Feature/checkm2 (#346)

* feat(docker): add checkm2 docker image * feat(magAttributes): add checkm2 process * doc(magAttributes): add checkm2 documentation * feat(config): add checkm2 parameters * feat(magAttributes): add checkm2 tests * fix(magAttributes): allow emgb script to search for checkm2 results * fix(aggregation): cleanup output directory of previous runs * fix(magAttributes): create yaml for db tests in work dir * fix(magAttributes): create secrets for checkm2 tests * fix(magAttributes): set missing credentials * fix(magAttributes): set missing checkm2 secrets variable * fix(magAttributes): add missing secrets tag for checkm2
metagenomics · Feb 7, 2024 · efd1725 · efd1725
1 parent 85af85e
commit efd1725
Show file tree

Hide file tree

Showing 14 changed files with 203 additions and 69 deletions.
diff --git a/.github/workflows/workflow_modules.yml b/.github/workflows/workflow_modules.yml
@@ -91,7 +91,9 @@ jobs:
           " --databases=/vol/scratch/databases/      " \
           ./example_params/fullPipelineONT.yml "${WORK_DIR}" \
           ${PROFILE} ${VERSION}  || exit 1
-
+      - name: Cleanup previous checkm results for correct aggregation run
+        run: |
+          rm -rf output
       - name: Test Full Pipeline ONT and Illumina Run
         run: |
           VERSION=$(sort -r VERSIONS.txt | tail -n 1)
@@ -120,6 +122,16 @@ jobs:
     runs-on: [ self-hosted, slurm]
     steps:
       - uses: actions/checkout@v2
+      - name: Set Secrets
+        run: |
+          make set_secrets SECRET_NAME=S3_ACCESS SECRET_VALUE=${{ secrets.S3_ACCESS }}
+          make set_secrets SECRET_NAME=S3_SECRET SECRET_VALUE=${{ secrets.S3_VALUE }}
+          make set_secrets SECRET_NAME=S3_checkm_ACCESS SECRET_VALUE=${{ secrets.S3_ACCESS }}
+          make set_secrets SECRET_NAME=S3_checkm_SECRET SECRET_VALUE=${{ secrets.S3_VALUE }}
+          make set_secrets SECRET_NAME=S3_checkm2_ACCESS SECRET_VALUE=${{ secrets.S3_ACCESS }}
+          make set_secrets SECRET_NAME=S3_checkm2_SECRET SECRET_VALUE=${{ secrets.S3_VALUE }}
+          make set_secrets SECRET_NAME=S3_gtdb_ACCESS SECRET_VALUE=${{ secrets.S3_ACCESS }}
+          make set_secrets SECRET_NAME=S3_gtdb_SECRET SECRET_VALUE=${{ secrets.S3_VALUE }}
       - name: Test MAG Attributes
         run: |
           bash ./scripts/test_magAttributes.sh \
@@ -131,29 +143,34 @@ jobs:
           bash ./scripts/test_magAttributes.sh \
           " --databases=/vol/scratch/databases/    " \
           example_params/magAttributes_fraction/magAttributes.yml "${WORK_DIR}" ${PROFILE} || exit 1
-      - name: Set Secrets
-        run: |
-          make set_secrets SECRET_NAME=S3_ACCESS SECRET_VALUE=${{ secrets.S3_ACCESS }}
-          make set_secrets SECRET_NAME=S3_SECRET SECRET_VALUE=${{ secrets.S3_VALUE }}
-          make set_secrets SECRET_NAME=S3_checkm_ACCESS SECRET_VALUE=${{ secrets.S3_ACCESS }}
-          make set_secrets SECRET_NAME=S3_checkm_SECRET SECRET_VALUE=${{ secrets.S3_VALUE }}
-          make set_secrets SECRET_NAME=S3_gtdb_ACCESS SECRET_VALUE=${{ secrets.S3_ACCESS }}
-          make set_secrets SECRET_NAME=S3_gtdb_SECRET SECRET_VALUE=${{ secrets.S3_VALUE }}
-
-
-      - name: Test Checkm runs against different database parameters
+      - name: Test Checkm1 runs against different database parameters
         run: |
           make runDatabaseTest MODULE_DB_TEST_EXTRACTED="/vol/spool/toolkit/checkm/" \
                                MODULE_DB_TEST_MD5SUM="0963b301dfe9345ea4be1246e32f6728" \
                                MODULE_DB_TEST_HTTPS="https://openstack.cebitec.uni-bielefeld.de:8080/databases/checkm_data_2015_01_16.tar.gz" \
                                MODULE_DB_TEST_PATH="/vol/spool/toolkit/checkm_data_2015_01_16.tar.gz" MODULE_DB_TEST_S3PATH="s3://databases/checkm_data_2015_01_16.tar.gz" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases/checkm/*"  \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/checkm \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/checkm \
                                MODULE_DB_TEST_YML=example_params/magAttributes.yml \
-                               MODULE_DB_TEST_YML_PATH="'.steps.magAttributes.checkm.database=env(database),del(.steps.magAttributes.gtdb,.steps.magAttributes.prokka)'" \
+                               MODULE_DB_TEST_YML_PATH="'.steps.magAttributes.checkm.database=env(database),del(.steps.magAttributes.gtdb,.steps.magAttributes.checkm2,.steps.magAttributes.prokka)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_magAttributes.sh" MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/checkm_yaml_database_tests" \
                                MODULE_DB_TEST_REMOVE_DB="yes"
+
+      - name: Test Checkm2 runs against different database parameters
+        run: |
+          make runDatabaseTest MODULE_DB_TEST_EXTRACTED="/vol/spool/toolkit/checkm2/" \
+                               MODULE_DB_TEST_MD5SUM="a634cb3d31a1f56f2912b74005f25f09" \
+                               MODULE_DB_TEST_HTTPS="https://openstack.cebitec.uni-bielefeld.de:8080/databases/checkm2_v2.tar.gz" \
+                               MODULE_DB_TEST_PATH="/vol/spool/toolkit/checkm2_v2.tar.gz" MODULE_DB_TEST_S3PATH="s3://databases/checkm2_v2.tar.gz" \
+                               MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases/checkm2/*"  \
+                               MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/checkm2 \
+                               MODULE_DB_TEST_YML=example_params/magAttributes.yml \
+                               MODULE_DB_TEST_YML_PATH="'.steps.magAttributes.checkm2.database=env(database),del(.steps.magAttributes.gtdb,.steps.magAttributes.checkm,.steps.magAttributes.prokka)'" \
+                               MODULE_DB_TEST_YML_SCRIPT="./scripts/test_magAttributes.sh" MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/checkm2_yaml_database_tests" \
+                               MODULE_DB_TEST_REMOVE_DB="yes"
+ 
 
