Fix minor issues in doc / code style and fix bug in species selection in Expression Atlas get accessions

bin/get_eatlas_accessions.py

@@ -108,7 +108,7 @@ def get_data(url: str) -> dict:
     return response.json()
 
 
-def get_experiment_description(exp_dict: dict):
+def get_experiment_description(exp_dict: dict) -> str:
     """
     Gets the description from an experiment dictionary
 
@@ -138,7 +138,7 @@ def get_experiment_description(exp_dict: dict):
         raise KeyError(f"Could not find description field in {exp_dict}")
 
 
-def get_experiment_accession(exp_dict: dict):
+def get_experiment_accession(exp_dict: dict) -> str:
     """
     Gets the accession from an experiment dictionary
 
@@ -168,7 +168,7 @@ def get_experiment_accession(exp_dict: dict):
         raise KeyError(f"Could not find accession field in {exp_dict}")
 
 
-def get_properties_values(exp_dict: dict):
+def get_properties_values(exp_dict: dict) -> list:
     """
     Gets all values from properties from an experiment dictionary
 
@@ -199,7 +199,7 @@ def get_properties_values(exp_dict: dict):
     return list(set(values))
 
 
-def get_eatlas_experiments():
+def get_eatlas_experiments() -> list[dict]:
     """
     Gets all experiments from Expression Atlas
 
@@ -215,7 +215,7 @@ def get_eatlas_experiments():
     return data["experiments"]
 
 
-def filter_by_platform(experiments: list[dict], platform: str | None):
+def filter_by_platform(experiments: list[dict], platform: str | None) -> list[dict]:
     """
     Gets all experiments for a given platform from Expression Atlas
     Possible platforms in Expression Atlas are 'rnaseq', 'microarray', 'proteomics'
@@ -258,7 +258,15 @@ def filter_by_platform(experiments: list[dict], platform: str | None):
     return platform_experiments
 
 
-def get_species_experiments(experiments: list[dict], species: str):
+def get_species_name_without_subspecies(species: str) -> str:
+    """
+    Returns the species name without the subspecies part.
+    Ex: Hordeum vulgare subsp. vulgare -> Hordeum vulgare
+    """
+    return " ".join(species.split(" ")[:2])
+
+
+def get_species_experiments(experiments: list[dict], species: str) -> list[dict]:
     """
     Gets all experiments for a given species from Expression Atlas
 
@@ -275,12 +283,14 @@ def get_species_experiments(experiments: list[dict], species: str):
     """
     species_experiments = []
     for exp_dict in experiments:
-        if exp_dict["species"] == species:
+        # in case the species name contains a subspecies part, we only use the first two words
+        exp_species = get_species_name_without_subspecies(exp_dict["species"])
+        if exp_species == species:
             species_experiments.append(exp_dict)
     return species_experiments
 
 
-def get_experiment_data(exp_dict: dict):
+def get_experiment_data(exp_dict: dict) -> dict:
     """
     Gets the full data for an experiment given its dictionary
 
@@ -312,7 +322,7 @@ def filter_out_excluded_accessions(experiments: list[dict]) -> list[dict]:
     return valid_experiments
 
 
-def parse_experiment(exp_dict: dict):
+def parse_experiment(exp_dict: dict) -> dict:
     # getting accession and description
     accession = get_experiment_accession(exp_dict)
     description = get_experiment_description(exp_dict)

conf/test.config

@@ -16,6 +16,6 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
     // Input data
-    species = 'beta vulgaris'
+    species = 'prunus persica'
     outdir = "results/test"
 }

galaxy/build/static/template.xml

@@ -109,7 +109,7 @@ INPUTS
         </test>
         <test>
             <section name="input_output_options">
-                <param name="species" value="beta vulgaris" />
+                <param name="species" value="prunus persica" />
                 <conditional name="datasets">
                     <param name="provide_datasets" value="false" />
                 </conditional>
@@ -128,7 +128,7 @@ INPUTS
         </test>
         <test>
             <section name="input_output_options">
-                <param name="species" value="beta vulgaris" />
+                <param name="species" value="prunus persica" />
                 <conditional name="datasets">
                     <param name="provide_datasets" value="true" />
                     <param name="samplesheet" value="test_data/input.csv" />

