Validation of configuration file with a json schema...

Validation of configuration file with a json schema `resources/config_schema.json` using the snakemake utility **validate**. The schema includes all the fields from `tests/input_files/config.yaml`, assigns certain fields as required and forbids the use of additional fields. All of the optional fields include default values, taken from the config above, except `rule_config` which has no default.

Added author name and author email as optional fields in `tests/input_files/config.yaml`, and added it into the multiqc report.

resources/config_schema.json

+{
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "title": "Configuration schema",
+    "required": ["samples", "output_dir", "log_dir", "kallisto_indexes", "salmon_indexes", "star_indexes", "alfa_indexes"],
+    "type": "object",
+    "additionalProperties": false,
+    "properties": {
+      "samples": {
+        "type": "string",
+        "description": "Path to samples table."
+      },
+      "output_dir": {
+        "type": "string",
+        "description": "Path to output directory."
+      },
+      "log_dir": {
+        "type": "string",
+        "description": "Path to log directory."
+      },
+      "kallisto_indexes": {
+        "type": "string",
+        "description": "Path to kallisto indexes directory."
+      },
+      "salmon_indexes": {
+        "type": "string",
+        "description": "Path to salmon indexes directory."
+      },
+      "star_indexes": {
+        "type": "string",
+        "description": "Path to star indexes directory."
+      },
+      "alfa_indexes": {
+        "type": "string",
+        "description": "Path to alfa indexes directory."
+      },
+      "rule_config": {
+        "type": "string",
+        "description": "Path to rule configuration file."
+      },
+      "report_description": {
+        "type": "string",
+        "description": "Description of the run to appear in the multiqc report.",
+        "default": "No description provided by user."
+      },
+      "report_logo": {
+        "type": "string",
+        "description": "Relative path to image to display as logo in multiqc report.",
+        "default": "../../images/logo.128px.png"
+      },
+      "report_url": {
+        "type": "string",
+        "description": "URL to appear in multiqc report.",
+        "default": "https://zavolan.biozentrum.unibas.ch/"
+      },
+      "author_name": {
+        "type": "string",
+        "description": "Full author name to display in multiqc report.",
+        "default": "NA" 
+      },
+      "author_email": {
+        "type": "string",
+        "description": "Author e-mail address to display in multiqc report.",
+        "default": "NA"
+      }
+    }
+}

tests/input_files/config.mutliple_lanes.yml

 ---
   samples: "../input_files/samples.multiple_lanes.tsv"
-  rule_config: "../input_files/rule_config.yaml"
   output_dir: "results"
   log_dir: "logs"
   kallisto_indexes: "results/kallisto_indexes"
   salmon_indexes: "results/salmon_indexes"
   star_indexes: "results/star_indexes"
   alfa_indexes: "results/alfa_indexes"
+  rule_config: "../input_files/rule_config.yaml"
   report_description: "No description provided by user"
   report_logo: "../../images/logo.128px.png"
   report_url: "https://zavolan.biozentrum.unibas.ch/"

tests/input_files/config.yaml

 ---
+  # Required fields
   samples: "../input_files/samples.tsv"
-  rule_config: "../input_files/rule_config.yaml"
   output_dir: "results"
   log_dir: "logs"
   kallisto_indexes: "results/kallisto_indexes"
   salmon_indexes: "results/salmon_indexes"
   star_indexes: "results/star_indexes"
   alfa_indexes: "results/alfa_indexes"
+  # Optional fields
+  rule_config: "../input_files/rule_config.yaml"
   report_description: "No description provided by user"
   report_logo: "../../images/logo.128px.png"
   report_url: "https://zavolan.biozentrum.unibas.ch/"
+  author_name: "NA"
+  author_email: "NA"
 ...

tests/input_files/config_alfa.yaml

 ---
   samples: "../input_files/samples_alfa.tsv"
-  output_dir: "results/"
-  log_dir: "logs/"
-  kallisto_indexes: "results/kallisto_indexes/"
-  salmon_indexes: "results/salmon_indexes/"
-  star_indexes: "results/star_indexes/"
-  alfa_indexes: "results/alfa_indexes/"
+  output_dir: "results"
+  log_dir: "logs"
+  kallisto_indexes: "results/kallisto_indexes"
+  salmon_indexes: "results/salmon_indexes"
+  star_indexes: "results/star_indexes"
+  alfa_indexes: "results/alfa_indexes"
+  rule_config: "../input_files/rule_config.yaml"
   report_description: "No description provided by user"
   report_logo: "../../images/logo.128px.png"
   report_url: "https://zavolan.biozentrum.unibas.ch/"

workflow/Snakefile

@@ -5,6 +5,7 @@ import shutil
 import yaml
 from shlex import quote
 from typing import Tuple
+from snakemake.utils import validate
 
 ## Preparations
 # Get sample table
@@ -17,16 +18,22 @@ samples_table = pd.read_csv(
     sep="\t",
 )
 
+# Validat config
+validate(config, os.path.join("..", "resources", "config_schema.json"))
+logger.info(f'Config file after validation: {config}')
+
 # Parse YAML rule config file
-if 'rule_config' in config and config['rule_config']:
-    try:
-        with open(config['rule_config']) as _file:
-            rule_config = yaml.safe_load(_file)
-        logger.info(f"Loaded rule_config from {config['rule_config']}.")
-    except FileNotFoundError:
-        logger.error(f"No rule config file found at {config['rule_config']}. Either provide file or remove rule_config parameter from config.yaml! ")
-        raise
-else:
+try:
+    with open(config['rule_config']) as _file:
+        rule_config = yaml.safe_load(_file)
+    logger.info(f"Loaded rule_config from {config['rule_config']}.")
+except TypeError:
+    logger.error(f'No string supplied at field "rule_config", but: {type(config["rule_config"])} with content: {config["rule_config"]}')
+    raise
+except FileNotFoundError:
+    logger.error(f"No rule config file found at {config['rule_config']}. Either provide file or remove rule_config parameter from config.yaml! ")
+    raise
+except KeyError:
     rule_config = {}
     logger.warning(f"No rule config specified: using default values for all tools.")
 
@@ -1547,6 +1554,8 @@ rule prepare_multiqc_config:
         logo_path = config['report_logo'],
         multiqc_intro_text = config['report_description'],
         url = config['report_url'],
+        author_name = config['author_name'],
+        author_email = config['author_email'],
         additional_params = parse_rule_config(
             rule_config,
             current_rule=current_rule,
@@ -1572,6 +1581,8 @@ rule prepare_multiqc_config:
         --intro-text '{params.multiqc_intro_text}' \
         --custom-logo {params.logo_path} \
         --url '{params.url}' \
+        --author-name {params.author_name} \
+        --author-email {params.author_email} \
         {params.additional_params}) \
         1> {log.stdout} 2> {log.stderr}"