies:
   - ragoo =1.1
diff --git a/workflow/envs/rbt.yaml b/workflow/envs/rbt.yaml
index c02a4aa57..b587821b4 100644
--- a/workflow/envs/rbt.yaml
+++ b/workflow/envs/rbt.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - rust-bio-tools =0.39
diff --git a/workflow/envs/samtools.yaml b/workflow/envs/samtools.yaml
index 8de8caf4e..5c86db4c8 100644
--- a/workflow/envs/samtools.yaml
+++ b/workflow/envs/samtools.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - samtools =1.14
diff --git a/workflow/envs/seqtk.yaml b/workflow/envs/seqtk.yaml
index 101cc3c9d..3db1b1995 100644
--- a/workflow/envs/seqtk.yaml
+++ b/workflow/envs/seqtk.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - seqtk =1.3
diff --git a/workflow/envs/snakemake.yaml b/workflow/envs/snakemake.yaml
index 522c65b4d..bf82582ac 100644
--- a/workflow/envs/snakemake.yaml
+++ b/workflow/envs/snakemake.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - snakemake =7.0
diff --git a/workflow/envs/sourmash.yaml b/workflow/envs/sourmash.yaml
index f24fcfd79..8182f7cea 100644
--- a/workflow/envs/sourmash.yaml
+++ b/workflow/envs/sourmash.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - sourmash =3.5
diff --git a/workflow/envs/spades.yaml b/workflow/envs/spades.yaml
index 4e37a04a2..d88fde2cb 100644
--- a/workflow/envs/spades.yaml
+++ b/workflow/envs/spades.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - spades =3.15
diff --git a/workflow/envs/svn.yaml b/workflow/envs/svn.yaml
index 19014f0ed..f803222eb 100644
--- a/workflow/envs/svn.yaml
+++ b/workflow/envs/svn.yaml
@@ -1,4 +1,5 @@
 channels:
   - anaconda
+  - nodefaults
 dependencies:
   - svn =1.10
diff --git a/workflow/envs/tabix.yaml b/workflow/envs/tabix.yaml
index 6db26455c..7fa9caf2c 100644
--- a/workflow/envs/tabix.yaml
+++ b/workflow/envs/tabix.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - tabix =0.2
   - curl
diff --git a/workflow/envs/trinity.yaml b/workflow/envs/trinity.yaml
index 90993fc33..8476259a8 100644
--- a/workflow/envs/trinity.yaml
+++ b/workflow/envs/trinity.yaml
@@ -1,7 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
-  - defaults
+  - bioconda
+  - nodefaults
 dependencies:
   - trinity =2.13
   # ensure that we use a bowtie2 that already contains fixed dependency constraints
diff --git a/workflow/envs/ucsc.yaml b/workflow/envs/ucsc.yaml
index 46f35cd28..47e50dbbd 100644
--- a/workflow/envs/ucsc.yaml
+++ b/workflow/envs/ucsc.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - ucsc-bigbedtobed =377
diff --git a/workflow/envs/unix.yaml b/workflow/envs/unix.yaml
index f1899ae37..56a2099aa 100644
--- a/workflow/envs/unix.yaml
+++ b/workflow/envs/unix.yaml
@@ -1,6 +1,7 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - curl
   - sed
diff --git a/workflow/envs/varlociraptor.yaml b/workflow/envs/varlociraptor.yaml
index 10b6135e9..39ff16514 100644
--- a/workflow/envs/varlociraptor.yaml
+++ b/workflow/envs/varlociraptor.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - varlociraptor =4.9
diff --git a/workflow/envs/velvet.yaml b/workflow/envs/velvet.yaml
index eca4e7763..6c7e886a1 100644
--- a/workflow/envs/velvet.yaml
+++ b/workflow/envs/velvet.yaml
@@ -1,5 +1,6 @@
 channels:
-  - bioconda
   - conda-forge
+  - bioconda
+  - nodefaults
 dependencies:
   - velvet =1.2
diff --git a/workflow/notebooks/assembly-benchmark-results.py.ipynb b/workflow/notebooks/assembly-benchmark-results.py.ipynb
index d8aa95695..46e7dbc64 100644
--- a/workflow/notebooks/assembly-benchmark-results.py.ipynb
+++ b/workflow/notebooks/assembly-benchmark-results.py.ipynb
@@ -197,5 +197,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 5
 }
diff --git a/workflow/notebooks/call-strains.py.ipynb b/workflow/notebooks/call-strains.py.ipynb
index ff610b737..686f045a9 100644
--- a/workflow/notebooks/call-strains.py.ipynb
+++ b/workflow/notebooks/call-strains.py.ipynb
@@ -74,5 +74,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 5
 }
diff --git a/workflow/notebooks/plot-all-strains-kallisto.py.ipynb b/workflow/notebooks/plot-all-strains-kallisto.py.ipynb
index abe135106..24b3e31aa 100644
--- a/workflow/notebooks/plot-all-strains-kallisto.py.ipynb
+++ b/workflow/notebooks/plot-all-strains-kallisto.py.ipynb
@@ -53,5 +53,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 5
 }
diff --git a/workflow/notebooks/plot-all-strains-pangolin.py.ipynb b/workflow/notebooks/plot-all-strains-pangolin.py.ipynb
index 502048479..7785d2b1d 100644
--- a/workflow/notebooks/plot-all-strains-pangolin.py.ipynb
+++ b/workflow/notebooks/plot-all-strains-pangolin.py.ipynb
@@ -46,5 +46,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 5
 }
diff --git a/workflow/notebooks/plot-read-call.py.ipynb b/workflow/notebooks/plot-read-call.py.ipynb
index aab051f9a..3ccc4d147 100644
--- a/workflow/notebooks/plot-read-call.py.ipynb
+++ b/workflow/notebooks/plot-read-call.py.ipynb
@@ -100,5 +100,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 5
 }
diff --git a/workflow/notebooks/plot-strains-kallisto.py.ipynb b/workflow/notebooks/plot-strains-kallisto.py.ipynb
index c2a26048a..bcfede786 100644
--- a/workflow/notebooks/plot-strains-kallisto.py.ipynb
+++ b/workflow/notebooks/plot-strains-kallisto.py.ipynb
@@ -60,5 +60,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 5
 }
diff --git a/workflow/notebooks/test-benchmark-results.py.ipynb b/workflow/notebooks/test-benchmark-results.py.ipynb
index 038f91089..616ac7ec7 100644
--- a/workflow/notebooks/test-benchmark-results.py.ipynb
+++ b/workflow/notebooks/test-benchmark-results.py.ipynb
@@ -52,5 +52,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 5
 }
diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index 6400076ac..d29581213 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -386,10 +386,6 @@ def get_reference(suffix=""):
     return inner
 
 
-def get_bwa_index_prefix(index_paths):
-    return os.path.splitext(index_paths[0])[0]
-
-
 def get_reads(wildcards):
     # alignment against the human reference genome is done with trimmed reads,
     # since this alignment is used to generate the ordered, non human reads
diff --git a/workflow/rules/lineage_variant_calling.smk b/workflow/rules/lineage_variant_calling.smk
index 3f6bbeed1..f50053f1f 100644
--- a/workflow/rules/lineage_variant_calling.smk
+++ b/workflow/rules/lineage_variant_calling.smk
@@ -48,6 +48,15 @@ rule generate_lineage_variant_table:
         "../scripts/generate-lineage-variant-table.py"
 
 
+rule get_lineage_variant_table:
+    input:
+        expand(
+            "results/{date}/lineage-variant-report/{sample}.csv",
+            date="2022-05-16",
+            sample=get_samples_for_date("2022-05-16"),
+        ),
+
+
 use rule overview_table_html as generate_lineage_variant_report with:
     input:
         "results/{date}/lineage-variant-report/{sample}.csv",
diff --git a/workflow/rules/qc.smk b/workflow/rules/qc.smk
index 5e1e26231..d45cd0a38b 100644
--- a/workflow/rules/qc.smk
+++ b/workflow/rules/qc.smk
@@ -13,7 +13,7 @@ rule fastqc:
     log:
         "logs/{date}/fastqc/{sample}.log",
     wrapper:
-        "0.69.0/bio/fastqc"
+        "v1.12.2/bio/fastqc"
 
 
 # TODO Change multiqc rules back to MultiQC wrapper once v1.11 is released
@@ -38,13 +38,13 @@ rule multiqc:
     output:
         "results/{date}/qc/multiqc.html",
     params:
-        params=(
+        extra=(
             "--config config/multiqc_config.yaml --title 'Results for data from {date}'"
         ),
     log:
         "logs/{date}/multiqc.log",
     wrapper:
-        "v0.86.0/bio/multiqc"
+        "v1.15.1/bio/multiqc"
 
 
 rule multiqc_lab:
@@ -66,11 +66,11 @@ rule multiqc_lab:
             subcategory="1. Quality Control",
         ),
     params:
-        params="--config config/multiqc_config_lab.yaml --title 'Results for data from {date}'",
+        extra="--config config/multiqc_config_lab.yaml --title 'Results for data from {date}'",
     log:
         "logs/{date}/multiqc.log",
     wrapper:
-        "v0.86.0/bio/multiqc"
+        "v1.15.1/bio/multiqc"
 
 
 rule samtools_flagstat:
@@ -81,7 +81,7 @@ rule samtools_flagstat:
     log:
         "logs/{date}/samtools/{sample}_flagstat.log",
     wrapper:
-        "0.70.0/bio/samtools/flagstat"
+        "v1.15.1/bio/samtools/flagstat"
 
 
 rule samtools_depth:
diff --git a/workflow/rules/read_clipping.smk b/workflow/rules/read_clipping.smk
index 8abdde7ed..8d93acc74 100644
--- a/workflow/rules/read_clipping.smk
+++ b/workflow/rules/read_clipping.smk
@@ -13,12 +13,11 @@ rule samtools_sort:
         extra=(
             lambda wildcards: "-n -m 4G" if wildcards.sorted_by == "name" else "-m 4G"
         ),
-        tmp_dir="/tmp/",
     log:
         "logs/{date}/sort-bam/{read_type}~{sorted_by}/{sample}.{stage}.log",
     threads: 8
     wrapper:
-        "0.74.0/bio/samtools/sort"
+        "v1.15.1/bio/samtools/sort"
 
 
 rule bed_to_bedpe:
diff --git a/workflow/rules/read_mapping.smk b/workflow/rules/read_mapping.smk
index b4b2243b2..5c369aef5 100644
--- a/workflow/rules/read_mapping.smk
+++ b/workflow/rules/read_mapping.smk
@@ -8,7 +8,7 @@ rule bwa_index:
     input:
         get_reference(),
     output:
-        multiext(
+        idx=multiext(
             "results/{date}/bwa/index/ref~{reference}.fasta",
             ".amb",
             ".ann",
@@ -16,19 +16,17 @@ rule bwa_index:
             ".pac",
             ".sa",
         ),
-    params:
-        prefix=lambda w, output: get_bwa_index_prefix(output),
     log:
         "logs/{date}/bwa-index/ref~{reference}.log",
     wrapper:
-        "0.69.0/bio/bwa/index"
+        "v1.15.1/bio/bwa/index"
 
 
 rule bwa_large_index:
     input:
         get_reference(),
     output:
-        multiext(
+        idx=multiext(
             "resources/bwa/index/ref~{reference}.fasta",
             ".amb",
             ".ann",
@@ -36,12 +34,10 @@ rule bwa_large_index:
             ".pac",
             ".sa",
         ),
-    params:
-        prefix=lambda w, output: get_bwa_index_prefix(output),
     log:
         "logs/bwa-index/ref~{reference}.log",
     wrapper:
-        "0.69.0/bio/bwa/index"
+        "v1.15.1/bio/bwa/index"
 