galaxy/tool_shed/tool/nf_core_stableexpression.xml

@@ -586,7 +586,7 @@ VERSION="1.1dev"; echo "$VERSION"
         </test>
         <test>
             <section name="input_output_options">
-                <param name="species" value="beta vulgaris" />
+                <param name="species" value="prunus persica" />
                 <conditional name="datasets">
                     <param name="provide_datasets" value="false" />
                 </conditional>
@@ -605,7 +605,7 @@ VERSION="1.1dev"; echo "$VERSION"
         </test>
         <test>
             <section name="input_output_options">
-                <param name="species" value="beta vulgaris" />
+                <param name="species" value="prunus persica" />
                 <conditional name="datasets">
                     <param name="provide_datasets" value="true" />
                     <param name="samplesheet" value="test_data/input.csv" />

subworkflows/local/download_public_datasets/main.nf

@@ -1,4 +1,4 @@
-include { EXPRESSIONATLAS_GETDATA as EXPRESSION_ATLAS     } from '../../../modules/local/expressionatlas/getdata'
+include { EXPRESSIONATLAS_GETDATA as EXPRESSION_ATLAS    } from '../../../modules/local/expressionatlas/getdata'
 include { GEO_GETDATA as GEO                             } from '../../../modules/local/geo/getdata'
 
 include { addDatasetIdToMetadata                        } from '../utils_nfcore_stableexpression_pipeline'
@@ -7,7 +7,7 @@ include { augmentMetadata                               } from '../utils_nfcore_
 
 /*
 ========================================================================================
-    SUBWORKFLOW TO DOWNLOAD GEO ACCESSIONS AND DATASETS
+    SUBWORKFLOW TO DOWNLOAD EXPRESSION ATLAS AND NCBI GEO DATASETS
 ========================================================================================
 */
 

subworkflows/local/gene_statistics/main.nf

@@ -1,9 +1,9 @@
-include { COMPUTE_GENE_STATISTICS as GLOBAL                      } from '../../../modules/local/compute_gene_statistics'
-include { COMPUTE_GENE_STATISTICS as PLATFORM                    } from '../../../modules/local/compute_gene_statistics'
+include { COMPUTE_GENE_STATISTICS as GLOBAL       } from '../../../modules/local/compute_gene_statistics'
+include { COMPUTE_GENE_STATISTICS as PLATFORM     } from '../../../modules/local/compute_gene_statistics'
 
 /*
 ========================================================================================
-    SUBWORKFLOW TO DOWNLOAD EXPRESSIONATLAS ACCESSIONS AND DATASETS
+    SUBWORKFLOW TO COMPUTE STATISTICS FOR ALL GENES
 ========================================================================================
 */
 

subworkflows/local/genorm/main.nf

@@ -16,7 +16,7 @@ include { COMPUTE_M_MEASURE            } from '../../../modules/local/genorm/com
 
 /*
 ========================================================================================
-    SUBWORKFLOW TO COMPUTE PAIRWISE GENE VARIATION
+    SUBWORKFLOW TO COMPUTE PAIRWISE GENE VARIATION (ADAPTED VERSION OF GENORM)
 ========================================================================================
 */
 

subworkflows/local/get_public_accessions/main.nf

@@ -3,7 +3,7 @@ include { GEO_GETACCESSIONS as GEO                                   } from '../
 
 /*
 ========================================================================================
-    SUBWORKFLOW TO DOWNLOAD EXPRESSIONATLAS ACCESSIONS AND DATASETS
+    SUBWORKFLOW TO FETCH EXPRESSION ATLAS AND NCBI GEO ACCESSIONS
 ========================================================================================
 */
 

subworkflows/local/get_transcript_lengths/main.nf

@@ -4,7 +4,7 @@ include { DOWNLOAD_ENSEMBL_ANNOTATION                  } from '../../../modules/
 
