Merge branch 'dev' into feature/remove-duplication-from-main-workflow

.github/workflows/test.yml

@@ -15,7 +15,7 @@ jobs:
     - uses: actions/checkout@v3
 
     - name: Prepare nf-test config file
-      run: cat .github/workflows/test.config | sed "s@%TMP%@${RUNNER_TEMP}@g" > tests/nextflow.config
+      run: sed -i -e "s@%TMP%@${RUNNER_TEMP}@g" tests/nextflow.config
 
     - uses: actions/setup-java@v3
       with:
@@ -38,10 +38,10 @@ jobs:
 
     - name: Fetch motif mapping files
       run: |
-        curl -k -o tests/data/zma_v4/zma_v4_genome_wide_motif_mappings_chr1.bed https://floppy.psb.ugent.be/index.php/s/NekMYztyxEnsQiY/download/zma_v4_genome_wide_motif_mappings_chr1.bed
-        curl -k -o tests/data/zma_v4/zma_v4_locus_based_motif_mappings_5kbup_1kbdown_chr1.bed https://floppy.psb.ugent.be/index.php/s/r2wQmFjPy79qSp7/download/zma_v4_locus_based_motif_mappings_5kbup_1kbdown_chr1.bed
-        curl -k -o tests/data/ath/ath_genome_wide_motif_mappings.bed https://floppy.psb.ugent.be/index.php/s/iaZPwdrRGe3YDdK/download/ath_genome_wide_motif_mappings.bed
-        curl -k -o tests/data/ath/ath_locus_based_motif_mappings_5kbup_1kbdown.bed https://floppy.psb.ugent.be/index.php/s/qcQ7KndzHaSpd9e/download/ath_locus_based_motif_mappings_5kbup_1kbdown.bed
+        curl -k -o tests/data/zma_v4_chr1/zma_v4_genome_wide_motif_mappings_chr1.bed https://floppy.psb.ugent.be/index.php/s/NekMYztyxEnsQiY/download/zma_v4_genome_wide_motif_mappings_chr1.bed
+        curl -k -o tests/data/zma_v4_chr1/zma_v4_locus_based_motif_mappings_5kbup_1kbdown_chr1.bed https://floppy.psb.ugent.be/index.php/s/r2wQmFjPy79qSp7/download/zma_v4_locus_based_motif_mappings_5kbup_1kbdown_chr1.bed
+        curl -k -o data/ath/ath_genome_wide_motif_mappings.bed https://floppy.psb.ugent.be/index.php/s/iaZPwdrRGe3YDdK/download/ath_genome_wide_motif_mappings.bed
+        curl -k -o data/ath/ath_locus_based_motif_mappings_5kbup_1kbdown.bed https://floppy.psb.ugent.be/index.php/s/qcQ7KndzHaSpd9e/download/ath_locus_based_motif_mappings_5kbup_1kbdown.bed
 
     - name: Run nf-test
       shell: bash

.gitignore

@@ -26,4 +26,4 @@ slurm.*.err
 
 # python cache and compiled files
 __pycache__/
-*.pyc
+*.pyc

README.md

@@ -81,7 +81,7 @@ Should you encounter a bug or have any questions or suggestions, please [open an
 
 When publishing results generated using MINI-AC, please cite:
 
-Manosalva Pérez, Nicolás, Camilla Ferrari, Julia Engelhorn, Thomas Depuydt, Hilde Nelissen, Thomas Hartwig, and Klaas Vandepoele. “MINI-AC: Inference of Plant Gene Regulatory Networks Using Bulk or Single-Cell Accessible Chromatin Profiles.” bioRxiv, May 26, 2023. https://doi.org/10.1101/2023.05.26.542269.
+Manosalva Pérez, Nicolás, Camilla Ferrari, Julia Engelhorn, Thomas Depuydt, Hilde Nelissen, Thomas Hartwig, and Klaas Vandepoele. “MINI-AC: Inference of Plant Gene Regulatory Networks Using Bulk or Single-Cell Accessible Chromatin Profiles.” The Plant Journal. https://doi.org/10.1111/tpj.16483.
 