 
 rule map_reads:
@@ -53,27 +49,24 @@ rule map_reads:
     log:
         "logs/{date}/bwa-mem/ref~{reference}/{sample}.log",
     params:
-        index=lambda w, input: get_bwa_index_prefix(input.idx),
         extra="",
-        sort="samtools",
+        sorting="samtools",
         sort_order="coordinate",
     threads: 8
     wrapper:
-        "0.69.0/bio/bwa/mem"
+        "v1.15.1/bio/bwa/mem"
 
 
 rule mark_duplicates:
     input:
-        "results/{date}/mapped/ref~{reference}/{sample}.bam",
+        bams="results/{date}/mapped/ref~{reference}/{sample}.bam",
     output:
         bam=temp("results/{date}/dedup/ref~{reference}/{sample}.bam"),
         metrics="results/{date}/qc/dedup/ref~{reference}/{sample}.metrics.txt",
     log:
         "logs/{date}/picard/dedup/ref~{reference}/{sample}.log",
-    params:
-        "",
     wrapper:
-        "0.69.0/bio/picard/markduplicates"
+        "v1.15.1/bio/picard/markduplicates"
 
 
 rule samtools_calmd:
@@ -85,7 +78,7 @@ rule samtools_calmd:
     log:
         "logs/{date}/samtools-calmd/ref~{reference}/{sample}.log",
     params:
-        "-A",
+        extra="-A",
     threads: 8
     wrapper:
-        "0.69.0/bio/samtools/calmd"
+        "v1.15.1/bio/samtools/calmd"
diff --git a/workflow/rules/read_trimming.smk b/workflow/rules/read_trimming.smk
index adad21cb0..0c1f4bdcf 100644
--- a/workflow/rules/read_trimming.smk
+++ b/workflow/rules/read_trimming.smk
@@ -28,7 +28,7 @@ rule fastp_pe:
         "logs/{date}/fastp/fastp-pe/{sample}.log",
     threads: 2
     wrapper:
-        "0.70.0/bio/fastp"
+        "v1.15.1/bio/fastp"
 
 
 rule fastp_se:
@@ -50,4 +50,4 @@ rule fastp_se:
         "results/{date}/trimmed/fastp-se/{sample}.log",
     threads: 2
     wrapper:
-        "0.80.2/bio/fastp"
+        "v1.15.1/bio/fastp"
diff --git a/workflow/rules/strain_calling.smk b/workflow/rules/strain_calling.smk
index 2ace90fe7..0d86db0a5 100644
--- a/workflow/rules/strain_calling.smk
+++ b/workflow/rules/strain_calling.smk
@@ -37,13 +37,11 @@ rule kallisto_index:
         fasta="results/{date}/kallisto/strain-genomes.fasta",
     output:
         index=temp("results/{date}/kallisto/strain-genomes.idx"),
-    params:
-        extra="",
     log:
         "logs/{date}/kallisto-index.log",
     threads: 8
     wrapper:
-        "0.70.0/bio/kallisto/index"
+        "v1.15.1/bio/kallisto/index"
 
 
 rule kallisto_metrics:
@@ -74,7 +72,7 @@ rule kallisto_quant:
         "logs/{date}/kallisto_quant/{sample}.log",
     threads: 8
     wrapper:
-        "0.70.0/bio/kallisto/quant"
+        "v1.15.1/bio/kallisto/quant"
 
 
 rule kallisto_call_strains:
diff --git a/workflow/rules/utils.smk b/workflow/rules/utils.smk
index e9efda07f..0b8749070 100644
--- a/workflow/rules/utils.smk
+++ b/workflow/rules/utils.smk
@@ -14,7 +14,7 @@ rule tabix_index:
     log:
         "logs/tabix-{fmt}/{prefix}.log",
     wrapper:
-        "0.70.0/bio/tabix"
+        "v1.15.1/bio/tabix/index"
 
 
 rule bam_index:
@@ -25,7 +25,7 @@ rule bam_index:
     log:
         "logs/bam-index/{prefix}.log",
     wrapper:
-        "0.70.0/bio/samtools/index"
+        "v1.15.1/bio/samtools/index"
 
 
 rule bcf_index:
@@ -62,7 +62,7 @@ rule faidx:
     log:
         "logs/faidx/{prefix}.log",
     wrapper:
-        "0.70.0/bio/samtools/faidx"
+        "v1.15.1/bio/samtools/faidx"
 
 
 rule gzip:
diff --git a/workflow/rules/variant_annotation.smk b/workflow/rules/variant_annotation.smk
index 687eb73ad..2d58cec4f 100644
--- a/workflow/rules/variant_annotation.smk
+++ b/workflow/rules/variant_annotation.smk
@@ -12,7 +12,7 @@ rule get_vep_plugins:
     log:
         "logs/vep-plugins.log",
     wrapper:
-        "0.69.0/bio/vep/plugins"
+        "v1.15.1/bio/vep/plugins"
 
 
 rule annotate_variants:
@@ -36,4 +36,4 @@ rule annotate_variants:
     log:
         "logs/{date}/vep/{annotation}/{sample}.log",
     wrapper:
-        "0.72.0/bio/vep/annotate"
+        "v1.15.1/bio/vep/annotate"
diff --git a/workflow/rules/variant_calling.smk b/workflow/rules/variant_calling.smk
index 8f757352c..ce9f060ec 100644
--- a/workflow/rules/variant_calling.smk
+++ b/workflow/rules/variant_calling.smk
@@ -10,9 +10,9 @@ rule freebayes:
         ref_idx=get_reference(".fai"),
         # you can have a list of samples here
         samples="results/{date}/recal/ref~{reference}/{sample}.bam",
-        index="results/{date}/recal/ref~{reference}/{sample}.bam.bai",
+        indexes="results/{date}/recal/ref~{reference}/{sample}.bam.bai",
     output:
-        temp("results/{date}/candidate-calls/ref~{reference}/{sample}.small.bcf"),
+        "results/{date}/candidate-calls/ref~{reference}/{sample}.small.bcf",
     params:
         # genotyping is performed by varlociraptor, hence we deactivate it in freebayes by
         # always setting --pooled-continuous
@@ -22,7 +22,7 @@ rule freebayes:
     log:
         "logs/{date}/freebayes/ref~{reference}/{sample}.log",
     wrapper:
-        "0.80.1/bio/freebayes"
+        "v1.15.1/bio/freebayes"
 
 
 # TODO check delly single end mode
@@ -33,7 +33,7 @@ rule delly:
         sample="results/{date}/recal/ref~{reference}/{sample}.bam",
         sample_idx="results/{date}/recal/ref~{reference}/{sample}.bam.bai",
     output:
-        temp("results/{date}/candidate-calls/ref~{reference}/{sample}.structural.bcf"),
+        "results/{date}/candidate-calls/ref~{reference}/{sample}.structural.bcf",
     log:
         "logs/{date}/delly/ref~{reference}/{sample}.log",
     conda:
@@ -100,7 +100,7 @@ rule vcf_2_bcf:
     conda:
         "../envs/bcftools.yaml"
     shell:
-        "bcftools view -Oz -o {output} {input} 2> {log}"
+        "bcftools view -Oz -o {output} {input} 2> {log}"  # TODO -Oz generates a .vcf.gz!!
 
 
 rule render_scenario:
@@ -184,6 +184,6 @@ rule merge_varranges:
     log:
         "logs/{date}/merge-calls/ref~{reference}/{sample}.log",
     params:
-        "-a -Ob",
+        extra="-a",
     wrapper:
-        "0.69.0/bio/bcftools/concat"
+        "v1.15.1/bio/bcftools/concat"
diff --git a/workflow/rules/variant_filtration.smk b/workflow/rules/variant_filtration.smk
index 0c81778c3..ab81d6d2b 100644
--- a/workflow/rules/variant_filtration.smk
+++ b/workflow/rules/variant_filtration.smk
@@ -6,9 +6,9 @@
 
 rule vembrane_filter:
     input:
-        "results/{date}/annotated-calls/ref~main/annot~{annotation}/{sample}.bcf",
+        vcf="results/{date}/annotated-calls/ref~main/annot~{annotation}/{sample}.bcf",
     output:
-        temp(
+        vcf=temp(
             "results/{date}/filtered-calls/ref~main/annot~{annotation}/{sample}.{filter}.bcf"
         ),
     params:
@@ -17,7 +17,7 @@ rule vembrane_filter:
     log:
         "logs/{date}/vembrane/{sample}.{filter}.{annotation}.log",
     wrapper:
-        "0.71.1/bio/vembrane/filter"
+        "v1.15.1/bio/vembrane/filter"
 
 
 rule control_fdr:
@@ -48,6 +48,6 @@ rule merge_calls:
     log:
         "logs/{date}/merge-calls/ref~{reference}/{sample}.{clonality}.{filter}.{annotation}.log",
     params:
-        "-a -Ob",
+        extra="-a",
     wrapper:
-        "0.69.0/bio/bcftools/concat"
+        "v1.15.1/bio/bcftools/concat"

From f34330b9e7228b22411a67cd8002ab21a2d85aca Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Fri, 21 Oct 2022 18:30:24 +0200
Subject: [PATCH 11/43] Update pangolin to 4.1.3 (#568)

Co-authored-by: thomasbtf <thomasbtf@users.noreply.github.com>
---
 workflow/envs/pangolin.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflow/envs/pangolin.yaml b/workflow/envs/pangolin.yaml
index 52f9310fd..93a50ace5 100644
--- a/workflow/envs/pangolin.yaml
+++ b/workflow/envs/pangolin.yaml
@@ -3,5 +3,5 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - pangolin =4.1.2
+  - pangolin =4.1.3
   - tabulate <0.9 # TODO remove once pangolin 4.1.3 is available in bioconda

From 3ae213ca97d48066cfc98a8fdb556cf77adc27c9 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Mon, 31 Oct 2022 11:15:23 +0100
Subject: [PATCH 12/43] chore(deps): bump amannn/action-semantic-pull-request
 from 4 to 5 (#567)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Bumps [amannn/action-semantic-pull-request](https://github.com/amannn/action-semantic-pull-request) from 4 to 5.
- [Release notes](https://github.com/amannn/action-semantic-pull-request/releases)
- [Changelog](https://github.com/amannn/action-semantic-pull-request/blob/main/CHANGELOG.md)
- [Commits](https://github.com/amannn/action-semantic-pull-request/compare/v4...v5)

---
updated-dependencies:
- dependency-name: amannn/action-semantic-pull-request
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Johannes Köster <johannes.koester@tu-dortmund.de>
---
 .github/workflows/conventional-prs.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/conventional-prs.yml b/.github/workflows/conventional-prs.yml
index 363efbd45..847189c08 100644
--- a/.github/workflows/conventional-prs.yml
+++ b/.github/workflows/conventional-prs.yml
@@ -12,6 +12,6 @@ jobs:
   title-format:
     runs-on: ubuntu-latest
     steps:
-      - uses: amannn/action-semantic-pull-request@v4
+      - uses: amannn/action-semantic-pull-request@v5
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

From 7f9ef833efff63f29b136741e5d731832d6697b7 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Mon, 31 Oct 2022 11:15:36 +0100
Subject: [PATCH 13/43] chore(deps): bump github/super-linter from 4.9.6 to
 4.9.7 (#565)

Bumps [github/super-linter](https://github.com/github/super-linter) from 4.9.6 to 4.9.7.
- [Release notes](https://github.com/github/super-linter/releases)
- [Changelog](https://github.com/github/super-linter/blob/main/docs/release-process.md)
- [Commits](https://github.com/github/super-linter/compare/v4.9.6...v4.9.7)

