feat: upgrade to antiSMASH 7

* feat: upgrade to antismash 7

* feat: upgrade gtdbtk and gtdb to release 214

* chore: move default logs location

* chore: make an alias for rules/pipelines and name/pep

* fix: grab ARTS from release instead of git clone

* fix: correct ARTS setup

* feat: upgrade bigslice for compatibility with antiSMASH7

* test: update test for 0.7.0

* fix: enable ani_screen in gtdbtk

* fix: correct gtdb release versioning

* chore: set ani_screen off as default for gtdbtk

* docs: add quickstart video

* feat: upgrade extraction from mmseqs2 and clinker

* feat: process mmseqs2 cog feature

* fix: handle non standard BGC genbanks

* feat: enable to switch between antismash 7 and 6

* docs: mention about the WIKI

.examples/_config_example.yaml

@@ -11,27 +11,22 @@
 #   - prokka-db (optional): list of the custom accessions to use as prokka reference database.
 #   - gtdb-tax (optional): output summary file of GTDB-tk with "user_genome" and "classification" as the two minimum columns
 # (2) To define project using PEP file, only variable "name" should be given that points to the location of the PEP yaml file.
-#   - name: path to PEP .yaml file. See project example_pep for details.
+#   - pep: path to PEP .yaml file. See project example_pep for details.
+# PS: the variable pep and name is an alias
 
 projects:
-# Project 1 (yaml object)
-  - name: example
-    samples: .examples/_genome_project_example/samples.csv
-    rules: .examples/_genome_project_example/project_config.yaml
-    prokka-db: .examples/_genome_project_example/prokka-db.csv
-    gtdb-tax: .examples/_genome_project_example/gtdbtk.bac120.summary.tsv
-
 # Project 2 (PEP file)
-  - name: .examples/_pep_example/project_config.yaml
+  - pep: .examples/_pep_example/project_config.yaml
+  - pep: .examples/lactobacillus_delbruecki/project_config.yaml
 
 bgc_projects:
-  - name: config/lanthipeptide/project_config.yaml
+  - pep: .examples/lanthipeptide_lactobacillus/project_config.yaml
 
 #### GLOBAL RULE CONFIGURATION ####
 # This section configures the rules to run globally.
 # Use project specific rule configurations if you want to run different rules for each projects.
-# rules: set value to TRUE if you want to run the analysis or FALSE if you don't
-rules:
+# pipelines or rules: set value to TRUE if you want to run the analysis or FALSE if you don't
+pipelines:
   seqfu: FALSE
   mash: FALSE
   fastani: FALSE
@@ -63,3 +58,17 @@ resources_path:
   checkm: resources/checkm
   gtdbtk: resources/gtdbtk
   #RNAmmer: resources/RNAmmer # If specified, will override Barnapp in Prokka
+
+# Check for valid release versions from https://data.gtdb.ecogenomic.org/releases/
+# Examples:
+# - release 214.1, release_version r214 --> https://data.gtdb.ecogenomic.org/releases/release214/214.1/auxillary_files/gtdbtk_r214_data.tar.gz
+# - release 207, release_version r207_v2 --> https://data.gtdb.ecogenomic.org/releases/release207/207.0/auxillary_files/gtdbtk_r207_v2_data.tar.gz
+
+rule_parameters:
+  install_gtdbtk:
+    release: "214.1"
+    release_version: "r214"
+  gtdbtk:
+    ani_screen: FALSE
+  antismash:
+    version: "7" # valid versions: 6, 7

.tests/unit/antismash_overview_gather/expected/data/processed/Lactobacillus_delbrueckii/tables/df_regions_antismash_6.1.1.csv → .examples/lanthipeptide_lactobacillus/df_regions_antismash_7.0.0.csv