       - name: Test GTDB runs against different database parameters
         run: |
@@ -163,9 +180,10 @@ jobs:
                                MODULE_DB_TEST_PATH="/vol/spool/toolkit/gtdbtk_r214_data.tar.gz" MODULE_DB_TEST_S3PATH="s3://databases/gtdbtk_r214_data.tar.gz" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases/gtdbtk_r214_data/*" \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/gtdb \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials \
+                               MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/gtdb \
                                MODULE_DB_TEST_YML=example_params/magAttributes.yml \
-                               MODULE_DB_TEST_YML_PATH="'.steps.magAttributes.gtdb.database=env(database),del(.steps.magAttributes.checkm,.steps.magAttributes.prokka)'" \
+                               MODULE_DB_TEST_YML_PATH="'.steps.magAttributes.gtdb.database=env(database),del(.steps.magAttributes.checkm,.steps.magAttributes.checkm2,.steps.magAttributes.prokka)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_magAttributes.sh" MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/gtdb_yaml_database_tests"  \
                                MODULE_DB_TEST_REMOVE_DB="yes"
 
@@ -296,7 +314,8 @@ jobs:
                                MODULE_DB_TEST_PATH="/vol/spool/toolkit/card_20221209.tar.bz2" MODULE_DB_TEST_S3PATH="s3://databases/card_20221209.tar.bz2" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases/card_20221209/*" \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/rgi \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials \
+                               MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/rgi \
                                MODULE_DB_TEST_YML=example_params/annotation.yml \
                                MODULE_DB_TEST_YML_PATH="'.steps.annotation.rgi.database=env(database),del(.steps.annotation.mmseqs2,.steps.annotation.keggFromBlast)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_annotation.sh" MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/rgi_yaml_database_tests" \
@@ -311,7 +330,8 @@ jobs:
                                MODULE_DB_TEST_PATH="/vol/spool/toolkit/kegg.tar.gz" MODULE_DB_TEST_S3PATH="s3://databases_internal/kegg-links-mirror-2021-01.tar.gz" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases_internal/kegg-links-mirror-2021-01/*"  \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/kegg \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials \
+                               MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/kegg \
                                MODULE_DB_TEST_YML=example_params/annotation.yml \
                                MODULE_DB_TEST_YML_PATH="'.steps.annotation.keggFromBlast.database=env(database),del(.steps.annotation.rgi)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_annotation.sh" MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/kegg_yaml_database_tests" \
@@ -339,7 +359,8 @@ jobs:
                                MODULE_DB_TEST_PATH="/vol/spool/toolkit/kegg-mirror-2021-01_mmseqs.tar.zst" MODULE_DB_TEST_S3PATH="s3://databases_internal/kegg-mirror-2021-01_mmseqs.tar.zst" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases_internal/kegg-mirror-2021-01_mmseqs/*" \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/mmseqs2 \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials \
+                               MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/mmseqs2 \
                                MODULE_DB_TEST_YML=example_params/annotation.yml \
                                MODULE_DB_TEST_YML_PATH="'.steps.annotation.mmseqs2.kegg.database=env(database),del(.steps.annotation.rgi,.steps.annotation.keggFromBlast)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_annotation.sh" \
@@ -387,7 +408,8 @@ jobs:
                                MODULE_DB_TEST_S3PATH="s3://databases/plasmids_plsdb_20220929.tar.bz2" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases/plasmids_plsdb_20220929/*" \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/plasmids \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials \
+                               MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/plasmids \
                                MODULE_DB_TEST_YML=example_params/plasmid.yml MODULE_DB_TEST_YML_PATH="'.steps.plasmid.PLSDB.database=env(database),del(.steps.plasmid.Platon,.steps.plasmid.ViralVerifyPlasmid,.steps.plasmid.MobTyper)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_plasmids.sh" MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/plasmid_yaml_database_tests" \
                                MODULE_DB_TEST_REMOVE_DB="yes"
@@ -399,7 +421,7 @@ jobs:
                                MODULE_DB_TEST_PATH="/vol/spool/toolkit/pfam-A_35.0.hmm.gz" MODULE_DB_TEST_S3PATH="s3://databases/pfam-A_35.0.hmm.gz" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases/pfam-A_35.*.hmm" \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl  --no-sign-request  --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/plasmids MODULE_DB_TEST_YML=example_params/plasmid.yml \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/plasmids MODULE_DB_TEST_YML=example_params/plasmid.yml \
                                MODULE_DB_TEST_YML_PATH="'.steps.plasmid.ViralVerifyPlasmid.database=env(database),del(.steps.plasmid.Platon,.steps.plasmid.PlasClass,.steps.plasmid.MobTyper,.steps.plasmid.PLSDB)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_plasmids.sh" \
                                MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/plasmid_yaml_database_tests" \
@@ -413,7 +435,7 @@ jobs:
                                MODULE_DB_TEST_PATH="/vol/spool/toolkit/platon_20220929.tar.gz" MODULE_DB_TEST_S3PATH="s3://databases/platon_20220929.tar.gz" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases/platon/*" \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl  --no-sign-request  --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/plasmids MODULE_DB_TEST_YML=example_params/plasmid.yml \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/plasmids MODULE_DB_TEST_YML=example_params/plasmid.yml \
                                MODULE_DB_TEST_YML_PATH="'.steps.plasmid.Platon.database=env(database),del(.steps.plasmid.ViralVerifyPlasmid,.steps.plasmid.PlasClass,.steps.plasmid.MobTyper,.steps.plasmid.PLSDB)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_plasmids.sh" MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/plasmid_yaml_database_tests" \
                                MODULE_DB_TEST_REMOVE_DB="yes"
@@ -426,7 +448,7 @@ jobs:
                                MODULE_DB_TEST_PATH="/vol/spool/toolkit/mob_20220929.gz" MODULE_DB_TEST_S3PATH="s3://databases/mob_20220929.gz" \
                                MODULE_DB_TEST_S3_DIRECTORY_PATH="s3://databases/mob_20220929/*" \
                                MODULE_DB_TEST_S5CMD_COMMAND='" --retry-count 30 --no-verify-ssl  --no-sign-request  --endpoint-url https://openstack.cebitec.uni-bielefeld.de:8080 "' \
-                               MODULE_DB_TEST_GENERATED_YML=/vol/spool/generated_yamls/plasmids MODULE_DB_TEST_YML=example_params/plasmid.yml \
+                               MODULE_DB_TEST_CREDENTIALS=/vol/spool/credentials MODULE_DB_TEST_GENERATED_YML=${WORK_DIR}/generated_yamls/plasmids MODULE_DB_TEST_YML=example_params/plasmid.yml \
                                MODULE_DB_TEST_YML_PATH="'.steps.plasmid.MobTyper.database=env(database),del(.steps.plasmid.ViralVerifyPlasmid,.steps.plasmid.PlasClass,.steps.plasmid.Platon,.steps.plasmid.PLSDB)'" \
                                MODULE_DB_TEST_YML_SCRIPT="./scripts/test_plasmids.sh" MODULE_DB_TEST_GENERATED_YML_DIR="${WORK_DIR}/plasmid_yaml_database_tests" \
                                MODULE_DB_TEST_REMOVE_DB="yes"