---
updated-dependencies:
- dependency-name: github/super-linter
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index f2ff33e4d..c93e2e629 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -24,7 +24,7 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - name: Formatting
-        uses: github/super-linter@v4.9.6
+        uses: github/super-linter@v4.9.7
         env:
           VALIDATE_ALL_CODEBASE: false
           DEFAULT_BRANCH: master

From 3d39461576fc16ab9fc92984c2917923805d1093 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Mon, 31 Oct 2022 11:15:48 +0100
Subject: [PATCH 14/43] chore(deps): bump snakemake/snakemake-github-action
 (#563)

Bumps [snakemake/snakemake-github-action](https://github.com/snakemake/snakemake-github-action) from 1.23.0 to 1.24.0.
- [Release notes](https://github.com/snakemake/snakemake-github-action/releases)
- [Changelog](https://github.com/snakemake/snakemake-github-action/blob/master/CHANGELOG.md)
- [Commits](https://github.com/snakemake/snakemake-github-action/compare/v1.23.0...v1.24.0)

---
updated-dependencies:
- dependency-name: snakemake/snakemake-github-action
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
---
 .github/workflows/release-please.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index cc87ad4f7..acb36005b 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -111,7 +111,7 @@ jobs:
 
       - name: Create Dockerfile
         if: ${{ steps.release.outputs.release_created == 'true' }}
-        uses: snakemake/snakemake-github-action@v1.23.0
+        uses: snakemake/snakemake-github-action@v1.24.0
         with:
           directory: .
           snakefile: workflow/Snakefile

From 3b9e9862b216eaa7e3e0f9c96aa0c261f7633b98 Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Mon, 31 Oct 2022 11:20:58 +0100
Subject: [PATCH 15/43] fix kraken db (#574)

---
 workflow/envs/kraken.yaml | 2 +-
 workflow/rules/ref.smk    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/workflow/envs/kraken.yaml b/workflow/envs/kraken.yaml
index 979d75cff..ca1a271e8 100644
--- a/workflow/envs/kraken.yaml
+++ b/workflow/envs/kraken.yaml
@@ -3,5 +3,5 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - kraken2 =2.1.1
+  - kraken2 =2.1.2
   - krona =2.7.1
diff --git a/workflow/rules/ref.smk b/workflow/rules/ref.smk
index 3f469ea3b..fa19e65b1 100644
--- a/workflow/rules/ref.smk
+++ b/workflow/rules/ref.smk
@@ -163,7 +163,7 @@ rule get_genome_db_for_kraken:
     conda:
         "../envs/unix.yaml"
     shell:
-        "mkdir {output} && curl -SL ftp://ftp.ccb.jhu.edu/pub/data/kraken2_dbs/minikraken_8GB_202003.tgz | tar zxvf - -C {output} --strip 1 2> {log}"
+        "mkdir {output} && curl -SL https://genome-idx.s3.amazonaws.com/kraken/k2_standard_08gb_20220926.tar.gz | tar zxvf - -C {output} 2> {log}"
 
 
 rule get_taxonomie_db_for_krona:

From fa957fd44594920c12df3821a23905055b1de9c9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20K=C3=B6ster?= <johannes.koester@tu-dortmund.de>
Date: Tue, 8 Nov 2022 12:34:21 +0100
Subject: [PATCH 16/43] fix: use latest varlociraptor release and ignore all
 biases in case of known lineage variant calling (#575)

* fix: use latest varlociraptor release and ignore all biases in case of known lineage variant calling

* Update common.smk
---
 workflow/envs/varlociraptor.yaml |  2 +-
 workflow/rules/common.smk        | 10 ++++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/workflow/envs/varlociraptor.yaml b/workflow/envs/varlociraptor.yaml
index 39ff16514..50d1bbeea 100644
--- a/workflow/envs/varlociraptor.yaml
+++ b/workflow/envs/varlociraptor.yaml
@@ -3,4 +3,4 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - varlociraptor =4.9
+  - varlociraptor =5.3
diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index d29581213..fe79af15d 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -805,6 +805,16 @@ def get_list_of_amplicon_states_assembler(samples):
 
 
 def get_varlociraptor_bias_flags(wildcards):
+    if wildcards.varrange == "lineage-variants":
+        # Known variants, we don't want to use bias detection at all.
+        # Rationale: the determined biases are hints for artifacts, which are particularly
+        # important to maintain a high precision with denovo calls. When there is prior knowledge
+        # about a variant like here, they are too conservative. E.g., when I see a typical omicron
+        # variant in a sample, I tend to believe it even if it happens to have a strand bias.
+        return (
+            "--omit-strand-bias --omit-read-orientation-bias --omit-read-position-bias "
+            "--omit-softclip-bias --omit-homopolymer-artifact-detection --omit-alt-locus-bias"
+        )
     if is_amplicon_data(wildcards.sample):
         # no bias detection possible
         return (

From cacd8b9a0bfc36d79c1d56af899de406fdcc0a35 Mon Sep 17 00:00:00 2001
From: simakro <74452164+simakro@users.noreply.github.com>
Date: Wed, 30 Nov 2022 10:31:42 +0100
Subject: [PATCH 17/43] refactor: Update medaka and deps for ont (#561)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* update medaka version, dependencies and mode

* cleanup

* use alternative output-folder for medaka results

* reset sample-sheet

* style: linting

* style: nl eof

* small change

* fix actions run

* change priority

* change dependency order

* chore: use safer path for temp-output of medaka_variant.

Co-authored-by: Simon Magin <simon@c46.ikim.uk-essen.de>
Co-authored-by: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Co-authored-by: Alex Thomas <alex.thomas89@gmail.com>
Co-authored-by: Johannes Köster <johannes.koester@tu-dortmund.de>
---
 workflow/envs/medaka.yaml          |  8 +++++---
 workflow/rules/variant_calling.smk | 19 ++++++++++---------
 2 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/workflow/envs/medaka.yaml b/workflow/envs/medaka.yaml
index dc5efb316..c345bbf77 100644
--- a/workflow/envs/medaka.yaml
+++ b/workflow/envs/medaka.yaml
@@ -3,6 +3,8 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - medaka =1.0
-  - tensorflow =1.14
-  - h5py =2.7
+  - python =3.8
+  - xz =5.2.6
+  - medaka =1.7.0
+  - tensorflow =2.7.0
+  - h5py =3.7.0
diff --git a/workflow/rules/variant_calling.smk b/workflow/rules/variant_calling.smk
index ce9f060ec..af5eda904 100644
--- a/workflow/rules/variant_calling.smk
+++ b/workflow/rules/variant_calling.smk
@@ -1,4 +1,4 @@
-# Copyright 2022 Thomas Battenfeld, Alexander Thomas, Johannes Köster.
+# Copyright 2022 Thomas Battenfeld, Alexander Thomas, Simon Magin, Johannes Köster.
 # Licensed under the BSD 2-Clause License (https://opensource.org/licenses/BSD-2-Clause)
 # This file may not be copied, modified, or distributed
 # except according to those terms.
@@ -45,23 +45,24 @@ rule delly:
 rule medaka_variant:
     input:
         ref=get_reference(),
-        sample="results/{date}/recal/ref~{reference}/{sample}.bam",
-        bai="results/{date}/recal/ref~{reference}/{sample}.bam.bai",
+        sample="results/{date}/norm_trim_raw_reads/{sample}/{sample}.cap.clip.fasta",
     output:
-        temp(
-            "results/{date}/candidate-calls/ref~{reference}/{sample}.homopolymer-medaka.vcf"
-        ),
+        "results/{date}/candidate-calls/ref~{reference}/{sample}.homopolymer-medaka.vcf",
     params:
         outdir=get_output_dir,
+        # The default model covers almost all current use cases on MinION & GridION. For best results
+        # with PromethION and future pores etc an option to switch between models would be required,
+        # e.g. add col model in sample-sheet & use default (will still work for all) if not provided.
+        model="r941_min_hac_variant_g507",
     log:
         "logs/{date}/medaka/variant/ref~{reference}/{sample}.log",
     conda:
         "../envs/medaka.yaml"
     threads: 4
     shell:
-        "(medaka_variant -i {input.sample} -f {input.ref} -o {params.outdir}/{wildcards.sample} -t {threads} &&"
-        " mv $(cat {log}| grep '\- Final VCF written to' | sed s/'- Final VCF written to '//\ ) {output})"
-        " > {log} 2>&1"
+        "(medaka_haploid_variant -i {input.sample} -r {input.ref} -o medaka_tmp/medaka/{wildcards.date}/{wildcards.reference}/{wildcards.sample}"
+        " -t {threads} -m {params.model} && mv medaka_tmp/medaka/{wildcards.date}/{wildcards.reference}/{wildcards.sample}/medaka.annotated.vcf {output} &&"
+        " rm -r medaka_tmp/medaka/{wildcards.date}/{wildcards.reference}/{wildcards.sample}) > {log} 2>&1"
 
 
 rule longshot:

From 79d288cfa7c5870932635a79dacb7c8bbf2bdefa Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Thu, 1 Dec 2022 12:00:09 +0100
Subject: [PATCH 18/43] chore(master): release 0.15.1 (#536)

* chore(master): release 0.15.1

* Changed containerized tag to 0.15.1

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
---
 CHANGELOG.md       | 12 ++++++++++++
 version.txt        |  2 +-
 workflow/Snakefile |  2 +-
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index f86ac484b..ac27577da 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,17 @@
 # Changelog
 
+## [0.15.1](https://github.com/IKIM-Essen/uncovar/compare/v0.15.0...v0.15.1) (2022-11-30)
+
+
+### Bug Fixes
+
+* **ci:** update black to rev 22.3.0 ([#523](https://github.com/IKIM-Essen/uncovar/issues/523)) ([2273b7d](https://github.com/IKIM-Essen/uncovar/commit/2273b7d49d21dfe48812f7e3e4d33969b62e1d9e))
+* disable ont actions ([#555](https://github.com/IKIM-Essen/uncovar/issues/555)) ([56e46ef](https://github.com/IKIM-Essen/uncovar/commit/56e46ef7e1663b4de3447068df7cb8b9d1d7b67f))
+* Replace outdated df append ([#544](https://github.com/IKIM-Essen/uncovar/issues/544)) ([4a40003](https://github.com/IKIM-Essen/uncovar/commit/4a4000310cba4f3e8640172eadebcd35239b2e34))
+* update channel priorities and snakemake wrappers ([#562](https://github.com/IKIM-Essen/uncovar/issues/562)) ([a0b6fd0](https://github.com/IKIM-Essen/uncovar/commit/a0b6fd0557b7e6cb3aeddd22e6a3350560c18415))
+* use latest varlociraptor release and ignore all biases in case of known lineage variant calling ([#575](https://github.com/IKIM-Essen/uncovar/issues/575)) ([fa957fd](https://github.com/IKIM-Essen/uncovar/commit/fa957fd44594920c12df3821a23905055b1de9c9))
+* voc probability ([#541](https://github.com/IKIM-Essen/uncovar/issues/541)) ([db6eb17](https://github.com/IKIM-Essen/uncovar/commit/db6eb175aa7c25948677a9b64258afd377016d8c))
+
 ## [0.15.0](https://github.com/IKIM-Essen/uncovar/compare/v0.14.0...v0.15.0) (2022-03-24)
 
 
diff --git a/version.txt b/version.txt
index a55105169..e815b861f 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-0.15.0
+0.15.1
diff --git a/workflow/Snakefile b/workflow/Snakefile
index 4abff6178..51ee6aedb 100644
--- a/workflow/Snakefile
+++ b/workflow/Snakefile
@@ -21,7 +21,7 @@ report: "report/workflow.rst"
 container: "docker://condaforge/mambaforge"
 