@@ -1,5 +1,5 @@
 bgc_id,genome_id,region,accession,start_pos,end_pos,contig_edge,product,region_length,source,gbk_path
-CR954253.1.region001,GCA_000056065.1,1.1,CR954253.1,17407,39909,False,['lanthipeptide-class-iii'],22502,bgcflow,data/interim/antismash/6.1.1/GCA_000056065.1/CR954253.1.region001.gbk
-CR954253.1.region002,GCA_000056065.1,1.2,CR954253.1,1745672,1767868,False,['lanthipeptide-class-iv'],22196,bgcflow,data/interim/antismash/6.1.1/GCA_000056065.1/CR954253.1.region002.gbk
-CP000156.1.region001,GCA_000191165.1,1.1,CP000156.1,1767251,1789447,False,['lanthipeptide-class-iv'],22196,bgcflow,data/interim/antismash/6.1.1/GCA_000191165.1/CP000156.1.region001.gbk
-CP000412.1.region001,GCA_000014405.1,1.1,CP000412.1,17283,39785,False,['lanthipeptide-class-iii'],22502,bgcflow,data/interim/antismash/6.1.1/GCA_000014405.1/CP000412.1.region001.gbk
+CR954253.1.region001,GCA_000056065.1,1.1,CR954253.1,17407,39909,False,['lanthipeptide-class-iii'],22502,bgcflow,data/interim/antismash/7.0.0/GCA_000056065.1/CR954253.1.region001.gbk
+CR954253.1.region003,GCA_000056065.1,1.3,CR954253.1,1745672,1767868,False,['lanthipeptide-class-iv'],22196,bgcflow,data/interim/antismash/7.0.0/GCA_000056065.1/CR954253.1.region003.gbk
+CP000156.1.region002,GCA_000191165.1,1.2,CP000156.1,1767251,1789447,False,['lanthipeptide-class-iv'],22196,bgcflow,data/interim/antismash/7.0.0/GCA_000191165.1/CP000156.1.region002.gbk
+CP000412.1.region001,GCA_000014405.1,1.1,CP000412.1,17283,39785,False,['lanthipeptide-class-iii'],22502,bgcflow,data/interim/antismash/7.0.0/GCA_000014405.1/CP000412.1.region001.gbk

.examples/lanthipeptide/project_config.yaml → .examples/lanthipeptide_lactobacillus/project_config.yaml

@@ -1,11 +1,12 @@
 name: lanthipeptide_lactobacillus
 pep_version: 2.1.0
 description: 'A selection of lanthipeptides from Lactobacillus delbrueckii'
-sample_table: df_antismash_6.1.1_bgc.csv
+sample_table: df_regions_antismash_7.0.0.csv
 
 rules:
   bigslice: TRUE
   bigscape: TRUE
   query-bigslice: TRUE
   clinker: TRUE
   interproscan: TRUE
+  mmseqs2: TRUE

.github/workflows/push.yml

@@ -57,6 +57,7 @@ jobs:
           python-version: 3.x
       - run: pip install git+https://github.com/NBChub/bgcflow_wrapper.git
       - run: pip install pytest-cov
+      - run: pip install alive-progress
       - name: Test coverage
         run: pytest --cov=.tests/unit .tests/unit/
       - name: Build coverage file

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 -   repo: https://github.com/Lucas-C/pre-commit-hooks
-    rev: v1.1.13
+    rev: v1.5.1
     hooks:
     -   id: forbid-crlf
     -   id: remove-crlf
@@ -9,7 +9,7 @@ repos:
     -   id: remove-tabs
         exclude_types: [csv]
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.1.0
+    rev: v4.3.0
     hooks:
     - id: trailing-whitespace
     - id: end-of-file-fixer
@@ -21,12 +21,12 @@ repos:
     hooks:
     - id: isort
 -   repo: https://github.com/ambv/black
-    rev: 22.3.0
+    rev: 23.3.0
     hooks:
     - id: black
-      language_version: python3.8
+      language_version: python3
 -   repo: https://github.com/PyCQA/flake8
-    rev: 3.9.2
+    rev: 5.0.4
     hooks:
     -   id: flake8
         args: ['--ignore=E501,W503']

.tests/unit/antismash_overview_gather/data/config/config.yaml → .tests/unit/antismash_overview/data/config/config.yaml