 ## Contact
 

docs/configuration_pipeline.md

@@ -28,7 +28,7 @@ MINI-AC has several optional parameters that affect the output and some aspects
 
 ### GRN inference parameters
 
-* **Motif enrichment p-value cut-off**: This is the p-value cut-off that determines which motifs are enriched and used for GRN building. We do not recommend changing this parameter. It has been internally pre-defined for each MINI-AC mode based on the p-value cut-offs with a false discovery rate of 0 (see publication). If wished, however, this p-value can be overwritten in the configuration file by setting the parameter ```P_val``` to whatever value (see below) or in the command line options. For example: ```nextflow -C mini_ac.config run mini_ac.nf --mode genome_wide --species maize_v4 --P_val 0.05```
+* **Motif enrichment p-value cut-off**: This is the p-value cut-off that determines which motifs are enriched and used for GRN building. We do not recommend changing this parameter. It has been internally pre-defined for each MINI-AC mode based on the p-value cut-offs with a false discovery rate of 0 (see [publication](https://doi.org/10.1111/tpj.16483)). If wished, however, this p-value can be overwritten in the configuration file by setting the parameter ```P_val``` to whatever value (see below) or in the command line options. For example: ```nextflow -C mini_ac.config run mini_ac.nf --mode genome_wide --species maize_v4 --P_val 0.05```
 
 * **Overlap criteria parameter**: By default, MINI-AC computes motif enrichment counting the motif matches within ACRs. This, however, is difficult if the ACRs are shorter than or of similar size to the motifs, which is the case of footprints. In this case, we observed that counting the absolute base-pair overlap is useful. Therefore, in case of using footprints or short ACRs (high resolution), we recommend setting the parameter ```Bps_intersect = true```. Otherwise it should be kept ```Bps_intersect = false```.
 

tests/mini_ac.nf.test

@@ -22,8 +22,8 @@ nextflow_workflow {
                 Shuffle_seed = 42
 
                 //// Hard code data paths
-                MotMapsFile = "${baseDir}/tests/data/zma_v4/zma_v4_genome_wide_motif_mappings_chr1.bed"
-                Non_cod_genome = "${baseDir}/tests/data/zma_v4/zma_v4_noncod_merged_chr1.bed"
+                MotMapsFile = "${baseDir}/tests/data/zma_v4_chr1/zma_v4_genome_wide_motif_mappings_chr1.bed"
+                Non_cod_genome = "${baseDir}/tests/data/zma_v4_chr1/zma_v4_noncod_merged_chr1.bed"
                 Faix_file = "${baseDir}/data/zma_v4/zma_v4.fasta.fai"
                 Motif_tf_file = "${baseDir}/data/zma_v4/zma_v4_motif_TF_file.txt"
                 Genes_coords = "${baseDir}/data/zma_v4/zma_v4_genes_coords_sorted.bed"
@@ -58,12 +58,6 @@ nextflow_workflow {
                 Second_gene_annot = true
                 Second_gene_dist = 500
             }
-            workflow {
-                """
-                // define inputs of the workflow here. Example:
-                // input[0] = file("test-file.txt")
-                """
-            }
         }
 
         then {
@@ -97,8 +91,8 @@ nextflow_workflow {
                 Shuffle_seed = 42
 
                 //// Hard code data paths
-                MotMapsFile = "${baseDir}/tests/data/zma_v4/zma_v4_locus_based_motif_mappings_5kbup_1kbdown_chr1.bed"
-                Promoter_file = "${baseDir}/tests/data/zma_v4/zma_v4_promoter_5kbup_1kbdown_sorted_chr1.bed"
+                MotMapsFile = "${baseDir}/tests/data/zma_v4_chr1/zma_v4_locus_based_motif_mappings_5kbup_1kbdown_chr1.bed"
+                Promoter_file = "${baseDir}/tests/data/zma_v4_chr1/zma_v4_promoter_5kbup_1kbdown_sorted_chr1.bed"
                 Faix_file = "${baseDir}/data/zma_v4/zma_v4.fasta.fai"
                 Motif_tf_file = "${baseDir}/data/zma_v4/zma_v4_motif_TF_file.txt"
                 Feature_file = "${baseDir}/data/zma_v4/zma_v4_go_gene_file.txt"
@@ -126,12 +120,6 @@ nextflow_workflow {
                 //// Prediction parameters
                 Bps_intersect = true
             }
-            workflow {
-                """
-                // define inputs of the workflow here. Example:
-                // input[0] = file("test-file.txt")
-                """
-            }
         }
 