 
-containerized: "quay.io/uncovar/uncovar#0.15.0"
+containerized: "quay.io/uncovar/uncovar#0.15.1"
 
 
 if config["strain-calling"]["use-gisaid"]:

From c11ee96f3fdb5f9ac66085f463ab83cff8f84fb6 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Wed, 25 Jan 2023 12:23:46 +0100
Subject: [PATCH 19/43] chore(deps): bump github/super-linter from 4.9.7 to
 4.10.1 (#577)

Bumps [github/super-linter](https://github.com/github/super-linter) from 4.9.7 to 4.10.1.
- [Release notes](https://github.com/github/super-linter/releases)
- [Changelog](https://github.com/github/super-linter/blob/main/docs/release-process.md)
- [Commits](https://github.com/github/super-linter/compare/v4.9.7...v4.10.1)

---
updated-dependencies:
- dependency-name: github/super-linter
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index c93e2e629..efa286b4a 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -24,7 +24,7 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - name: Formatting
-        uses: github/super-linter@v4.9.7
+        uses: github/super-linter@v4.10.1
         env:
           VALIDATE_ALL_CODEBASE: false
           DEFAULT_BRANCH: master

From 444f89c5426ceec5da7c3ce04942ae6f5d1f3c1c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20K=C3=B6ster?= <johannes.koester@tu-dortmund.de>
Date: Thu, 26 Jan 2023 20:22:41 +0100
Subject: [PATCH 20/43] refactor: work around bug in snakefmt that adds two
 lines after each include by moving an if statement into common.smk (#578)

* refactor: work around bug in snakefmt that adds two lines after each include by moving an if statement into common.smk

* more refactoring
---
 workflow/Snakefile        | 12 ++----------
 workflow/rules/common.smk | 10 ++++++++++
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/workflow/Snakefile b/workflow/Snakefile
index 51ee6aedb..d8f339ce5 100644
--- a/workflow/Snakefile
+++ b/workflow/Snakefile
@@ -24,12 +24,6 @@ container: "docker://condaforge/mambaforge"
 containerized: "quay.io/uncovar/uncovar#0.15.1"
 
 
-if config["strain-calling"]["use-gisaid"]:
-
-    envvars:
-        "GISAID_API_TOKEN",
-
-
 include: "rules/common.smk"
 include: "rules/benchmarking_common.smk"
 include: "rules/utils.smk"
@@ -47,6 +41,8 @@ include: "rules/variant_filtration.smk"
 include: "rules/variant_report.smk"
 include: "rules/generate_output.smk"
 include: "rules/benchmarking.smk"
+include: "rules/long_read.smk"
+include: "rules/lineage_variant_calling.smk"
 
 
 if config["data-handling"]["use-data-handling"]:
@@ -54,10 +50,6 @@ if config["data-handling"]["use-data-handling"]:
     include: "rules/preprocessing.smk"
 
 
-include: "rules/long_read.smk"
-include: "rules/lineage_variant_calling.smk"
-
-
 if config["data-handling"]["archive-data"]:
 
     rule save_latest_run:
diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index fe79af15d..3cb8c7b49 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -11,8 +11,18 @@ import urllib.request
 from snakemake.utils import validate
 
 
+if config["strain-calling"]["use-gisaid"]:
+
+    envvars:
+        "GISAID_API_TOKEN",
+
+
 VARTYPES = ["SNV", "MNV", "INS", "DEL", "REP", "INV", "DUP"]
+
+
 ILLUMINA_VARRANGE = ["small", "structural"]
+
+
 ONT_VARRANGE = ["homopolymer-medaka", "homopolymer-longshot"]
 ION_VARRANGE = ["small", "structural"]
 

From 505a2714ba0e5642312051f5e5154f7d454ff57f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20K=C3=B6ster?= <johannes.koester@uni-due.de>
Date: Wed, 1 Mar 2023 15:57:28 +0100
Subject: [PATCH 21/43] fix: use homopolymer-pair-HMM-mode of Varlociraptor in
 case of nanopore reads

---
 workflow/rules/common.smk          | 10 ++++++++++
 workflow/rules/variant_calling.smk |  3 ++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index 3cb8c7b49..9491bdd9f 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -1587,6 +1587,16 @@ def get_checked_mode():
     raise TypeError(f'Mode {mode} not recognized. Can be "patient" or "environment".')
 
 
+def get_varlociraptor_preprocess_flags(wildcards):
+    technology = samples.loc[wildcards.sample, "technology"]
+    if technology == "ont":
+        return "--pairhmm-mode homopolymer"
+    elif technolgy == "illumina" or technology == "ion":
+        return ""
+    else:
+        raise NotImplementedError(f"Technology {technology} not supported.")
+
+
 def get_input_by_mode(wildcard):
     paths = [
         expand(
diff --git a/workflow/rules/variant_calling.smk b/workflow/rules/variant_calling.smk
index af5eda904..8682bc980 100644
--- a/workflow/rules/variant_calling.smk
+++ b/workflow/rules/variant_calling.smk
@@ -143,12 +143,13 @@ rule varlociraptor_preprocess:
         temp("results/{date}/observations/ref~{reference}/{sample}.{varrange}.bcf"),
     params:
         depth=config["variant-calling"]["max-read-depth"],
+        extra=get_varlociraptor_preprocess_flags,
     log:
         "logs/{date}/varlociraptor/preprocess/ref~{reference}/{sample}.{varrange}.log",
     conda:
         "../envs/varlociraptor.yaml"
     shell:
-        "varlociraptor preprocess variants --candidates {input.candidates} "
+        "varlociraptor preprocess variants {params.extra} --candidates {input.candidates} "
         "{input.ref} --bam {input.bam} --max-depth {params.depth} --output {output} 2> {log}"
 
 

From 91274a59de8f8802cb524655c2b202e43d10d236 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20K=C3=B6ster?= <johannes.koester@uni-due.de>
Date: Wed, 1 Mar 2023 15:58:03 +0100
Subject: [PATCH 22/43] Revert "fix: use homopolymer-pair-HMM-mode of
 Varlociraptor in case of nanopore reads"

This reverts commit 505a2714ba0e5642312051f5e5154f7d454ff57f.
---
 workflow/rules/common.smk          | 10 ----------
 workflow/rules/variant_calling.smk |  3 +--
 2 files changed, 1 insertion(+), 12 deletions(-)

diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index 9491bdd9f..3cb8c7b49 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -1587,16 +1587,6 @@ def get_checked_mode():
     raise TypeError(f'Mode {mode} not recognized. Can be "patient" or "environment".')
 
 
-def get_varlociraptor_preprocess_flags(wildcards):
-    technology = samples.loc[wildcards.sample, "technology"]
-    if technology == "ont":
-        return "--pairhmm-mode homopolymer"
-    elif technolgy == "illumina" or technology == "ion":
-        return ""
-    else:
-        raise NotImplementedError(f"Technology {technology} not supported.")
-
-
 def get_input_by_mode(wildcard):
     paths = [
         expand(
diff --git a/workflow/rules/variant_calling.smk b/workflow/rules/variant_calling.smk
index 8682bc980..af5eda904 100644
--- a/workflow/rules/variant_calling.smk
+++ b/workflow/rules/variant_calling.smk
@@ -143,13 +143,12 @@ rule varlociraptor_preprocess:
         temp("results/{date}/observations/ref~{reference}/{sample}.{varrange}.bcf"),
     params:
         depth=config["variant-calling"]["max-read-depth"],
-        extra=get_varlociraptor_preprocess_flags,
     log:
         "logs/{date}/varlociraptor/preprocess/ref~{reference}/{sample}.{varrange}.log",
     conda:
         "../envs/varlociraptor.yaml"
     shell:
-        "varlociraptor preprocess variants {params.extra} --candidates {input.candidates} "
+        "varlociraptor preprocess variants --candidates {input.candidates} "
         "{input.ref} --bam {input.bam} --max-depth {params.depth} --output {output} 2> {log}"
 
 

From 9455a572dead7f448cb8af7679f1f89ce7033a3e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20K=C3=B6ster?= <johannes.koester@tu-dortmund.de>
Date: Wed, 1 Mar 2023 22:09:49 +0100
Subject: [PATCH 23/43] chore: temporarily disable pre-commit ci action as it
 currently fails during installation (waiting for new release) (#588)

---
 .github/workflows/main.yml | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index efa286b4a..57eb14142 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -48,13 +48,16 @@ jobs:
           stagein: mamba install -n snakemake -c conda-forge peppy
           args: "--lint"
 
-  Pre-Commit:
-    runs-on: ubuntu-latest
-    if: github.ref != 'refs/heads/master'
-    steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v4
-      - uses: pre-commit/action@v3.0.0
+  # pre-commit action currently fails:
+  # https://github.com/IKIM-Essen/uncovar/actions/runs/4304753941/jobs/7506225198#step:4:115
+  # revisit when new pre-commit release >3.0.0 is out
+  # Pre-Commit:
+  #   runs-on: ubuntu-latest
+  #   if: github.ref != 'refs/heads/master'
+  #   steps:
+  #     - uses: actions/checkout@v2
+  #     - uses: actions/setup-python@v4
+  #     - uses: pre-commit/action@v3.0.0
 
   Technology-Tests:
     runs-on: ubuntu-latest
@@ -63,7 +66,7 @@ jobs:
     needs:
       - Formatting
       - Linting
-      - Pre-Commit
+      #- Pre-Commit
     strategy:
       matrix:
         rule: [all, all -npr]
@@ -172,18 +175,19 @@ jobs:
     needs:
       - Formatting
       - Linting
-      - Pre-Commit
+      #- Pre-Commit
     strategy:
       matrix:
-        rule: [
+        rule:
+          [
             benchmark_strain_calling,
             benchmark_assembly,
             benchmark_mixtures,
             benchmark_non_sars_cov_2,
             benchmark_reads,
             compare_assemblers,
-            # generate_test_cases,
           ]
+    # generate_test_cases,
     steps:
       - uses: actions/checkout@v2
 

From 406d456edd15715f7e14338b8195d2a09a807e49 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ann-Kathrin=20Br=C3=BCggemann?=
 <90249112+AKBrueggemann@users.noreply.github.com>
Date: Thu, 23 Mar 2023 13:53:47 +0100
Subject: [PATCH 24/43] fix: changes in path requirements for snakedeploy
 (#590)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Changes in path requirements for snakedeploy

* fmt

* Changed path

* Different approach to url passing

* fmt

* Changed path creation

* Update workflow/rules/common.smk

Co-authored-by: Johannes Köster <johannes.koester@tu-dortmund.de>

* fmt

* Rewind change

* Change in directory call

* Revert "Change in directory call"

This reverts commit b5501c414a7275e8ad0cb41bfc918e8a663a88d2.