@@ -11,24 +11,21 @@
 #   - prokka-db (optional): list of the custom accessions to use as prokka reference database.
 #   - gtdb-tax (optional): output summary file of GTDB-tk with "user_genome" and "classification" as the two minimum columns
 # (2) To define project using PEP file, only variable "name" should be given that points to the location of the PEP yaml file.
-#   - name: path to PEP .yaml file. See project example_pep for details.
+#   - pep: path to PEP .yaml file. See project example_pep for details.
+# PS: the variable pep and name is an alias
 
 projects:
 # Project 1 (yaml object)
-#  - name: example
-#    samples: config/_genome_project_example/samples.csv
-#    rules: config/_genome_project_example/project_config.yaml
-#    prokka-db: config/_genome_project_example/prokka-db.csv
-#    gtdb-tax: config/_genome_project_example/gtdbtk.bac120.summary.tsv
-
-# Project 2 (PEP file)
-#  - name: config/_pep_example/project_config.yaml
   - name: config/lactobacillus_delbruecki/project_config.yaml
+
+bgc_projects:
+  - pep: config/lanthipeptide/project_config.yaml
+
 #### GLOBAL RULE CONFIGURATION ####
 # This section configures the rules to run globally.
 # Use project specific rule configurations if you want to run different rules for each projects.
-# rules: set value to TRUE if you want to run the analysis or FALSE if you don't
-rules:
+# pipelines or rules: set value to TRUE if you want to run the analysis or FALSE if you don't
+pipelines:
   seqfu: FALSE
   mash: FALSE
   fastani: FALSE
@@ -60,3 +57,8 @@ resources_path:
   checkm: resources/checkm
   gtdbtk: resources/gtdbtk
   #RNAmmer: resources/RNAmmer # If specified, will override Barnapp in Prokka
+
+rule_parameters:
+  install_gtdbtk:
+    release: 214
+    release_version: 214

.tests/unit/antismash_overview_gather/data/data/interim/antismash/6.1.1/GCA_000056065.1_bgc_overview.json → .tests/unit/antismash_overview/expected/data/interim/antismash/7.0.0/GCA_000056065.1_bgc_overview.json

@@ -15,6 +15,18 @@
     "genome_id": "GCA_000056065.1",
     "region": "1.2",
     "accession": "CR954253.1",
+    "start_pos": "125153",
+    "end_pos": "136119",
+    "contig_edge": "False",
+    "product": [
+      "RiPP-like"
+    ],
+    "region_length": 10966
+  },
+  "CR954253.1.region003": {
+    "genome_id": "GCA_000056065.1",
+    "region": "1.3",
+    "accession": "CR954253.1",
     "start_pos": "1745672",
     "end_pos": "1767868",
     "contig_edge": "False",