 /*
 ========================================================================================
-    SUBWORKFLOW TO DOWNLOAD EXPRESSIONATLAS ACCESSIONS AND DATASETS
+    SUBWORKFLOW TO GET TRANSCRIPT LENGTHS FROM GENOME ANNOTATION
 ========================================================================================
 */
 

subworkflows/local/idmapping/main.nf

@@ -7,7 +7,7 @@ include { FILTER_AND_RENAME_GENES                } from '../../../modules/local/
 
 /*
 ========================================================================================
-    SUBWORKFLOW TO DOWNLOAD EXPRESSIONATLAS ACCESSIONS AND DATASETS
+    SUBWORKFLOW TO MAP GENE IDS TO COMMON IDS AMONG ALL DATASETS AND TO REMOVE RARE GENES
 ========================================================================================
 */
 

subworkflows/local/merge_data/main.nf

@@ -50,7 +50,7 @@ workflow MERGE_DATA {
                                     .collect( sort: true )
                                     .map { files -> [ [ platform: "all" ], files ] }
 
-    GLOBAL( ch_collected_merged_counts.collect() )
+    GLOBAL( ch_collected_merged_counts )
     ch_all_counts = GLOBAL.out.counts
 
     // -----------------------------------------------------------------

subworkflows/local/reporting/main.nf

@@ -11,7 +11,7 @@ include { paramsSummaryMap                       } from 'plugin/nf-schema'
 
 /*
 ========================================================================================
-    SUBWORKFLOW TO DOWNLOAD EXPRESSIONATLAS ACCESSIONS AND DATASETS
+    SUBWORKFLOW DEDICATED TO AGGREGATION OF RESULTS AND REPORTING (DASH APP AND MULTIQC)
 ========================================================================================
 */
 

subworkflows/local/sample_filtering/main.nf

@@ -1,5 +1,5 @@
-include { FILTER_OUT_SAMPLES_WITH_TOO_MANY_ZEROS          as TOO_MANY_ZEROS                                   } from '../../../modules/local/filter_out_samples/with_too_many_zeros'
-include { FILTER_OUT_SAMPLES_WITH_TOO_MANY_MISSING_VALUES as TOO_MANY_MISSING_VALUES                          } from '../../../modules/local/filter_out_samples/with_too_many_missing_values'
+include { FILTER_OUT_SAMPLES_WITH_TOO_MANY_ZEROS          as TOO_MANY_ZEROS             } from '../../../modules/local/filter_out_samples/with_too_many_zeros'
+include { FILTER_OUT_SAMPLES_WITH_TOO_MANY_MISSING_VALUES as TOO_MANY_MISSING_VALUES    } from '../../../modules/local/filter_out_samples/with_too_many_missing_values'
 
 
 /*

subworkflows/local/stability_scoring/main.nf

@@ -6,7 +6,7 @@ include { GENORM                             } from '../genorm'
 
 /*
 ========================================================================================
-    COMPUTE STABILITY SCORES
+    SUBWORKFLOW TO COMPUTE STABILITY SCORES
 ========================================================================================
 */
 
@@ -61,7 +61,7 @@ workflow STABILITY_SCORING {
     // -----------------------------------------------------------------
     // AGGREGATION AND FINAL STABILITY SCORE
     // -----------------------------------------------------------------
- //ch_normfinder_stabilities.join( ch_genorm_stability ).join( ch_section_stats ),
+
     COMPUTE_STABILITY_SCORES (
         ch_normfinder_stabilities.join( ch_genorm_stability ).join( ch_section_stats ),
         stability_score_weights

tests/default.nf.test

@@ -9,7 +9,7 @@ nextflow_pipeline {
 
         when {
             params {
-                species = 'beta vulgaris'
+                species = 'prunus persica'
                 outdir = "$outputDir"
             }
         }
@@ -110,7 +110,7 @@ nextflow_pipeline {
 
         when {
             params {
-                species = 'beta vulgaris'
+                species = 'arabidopsis lyrata'
                 accessions_only = true
                 outdir = "$outputDir"
             }
@@ -140,7 +140,7 @@ nextflow_pipeline {
 
         when {
             params {
-                species = 'beta vulgaris'
+                species = 'aspergillus fumigatus'
                 download_only = true
                 outdir = "$outputDir"
             }