---------

Co-authored-by: Johannes Köster <johannes.koester@tu-dortmund.de>
Co-authored-by: Johannes Köster <johannes.koester@uni-due.de>
---
 workflow/rules/common.smk | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index 3cb8c7b49..e3b72a97f 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -4,6 +4,7 @@
 # except according to those terms.
 
 from pathlib import Path
+import os.path
 import pandas as pd
 import re
 import random
@@ -212,7 +213,7 @@ def get_fastqs(wildcards):
 
 
 def get_resource(name):
-    return str((Path(workflow.snakefile).parent.parent.parent / "resources") / name)
+    return workflow.source_path(f"../../resources/{name}")
 
 
 def get_report_input(pattern):

From aced95e798fd0483e99120550f49614e680f56dd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20K=C3=B6ster?= <johannes.koester@tu-dortmund.de>
Date: Thu, 23 Mar 2023 16:22:55 +0100
Subject: [PATCH 25/43] fix: improved clonality event definition, usage of
 major subclone for assembly polishing; upgrade to varlociraptor 6.0 (#585)

* fix: improved clonality event definition, usage of major subclone for assembly polishing; upgrade to varlociraptor 6.0

* adapt wildcard constraints
---
 workflow/envs/varlociraptor.yaml      |  2 +-
 workflow/rules/assembly.smk           |  4 ++--
 workflow/rules/common.smk             | 16 ++++++++++------
 workflow/rules/variant_filtration.smk |  2 +-
 4 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/workflow/envs/varlociraptor.yaml b/workflow/envs/varlociraptor.yaml
index 50d1bbeea..151fb2668 100644
--- a/workflow/envs/varlociraptor.yaml
+++ b/workflow/envs/varlociraptor.yaml
@@ -3,4 +3,4 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - varlociraptor =5.3
+  - varlociraptor =6.0
diff --git a/workflow/rules/assembly.smk b/workflow/rules/assembly.smk
index 62cc50298..08c92dbbb 100644
--- a/workflow/rules/assembly.smk
+++ b/workflow/rules/assembly.smk
@@ -159,8 +159,8 @@ rule filter_chr0:
 rule assembly_polishing_illumina:
     input:
         fasta="results/{date}/contigs/ordered/{sample}.fasta",
-        bcf="results/{date}/filtered-calls/ref~{sample}/{sample}.clonal.nofilter.orf.bcf",
-        bcfidx="results/{date}/filtered-calls/ref~{sample}/{sample}.clonal.nofilter.orf.bcf.csi",
+        bcf="results/{date}/filtered-calls/ref~{sample}/{sample}.subclonal-major.nofilter.orf.bcf",
+        bcfidx="results/{date}/filtered-calls/ref~{sample}/{sample}.subclonal-major.nofilter.orf.bcf.csi",
     output:
         report(
             "results/{date}/polishing/bcftools-illumina/{sample}.fasta",
diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index e3b72a97f..79c87962e 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -599,12 +599,16 @@ def get_bwa_index(wildcards):
 
 
 def get_target_events(wildcards):
-    if wildcards.reference == "main" or wildcards.clonality != "clonal":
-        # calling variants against the wuhan reference or we are explicitly interested in subclonal as well
-        return "SUBCLONAL_MINOR SUBCLONAL_MAJOR SUBCLONAL_HIGH CLONAL"
-    else:
-        # only keep clonal variants
+    if wildcards.clonality == "clonal":
         return "CLONAL"
+    elif wildcards.clonality == "subclonal-major":
+        return "CLONAL SUBCLONAL_MAJOR SUBCLONAL_HIGH"
+    elif wildcards.clonality == "subclonal-high":
+        return "CLONAL SUBCLONAL_HIGH"
+    elif wildcards.clonality == "subclonal":
+        return "CLONAL SUBCLONAL_MAJOR SUBCLONAL_HIGH SUBCLONAL_MINOR"
+    else:
+        raise ValueError(f"Unsupported clonality value: {wildcards.clonality}")
 
 
 def get_control_fdr_input(wildcards):
@@ -1670,7 +1674,7 @@ def get_genome_annotation(suffix=""):
 wildcard_constraints:
     sample="[^/.]+",
     vartype="|".join(VARTYPES),
-    clonality="subclonal|clonal",
+    clonality="subclonal|clonal|subclonal-major|subclonal-high",
     annotation="orf|protein",
     filter="|".join(
         list(map(re.escape, config["variant-calling"]["filters"])) + ["nofilter"]
diff --git a/workflow/rules/variant_filtration.smk b/workflow/rules/variant_filtration.smk
index ab81d6d2b..e9ed62cd1 100644
--- a/workflow/rules/variant_filtration.smk
+++ b/workflow/rules/variant_filtration.smk
@@ -35,7 +35,7 @@ rule control_fdr:
     conda:
         "../envs/varlociraptor.yaml"
     shell:
-        "varlociraptor filter-calls control-fdr --local {input} --var {wildcards.vartype} "
+        "varlociraptor filter-calls control-fdr --mode local-smart {input} --var {wildcards.vartype} "
         "--events {params.events} --fdr {params.fdr} > {output} 2> {log}"
 
 

From 9bc814f7cb9e9d9e53d557d463e782801070b46e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20K=C3=B6ster?= <johannes.koester@tu-dortmund.de>
Date: Thu, 14 Sep 2023 14:19:46 +0200
Subject: [PATCH 26/43] fix: use homopolymer-pair-HMM-mode of Varlociraptor in
 case of nanopore reads (#587)

* Revert "Revert "fix: use homopolymer-pair-HMM-mode of Varlociraptor in case of nanopore reads""

This reverts commit 91274a59de8f8802cb524655c2b202e43d10d236.

* properly retrieve sample data frame

* use pep sample table

* fix typo

* fix technology call

---------

Co-authored-by: Alex Thomas <alex.thomas89@gmail.com>
---
 workflow/rules/common.smk          | 10 ++++++++++
 workflow/rules/variant_calling.smk |  3 ++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index 79c87962e..d712652ad 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -1592,6 +1592,16 @@ def get_checked_mode():
     raise TypeError(f'Mode {mode} not recognized. Can be "patient" or "environment".')
 
 
+def get_varlociraptor_preprocess_flags(wildcards):
+    technology = get_technology(wildcards)
+    if technology == "ont":
+        return "--pairhmm-mode homopolymer"
+    elif technology == "illumina" or technology == "ion":
+        return ""
+    else:
+        raise NotImplementedError(f"Technology {technology} not supported.")
+
+
 def get_input_by_mode(wildcard):
     paths = [
         expand(
diff --git a/workflow/rules/variant_calling.smk b/workflow/rules/variant_calling.smk
index af5eda904..8682bc980 100644
--- a/workflow/rules/variant_calling.smk
+++ b/workflow/rules/variant_calling.smk
@@ -143,12 +143,13 @@ rule varlociraptor_preprocess:
         temp("results/{date}/observations/ref~{reference}/{sample}.{varrange}.bcf"),
     params:
         depth=config["variant-calling"]["max-read-depth"],
+        extra=get_varlociraptor_preprocess_flags,
     log:
         "logs/{date}/varlociraptor/preprocess/ref~{reference}/{sample}.{varrange}.log",
     conda:
         "../envs/varlociraptor.yaml"
     shell:
-        "varlociraptor preprocess variants --candidates {input.candidates} "
+        "varlociraptor preprocess variants {params.extra} --candidates {input.candidates} "
         "{input.ref} --bam {input.bam} --max-depth {params.depth} --output {output} 2> {log}"
 
 

From d0f293d2b8136fb0d8ef3753733ab1d30fb20d56 Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Thu, 21 Sep 2023 16:07:57 +0200
Subject: [PATCH 27/43] fix: switch from jupyter notebook to script (#598)

* switch from jupyter notebook to script

* change code format

* fmt
---
 .../assembly-benchmark-results.py.ipynb       | 201 ------------------
 workflow/rules/benchmarking.smk               |   4 +-
 .../scripts/assembly-benchmark-results.py     | 167 +++++++++++++++
 3 files changed, 169 insertions(+), 203 deletions(-)
 delete mode 100644 workflow/notebooks/assembly-benchmark-results.py.ipynb
 create mode 100644 workflow/scripts/assembly-benchmark-results.py