         then {
@@ -165,7 +153,7 @@ nextflow_workflow {
                 Shuffle_seed = 42
 
                 //// Hard code data paths
-                MotMapsFile = "${baseDir}/tests/data/ath/ath_genome_wide_motif_mappings.bed"
+                MotMapsFile = "${baseDir}/data/ath/ath_genome_wide_motif_mappings.bed"
                 Non_cod_genome = "${baseDir}/data/ath/ath_noncod_merged.bed"
                 Faix_file = "${baseDir}/data/ath/ath.fasta.fai"
                 Motif_tf_file = "${baseDir}/data/ath/ath_motif_TF_file.txt"
@@ -199,12 +187,6 @@ nextflow_workflow {
                 Second_gene_annot = false
                 Second_gene_dist = 0
             }
-            workflow {
-                """
-                // define inputs of the workflow here. Example:
-                // input[0] = file("test-file.txt")
-                """
-            }
         }
 
         then {
@@ -238,7 +220,7 @@ nextflow_workflow {
                 Shuffle_seed = 42
 
                 //// Hard code data paths
-                MotMapsFile = "${baseDir}/tests/data/ath/ath_locus_based_motif_mappings_5kbup_1kbdown.bed"
+                MotMapsFile = "${baseDir}/data/ath/ath_locus_based_motif_mappings_5kbup_1kbdown.bed"
                 Promoter_file = "${baseDir}/data/ath/ath_promoter_5kbup_1kbdown_sorted.bed"
                 Faix_file = "${baseDir}/data/ath/ath.fasta.fai"
                 Motif_tf_file = "${baseDir}/data/ath/ath_motif_TF_file.txt"
@@ -265,12 +247,6 @@ nextflow_workflow {
                 //// Prediction parameters
                 Bps_intersect = false
             }
-            workflow {
-                """
-                // define inputs of the workflow here. Example:
-                // input[0] = file("test-file.txt")
-                """
-            }
         }
 
         then {

tests/nextflow.config

@@ -1,46 +1,19 @@
 /*
-========================================================================================
-    Nextflow config file for running tests
-========================================================================================
+===========================================================================
+    Nextflow config file for running tests (GitHub Actions workflow)
+===========================================================================
 */
 
 process.container = "vibpsb/mini-ac:latest"
 singularity {
     enabled = true
     cacheDir = "singularity_cache"
     autoMounts = true
-    runOptions = "--bind $TMPDIR"
+    runOptions = "--bind %TMP%"
 }
 
-workDir = "$TMPDIR/MINI-AC"
-
-// WHEN USING HPC SLURM UNCOMMENT THE CODE BELOW
+workDir = "%TMP%/MINI-AC"
 
 executor {
-    name = 'slurm'
-    queueSize = 25
-}
-
-process {
-    withName: get_ACR_shufflings {
-        clusterOptions = '--mem 4G'
-    }
-    withName: getStats {
-        clusterOptions = '--mem 10G'
-    }
-    withName: getStats_bps {
-        clusterOptions = '--mem 50G'
-    }
-    withName: getNetwork {
-        clusterOptions = '--mem 20G'
-    }
-    withName: filterSetOfGenes {
-        clusterOptions = '--mem 5G'
-    }
-    withName: GOenrichment {
-        clusterOptions = '--mem 5G'
-    }
-    withName: getIntegrativeOutputs {
-        clusterOptions = '--mem 3G'
-    }
+    name = 'local'
 }