Merge branch 'dev' into hit_selection

CHANGELOG.md

@@ -13,6 +13,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Fixed
 
 - Fix cutadapt 3' and 5' no such variable found bug ([#187](https://github.com/nf-core/crisprseq/pull/187))
+- Fix design matrix bug that introduced dots instead of a hyphen ([#190](https://github.com/nf-core/crisprseq/pull/190))
+- Make output of FluteMLE optional as when some pathways produce bugs some channels are then empty ([#190](https://github.com/nf-core/crisprseq/pull/190))
+- Fix a typo in crisprcleanr/normalize, when a user inputs a file ([#192](https://github.com/nf-core/crisprseq/pull/192))
 
 ### Deprecated
 

README.md

@@ -127,14 +127,15 @@ Main developers:
 We thank the following people for their extensive assistance in the development of this pipeline:
 
 - [@alan-tracey](https://github.com/alan-tracey)
+- [@bolenala](https://github.com/bolenala)
 - [@ggabernet](https://github.com/ggabernet)
 - [@jianhong](https://github.com/jianhong)
+- [@joannakraw](https://github.com/joannakraw)
 - [@mashehu](https://github.com/mashehu)
+- [@metinyazar](https://github.com/metinyazar)
 - [@msanvicente](https://github.com/msanvicente)
 - [@mschaffer-incyte](https://github.com/mschaffer-incyte)
 - [@SusiJo](https://github.com/SusiJo)
-- [@joannakraw](https://github.com/joannakraw)
-- [@metinyazar](https://github.com/metinyazar)
 
 ## Contributions and Support
 

bin/BAGEL.py

@@ -677,7 +677,6 @@ def calculate_bayes_factors(
     print("Iter TrainEss TrainNon TestSet")
     sys.stdout.flush()
     for loop in range(LOOPCOUNT):
-        # currentbf = {}
         printstr = ""
         printstr += str(loop)
 
@@ -984,7 +983,6 @@ def calculate_bayes_factors(
         #
 
         for loop in range(LOOPCOUNT):
-            # currentnbf = {}
             printstr = ""
             printstr += str(loop)
 

bin/drugz.py

@@ -123,7 +123,6 @@ def calculate_fold_change(
     fc_replicate_id = "fc_{replicate}".format(replicate=replicate)
     fc_zscore_id = "zscore_" + fc_replicate_id
     empirical_bayes_id = "eb_std_{replicate}".format(replicate=replicate)
-    # one_based_idx = replicate + 1
 
     # Get the control and treatment sample ids for each replicate
     control_sample = control_samples[replicate]

docs/usage/screening.md

@@ -89,7 +89,8 @@ Running MAGeCK MLE and BAGEL2 with a contrast file will also output a Venn diagr
 
 ### Running MAGeCK RRA only
 
-MAGeCK RRA performs robust ranking aggregation to identify genes that are consistently ranked highly across multiple replicate screens. To run MAGeCK RRA, you can define the contrasts as previously stated in the last section (with a `.txt` extension) and also specify `--rra`.
+MAGeCK RRA performs robust ranking aggregation to identify genes that are consistently ranked highly across multiple replicate screens. To run MAGeCK RRA, you can define the contrasts as previously stated in the last section with --contrasts your_file.txt(with a `.txt` extension) and also specify `--rra`.
+MAGeCK RRA performs robust ranking aggregation to identify genes that are consistently ranked highly across multiple replicate screens. To run MAGeCK RRA, you can define the contrasts as previously stated in the last section with `--contrasts your_file.txt` (with a `.txt` extension) and also specify `--rra`.
 
 ### Running MAGeCK MLE only
 
@@ -109,6 +110,10 @@ This label is not mandatory as in case you are running time series. If you wish
 
 The downstream analysis involves distinguishing essential, non-essential, and target-associated genes. Additionally, it encompasses conducting biological functional category analysis and pathway enrichment analysis for these genes. Furthermore, it provides visualization of genes within pathways, enhancing user exploration of screening data. MAGECKFlute is run automatically after MAGeCK MLE and for each MLE design matrice. If you have used the `--day0_label`, MAGeCKFlute will be ran on all the other conditions. Please note that the DepMap data is used for these plots.
 
+#### Using negative control sgRNAs for MAGeCK MLE
+
+You can add the parameter `--mle_control_sgrna` followed by your file (one non targeting control sgRNA per line) to integrate the control sgRNA in MAGeCK MLE.
+
 ### Running BAGEL2
 
 BAGEL2 (Bayesian Analysis of Gene Essentiality with Location) is a computational tool developed by the Hart Lab at Harvard University. It is designed for analyzing large-scale genetic screens, particularly CRISPR-Cas9 screens, to identify genes that are essential for the survival or growth of cells under different conditions. BAGEL2 integrates information about the location of guide RNAs within a gene and leverages this information to improve the accuracy of gene essentiality predictions.

modules/local/mageck/flutemle.nf

@@ -12,11 +12,11 @@ process MAGECK_FLUTEMLE {
     tuple val(meta), path(gene_summary)
 
     output:
-    tuple val(meta), path("MAGeCKFlute_*/Enrichment/*") , emit: enrich
-    tuple val(meta), path("MAGeCKFlute_*/QC/*")         , emit: qc
-    tuple val(meta), path("MAGeCKFlute_*/Selection/*")  , emit: select
-    tuple val(meta), path("MAGeCKFlute_*/PathwayView/*"), emit: pathwayview
-    path "versions.yml"                                 , emit: versions
+    tuple val(meta), path("MAGeCKFlute_*/Enrichment/*") , emit: enrich     , optional: true
+    tuple val(meta), path("MAGeCKFlute_*/QC/*")         , emit: qc         , optional: true
+    tuple val(meta), path("MAGeCKFlute_*/Selection/*")  , emit: select     , optional: true
+    tuple val(meta), path("MAGeCKFlute_*/PathwayView/*"), emit: pathwayview, optional: true
+    path "versions.yml"                                 , emit: versions   , optional: true
 
     when:
     task.ext.when == null || task.ext.when

modules/local/matricescreation.nf

@@ -33,13 +33,17 @@ process MATRICESCREATION {
                                 dimnames = list(all_samples,
                                                 c("Samples", "baseline",
                                                     name))))
+    # R automatically converts "-" to "." in the column names
+    # so here we re-assign the column names to keep the dashes defined by the user
+    colnames(design_matrix) <- c("Samples", "baseline", name)
 