diff --git a/workflow/notebooks/assembly-benchmark-results.py.ipynb b/workflow/notebooks/assembly-benchmark-results.py.ipynb
deleted file mode 100644
index 46e7dbc64..000000000
--- a/workflow/notebooks/assembly-benchmark-results.py.ipynb
+++ /dev/null
@@ -1,201 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "sys.stderr = open(snakemake.log[0], \"w\")\n",
-    "import pysam\n",
-    "\n",
-    "# see https://pysam.readthedocs.io/en/latest/api.html#pysam.AlignedSegment.cigartuples\n",
-    "BAM_CEQUAL = 7\n",
-    "BAM_CDIFF = 8\n",
-    "BAM_CSOFT_CLIP = 4\n",
-    "BAM_CHARD_CLIP = 5\n",
-    "BAM_CINS = 1\n",
-    "BAM_CDEL = 2\n",
-    "\n",
-    "N_WINDOW = 100\n",
-    "\n",
-    "\n",
-    "def is_uncertain_region(record, rpos, rend, ref_fasta):\n",
-    "    refseq = ref_fasta.fetch(record.reference_name, rpos - N_WINDOW, rend + N_WINDOW)\n",
-    "    return (\"N\" * 10) in refseq\n",
-    "\n",
-    "\n",
-    "def get_edit_dist(record, ref_fasta):\n",
-    "    edit_dist = 0\n",
-    "    qpos = 0\n",
-    "    rpos = record.reference_start\n",
-    "    for op, length in record.cigartuples:\n",
-    "        if op == BAM_CEQUAL:\n",
-    "            # no edit\n",
-    "            qpos += length\n",
-    "            rpos += length\n",
-    "        else:\n",
-    "            if op == BAM_CDIFF:\n",
-    "                refseq = ref_fasta.fetch(record.reference_name, rpos, rpos + length)\n",
-    "                if not is_uncertain_region(record, rpos, rpos + length, ref_fasta):\n",
-    "                    # Only consider edits where the reference has a true nucleotide\n",
-    "                    # because IUPAC codes lead to mason simulating an N in the reads.\n",
-    "                    edit_dist += sum(base in \"ACGT\" for base in refseq)\n",
-    "                qpos += length\n",
-    "                rpos += length\n",
-    "\n",
-    "            elif op == BAM_CSOFT_CLIP:\n",
-    "                edit_dist += length\n",
-    "                qpos += length\n",
-    "            elif op == BAM_CHARD_CLIP:\n",
-    "                edit_dist += length\n",
-    "            elif op == BAM_CINS:\n",
-    "                refseq = ref_fasta.fetch(record.reference_name, rpos, rpos + length)\n",
-    "                if not is_uncertain_region(record, rpos, rpos + length, ref_fasta):\n",
-    "                    # only count edit distance if the region behind the insert does not\n",
-    "                    # contain N stretches in the reference. Rationale: those regions are apparently\n",
-    "                    # hard to assemble, and we cannot properly simulate reads for them, so\n",
-    "                    # we should not count them in a benchmark.\n",
-    "                    edit_dist += length\n",
-    "                qpos += length\n",
-    "            elif op == BAM_CDEL:\n",
-    "                refseq = ref_fasta.fetch(record.reference_name, rpos, rpos + length)\n",
-    "                if not is_uncertain_region(record, rpos, rpos + length, ref_fasta):\n",
-    "                    # only count edit distance if the region behind the insert does not\n",
-    "                    # contain N stretches in the reference. Rationale: those regions are apparently\n",
-    "                    # hard to assemble, and we cannot properly simulate reads for them, so\n",
-    "                    # we should not count them in a benchmark.\n",
-    "                    edit_dist += length\n",
-    "                rpos += length\n",
-    "            else:\n",
-    "                raise ValueError(f\"Unsupported CIGAR operation: {op}\")\n",
-    "    return edit_dist\n",
-    "\n",
-    "\n",
-    "with open(snakemake.output[0], \"w\") as out:\n",
-    "    print(\n",
-    "        \"Accession\",\n",
-    "        \"Contigs\",\n",
-    "        \"Total contigs\",\n",
-    "        \"Contig length\",\n",
-    "        \"Reference length\",\n",
-    "        \"Contig frac\",\n",
-    "        \"Cum frac\",\n",
-    "        \"Relevant edit dist\",\n",
-    "        \"Cigar string\",\n",
-    "        \"Edit frac\",\n",
-    "        sep=\"\\t\",\n",
-    "        file=out,\n",
-    "    )\n",
-    "    sum_of_edit_dist = 0\n",
-    "    largest_no_contig = 0\n",
-    "    small_larg_cover = 1.0\n",
-    "    small_larg_cover_name = \"asd\"\n",
-    "    smallest_cum_frac = 1.0\n",
-    "\n",
-    "    # for bam_file in snakemake_input:\n",
-    "    for bam_file, ref_fasta in zip(snakemake.input.bams, snakemake.input.refs):\n",
-    "        current_contig = 1\n",
-    "\n",
-    "        ref_fasta = pysam.FastaFile(ref_fasta)\n",
-    "\n",
-    "        with pysam.AlignmentFile(bam_file, \"rb\") as samfile:\n",
-    "            total_contigs = samfile.count()\n",
-    "            accession = samfile.get_reference_name(0)\n",
-    "\n",
-    "            largest_no_contig = (\n",
-    "                total_contigs\n",
-    "                if total_contigs > largest_no_contig\n",
-    "                else largest_no_contig\n",
-    "            )\n",
-    "\n",
-    "        with pysam.AlignmentFile(bam_file, \"rb\") as samfile:\n",
-    "            ref_lengths = samfile.lengths[0]\n",
-    "            largest_coverage = 0\n",
-    "            cum_frac = 0\n",
-    "            for read in samfile.fetch():\n",
-    "                query_alignment_length = read.query_alignment_length\n",
-    "                frac = round(query_alignment_length / ref_lengths, 2)\n",
-    "\n",
-    "                # Calculate edit distance from CIGAR string, because NM tag counts matching Ns as edits.\n",
-    "                edit = get_edit_dist(read, ref_fasta)\n",
-    "\n",
-    "                cum_frac += frac\n",
-    "                cum_frac = round(cum_frac, 2)\n",
-    "                sum_of_edit_dist = sum_of_edit_dist + edit\n",
-    "                edit_frac = round(edit / query_alignment_length, 5)\n",
-    "                largest_coverage = frac if frac > largest_coverage else largest_coverage\n",
-    "\n",
-    "                print(\n",
-    "                    accession,\n",
-    "                    current_contig,\n",
-    "                    total_contigs,\n",
-    "                    query_alignment_length,\n",
-    "                    ref_lengths,\n",
-    "                    frac,\n",
-    "                    cum_frac,\n",
-    "                    edit,\n",
-    "                    read.cigarstring,\n",
-    "                    edit_frac,\n",
-    "                    sep=\"\\t\",\n",
-    "                    file=out,\n",
-    "                )\n",
-    "\n",
-    "                current_contig += 1\n",
-    "            smallest_cum_frac = (\n",
-    "                cum_frac if smallest_cum_frac > cum_frac else smallest_cum_frac\n",
-    "            )\n",
-    "            small_larg_cover = (\n",
-    "                largest_coverage\n",
-    "                if small_larg_cover > largest_coverage\n",
-    "                else small_larg_cover\n",
-    "            )\n",
-    "            small_larg_cover_name = (\n",
-    "                accession\n",
-    "                if small_larg_cover >= largest_coverage\n",
-    "                else small_larg_cover_name\n",
-    "            )\n",
-    "\n",
-    "    print(\"Largest number of contigs\")\n",
-    "    print(largest_no_contig)\n",
-    "    print(\"Smallest largest coverage in \" + str(small_larg_cover_name))\n",
-    "    print(small_larg_cover)\n",
-    "    print(\"Sum of edit distances\")\n",
-    "    print(sum_of_edit_dist)\n",
-    "    print(\"Smallest cum. fraction of contigs\")\n",
-    "    print(smallest_cum_frac)\n",
-    "    print(\"Largest number of contigs\", file=out)\n",
-    "    print(largest_no_contig, file=out)\n",
-    "    print(\"Smallest largest coverage in \" + str(small_larg_cover_name), file=out)\n",
-    "    print(small_larg_cover, file=out)\n",
-    "    print(\"Sum of edit distances\", file=out)\n",
-    "    print(sum_of_edit_dist, file=out)\n",
-    "    print(\"Smallest cum. fraction of contigs\", file=out)\n",
-    "    print(smallest_cum_frac, file=out)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
diff --git a/workflow/rules/benchmarking.smk b/workflow/rules/benchmarking.smk
index c5683ecf1..6f455f0ce 100644
--- a/workflow/rules/benchmarking.smk
+++ b/workflow/rules/benchmarking.smk
@@ -130,8 +130,8 @@ rule summarize_assembly_results:
         notebooks=1,
     conda:
         "../envs/pysam.yaml"
-    notebook:
-        "../notebooks/assembly-benchmark-results.py.ipynb"
+    script:
+        "../scripts/assembly-benchmark-results.py"
 
 
 rule test_non_cov2:
diff --git a/workflow/scripts/assembly-benchmark-results.py b/workflow/scripts/assembly-benchmark-results.py
new file mode 100644
index 000000000..aca8c4c7e
--- /dev/null
+++ b/workflow/scripts/assembly-benchmark-results.py
@@ -0,0 +1,167 @@
+# %%
+sys.stderr = open(snakemake.log[0], "w")
+import pysam
+
+# see https://pysam.readthedocs.io/en/latest/api.html#pysam.AlignedSegment.cigartuples
+BAM_CEQUAL = 7
+BAM_CDIFF = 8
+BAM_CSOFT_CLIP = 4
+BAM_CHARD_CLIP = 5
+BAM_CINS = 1
+BAM_CDEL = 2
+
+N_WINDOW = 100
+
+
+def is_uncertain_region(record, rpos, rend, ref_fasta):
+    refseq = ref_fasta.fetch(record.reference_name, rpos - N_WINDOW, rend + N_WINDOW)
+    return ("N" * 10) in refseq
+
+
+def get_edit_dist(record, ref_fasta):
+    edit_dist = 0
+    qpos = 0
+    rpos = record.reference_start
+    for op, length in record.cigartuples:
+        if op == BAM_CEQUAL:
+            # no edit
+            qpos += length
+            rpos += length
+        else:
+            if op == BAM_CDIFF:
+                refseq = ref_fasta.fetch(record.reference_name, rpos, rpos + length)
+                if not is_uncertain_region(record, rpos, rpos + length, ref_fasta):
+                    # Only consider edits where the reference has a true nucleotide
+                    # because IUPAC codes lead to mason simulating an N in the reads.
+                    edit_dist += sum(base in "ACGT" for base in refseq)
+                qpos += length
+                rpos += length
+
+            elif op == BAM_CSOFT_CLIP:
+                edit_dist += length
+                qpos += length
+            elif op == BAM_CHARD_CLIP:
+                edit_dist += length
+            elif op == BAM_CINS:
+                refseq = ref_fasta.fetch(record.reference_name, rpos, rpos + length)
+                if not is_uncertain_region(record, rpos, rpos + length, ref_fasta):
+                    # only count edit distance if the region behind the insert does not
+                    # contain N stretches in the reference. Rationale: those regions are apparently
+                    # hard to assemble, and we cannot properly simulate reads for them, so
+                    # we should not count them in a benchmark.
+                    edit_dist += length
+                qpos += length
+            elif op == BAM_CDEL:
+                refseq = ref_fasta.fetch(record.reference_name, rpos, rpos + length)
+                if not is_uncertain_region(record, rpos, rpos + length, ref_fasta):
+                    # only count edit distance if the region behind the insert does not
+                    # contain N stretches in the reference. Rationale: those regions are apparently
+                    # hard to assemble, and we cannot properly simulate reads for them, so
+                    # we should not count them in a benchmark.
+                    edit_dist += length
+                rpos += length
+            else:
+                raise ValueError(f"Unsupported CIGAR operation: {op}")
+    return edit_dist
+
+
+with open(snakemake.output[0], "w") as out:
+    print(
+        "Accession",
+        "Contigs",
+        "Total contigs",
+        "Contig length",
+        "Reference length",
+        "Contig frac",
+        "Cum frac",
+        "Relevant edit dist",
+        "Cigar string",
+        "Edit frac",
+        sep="\t",
+        file=out,
+    )
+    sum_of_edit_dist = 0
+    largest_no_contig = 0
+    small_larg_cover = 1.0
+    small_larg_cover_name = "asd"
+    smallest_cum_frac = 1.0
+
+    # for bam_file in snakemake_input:
+    for bam_file, ref_fasta in zip(snakemake.input.bams, snakemake.input.refs):
+        current_contig = 1
+
+        ref_fasta = pysam.FastaFile(ref_fasta)
+
+        with pysam.AlignmentFile(bam_file, "rb") as samfile:
+            total_contigs = samfile.count()
+            accession = samfile.get_reference_name(0)
+
+            largest_no_contig = (
+                total_contigs
+                if total_contigs > largest_no_contig
+                else largest_no_contig
+            )
+
+        with pysam.AlignmentFile(bam_file, "rb") as samfile:
+            ref_lengths = samfile.lengths[0]
+            largest_coverage = 0
+            cum_frac = 0
+            for read in samfile.fetch():
+                query_alignment_length = read.query_alignment_length
+                frac = round(query_alignment_length / ref_lengths, 2)
+
+                # Calculate edit distance from CIGAR string, because NM tag counts matching Ns as edits.
+                edit = get_edit_dist(read, ref_fasta)
+
+                cum_frac += frac
+                cum_frac = round(cum_frac, 2)
+                sum_of_edit_dist = sum_of_edit_dist + edit
+                edit_frac = round(edit / query_alignment_length, 5)
+                largest_coverage = frac if frac > largest_coverage else largest_coverage
+
+                print(
+                    accession,
+                    current_contig,
+                    total_contigs,
+                    query_alignment_length,
+                    ref_lengths,
+                    frac,
+                    cum_frac,
+                    edit,
+                    read.cigarstring,
+                    edit_frac,
+                    sep="\t",
+                    file=out,
+                )
+
+                current_contig += 1
+            smallest_cum_frac = (
+                cum_frac if smallest_cum_frac > cum_frac else smallest_cum_frac
+            )
+            small_larg_cover = (
+                largest_coverage
+                if small_larg_cover > largest_coverage
+                else small_larg_cover
+            )
+            small_larg_cover_name = (
+                accession
+                if small_larg_cover >= largest_coverage
+                else small_larg_cover_name
+            )
+
+    print("Largest number of contigs")
+    print(largest_no_contig)
+    print("Smallest largest coverage in " + str(small_larg_cover_name))
+    print(small_larg_cover)
+    print("Sum of edit distances")
+    print(sum_of_edit_dist)
+    print("Smallest cum. fraction of contigs")
+    print(smallest_cum_frac)
+    print("Largest number of contigs", file=out)
+    print(largest_no_contig, file=out)
+    print("Smallest largest coverage in " + str(small_larg_cover_name), file=out)
+    print(small_larg_cover, file=out)
+    print("Sum of edit distances", file=out)
+    print(sum_of_edit_dist, file=out)
+    print("Smallest cum. fraction of contigs", file=out)
+    print(smallest_cum_frac, file=out)

From 182121ba0ae7b5121a8719a008806bc156cfb066 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Tue, 10 Oct 2023 09:55:21 +0200
Subject: [PATCH 28/43] chore(deps): bump github/super-linter from 4.10.1 to
 5.0.0 (#593)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Bumps [github/super-linter](https://github.com/github/super-linter) from 4.10.1 to 5.0.0.
- [Release notes](https://github.com/github/super-linter/releases)
- [Changelog](https://github.com/github/super-linter/blob/main/docs/release-process.md)
- [Commits](https://github.com/github/super-linter/compare/v4.10.1...v5.0.0)