diff --git a/bin/emgb.sh b/bin/emgb.sh
@@ -79,7 +79,7 @@ function getContigs {
 
 
 function getBins {
-	checkm=$(find $OUTPUT_PATH/$RUN_ID/magAttributes/*/checkm/ -name "*_checkm_*.tsv" -exec readlink -f {} \; | sed 's/^/ -checkm-tsv /g')
+	checkm=$(find $OUTPUT_PATH/$RUN_ID/magAttributes/*/checkm*/ -name "*_checkm*_*.tsv" -exec readlink -f {} \; | sed 's/^/ -checkm-tsv /g')
 	gtdbtk=$(find $OUTPUT_PATH/$RUN_ID/magAttributes/*/gtdb/ -name "*.summary.tsv" -exec readlink -f {} \; | sed 's/^/ -gtdbtk-tsvs /g')
 	bins=$(find $BINS_DIR -name "*_bin.*.fa" -exec readlink -f {} \; | tail -n 1 | rev | cut -f 1 -d '/' | rev | cut -d '.' -f 1 | sed 's/^/  -bin-id-prefix /g')
 	json=" -json-gz $(pwd)/${NAME}.bins.json.gz "

diff --git a/default/fullPipeline_illumina_nanpore.yml b/default/fullPipeline_illumina_nanpore.yml
@@ -101,18 +101,12 @@ steps:
           source: https://openstack.cebitec.uni-bielefeld.de:8080/databases/gtdbtk_r214_data.tar.gz
           md5sum: 390e16b3f7b0c4463eb7a3b2149261d9
       additionalParams: " --min_af 0.65 --scratch_dir . "
-    # checkm lineage_wf
-    checkm:
+    checkm2:
       database:
         download:
-                # Use Version number in databse names
-          source: "https://openstack.cebitec.uni-bielefeld.de:8080/databases/checkm_data_2015_01_16.tar.gz"
-          md5sum: 0963b301dfe9345ea4be1246e32f6728
-      buffer: 200
-      additionalParams:
-        tree: " --reduced_tree "
-        lineage_set: " " 
-        qa: "  "
+          source: "https://openstack.cebitec.uni-bielefeld.de:8080/databases/checkm2_v2.tar.gz"
+          md5sum: a634cb3d31a1f56f2912b74005f25f09
+      additionalParams: "  "
   fragmentRecruitment:
     mashScreen:
       genomes: test_data/fragmentRecruitment/mags.tsv