.tests/unit/antismash_summary/data/config/config.yaml

@@ -0,0 +1,64 @@
+# This file should contain everything to configure the workflow on a global scale.
+
+#### PROJECT INFORMATION ####
+# This section control your project configuration.
+# Each project are separated by "-".
+# A project can be defined as (1) a yaml object or (2) a Portable Encapsulated Project (PEP) file.
+# (1) To define project as a yaml object, it must contain the variable "name" and "samples".
+#   - name : name of your project
+#   - samples : a csv file containing a list of genome ids for analysis with multiple sources mentioned. Genome ids must be unique.
+#   - rules: a yaml file containing project rule configurations. This will override global rule configuration.
+#   - prokka-db (optional): list of the custom accessions to use as prokka reference database.
+#   - gtdb-tax (optional): output summary file of GTDB-tk with "user_genome" and "classification" as the two minimum columns
+# (2) To define project using PEP file, only variable "name" should be given that points to the location of the PEP yaml file.
+#   - pep: path to PEP .yaml file. See project example_pep for details.
+# PS: the variable pep and name is an alias
+
+projects:
+# Project 1 (yaml object)
+  - name: config/lactobacillus_delbruecki/project_config.yaml
+
+bgc_projects:
+  - pep: config/lanthipeptide/project_config.yaml
+
+#### GLOBAL RULE CONFIGURATION ####
+# This section configures the rules to run globally.
+# Use project specific rule configurations if you want to run different rules for each projects.
+# pipelines or rules: set value to TRUE if you want to run the analysis or FALSE if you don't
+pipelines:
+  seqfu: FALSE
+  mash: FALSE
+  fastani: FALSE
+  checkm: FALSE
+  gtdbtk: FALSE
+  prokka-gbk: FALSE
+  antismash: TRUE
+  query-bigslice: FALSE
+  bigscape: FALSE
+  bigslice: FALSE
+  automlst-wrapper: FALSE
+  arts: FALSE
+  roary: FALSE
+  eggnog: FALSE
+  eggnog-roary: FALSE
+  deeptfactor: FALSE
+  deeptfactor-roary: FALSE
+  cblaster-genome: FALSE
+  cblaster-bgc: FALSE
+
+#### RESOURCES CONFIGURATION ####
+# resources : the location of the resources to run the rule.
+# The default location is at "resources/{resource_name}".
+resources_path:
+  antismash_db: resources/antismash_db
+  eggnog_db: resources/eggnog_db
+  BiG-SCAPE: resources/BiG-SCAPE
+  bigslice: resources/bigslice
+  checkm: resources/checkm
+  gtdbtk: resources/gtdbtk
+  #RNAmmer: resources/RNAmmer # If specified, will override Barnapp in Prokka
+
+rule_parameters:
+  install_gtdbtk:
+    release: 214
+    release_version: 214

.tests/unit/antismash_summary/data/config/lactobacillus_delbruecki/project_config.yaml

@@ -0,0 +1,30 @@
+name: Lactobacillus_delbrueckii
+
+pep_version: 2.1.0
+
+description: "Lactobacillus delbrueckii 27 01 2023"
+
+sample_table: samples.csv
+
+#### RULE CONFIGURATION ####
+# rules: set value to TRUE if you want to run the analysis or FALSE if you don't
+rules:
+  seqfu: TRUE
+  mash: TRUE
+  fastani: TRUE
+  checkm: FALSE
+  gtdbtk: FALSE
+  prokka-gbk: TRUE
+  antismash: TRUE
+  query-bigslice: TRUE
+  bigscape: TRUE
+  bigslice: TRUE
+  automlst-wrapper: TRUE
+  arts: TRUE
+  roary: TRUE
+  eggnog: TRUE
+  eggnog-roary: TRUE
+  deeptfactor: TRUE
+  deeptfactor-roary: TRUE
+  cblaster-genome: TRUE
+  cblaster-bgc: TRUE

.tests/unit/gtdb_prep/data/config/gtdb_prep/samples.csv → .tests/unit/antismash_summary/data/config/lactobacillus_delbruecki/samples.csv

@@ -3,5 +3,3 @@ GCA_000056065.1,ncbi,,,,,,
 GCA_000182835.1,ncbi,,,,,,
 GCA_000191165.1,ncbi,,,,,,
 GCA_000014405.1,ncbi,,,,,,
-GCF_024734405.1,ncbi,,,,,,
-GCF_025643595.1,ncbi,,,,,,

.tests/unit/antismash_summary/data/data/interim/antismash/7.0.0/GCA_000014405.1_bgc_counts.json

@@ -0,0 +1,12 @@
+{
+  "GCA_000014405.1": {
+    "bgcs_count": 2,
+    "bgcs_on_contig_edge": 0,
+    "protoclusters_count": 0,
+    "cand_clusters_count": 0,
+    "products": {
+      "lanthipeptide-class-iii": 1,
+      "RiPP-like": 1
+    }
+  }
+}

.tests/unit/antismash_summary/data/data/interim/antismash/7.0.0/GCA_000056065.1_bgc_counts.json

@@ -0,0 +1,13 @@
+{
+  "GCA_000056065.1": {
+    "bgcs_count": 3,
+    "bgcs_on_contig_edge": 0,
+    "protoclusters_count": 0,
+    "cand_clusters_count": 0,
+    "products": {
+      "lanthipeptide-class-iii": 1,
+      "RiPP-like": 1,
+      "lanthipeptide-class-iv": 1
+    }
+  }
+}