---
updated-dependencies:
- dependency-name: github/super-linter
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Johannes Köster <johannes.koester@tu-dortmund.de>
---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 57eb14142..e7c077081 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -24,7 +24,7 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - name: Formatting
-        uses: github/super-linter@v4.10.1
+        uses: github/super-linter@v5.0.0
         env:
           VALIDATE_ALL_CODEBASE: false
           DEFAULT_BRANCH: master

From 6bd84342cce0727d1af8dd35f92f967bd43eb2e2 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Tue, 24 Oct 2023 16:58:25 +0200
Subject: [PATCH 29/43] chore(deps): bump docker/setup-buildx-action from 2 to
 3 (#605)

Bumps [docker/setup-buildx-action](https://github.com/docker/setup-buildx-action) from 2 to 3.
- [Release notes](https://github.com/docker/setup-buildx-action/releases)
- [Commits](https://github.com/docker/setup-buildx-action/compare/v2...v3)

---
updated-dependencies:
- dependency-name: docker/setup-buildx-action
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
---
 .github/workflows/release-please.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index acb36005b..2c4b823dc 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -128,7 +128,7 @@ jobs:
 
       - name: Set up Docker Buildx
         if: ${{ steps.release.outputs.release_created == 'true' }}
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Login to Quay Registry
         if: ${{ steps.release.outputs.release_created == 'true' }}

From 0070d8927290dd01f418b876b60f3405158f1ab9 Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Tue, 31 Oct 2023 14:33:10 +0100
Subject: [PATCH 30/43] fix: update multiqc (#607)

* update multiqc

* change action with pinned python version

* re-implement ont testing

* update multiqc

* leave old fastqc version

* input only one fastq file

* update fastqc and add resources

* add new input rule for only one fastq file

* fmt

* fmt

* fmt

* update multiqc

* exclude kraken input

* iclude TODO for kraken in multiqc
---
 .github/workflows/main.yml | 23 +++++++++++++----------
 workflow/rules/common.smk  |  9 ++++-----
 workflow/rules/qc.smk      | 19 ++++++++++++-------
 3 files changed, 29 insertions(+), 22 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index e7c077081..1dd78e03f 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -71,11 +71,14 @@ jobs:
       matrix:
         rule: [all, all -npr]
         # disable ont actions
-        # technology: [all, illumina, ont, ion]
-        technology: [all, illumina, ion]
+        technology: [all, illumina, ont, ion]
+        # technology: [all, illumina, ion]
         seq_method: [shotgun, amplicon]
     steps:
       - uses: actions/checkout@v2
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
 
       # android - will release about 10 GB if you don't need Android
       # dotnet  - will release about 20 GB if you don't need .NET
@@ -103,14 +106,14 @@ jobs:
           curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/B.1.1.7.reads.1.fastq.gz > .tests/data/B117.2.fastq.gz
           echo sample_name,fq1,fq2,date,is_amplicon_data,technology > .tests/config/pep/samples.csv
           echo illumina-test,data/B117.1.fastq.gz,data/B117.2.fastq.gz,2022-01-01,$AMPLICON,illumina >> .tests/config/pep/samples.csv
-      # - name: Prepare test data for Oxford Nanopore
-      #   if: steps.test-data.outputs.cache-hit != true && (startsWith(matrix.rule, 'all') && matrix.technology == 'ont' || matrix.rule == 'compare_assemblers')
-      #   run: |
-      #     if [[ "${{ matrix.seq_method }}"  = "shotgun" ]] ; then export AMPLICON=0; else export AMPLICON=1; fi
-      #     mkdir -p .tests/data
-      #     curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/ont_reads.fastq.gz > .tests/data/ont_reads.fastq.gz
-      #     echo sample_name,fq1,date,is_amplicon_data,technology > .tests/config/pep/samples.csv
-      #     echo ont-test,data/ont_reads.fastq.gz,2022-01-01,$AMPLICON,ont >> .tests/config/pep/samples.csv
+      - name: Prepare test data for Oxford Nanopore
+        if: steps.test-data.outputs.cache-hit != true && (startsWith(matrix.rule, 'all') && matrix.technology == 'ont' || matrix.rule == 'compare_assemblers')
+        run: |
+          if [[ "${{ matrix.seq_method }}"  = "shotgun" ]] ; then export AMPLICON=0; else export AMPLICON=1; fi
+          mkdir -p .tests/data
+          curl -L https://github.com/thomasbtf/small-kraken-db/raw/master/ont_reads.fastq.gz > .tests/data/ont_reads.fastq.gz
+          echo sample_name,fq1,date,is_amplicon_data,technology > .tests/config/pep/samples.csv
+          echo ont-test,data/ont_reads.fastq.gz,2022-01-01,$AMPLICON,ont >> .tests/config/pep/samples.csv
       - name: Prepare test data for Ion Torrent
         if: steps.test-data.outputs.cache-hit != true && (startsWith(matrix.rule, 'all') && matrix.technology == 'ion' || matrix.rule == 'compare_assemblers')
         run: |
diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
index d712652ad..a372380eb 100644
--- a/workflow/rules/common.smk
+++ b/workflow/rules/common.smk
@@ -71,7 +71,6 @@ def get_samples_for_date(date, filtered=False):
     # filter
     if filtered:
         with checkpoints.quality_filter.get(date=date).output.passed_filter.open() as f:
-
             passend_samples = []
             for line in f:
                 passend_samples.append(line.strip())
@@ -212,6 +211,10 @@ def get_fastqs(wildcards):
         return pep.sample_table.loc[wildcards.sample][["fq1"]]
 
 
+def get_fastqc_input(wildcards):
+    return pep.sample_table.loc[wildcards.sample][["fq1"]]
+
+
 def get_resource(name):
     return workflow.source_path(f"../../resources/{name}")
 
@@ -406,7 +409,6 @@ def get_reads(wildcards):
         or wildcards.reference.startswith("polished-")
         or wildcards.reference.startswith("consensus-")
     ):
-
         illumina_pattern = expand(
             "results/{date}/trimmed/fastp-pe/{sample}.{read}.fastq.gz",
             read=[1, 2],
@@ -683,7 +685,6 @@ def generate_mixtures(wildcards):
         mixture_list = []
 
         for mix in range(no_mixtures):
-
             fractions = [random.randint(1, 100) for _ in range(no_strains)]
             s = sum(fractions)
             fractions = [round(i / s * 100) for i in fractions]
@@ -964,7 +965,6 @@ def get_assemblies_for_submission(wildcards, agg_type):
                 return "results/{date}/contigs/pseudoassembled/{sample}.fasta"
 
     if wildcards.date != BENCHMARK_DATE_WILDCARD:
-
         all_samples_for_date = get_samples_for_date(wildcards.date)
 
         masked_samples = load_filtered_samples(wildcards, "masked-assembly")
@@ -1558,7 +1558,6 @@ def get_aggregated_pangolin_calls(wildcards, return_list="paths"):
     expanded_patterns = []
 
     for sample in samples:
-
         stage_wildcards = get_pattern_by_technology(
             wildcards,
             sample=sample,
diff --git a/workflow/rules/qc.smk b/workflow/rules/qc.smk
index d45cd0a38b..9d80ed7cb 100644
--- a/workflow/rules/qc.smk
+++ b/workflow/rules/qc.smk
@@ -6,14 +6,17 @@
 
 rule fastqc:
     input:
-        get_fastqs,
+        get_fastqc_input,
     output:
         html="results/{date}/qc/fastqc/{sample}.html",
         zip="results/{date}/qc/fastqc/{sample}_fastqc.zip",
     log:
         "logs/{date}/fastqc/{sample}.log",
+    threads: 1
+    resources:
+        mem_mb=1024,
     wrapper:
-        "v1.12.2/bio/fastqc"
+        "v2.6.0/bio/fastqc"
 
 
 # TODO Change multiqc rules back to MultiQC wrapper once v1.11 is released
@@ -33,8 +36,9 @@ rule multiqc:
         ),
         expand_samples_for_date("logs/{{date}}/kallisto_quant/{sample}.log"),
         get_fastp_results,
-        get_kraken_output,
-        get_kraken_output_after_filtering,
+        # TODO re-implement kraken output
+        # get_kraken_output,
+        # get_kraken_output_after_filtering,
     output:
         "results/{date}/qc/multiqc.html",
     params:
@@ -44,7 +48,7 @@ rule multiqc:
     log:
         "logs/{date}/multiqc.log",
     wrapper:
-        "v1.15.1/bio/multiqc"
+        "v2.8.0/bio/multiqc"
 
 
 rule multiqc_lab:
@@ -56,7 +60,8 @@ rule multiqc_lab:
             ]
         ),
         get_fastp_results,
-        get_kraken_output,
+        # TODO re-implement kraken output
+        # get_kraken_output,
     output:
         report(
             "results/{date}/qc/laboratory/multiqc.html",
@@ -70,7 +75,7 @@ rule multiqc_lab:
     log:
         "logs/{date}/multiqc.log",
     wrapper:
-        "v1.15.1/bio/multiqc"
+        "v2.8.0/bio/multiqc"
 
 
 rule samtools_flagstat:

From 7106afa390bdfdde8048d28ade9cff80b1187640 Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Mon, 6 Nov 2023 09:56:04 +0100
Subject: [PATCH 31/43] update pangolin to version 4.3 (#610)

---
 workflow/envs/pangolin.yaml | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/workflow/envs/pangolin.yaml b/workflow/envs/pangolin.yaml
index 93a50ace5..f6a26ad42 100644
--- a/workflow/envs/pangolin.yaml
+++ b/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

From 34701af485aa1ec199a418ec1487a97677f624ca Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20K=C3=B6ster?= <johannes.koester@tu-dortmund.de>
Date: Mon, 13 Nov 2023 13:03:17 +0100
Subject: [PATCH 32/43] perf: update to varlociraptor 8.4 (#596)

* Update to latest varlociraptor

* Update varlociraptor.yaml

* Update config.yaml

* trigger rerun

---------

Co-authored-by: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
---
 config/config.yaml               | 6 +++---
 workflow/envs/varlociraptor.yaml | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/config/config.yaml b/config/config.yaml
index afea4a946..898b305ac 100644
--- a/config/config.yaml
+++ b/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
 
diff --git a/workflow/envs/varlociraptor.yaml b/workflow/envs/varlociraptor.yaml
index 151fb2668..8501cab77 100644
--- a/workflow/envs/varlociraptor.yaml
+++ b/workflow/envs/varlociraptor.yaml
@@ -3,4 +3,4 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - varlociraptor =6.0
+  - varlociraptor =8.4

From 33ac5f7b4f7af8bbb500e9f531ccbdc45ac9427f Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Wed, 15 Nov 2023 11:53:40 +0100
Subject: [PATCH 33/43] feat: Update README.md for dark/light theme (#614)

* Update README.md for dark/light theme

* Update README.md

* Update README.md

* Update README.md
---
 README.md | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 0cbd7b4f2..85ddca2b2 100644
--- a/README.md
+++ b/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
 

From 2bb74bfc26dee80af7d04089aafe636ea7c6d76a Mon Sep 17 00:00:00 2001
From: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Date: Wed, 15 Nov 2023 14:43:15 +0100
Subject: [PATCH 34/43] fix: QA genome generation (#613)

* fix deprecated squeeze

* fix wrong seq name

* fmt

* remove not needed file handling
---
 workflow/scripts/masking.py        | 8 ++------
 workflow/scripts/quality-filter.py | 8 +++-----
 2 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/workflow/scripts/masking.py b/workflow/scripts/masking.py
index 95fdb9d75..e02d46009 100644
--- a/workflow/scripts/masking.py
+++ b/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)
 
 
diff --git a/workflow/scripts/quality-filter.py b/workflow/scripts/quality-filter.py
index 7cc41b50c..68977de25 100644
--- a/workflow/scripts/quality-filter.py
+++ b/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