diff --git a/default/fullPipeline_illumina_nanpore_without_aggregate.yml b/default/fullPipeline_illumina_nanpore_without_aggregate.yml
@@ -101,18 +101,12 @@ steps:
           source: https://openstack.cebitec.uni-bielefeld.de:8080/databases/gtdbtk_r214_data.tar.gz
           md5sum: 390e16b3f7b0c4463eb7a3b2149261d9
       additionalParams: " --min_af 0.65 --scratch_dir . "
-    # checkm lineage_wf
-    checkm:
+    checkm2:
       database:
         download:
-                # Use Version number in databse names
-          source: "https://openstack.cebitec.uni-bielefeld.de:8080/databases/checkm_data_2015_01_16.tar.gz"
-          md5sum: 0963b301dfe9345ea4be1246e32f6728
-      buffer: 200
-      additionalParams:
-        tree: " --reduced_tree "
-        lineage_set: " " 
-        qa: "  "
+          source: "https://openstack.cebitec.uni-bielefeld.de:8080/databases/checkm2_v2.tar.gz"
+          md5sum: a634cb3d31a1f56f2912b74005f25f09
+      additionalParams: "  "
   fragmentRecruitment:
     mashScreen:
       genomes: test_data/fragmentRecruitment/mags.tsv

diff --git a/docker/toolkit-checkm2/Dockerfile b/docker/toolkit-checkm2/Dockerfile
@@ -0,0 +1,14 @@
+FROM ubuntu:focal
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update \
+    && apt install -y git python3-pip prodigal diamond-aligner wget \
+    && pip3 install setuptools wheel requests packaging tqdm \    
+    && pip3 install protobuf==3.20.* scikit-learn==0.23.2 h5py==2.10.0 numpy==1.19.2 tensorflow==2.5.0 lightgbm==3.2.1 pandas==1.4.0 scipy==1.8.0
+
+ENV CHECKM2_VERSION=1.0.2
+
+RUN git clone -b $CHECKM2_VERSION --recursive https://github.com/chklovski/checkm2.git && cd checkm2 \
+    && python3 setup.py install
+
+ENV PATH="$HOME/.local/bin:$PATH"
diff --git a/docker/toolkit-checkm2/VERSION b/docker/toolkit-checkm2/VERSION
@@ -0,0 +1 @@
+1.0.2-1
diff --git a/docs/modules/magAttributes.md b/docs/modules/magAttributes.md
@@ -49,7 +49,8 @@ nextflow secrets set S3_checkm_SECRET XXXXXXX
 All GTDB files include the GTDB specific columns in addition to a `SAMPLE` column (`SAMPLE_gtdbtk.bac120.summary.tsv`, `SAMPLE_gtdbtk.ar122.summary.tsv`).
 In addition, this module produces a file `SAMPLE_gtdbtk_CHUNK.tsv` that combines both files and adds a `BIN_ID` column that adheres to the magAttributes specification
 
-### Checkm
+### Checkm and Checkm2
 
-The Checkm output adheres to the magAttributes specification and adds a `BIN_ID` and `SAMPLE` column to the output file.
+The Checkm and Checkm2 output adheres to the magAttributes specification and adds a `BIN_ID` and `SAMPLE` column to the output file.
+If Checkm2 and Checkm are both specified in the config file then only the Checkm2 results are used for downstream pipeline steps.
 
diff --git a/example_params/fullPipeline.yml b/example_params/fullPipeline.yml
@@ -53,16 +53,12 @@ steps:
           source: https://openstack.cebitec.uni-bielefeld.de:8080/databases/gtdbtk_r214_data.tar.gz
           md5sum: 390e16b3f7b0c4463eb7a3b2149261d9
       additionalParams: " --min_af 0.65 --scratch_dir . "
-    checkm:
+    checkm2:
       database:
         download:
-          source: "https://openstack.cebitec.uni-bielefeld.de:8080/databases/checkm_data_2015_01_16.tar.gz"
-          md5sum: 0963b301dfe9345ea4be1246e32f6728
-      buffer: 200
-      additionalParams:
-        tree: " --reduced_tree "
-        lineage_set: " " 
-        qa: "  "
+          source: "https://openstack.cebitec.uni-bielefeld.de:8080/databases/checkm2_v2.tar.gz"
+          md5sum: a634cb3d31a1f56f2912b74005f25f09
+      additionalParams: "  "
   fragmentRecruitment:
     mashScreen:
       genomes: test_data/fragmentRecruitment/mags.tsv