     # Set baseline and treatment values in the design matrix
     design_matrix[, "Samples"] <- rownames(design_matrix)
     design_matrix\$baseline <- 1
     design_matrix[treatment_samples, name] <- 1
     design_matrix[treatment_samples, paste0(gsub(',', '_', '$meta.treatment'),"_vs_",gsub(",","_",'$meta.reference'))] <- 1
 
+
     # Print the design matrix to a file
     output_file <- paste0(gsub(',', '_', '$meta.treatment' ),"_vs_",gsub(",","_",'$meta.reference'),".txt")
     write.table(design_matrix, output_file, sep = "\t", quote = FALSE, row.names=FALSE)

nextflow.config

@@ -17,6 +17,7 @@ params {
     library                    = null
     crisprcleanr               = null
     contrasts                  = null
+    mle_control_sgrna          = null
     mle_design_matrix          = null
     count_table                = null
     fasta                      = null

nextflow_schema.json

@@ -191,6 +191,10 @@
                     "exists": true,
                     "description": "Design matrix used for MAGeCK MLE to call essential genes under multiple conditions while considering sgRNA knockout efficiency"
                 },
+                "mle_control_sgrna": {
+                    "type": "string",
+                    "description": "control-sgrna file for MAGeCK MLE"
+                },
                 "contrasts": {
                     "type": "string",
                     "format": "file-path",

subworkflows/local/utils_nfcore_crisprseq_pipeline/main.nf

@@ -168,16 +168,24 @@ workflow INITIALISATION_CHANNEL_CREATION_SCREENING {
         ch_design = Channel.fromPath(params.mle_design_matrix)
     }
 
+
     ch_biogrid = Channel.fromPath("$projectDir/assets/biogrid_hgncid_noduplicate_dropna.csv", checkIfExists: true)
     ch_hgnc = Channel.fromPath("$projectDir/assets/hgnc_complete_set.txt", checkIfExists: true)
 
+    if(params.mle_control_sgrna) {
+        ch_mle_control_sgrna = Channel.fromPath(params.mle_control_sgrna)
+    } else {
+        ch_mle_control_sgrna = []
+    }
 
     emit:
-    library = ch_library            // channel: library file
-    crisprcleanr = ch_crisprcleanr  // channel: crisprcleanr file or value
-    design = ch_design              // channel: design matrix file
+    library = ch_library                     // channel: library file
+    crisprcleanr = ch_crisprcleanr           // channel: crisprcleanr file or value
+    design = ch_design                       // channel: design matrix file
+    mle_control_sgrna = ch_mle_control_sgrna // channel: negative control sgRNA for MAGeCK MLE
     biogrid = ch_biogrid            // channel: biogrid
     hgnc = ch_hgnc                  // channel: hgnc
+
 }
 
 /*

workflows/crisprseq_screening.nf

@@ -271,7 +271,7 @@ workflow CRISPRSEQ_SCREENING {
                 }.set { ch_designed_mle }
 
             ch_mle = ch_designed_mle.combine(ch_counts)
-            MAGECK_MLE_MATRIX (ch_mle)
+            MAGECK_MLE_MATRIX (ch_mle, INITIALISATION_CHANNEL_CREATION_SCREENING.out.mle_control_sgrna)
             ch_versions = ch_versions.mix(MAGECK_MLE_MATRIX.out.versions)
             MAGECK_FLUTEMLE(MAGECK_MLE_MATRIX.out.gene_summary)
             ch_versions = ch_versions.mix(MAGECK_FLUTEMLE.out.versions)
@@ -280,7 +280,7 @@ workflow CRISPRSEQ_SCREENING {
         if(params.contrasts) {
             MATRICESCREATION(ch_contrasts)
             ch_mle = MATRICESCREATION.out.design_matrix.combine(ch_counts)
-            MAGECK_MLE (ch_mle)
+            MAGECK_MLE (ch_mle, INITIALISATION_CHANNEL_CREATION_SCREENING.out.mle_control_sgrna)
             ch_versions = ch_versions.mix(MAGECK_MLE.out.versions)
             MAGECK_FLUTEMLE_CONTRASTS(MAGECK_MLE.out.gene_summary)
             ch_versions = ch_versions.mix(MAGECK_FLUTEMLE_CONTRASTS.out.versions)
@@ -290,7 +290,7 @@ workflow CRISPRSEQ_SCREENING {
         }
         if(params.day0_label) {
             ch_mle = Channel.of([id: "day0"]).merge(Channel.of([[]])).merge(ch_counts)
-            MAGECK_MLE_DAY0 (ch_mle)
+            MAGECK_MLE_DAY0 (ch_mle, INITIALISATION_CHANNEL_CREATION_SCREENING.out.mle_control_sgrna)
             ch_versions = ch_versions.mix(MAGECK_MLE_DAY0.out.versions)
             MAGECK_FLUTEMLE_DAY0(MAGECK_MLE_DAY0.out.gene_summary)
             ch_versions = ch_versions.mix(MAGECK_FLUTEMLE_DAY0.out.versions)