From 7f6146e925913480d26b600abd8815ae83127fad Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Thu, 16 Nov 2023 14:36:28 +0100
Subject: [PATCH 35/43] chore(deps): bump actions/checkout from 2 to 4 (#602)

Bumps [actions/checkout](https://github.com/actions/checkout) from 2 to 4.
- [Release notes](https://github.com/actions/checkout/releases)
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/checkout/compare/v2...v4)

---
updated-dependencies:
- dependency-name: actions/checkout
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 .github/workflows/copyright-preamble.yml |  2 +-
 .github/workflows/documentation.yml      |  2 +-
 .github/workflows/main.yml               | 10 +++++-----
 .github/workflows/release-please.yml     |  4 ++--
 .github/workflows/update-pangolin.yaml   |  2 +-
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/.github/workflows/copyright-preamble.yml b/.github/workflows/copyright-preamble.yml
index 50aa610ff..4005485fe 100644
--- a/.github/workflows/copyright-preamble.yml
+++ b/.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/copyright-action@v1.0.0
         with:
diff --git a/.github/workflows/documentation.yml b/.github/workflows/documentation.yml
index 226a47ce4..2db38f85c 100644
--- a/.github/workflows/documentation.yml
+++ b/.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
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 1dd78e03f..728c2546a 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -22,7 +22,7 @@ jobs:
   Formatting:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Formatting
         uses: github/super-linter@v5.0.0
         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/snakemake-github-action@v1.24.0
         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/action@v3.0.0
 
@@ -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
diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index 2c4b823dc..0f2ca6599 100644
--- a/.github/workflows/release-please.yml
+++ b/.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' }}
diff --git a/.github/workflows/update-pangolin.yaml b/.github/workflows/update-pangolin.yaml
index 99a9e4b53..736c8fd18 100644
--- a/.github/workflows/update-pangolin.yaml
+++ b/.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

From b986b20b226a0bae74cec0cbe815892b20debe5f Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Thu, 16 Nov 2023 17:09:14 +0100
Subject: [PATCH 36/43] chore(deps): bump khan/pull-request-workflow-cancel
 from 1.0.0 to 1.0.1 (#580)

Bumps [khan/pull-request-workflow-cancel](https://github.com/khan/pull-request-workflow-cancel) from 1.0.0 to 1.0.1.
- [Release notes](https://github.com/khan/pull-request-workflow-cancel/releases)
- [Commits](https://github.com/khan/pull-request-workflow-cancel/compare/1.0.0...1.0.1)

---
updated-dependencies:
- dependency-name: khan/pull-request-workflow-cancel
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 .github/workflows/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 728c2546a..ea3320a80 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.ref != 'refs/heads/master'
     steps:
-      - uses: khan/pull-request-workflow-cancel@1.0.0
+      - uses: khan/pull-request-workflow-cancel@1.0.1
         with:
           workflows: "main.yml"
         env:

From ed041c832987f014e267a85686465b1ac469fa11 Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Fri, 17 Nov 2023 10:13:44 +0100
Subject: [PATCH 37/43] chore(master): release 0.16.0 (#586)

* chore(master): release 0.16.0

* Changed containerized tag to 0.16.0

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 CHANGELOG.md       | 23 +++++++++++++++++++++++
 version.txt        |  2 +-
 workflow/Snakefile |  2 +-
 3 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index ac27577da..5f16dd03d 100644
--- a/CHANGELOG.md
+++ b/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)
 
 
diff --git a/version.txt b/version.txt
index e815b861f..04a373efe 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-0.15.1
+0.16.0
diff --git a/workflow/Snakefile b/workflow/Snakefile
index d8f339ce5..cd146b369 100644
--- a/workflow/Snakefile
+++ b/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"

From d87c9ad42cd295f429b5e5f8d17fba1ad7d11e60 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Fri, 17 Nov 2023 14:17:16 +0100
Subject: [PATCH 38/43] chore(deps): bump peter-evans/create-pull-request from
 4 to 5 (#592)

Bumps [peter-evans/create-pull-request](https://github.com/peter-evans/create-pull-request) from 4 to 5.
- [Release notes](https://github.com/peter-evans/create-pull-request/releases)
- [Commits](https://github.com/peter-evans/create-pull-request/compare/v4...v5)

---
updated-dependencies:
- dependency-name: peter-evans/create-pull-request
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 .github/workflows/copyright-preamble.yml | 2 +-
 .github/workflows/update-pangolin.yaml   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/copyright-preamble.yml b/.github/workflows/copyright-preamble.yml
index 4005485fe..dae852eed 100644
--- a/.github/workflows/copyright-preamble.yml
+++ b/.github/workflows/copyright-preamble.yml
@@ -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
diff --git a/.github/workflows/update-pangolin.yaml b/.github/workflows/update-pangolin.yaml
index 736c8fd18..bdb8d0557 100644
--- a/.github/workflows/update-pangolin.yaml
+++ b/.github/workflows/update-pangolin.yaml
@@ -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 <noreply@github.com>

From 4b2f34c54b522152f402112b7d82c42d6c95b95d Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Fri, 17 Nov 2023 16:07:09 +0100
Subject: [PATCH 39/43] chore(deps): bump docker/build-push-action from 3 to 5
 (#599)

Bumps [docker/build-push-action](https://github.com/docker/build-push-action) from 3 to 5.
- [Release notes](https://github.com/docker/build-push-action/releases)
- [Commits](https://github.com/docker/build-push-action/compare/v3...v5)

---
updated-dependencies:
- dependency-name: docker/build-push-action
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 .github/workflows/release-please.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index 0f2ca6599..ad185be43 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -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

From 99ad0e14c8ac6196dd18dbe4f16f1bc01b90b035 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Sat, 18 Nov 2023 12:00:31 +0100
Subject: [PATCH 40/43] chore(deps): bump snakemake/snakemake-github-action
 (#600)

Bumps [snakemake/snakemake-github-action](https://github.com/snakemake/snakemake-github-action) from 1.24.0 to 1.25.1.
- [Release notes](https://github.com/snakemake/snakemake-github-action/releases)
- [Changelog](https://github.com/snakemake/snakemake-github-action/blob/master/CHANGELOG.md)
- [Commits](https://github.com/snakemake/snakemake-github-action/compare/v1.24.0...v1.25.1)

---
updated-dependencies:
- dependency-name: snakemake/snakemake-github-action
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 .github/workflows/main.yml           | 10 +++++-----
 .github/workflows/release-please.yml |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index ea3320a80..828c4acb9 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -41,7 +41,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Lint workflow
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         with:
           directory: .
           snakefile: workflow/Snakefile
@@ -137,14 +137,14 @@ jobs:
           curl "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nuccore&id=MZ314997.1&rettype=fasta" | sed '$ d' > .tests/resources/genomes/B.1.1.7.fasta
           curl "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nuccore&id=MZ314998.1&rettype=fasta" | sed '$ d' > .tests/resources/genomes/B.1.351.fasta
       - name: Test rule ${{ matrix.rule }} on ${{ matrix.technology }} ${{ matrix.seq_method }} data
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         with:
           directory: .tests
           snakefile: workflow/Snakefile
           args: "-pr --use-conda --show-failed-logs --cores 2 --resources ncbi_api_requests=1 --conda-cleanup-pkgs cache --conda-frontend mamba ${{ matrix.rule }}"
 
       - name: Test report
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         if: startsWith(matrix.rule, 'all -npr') != true
         with:
           directory: .tests
@@ -315,14 +315,14 @@ jobs:
           curl "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nuccore&id=MZ314997.1&rettype=fasta" | sed '$ d' > .tests/resources/genomes/B.1.1.7.fasta
           curl "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nuccore&id=MZ314998.1&rettype=fasta" | sed '$ d' > .tests/resources/genomes/B.1.351.fasta
       - name: Test rule ${{ matrix.rule }}
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         with:
           directory: .tests
           snakefile: workflow/Snakefile
           args: "-pr --use-conda --show-failed-logs --cores 2 --resources ncbi_api_requests=1 --conda-cleanup-pkgs cache --conda-frontend mamba ${{ matrix.rule }}"
 
       - name: Test report
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         if: startsWith(matrix.rule, 'all -npr') != true
         with:
           directory: .tests
diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index ad185be43..a944169b2 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -111,7 +111,7 @@ jobs:
 
       - name: Create Dockerfile
         if: ${{ steps.release.outputs.release_created == 'true' }}
-        uses: snakemake/snakemake-github-action@v1.24.0
+        uses: snakemake/snakemake-github-action@v1.25.1
         with:
           directory: .
           snakefile: workflow/Snakefile

From 521df0ce4a667d16800f3509b796c9f7ce0564b8 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Sat, 18 Nov 2023 15:08:09 +0100
Subject: [PATCH 41/43] chore(deps): bump docker/login-action from 2 to 3
 (#601)

Bumps [docker/login-action](https://github.com/docker/login-action) from 2 to 3.
- [Release notes](https://github.com/docker/login-action/releases)
- [Commits](https://github.com/docker/login-action/compare/v2...v3)

---
updated-dependencies:
- dependency-name: docker/login-action
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 .github/workflows/release-please.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index a944169b2..9c0f9cb25 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -132,7 +132,7 @@ jobs:
 
       - name: Login to Quay Registry
         if: ${{ steps.release.outputs.release_created == 'true' }}
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: quay.io
           username: uncovar+robot

From c44761161720004ad505eb1bbfafd76881d77ffe Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Sat, 18 Nov 2023 16:51:57 +0100
Subject: [PATCH 42/43] chore(deps): bump alstr/todo-to-issue-action from 4.6
 to 4.11 (#603)

Bumps [alstr/todo-to-issue-action](https://github.com/alstr/todo-to-issue-action) from 4.6 to 4.11.
- [Release notes](https://github.com/alstr/todo-to-issue-action/releases)
- [Commits](https://github.com/alstr/todo-to-issue-action/compare/v4.6...v4.11)

---
updated-dependencies:
- dependency-name: alstr/todo-to-issue-action
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Alexander Thomas <77535027+alethomas@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 .github/workflows/check-todos.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/check-todos.yml b/.github/workflows/check-todos.yml
index 6e5247d5c..ef1b16de0 100644
--- a/.github/workflows/check-todos.yml
+++ b/.github/workflows/check-todos.yml
@@ -11,4 +11,4 @@ jobs:
     steps:
       - uses: "actions/checkout@master"
       - name: "TODO to Issue"
-        uses: "alstr/todo-to-issue-action@v4.6"
+        uses: "alstr/todo-to-issue-action@v4.11"

From b232c0043134cc15f7d0bbedcd02275d16ef38d1 Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Sat, 18 Nov 2023 18:36:45 +0100
Subject: [PATCH 43/43] chore(deps): bump docker/setup-qemu-action from 2 to 3
 (#604)

Bumps [docker/setup-qemu-action](https://github.com/docker/setup-qemu-action) from 2 to 3.
- [Release notes](https://github.com/docker/setup-qemu-action/releases)
- [Commits](https://github.com/docker/setup-qemu-action/compare/v2...v3)

---
updated-dependencies:
- dependency-name: docker/setup-qemu-action
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: vBassewitz <104062464+vBassewitz@users.noreply.github.com>
---
 .github/workflows/release-please.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index 9c0f9cb25..1e69799d6 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -124,7 +124,7 @@ jobs:
 
       - name: Set up QEMU
         if: ${{ steps.release.outputs.release_created == 'true' }}
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         if: ${{ steps.release.outputs.release_created == 'true' }}